Skip to content

Instantly share code, notes, and snippets.

@tnedev

tnedev/ran.ipynb

Created November 18, 2024 11:19
Show Gist options
  • Save tnedev/56b460eb7b6bb64ede8890d6673e0f6c to your computer and use it in GitHub Desktop.
Save tnedev/56b460eb7b6bb64ede8890d6673e0f6c to your computer and use it in GitHub Desktop.
Download ZIP
RAN.ipynb
Display the source blob
Display the rendered blob
Raw
ran.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/tnedev/56b460eb7b6bb64ede8890d6673e0f6c/ran.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"source": [
"# Analysis of the Augmented Solow Growth Model Across Country Groups and Periods\n",
"\n",
"This Jupyter notebook explores the applicability of the **augmented Solow growth model** across different groups of countries and time periods. Specifically, it examines how **physical capital investment**, **human capital**, and **population growth** affect **output per worker** in:\n",
"\n",
"- **Non-Oil-Exporting Countries**\n",
"- **Western Developed Countries**\n",
"- **Eastern European (Socialist) Countries**\n",
"\n",
"during two distinct periods:\n",
"\n",
"- **1960–1985**\n",
"- **1990–2010**\n",
"\n",
"## Data Used\n",
"\n",
"The analysis utilizes data on:\n",
"\n",
"- **Output per Worker (\\( Y/L \\))**: Gross Domestic Product (GDP) per worker.\n",
"- **Physical Capital Investment Rate (\\( S_k \\))**: The proportion of GDP invested in physical capital.\n",
"- **Human Capital (\\( h \\))**: Measured by average years of schooling or other human capital indices.\n",
"- **Population Growth (\\( n \\))**: The growth rate of the population.\n",
"- **Technological Progress and Depreciation (\\( g + \\delta \\))**: Assumed to be constant across countries (commonly set at 0.05).\n",
"\n",
"The data is aggregated into **10 five-year periods** to reduce volatility and capture long-term trends.\n",
"\n",
"## Analysis Overview\n",
"\n",
"For each country group and period, the following steps were performed:\n",
"\n",
"1. **Data Preparation**:\n",
" - Assigned years to two periods: **1960–1985** and **1990–2010**.\n",
" - Grouped data into five-year intervals using the `year_group` variable.\n",
" - Calculated the natural logarithms of key variables to linearize the relationships.\n",
"\n",
"2. **Regression Analysis**:\n",
" - Estimated the augmented Solow model using Ordinary Least Squares (OLS) regression:\n",
"\n",
" \\[\n",
" \\ln(Y/L) = \\beta_0 + \\beta_1 \\ln(S_k) + \\beta_2 \\ln(h) + \\beta_3 \\ln(n + g + \\delta) + \\epsilon\n",
" \\]\n",
"\n",
" - The dependent variable is the natural log of output per worker (\\( \\ln(Y/L) \\)).\n",
" - Independent variables include the natural logs of:\n",
" - Physical capital investment rate (\\( \\ln(S_k) \\))\n",
" - Human capital (\\( \\ln(h) \\))\n",
" - The sum of population growth, technological progress, and depreciation (\\( \\ln(n + g + \\delta) \\))\n",
"\n",
"3. **Model Evaluation**:\n",
" - Examined the statistical significance of the coefficients and the overall fit of the model (R-squared values).\n",
" - Compared the estimated coefficients with theoretical expectations from the Solow model.\n",
"\n",
"4. **Visualization**:\n",
" - Plotted actual versus predicted \\( \\ln(Y/L) \\) values to assess the model's predictive accuracy.\n",
" - Identified and annotated significant outliers with country codes and years to investigate deviations from the model.\n",
"\n",
"## Country Groups Analyzed\n",
"\n",
"- **Non-Oil-Exporting Countries**: Countries that are not major exporters of oil, to avoid distortions caused by oil revenues.\n",
"- **Western Developed Countries**: Economically advanced countries with developed market economies.\n",
"- **Eastern European (Socialist) Countries**: Countries that had centrally planned economies during the socialist period.\n",
"\n",
"## Key Findings\n",
"\n",
"### Western Developed Countries\n",
"\n",
"- **1960–1985**:\n",
" - The model showed a moderate fit, with **human capital** being a significant predictor of output per worker.\n",
" - **Physical capital investment rate** and **population growth** were not statistically significant.\n",
"- **Interpretation**:\n",
" - Human capital plays a crucial role in developed economies.\n",
" - Other factors may have less variation or be influenced by dynamics not captured in the model.\n",
"\n",
"### Eastern European Countries\n",
"\n",
"- **1960–1985**:\n",
" - Unexpected results were observed:\n",
" - **Negative coefficient** on physical capital investment.\n",
" - **Positive coefficient** on the population growth term.\n",
"- **Interpretation**:\n",
" - The standard Solow model may not fully capture the dynamics of centrally planned economies.\n",
" - Inefficiencies and different investment behaviors prevail in these economies.\n",
"\n",
"### Non-Oil-Exporting Countries\n",
"\n",
"- The model performed relatively well, with coefficients aligning with theoretical expectations.\n",
"- **Interpretation**:\n",
" - The augmented Solow model is more applicable to countries without significant distortions from natural resource exports.\n",
"\n",
"## Outlier Analysis\n",
"\n",
"- **Significant outliers** were identified in the plots of actual versus predicted \\( \\ln(Y/L) \\).\n",
"- **Annotations**:\n",
" - Outliers were annotated with country codes and years to facilitate further investigation.\n",
"- **Insights**:\n",
" - Outliers may result from data errors, unique economic events, or model limitations.\n",
" - Understanding these outliers provides valuable insights into factors affecting economic growth not captured by the model.\n",
"\n",
"## Conclusion\n",
"\n",
"The analysis highlights the varying applicability of the augmented Solow growth model across different country groups and time periods:\n",
"\n",
"- **Applicability**:\n",
" - The model explains a significant portion of the variation in output per worker for some groups.\n",
" - It falls short in others, particularly in centrally planned economies.\n",
"- **Implications**:\n",
" - Emphasizes the importance of considering institutional contexts and additional factors when modeling economic growth.\n",
" - Suggests that models may need to be adapted or expanded to capture the nuances of different economic systems.\n",
"\n",
"---\n",
"\n",
"**Note**: This notebook provides code for replicating the analysis, including data preparation, regression modeling, and visualization. It serves as a resource for understanding the dynamics of economic growth across different regions and periods."
],
"metadata": {
"id": "aN5oX6bp-MhZ"
}
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"id": "zVs0rCTT1863"
},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n"
]
},
{
"cell_type": "code",
"source": [
"# Load Penn data. Stripped version with POP, RGDPL, ki\n",
"penn = pd.read_csv(\"penn_csv.csv\")\n",
"penn"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 424
},
"id": "Xmmi2hkr25wi",
"outputId": "5baf4f18-c74d-4592-8bf6-db29e7ebb8f8"
},
"execution_count": 5,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" isocode year POP rgdpl ki\n",
"0 AFG 1950.0 8150.368 NaN NaN\n",
"1 AFG 1951.0 8284.473 NaN NaN\n",
"2 AFG 1952.0 8425.333 NaN NaN\n",
"3 AFG 1953.0 8573.217 NaN NaN\n",
"4 AFG 1954.0 8728.408 NaN NaN\n",
"... ... ... ... ... ...\n",
"11585 ZWE 2006.0 11544.326 361.018746 3.118174\n",
"11586 ZWE 2007.0 11443.187 294.536335 3.164092\n",
"11587 ZWE 2008.0 11350.111 275.703327 3.295467\n",
"11588 ZWE 2009.0 11392.629 300.428289 2.937018\n",
"11589 ZWE 2010.0 11651.858 318.804100 3.131205\n",
"\n",
"[11590 rows x 5 columns]"
],
"text/html": [
"\n",
" <div id=\"df-a66b5c0a-9521-4cc2-9dd8-887a232cec02\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>isocode</th>\n",
" <th>year</th>\n",
" <th>POP</th>\n",
" <th>rgdpl</th>\n",
" <th>ki</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>AFG</td>\n",
" <td>1950.0</td>\n",
" <td>8150.368</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>AFG</td>\n",
" <td>1951.0</td>\n",
" <td>8284.473</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>AFG</td>\n",
" <td>1952.0</td>\n",
" <td>8425.333</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>AFG</td>\n",
" <td>1953.0</td>\n",
" <td>8573.217</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>AFG</td>\n",
" <td>1954.0</td>\n",
" <td>8728.408</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11585</th>\n",
" <td>ZWE</td>\n",
" <td>2006.0</td>\n",
" <td>11544.326</td>\n",
" <td>361.018746</td>\n",
" <td>3.118174</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11586</th>\n",
" <td>ZWE</td>\n",
" <td>2007.0</td>\n",
" <td>11443.187</td>\n",
" <td>294.536335</td>\n",
" <td>3.164092</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11587</th>\n",
" <td>ZWE</td>\n",
" <td>2008.0</td>\n",
" <td>11350.111</td>\n",
" <td>275.703327</td>\n",
" <td>3.295467</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11588</th>\n",
" <td>ZWE</td>\n",
" <td>2009.0</td>\n",
" <td>11392.629</td>\n",
" <td>300.428289</td>\n",
" <td>2.937018</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11589</th>\n",
" <td>ZWE</td>\n",
" <td>2010.0</td>\n",
" <td>11651.858</td>\n",
" <td>318.804100</td>\n",
" <td>3.131205</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>11590 rows × 5 columns</p>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-a66b5c0a-9521-4cc2-9dd8-887a232cec02')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-a66b5c0a-9521-4cc2-9dd8-887a232cec02 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-a66b5c0a-9521-4cc2-9dd8-887a232cec02');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-a144608c-ccb3-4f07-b88b-d3c18939c2f7\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-a144608c-ccb3-4f07-b88b-d3c18939c2f7')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-a144608c-ccb3-4f07-b88b-d3c18939c2f7 button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" <div id=\"id_b97af97d-2c6b-4e28-8838-1f26842ea67e\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('penn')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_b97af97d-2c6b-4e28-8838-1f26842ea67e button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('penn');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "penn",
"summary": "{\n \"name\": \"penn\",\n \"rows\": 11590,\n \"fields\": [\n {\n \"column\": \"isocode\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 190,\n \"samples\": [\n \"TUR\",\n \"GBR\",\n \"MUS\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"year\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 37.65478684712668,\n \"min\": 13.5,\n \"max\": 2010.0,\n \"num_unique_values\": 69,\n \"samples\": [\n 1972.0,\n 1950.0,\n 1997.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"POP\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 117884.82140016912,\n \"min\": 7.251,\n \"max\": 1330141.295,\n \"num_unique_values\": 11517,\n \"samples\": [\n 5010.143,\n 2570.292,\n 37506.719\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rgdpl\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 11006.966432956639,\n \"min\": 160.7972212,\n \"max\": 136311.0084,\n \"num_unique_values\": 8940,\n \"samples\": [\n 39878.95654,\n 835.7301094,\n 15063.23452\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ki\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 11.23838086026967,\n \"min\": -11.49638271,\n \"max\": 93.63680575,\n \"num_unique_values\": 8938,\n \"samples\": [\n 28.09762872,\n 36.12523942,\n 15.9550409\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 5
}
]
},
{
"cell_type": "code",
"source": [
"# Load World Development Indicators from World Bank\n",
"wb = pd.read_csv(\"wb_data.csv\")\n",
"wb"
],
"metadata": {
"id": "LEouFsrA3U_L",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 912
},
"outputId": "68c23d76-38d7-46f4-cd35-998d4de5e765"
},
"execution_count": 6,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" Country Name Country Code \\\n",
"0 Afghanistan AFG \n",
"1 Africa Eastern and Southern AFE \n",
"2 Africa Western and Central AFW \n",
"3 Albania ALB \n",
"4 Algeria DZA \n",
".. ... ... \n",
"266 NaN NaN \n",
"267 NaN NaN \n",
"268 NaN NaN \n",
"269 Data from database: Population estimates and p... NaN \n",
"270 Last Updated: 07/01/2024 NaN \n",
"\n",
" Series Name Series Code \\\n",
"0 Population ages 15-64 (% of total population) SP.POP.1564.TO.ZS \n",
"1 Population ages 15-64 (% of total population) SP.POP.1564.TO.ZS \n",
"2 Population ages 15-64 (% of total population) SP.POP.1564.TO.ZS \n",
"3 Population ages 15-64 (% of total population) SP.POP.1564.TO.ZS \n",
"4 Population ages 15-64 (% of total population) SP.POP.1564.TO.ZS \n",
".. ... ... \n",
"266 NaN NaN \n",
"267 NaN NaN \n",
"268 NaN NaN \n",
"269 NaN NaN \n",
"270 NaN NaN \n",
"\n",
" 1960 [YR1960] 1961 [YR1961] 1962 [YR1962] 1963 [YR1963] 1964 [YR1964] \\\n",
"0 55,53978409 55,48702296 55,43177862 55,33565541 55,18168216 \n",
"1 52,82741578 52,76049028 52,68267584 52,58650966 52,48552001 \n",
"2 55,37594595 55,27524348 55,14979258 54,97157907 54,71634399 \n",
"3 53,47226402 53,07780294 52,69714128 52,37757318 52,16105592 \n",
"4 51,1212968 50,60862907 50,13594962 49,65866228 49,27720225 \n",
".. ... ... ... ... ... \n",
"266 NaN NaN NaN NaN NaN \n",
"267 NaN NaN NaN NaN NaN \n",
"268 NaN NaN NaN NaN NaN \n",
"269 NaN NaN NaN NaN NaN \n",
"270 NaN NaN NaN NaN NaN \n",
"\n",
" 1965 [YR1965] ... 2001 [YR2001] 2002 [YR2002] 2003 [YR2003] \\\n",
"0 54,94662027 ... 47,84920436 47,76754512 47,74465636 \n",
"1 52,37662819 ... 52,49528941 52,69527811 52,8812795 \n",
"2 54,4902649 ... 52,70385502 52,73512845 52,7734004 \n",
"3 52,08922429 ... 63,00657785 63,41676509 63,84814893 \n",
"4 49,04200753 ... 62,93806008 63,89414247 64,76187593 \n",
".. ... ... ... ... ... \n",
"266 NaN ... NaN NaN NaN \n",
"267 NaN ... NaN NaN NaN \n",
"268 NaN ... NaN NaN NaN \n",
"269 NaN ... NaN NaN NaN \n",
"270 NaN ... NaN NaN NaN \n",
"\n",
" 2004 [YR2004] 2005 [YR2005] 2006 [YR2006] 2007 [YR2007] 2008 [YR2008] \\\n",
"0 47,78131645 48,08510671 48,46694431 47,9988969 47,79192263 \n",
"1 53,05303164 53,20140255 53,33356692 53,45488762 53,56174799 \n",
"2 52,81094414 52,83218736 52,832747 52,82931359 52,82544291 \n",
"3 64,30753382 64,80907356 65,33881581 65,8829969 66,41929417 \n",
"4 65,52229661 66,14522323 66,65768907 67,08056354 67,38206756 \n",
".. ... ... ... ... ... \n",
"266 NaN NaN NaN NaN NaN \n",
"267 NaN NaN NaN NaN NaN \n",
"268 NaN NaN NaN NaN NaN \n",
"269 NaN NaN NaN NaN NaN \n",
"270 NaN NaN NaN NaN NaN \n",
"\n",
" 2009 [YR2009] 2010 [YR2010] \n",
"0 48,34519934 48,67757064 \n",
"1 53,66134077 53,76713151 \n",
"2 52,82084744 52,81440047 \n",
"3 66,93594 67,40694162 \n",
"4 67,55728447 67,5980207 \n",
".. ... ... \n",
"266 NaN NaN \n",
"267 NaN NaN \n",
"268 NaN NaN \n",
"269 NaN NaN \n",
"270 NaN NaN \n",
"\n",
"[271 rows x 55 columns]"
],
"text/html": [
"\n",
" <div id=\"df-05b0bfc1-5282-4dea-9c49-ddaf55934096\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Country Name</th>\n",
" <th>Country Code</th>\n",
" <th>Series Name</th>\n",
" <th>Series Code</th>\n",
" <th>1960 [YR1960]</th>\n",
" <th>1961 [YR1961]</th>\n",
" <th>1962 [YR1962]</th>\n",
" <th>1963 [YR1963]</th>\n",
" <th>1964 [YR1964]</th>\n",
" <th>1965 [YR1965]</th>\n",
" <th>...</th>\n",
" <th>2001 [YR2001]</th>\n",
" <th>2002 [YR2002]</th>\n",
" <th>2003 [YR2003]</th>\n",
" <th>2004 [YR2004]</th>\n",
" <th>2005 [YR2005]</th>\n",
" <th>2006 [YR2006]</th>\n",
" <th>2007 [YR2007]</th>\n",
" <th>2008 [YR2008]</th>\n",
" <th>2009 [YR2009]</th>\n",
" <th>2010 [YR2010]</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Afghanistan</td>\n",
" <td>AFG</td>\n",
" <td>Population ages 15-64 (% of total population)</td>\n",
" <td>SP.POP.1564.TO.ZS</td>\n",
" <td>55,53978409</td>\n",
" <td>55,48702296</td>\n",
" <td>55,43177862</td>\n",
" <td>55,33565541</td>\n",
" <td>55,18168216</td>\n",
" <td>54,94662027</td>\n",
" <td>...</td>\n",
" <td>47,84920436</td>\n",
" <td>47,76754512</td>\n",
" <td>47,74465636</td>\n",
" <td>47,78131645</td>\n",
" <td>48,08510671</td>\n",
" <td>48,46694431</td>\n",
" <td>47,9988969</td>\n",
" <td>47,79192263</td>\n",
" <td>48,34519934</td>\n",
" <td>48,67757064</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Africa Eastern and Southern</td>\n",
" <td>AFE</td>\n",
" <td>Population ages 15-64 (% of total population)</td>\n",
" <td>SP.POP.1564.TO.ZS</td>\n",
" <td>52,82741578</td>\n",
" <td>52,76049028</td>\n",
" <td>52,68267584</td>\n",
" <td>52,58650966</td>\n",
" <td>52,48552001</td>\n",
" <td>52,37662819</td>\n",
" <td>...</td>\n",
" <td>52,49528941</td>\n",
" <td>52,69527811</td>\n",
" <td>52,8812795</td>\n",
" <td>53,05303164</td>\n",
" <td>53,20140255</td>\n",
" <td>53,33356692</td>\n",
" <td>53,45488762</td>\n",
" <td>53,56174799</td>\n",
" <td>53,66134077</td>\n",
" <td>53,76713151</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Africa Western and Central</td>\n",
" <td>AFW</td>\n",
" <td>Population ages 15-64 (% of total population)</td>\n",
" <td>SP.POP.1564.TO.ZS</td>\n",
" <td>55,37594595</td>\n",
" <td>55,27524348</td>\n",
" <td>55,14979258</td>\n",
" <td>54,97157907</td>\n",
" <td>54,71634399</td>\n",
" <td>54,4902649</td>\n",
" <td>...</td>\n",
" <td>52,70385502</td>\n",
" <td>52,73512845</td>\n",
" <td>52,7734004</td>\n",
" <td>52,81094414</td>\n",
" <td>52,83218736</td>\n",
" <td>52,832747</td>\n",
" <td>52,82931359</td>\n",
" <td>52,82544291</td>\n",
" <td>52,82084744</td>\n",
" <td>52,81440047</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Albania</td>\n",
" <td>ALB</td>\n",
" <td>Population ages 15-64 (% of total population)</td>\n",
" <td>SP.POP.1564.TO.ZS</td>\n",
" <td>53,47226402</td>\n",
" <td>53,07780294</td>\n",
" <td>52,69714128</td>\n",
" <td>52,37757318</td>\n",
" <td>52,16105592</td>\n",
" <td>52,08922429</td>\n",
" <td>...</td>\n",
" <td>63,00657785</td>\n",
" <td>63,41676509</td>\n",
" <td>63,84814893</td>\n",
" <td>64,30753382</td>\n",
" <td>64,80907356</td>\n",
" <td>65,33881581</td>\n",
" <td>65,8829969</td>\n",
" <td>66,41929417</td>\n",
" <td>66,93594</td>\n",
" <td>67,40694162</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Algeria</td>\n",
" <td>DZA</td>\n",
" <td>Population ages 15-64 (% of total population)</td>\n",
" <td>SP.POP.1564.TO.ZS</td>\n",
" <td>51,1212968</td>\n",
" <td>50,60862907</td>\n",
" <td>50,13594962</td>\n",
" <td>49,65866228</td>\n",
" <td>49,27720225</td>\n",
" <td>49,04200753</td>\n",
" <td>...</td>\n",
" <td>62,93806008</td>\n",
" <td>63,89414247</td>\n",
" <td>64,76187593</td>\n",
" <td>65,52229661</td>\n",
" <td>66,14522323</td>\n",
" <td>66,65768907</td>\n",
" <td>67,08056354</td>\n",
" <td>67,38206756</td>\n",
" <td>67,55728447</td>\n",
" <td>67,5980207</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>266</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>267</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>268</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>269</th>\n",
" <td>Data from database: Population estimates and p...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>270</th>\n",
" <td>Last Updated: 07/01/2024</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>271 rows × 55 columns</p>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-05b0bfc1-5282-4dea-9c49-ddaf55934096')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-05b0bfc1-5282-4dea-9c49-ddaf55934096 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-05b0bfc1-5282-4dea-9c49-ddaf55934096');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-cd8e77ab-d216-496d-8174-c2c3a143be70\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-cd8e77ab-d216-496d-8174-c2c3a143be70')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-cd8e77ab-d216-496d-8174-c2c3a143be70 button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" <div id=\"id_ca9bb636-13d4-468f-9ce3-3b783d3fb0cb\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('wb')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_ca9bb636-13d4-468f-9ce3-3b783d3fb0cb button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('wb');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "wb"
}
},
"metadata": {},
"execution_count": 6
}
]
},
{
"cell_type": "code",
"source": [
"# Load Barro-Lee Data on Education\n",
"bl=pd.read_csv(\"BL_v3.csv\")\n",
"bl"
],
"metadata": {
"id": "oFS9xcSS5d95",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 704
},
"outputId": "1ff4232e-992e-4afe-a166-f10c4ba32552"
},
"execution_count": 7,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" BLcode country year sex agefrom ageto lu lp lpc ls \\\n",
"0 1 Algeria 1950 MF 15 64 81.12 17.10 3.65 1.48 \n",
"1 1 Algeria 1955 MF 15 64 81.50 16.54 3.43 1.66 \n",
"2 1 Algeria 1960 MF 15 64 82.50 14.29 3.16 2.88 \n",
"3 1 Algeria 1965 MF 15 64 80.08 15.00 4.21 4.46 \n",
"4 1 Algeria 1970 MF 15 64 72.02 20.25 6.06 7.25 \n",
"... ... ... ... .. ... ... ... ... ... ... \n",
"2039 358 Ukraine 1995 MF 15 64 1.49 6.41 5.38 62.19 \n",
"2040 358 Ukraine 2000 MF 15 64 0.52 3.19 2.85 59.08 \n",
"2041 358 Ukraine 2005 MF 15 64 0.29 3.82 3.56 56.51 \n",
"2042 358 Ukraine 2010 MF 15 64 0.23 5.02 4.76 52.34 \n",
"2043 358 Ukraine 2015 MF 15 64 0.24 6.34 6.04 49.08 \n",
"\n",
" lsc lh lhc yr_sch yr_sch_pri yr_sch_sec yr_sch_ter WBcode \\\n",
"0 0.50 0.30 0.18 0.834 0.729 0.095 0.010 DZA \n",
"1 0.53 0.26 0.17 0.823 0.714 0.100 0.008 DZA \n",
"2 1.02 0.33 0.19 0.896 0.716 0.169 0.010 DZA \n",
"3 1.90 0.45 0.24 1.151 0.871 0.267 0.014 DZA \n",
"4 3.87 0.38 0.18 1.690 1.247 0.432 0.011 DZA \n",
"... ... ... ... ... ... ... ... ... \n",
"2039 44.42 29.91 18.96 10.811 5.296 4.538 0.977 UKR \n",
"2040 43.18 36.99 24.09 11.343 5.408 4.713 1.222 UKR \n",
"2041 43.04 39.38 24.63 11.518 5.415 4.823 1.280 UKR \n",
"2042 41.00 42.41 26.42 11.533 5.299 4.858 1.377 UKR \n",
"2043 39.18 44.35 27.38 11.568 5.322 4.812 1.434 UKR \n",
"\n",
" region_code pop \n",
"0 Middle East and North Africa 4858.0 \n",
"1 Middle East and North Africa 5302.0 \n",
"2 Middle East and North Africa 5658.0 \n",
"3 Middle East and North Africa 5982.0 \n",
"4 Middle East and North Africa 6531.0 \n",
"... ... ... \n",
"2039 Europe and Central Asia 33996.0 \n",
"2040 Europe and Central Asia 33469.0 \n",
"2041 Europe and Central Asia 32069.0 \n",
"2042 Europe and Central Asia 31091.0 \n",
"2043 Europe and Central Asia 31027.0 \n",
"\n",
"[2044 rows x 20 columns]"
],
"text/html": [
"\n",
" <div id=\"df-4583bfcb-b151-46e1-bf7d-c1517e0e36bc\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>BLcode</th>\n",
" <th>country</th>\n",
" <th>year</th>\n",
" <th>sex</th>\n",
" <th>agefrom</th>\n",
" <th>ageto</th>\n",
" <th>lu</th>\n",
" <th>lp</th>\n",
" <th>lpc</th>\n",
" <th>ls</th>\n",
" <th>lsc</th>\n",
" <th>lh</th>\n",
" <th>lhc</th>\n",
" <th>yr_sch</th>\n",
" <th>yr_sch_pri</th>\n",
" <th>yr_sch_sec</th>\n",
" <th>yr_sch_ter</th>\n",
" <th>WBcode</th>\n",
" <th>region_code</th>\n",
" <th>pop</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>Algeria</td>\n",
" <td>1950</td>\n",
" <td>MF</td>\n",
" <td>15</td>\n",
" <td>64</td>\n",
" <td>81.12</td>\n",
" <td>17.10</td>\n",
" <td>3.65</td>\n",
" <td>1.48</td>\n",
" <td>0.50</td>\n",
" <td>0.30</td>\n",
" <td>0.18</td>\n",
" <td>0.834</td>\n",
" <td>0.729</td>\n",
" <td>0.095</td>\n",
" <td>0.010</td>\n",
" <td>DZA</td>\n",
" <td>Middle East and North Africa</td>\n",
" <td>4858.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>Algeria</td>\n",
" <td>1955</td>\n",
" <td>MF</td>\n",
" <td>15</td>\n",
" <td>64</td>\n",
" <td>81.50</td>\n",
" <td>16.54</td>\n",
" <td>3.43</td>\n",
" <td>1.66</td>\n",
" <td>0.53</td>\n",
" <td>0.26</td>\n",
" <td>0.17</td>\n",
" <td>0.823</td>\n",
" <td>0.714</td>\n",
" <td>0.100</td>\n",
" <td>0.008</td>\n",
" <td>DZA</td>\n",
" <td>Middle East and North Africa</td>\n",
" <td>5302.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>Algeria</td>\n",
" <td>1960</td>\n",
" <td>MF</td>\n",
" <td>15</td>\n",
" <td>64</td>\n",
" <td>82.50</td>\n",
" <td>14.29</td>\n",
" <td>3.16</td>\n",
" <td>2.88</td>\n",
" <td>1.02</td>\n",
" <td>0.33</td>\n",
" <td>0.19</td>\n",
" <td>0.896</td>\n",
" <td>0.716</td>\n",
" <td>0.169</td>\n",
" <td>0.010</td>\n",
" <td>DZA</td>\n",
" <td>Middle East and North Africa</td>\n",
" <td>5658.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>Algeria</td>\n",
" <td>1965</td>\n",
" <td>MF</td>\n",
" <td>15</td>\n",
" <td>64</td>\n",
" <td>80.08</td>\n",
" <td>15.00</td>\n",
" <td>4.21</td>\n",
" <td>4.46</td>\n",
" <td>1.90</td>\n",
" <td>0.45</td>\n",
" <td>0.24</td>\n",
" <td>1.151</td>\n",
" <td>0.871</td>\n",
" <td>0.267</td>\n",
" <td>0.014</td>\n",
" <td>DZA</td>\n",
" <td>Middle East and North Africa</td>\n",
" <td>5982.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1</td>\n",
" <td>Algeria</td>\n",
" <td>1970</td>\n",
" <td>MF</td>\n",
" <td>15</td>\n",
" <td>64</td>\n",
" <td>72.02</td>\n",
" <td>20.25</td>\n",
" <td>6.06</td>\n",
" <td>7.25</td>\n",
" <td>3.87</td>\n",
" <td>0.38</td>\n",
" <td>0.18</td>\n",
" <td>1.690</td>\n",
" <td>1.247</td>\n",
" <td>0.432</td>\n",
" <td>0.011</td>\n",
" <td>DZA</td>\n",
" <td>Middle East and North Africa</td>\n",
" <td>6531.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2039</th>\n",
" <td>358</td>\n",
" <td>Ukraine</td>\n",
" <td>1995</td>\n",
" <td>MF</td>\n",
" <td>15</td>\n",
" <td>64</td>\n",
" <td>1.49</td>\n",
" <td>6.41</td>\n",
" <td>5.38</td>\n",
" <td>62.19</td>\n",
" <td>44.42</td>\n",
" <td>29.91</td>\n",
" <td>18.96</td>\n",
" <td>10.811</td>\n",
" <td>5.296</td>\n",
" <td>4.538</td>\n",
" <td>0.977</td>\n",
" <td>UKR</td>\n",
" <td>Europe and Central Asia</td>\n",
" <td>33996.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2040</th>\n",
" <td>358</td>\n",
" <td>Ukraine</td>\n",
" <td>2000</td>\n",
" <td>MF</td>\n",
" <td>15</td>\n",
" <td>64</td>\n",
" <td>0.52</td>\n",
" <td>3.19</td>\n",
" <td>2.85</td>\n",
" <td>59.08</td>\n",
" <td>43.18</td>\n",
" <td>36.99</td>\n",
" <td>24.09</td>\n",
" <td>11.343</td>\n",
" <td>5.408</td>\n",
" <td>4.713</td>\n",
" <td>1.222</td>\n",
" <td>UKR</td>\n",
" <td>Europe and Central Asia</td>\n",
" <td>33469.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2041</th>\n",
" <td>358</td>\n",
" <td>Ukraine</td>\n",
" <td>2005</td>\n",
" <td>MF</td>\n",
" <td>15</td>\n",
" <td>64</td>\n",
" <td>0.29</td>\n",
" <td>3.82</td>\n",
" <td>3.56</td>\n",
" <td>56.51</td>\n",
" <td>43.04</td>\n",
" <td>39.38</td>\n",
" <td>24.63</td>\n",
" <td>11.518</td>\n",
" <td>5.415</td>\n",
" <td>4.823</td>\n",
" <td>1.280</td>\n",
" <td>UKR</td>\n",
" <td>Europe and Central Asia</td>\n",
" <td>32069.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2042</th>\n",
" <td>358</td>\n",
" <td>Ukraine</td>\n",
" <td>2010</td>\n",
" <td>MF</td>\n",
" <td>15</td>\n",
" <td>64</td>\n",
" <td>0.23</td>\n",
" <td>5.02</td>\n",
" <td>4.76</td>\n",
" <td>52.34</td>\n",
" <td>41.00</td>\n",
" <td>42.41</td>\n",
" <td>26.42</td>\n",
" <td>11.533</td>\n",
" <td>5.299</td>\n",
" <td>4.858</td>\n",
" <td>1.377</td>\n",
" <td>UKR</td>\n",
" <td>Europe and Central Asia</td>\n",
" <td>31091.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2043</th>\n",
" <td>358</td>\n",
" <td>Ukraine</td>\n",
" <td>2015</td>\n",
" <td>MF</td>\n",
" <td>15</td>\n",
" <td>64</td>\n",
" <td>0.24</td>\n",
" <td>6.34</td>\n",
" <td>6.04</td>\n",
" <td>49.08</td>\n",
" <td>39.18</td>\n",
" <td>44.35</td>\n",
" <td>27.38</td>\n",
" <td>11.568</td>\n",
" <td>5.322</td>\n",
" <td>4.812</td>\n",
" <td>1.434</td>\n",
" <td>UKR</td>\n",
" <td>Europe and Central Asia</td>\n",
" <td>31027.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>2044 rows × 20 columns</p>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-4583bfcb-b151-46e1-bf7d-c1517e0e36bc')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-4583bfcb-b151-46e1-bf7d-c1517e0e36bc button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-4583bfcb-b151-46e1-bf7d-c1517e0e36bc');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-3b4649fe-c306-48a5-9944-ccaffd679e39\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-3b4649fe-c306-48a5-9944-ccaffd679e39')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-3b4649fe-c306-48a5-9944-ccaffd679e39 button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" <div id=\"id_8529474c-ebe7-4648-8ff3-cf1295b00152\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('bl')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_8529474c-ebe7-4648-8ff3-cf1295b00152 button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('bl');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "bl",
"summary": "{\n \"name\": \"bl\",\n \"rows\": 2044,\n \"fields\": [\n {\n \"column\": \"BLcode\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 91,\n \"min\": 1,\n \"max\": 358,\n \"num_unique_values\": 146,\n \"samples\": [\n 61,\n 118,\n 40\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"country\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 146,\n \"samples\": [\n \"Nicaragua\",\n \"Italy\",\n \"Swaziland\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"year\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 20,\n \"min\": 1950,\n \"max\": 2015,\n \"num_unique_values\": 14,\n \"samples\": [\n 1995,\n 2005,\n 1950\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"sex\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 1,\n \"samples\": [\n \"MF\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"agefrom\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 15,\n \"max\": 15,\n \"num_unique_values\": 1,\n \"samples\": [\n 15\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ageto\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0,\n \"min\": 64,\n \"max\": 64,\n \"num_unique_values\": 1,\n \"samples\": [\n 64\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"lu\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 28.68927648676601,\n \"min\": 0.0,\n \"max\": 99.56,\n \"num_unique_values\": 1635,\n \"samples\": [\n 4.83\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"lp\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 20.03316901086185,\n \"min\": 0.14,\n \"max\": 91.14,\n \"num_unique_values\": 1776,\n \"samples\": [\n 51.17\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"lpc\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 13.555896408912883,\n \"min\": 0.08,\n \"max\": 81.54,\n \"num_unique_values\": 1576,\n \"samples\": [\n 10.34\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ls\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 22.138534225410048,\n \"min\": 0.0,\n \"max\": 95.99,\n \"num_unique_values\": 1747,\n \"samples\": [\n 59.4\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"lsc\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 15.48164047006402,\n \"min\": 0.0,\n \"max\": 72.24,\n \"num_unique_values\": 1538,\n \"samples\": [\n 3.57\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"lh\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 9.322672304230123,\n \"min\": 0.0,\n \"max\": 64.73,\n \"num_unique_values\": 1140,\n \"samples\": [\n 31.98\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"lhc\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 5.663960335940126,\n \"min\": 0.0,\n \"max\": 41.65,\n \"num_unique_values\": 915,\n \"samples\": [\n 25.5\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"yr_sch\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3.3834906469634203,\n \"min\": 0.026,\n \"max\": 13.275,\n \"num_unique_values\": 1881,\n \"samples\": [\n 11.961\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"yr_sch_pri\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.9123595888279241,\n \"min\": 0.02,\n \"max\": 8.866,\n \"num_unique_values\": 1786,\n \"samples\": [\n 1.302\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"yr_sch_sec\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.570404432407431,\n \"min\": 0.0,\n \"max\": 7.915,\n \"num_unique_values\": 1617,\n \"samples\": [\n 0.109\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"yr_sch_ter\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.2962771443809308,\n \"min\": 0.0,\n \"max\": 1.846,\n \"num_unique_values\": 689,\n \"samples\": [\n 0.31\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"WBcode\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 146,\n \"samples\": [\n \"NIC\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"region_code\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 7,\n \"samples\": [\n \"Middle East and North Africa\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"pop\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 72943.94497184773,\n \"min\": 14.0,\n \"max\": 1021572.0,\n \"num_unique_values\": 1885,\n \"samples\": [\n 2601.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 7
}
]
},
{
"cell_type": "code",
"source": [
"# wb data has bad column names '1961 [YR1961]'. Clean it, so it can be joined with the other tables.\n",
"wb.columns = wb.columns.str.replace(r'\\s+\\[.*\\]', '', regex=True)\n",
"\n",
"# Remove Series Name and Code, we don't need it.\n",
"wb.drop(columns=[\"Series Name\", \"Series Code\"], inplace=True)\n",
"\n",
"# display new column names\n",
"print(wb.columns.values)"
],
"metadata": {
"id": "I6WmCZaQ4X56",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "4a752b85-6d04-42b2-d772-225f7f05a21d"
},
"execution_count": 8,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"['Country Name' 'Country Code' '1960' '1961' '1962' '1963' '1964' '1965'\n",
" '1966' '1967' '1968' '1969' '1970' '1971' '1972' '1973' '1974' '1975'\n",
" '1976' '1977' '1978' '1979' '1980' '1981' '1982' '1983' '1984' '1985'\n",
" '1986' '1987' '1988' '1989' '1990' '1991' '1992' '1993' '1994' '1995'\n",
" '1996' '1997' '1998' '1999' '2000' '2001' '2002' '2003' '2004' '2005'\n",
" '2006' '2007' '2008' '2009' '2010']\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"*italicized text*# New Section"
],
"metadata": {
"id": "dZsZKCnH2ATE"
}
},
{
"cell_type": "code",
"source": [
"# Melt the DataFrame to long format\n",
"wb_long = wb.melt(\n",
" id_vars=['Country Name', 'Country Code'],\n",
" var_name='year',\n",
" value_name='L_P'\n",
")\n",
"# Drop rows where 'Country Name' is NaN\n",
"wb_long.dropna(subset=[\"Country Name\", \"Country Code\"], inplace=True)\n",
"\n",
"# Convert from object to numeric\n",
"wb_long['year'] = pd.to_numeric(wb_long['year'], errors='coerce')\n",
"wb_long['L_P'] = wb_long['L_P'].str.replace(',', '.') # Remove comma separator\n",
"wb_long['L_P'] = pd.to_numeric(wb_long['L_P'], errors='coerce')\n",
"\n",
"# Make sure country code is uppercase for matching\n",
"wb_long['Country Code'] = wb_long['Country Code'].str.upper()\n",
"\n",
"# Rename 'Country Code' to 'isocode' to match with Penn data\n",
"wb_long.rename(columns={'Country Code': 'isocode'}, inplace=True)\n",
"\n",
"# Rename Country Name to country\n",
"wb_long.rename(columns={'Country Name': 'country'}, inplace=True)\n",
"\n",
"# Filter years between 1960 and 2010\n",
"wb_long = wb_long[(wb_long['year'] >= 1960) & (wb_long['year'] <= 2010)]\n",
"\n",
"wb_long"
],
"metadata": {
"id": "6lcrW_f44hYr",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 424
},
"outputId": "4b6f9f09-18e2-4cd7-92cc-db12dcaf82ec"
},
"execution_count": 9,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" country isocode year L_P\n",
"0 Afghanistan AFG 1960 55.539784\n",
"1 Africa Eastern and Southern AFE 1960 52.827416\n",
"2 Africa Western and Central AFW 1960 55.375946\n",
"3 Albania ALB 1960 53.472264\n",
"4 Algeria DZA 1960 51.121297\n",
"... ... ... ... ...\n",
"13811 West Bank and Gaza PSE 2010 54.740677\n",
"13812 World WLD 2010 65.262449\n",
"13813 Yemen, Rep. YEM 2010 53.612287\n",
"13814 Zambia ZMB 2010 51.670663\n",
"13815 Zimbabwe ZWE 2010 53.889596\n",
"\n",
"[13566 rows x 4 columns]"
],
"text/html": [
"\n",
" <div id=\"df-d5e7386a-888c-4293-8df4-ab221afe588c\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>country</th>\n",
" <th>isocode</th>\n",
" <th>year</th>\n",
" <th>L_P</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Afghanistan</td>\n",
" <td>AFG</td>\n",
" <td>1960</td>\n",
" <td>55.539784</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Africa Eastern and Southern</td>\n",
" <td>AFE</td>\n",
" <td>1960</td>\n",
" <td>52.827416</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Africa Western and Central</td>\n",
" <td>AFW</td>\n",
" <td>1960</td>\n",
" <td>55.375946</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>Albania</td>\n",
" <td>ALB</td>\n",
" <td>1960</td>\n",
" <td>53.472264</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>Algeria</td>\n",
" <td>DZA</td>\n",
" <td>1960</td>\n",
" <td>51.121297</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13811</th>\n",
" <td>West Bank and Gaza</td>\n",
" <td>PSE</td>\n",
" <td>2010</td>\n",
" <td>54.740677</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13812</th>\n",
" <td>World</td>\n",
" <td>WLD</td>\n",
" <td>2010</td>\n",
" <td>65.262449</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13813</th>\n",
" <td>Yemen, Rep.</td>\n",
" <td>YEM</td>\n",
" <td>2010</td>\n",
" <td>53.612287</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13814</th>\n",
" <td>Zambia</td>\n",
" <td>ZMB</td>\n",
" <td>2010</td>\n",
" <td>51.670663</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13815</th>\n",
" <td>Zimbabwe</td>\n",
" <td>ZWE</td>\n",
" <td>2010</td>\n",
" <td>53.889596</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>13566 rows × 4 columns</p>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-d5e7386a-888c-4293-8df4-ab221afe588c')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-d5e7386a-888c-4293-8df4-ab221afe588c button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-d5e7386a-888c-4293-8df4-ab221afe588c');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-5043616a-6846-4b09-a74c-f540305aaed9\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-5043616a-6846-4b09-a74c-f540305aaed9')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-5043616a-6846-4b09-a74c-f540305aaed9 button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" <div id=\"id_9c1f2885-8317-4831-8416-10737ba62627\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('wb_long')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_9c1f2885-8317-4831-8416-10737ba62627 button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('wb_long');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "wb_long",
"summary": "{\n \"name\": \"wb_long\",\n \"rows\": 13566,\n \"fields\": [\n {\n \"column\": \"country\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 266,\n \"samples\": [\n \"Northern Mariana Islands\",\n \"Jamaica\",\n \"Liberia\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"isocode\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 266,\n \"samples\": [\n \"MNP\",\n \"JAM\",\n \"LBR\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"year\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 14,\n \"min\": 1960,\n \"max\": 2010,\n \"num_unique_values\": 51,\n \"samples\": [\n 2003,\n 2000,\n 2006\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"L_P\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 6.786008422117051,\n \"min\": 44.77987337,\n \"max\": 86.07924571,\n \"num_unique_values\": 13179,\n \"samples\": [\n 62.46613827,\n 56.28631615,\n 62.19239713\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 9
}
]
},
{
"cell_type": "code",
"source": [
"# Convert 'year' to integer\n",
"penn['year'] = penn['year'].astype(int)\n",
"\n",
"# PENN Data uses bad Romania isocode. Convert ROM to ROU\n",
"penn['isocode'] = penn.isocode.replace('ROM', 'ROU')\n",
"\n",
"# Filter years between 1960 and 2010\n",
"penn = penn[(penn['year'] >= 1960) & (penn['year'] <= 2010)]\n",
"\n",
"# Ensure 'isocode' and 'Country Code' are uppercase (if necessary)\n",
"penn['isocode'] = penn['isocode'].str.upper()\n"
],
"metadata": {
"id": "mmVdGCEN7Iqq",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "86207abe-8d96-43ab-d112-766e74f26775"
},
"execution_count": 10,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"<ipython-input-10-db7ad7d5a9bd>:11: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" penn['isocode'] = penn['isocode'].str.upper()\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Select the columns we need from bl_data\n",
"bl_selected = bl[['WBcode', 'year', 'yr_sch_pri', 'yr_sch_sec']]\n",
"\n",
"# Rename columns, convert isocode to uppercase\n",
"bl_selected.rename(columns={\n",
" 'WBcode': 'isocode',\n",
" 'yr_sch_pri': 'H_P',\n",
" 'yr_sch_sec': 'H_S'\n",
"}, inplace=True)\n",
"bl_selected['isocode'] = bl_selected['isocode'].str.upper()\n",
"\n",
"bl_selected"
],
"metadata": {
"id": "0pZZqhqqpk1u",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 620
},
"outputId": "f5de074c-7b87-4176-99d9-a2cf7d897ee6"
},
"execution_count": 11,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"<ipython-input-11-ad2695cb8958>:5: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" bl_selected.rename(columns={\n",
"<ipython-input-11-ad2695cb8958>:10: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" bl_selected['isocode'] = bl_selected['isocode'].str.upper()\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
" isocode year H_P H_S\n",
"0 DZA 1950 0.729 0.095\n",
"1 DZA 1955 0.714 0.100\n",
"2 DZA 1960 0.716 0.169\n",
"3 DZA 1965 0.871 0.267\n",
"4 DZA 1970 1.247 0.432\n",
"... ... ... ... ...\n",
"2039 UKR 1995 5.296 4.538\n",
"2040 UKR 2000 5.408 4.713\n",
"2041 UKR 2005 5.415 4.823\n",
"2042 UKR 2010 5.299 4.858\n",
"2043 UKR 2015 5.322 4.812\n",
"\n",
"[2044 rows x 4 columns]"
],
"text/html": [
"\n",
" <div id=\"df-797d4714-c6f4-42fb-bb25-cd5aa76e6335\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>isocode</th>\n",
" <th>year</th>\n",
" <th>H_P</th>\n",
" <th>H_S</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>DZA</td>\n",
" <td>1950</td>\n",
" <td>0.729</td>\n",
" <td>0.095</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>DZA</td>\n",
" <td>1955</td>\n",
" <td>0.714</td>\n",
" <td>0.100</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>DZA</td>\n",
" <td>1960</td>\n",
" <td>0.716</td>\n",
" <td>0.169</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>DZA</td>\n",
" <td>1965</td>\n",
" <td>0.871</td>\n",
" <td>0.267</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>DZA</td>\n",
" <td>1970</td>\n",
" <td>1.247</td>\n",
" <td>0.432</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2039</th>\n",
" <td>UKR</td>\n",
" <td>1995</td>\n",
" <td>5.296</td>\n",
" <td>4.538</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2040</th>\n",
" <td>UKR</td>\n",
" <td>2000</td>\n",
" <td>5.408</td>\n",
" <td>4.713</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2041</th>\n",
" <td>UKR</td>\n",
" <td>2005</td>\n",
" <td>5.415</td>\n",
" <td>4.823</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2042</th>\n",
" <td>UKR</td>\n",
" <td>2010</td>\n",
" <td>5.299</td>\n",
" <td>4.858</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2043</th>\n",
" <td>UKR</td>\n",
" <td>2015</td>\n",
" <td>5.322</td>\n",
" <td>4.812</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>2044 rows × 4 columns</p>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-797d4714-c6f4-42fb-bb25-cd5aa76e6335')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-797d4714-c6f4-42fb-bb25-cd5aa76e6335 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-797d4714-c6f4-42fb-bb25-cd5aa76e6335');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-1fc64782-89a0-4c9e-9321-27b06bf3f8bb\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-1fc64782-89a0-4c9e-9321-27b06bf3f8bb')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-1fc64782-89a0-4c9e-9321-27b06bf3f8bb button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" <div id=\"id_d4973bfc-ee0f-4c9e-8437-26932c7fc8a4\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('bl_selected')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_d4973bfc-ee0f-4c9e-8437-26932c7fc8a4 button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('bl_selected');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "bl_selected",
"summary": "{\n \"name\": \"bl_selected\",\n \"rows\": 2044,\n \"fields\": [\n {\n \"column\": \"isocode\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 146,\n \"samples\": [\n \"NIC\",\n \"ITA\",\n \"SWZ\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"year\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 20,\n \"min\": 1950,\n \"max\": 2015,\n \"num_unique_values\": 14,\n \"samples\": [\n 1995,\n 2005,\n 1950\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"H_P\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.9123595888279241,\n \"min\": 0.02,\n \"max\": 8.866,\n \"num_unique_values\": 1786,\n \"samples\": [\n 1.302,\n 5.596,\n 6.655\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"H_S\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.570404432407431,\n \"min\": 0.0,\n \"max\": 7.915,\n \"num_unique_values\": 1617,\n \"samples\": [\n 0.109,\n 1.164,\n 0.379\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 11
}
]
},
{
"cell_type": "code",
"source": [
"\n",
"# Merge the DataFrames\n",
"merged_df = pd.merge(\n",
" penn,\n",
" wb_long[['isocode', 'year', 'L_P']],\n",
" on=['isocode', 'year'],\n",
" how='left'\n",
")\n",
"merged_df"
],
"metadata": {
"id": "ptUYXuCf7Wb1",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 424
},
"outputId": "7e3838a9-d2a7-4955-8ccc-169f37fd7596"
},
"execution_count": 12,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" isocode year POP rgdpl ki L_P\n",
"0 AFG 1960 9829.450 NaN NaN 55.539784\n",
"1 AFG 1961 10043.473 NaN NaN 55.487023\n",
"2 AFG 1962 10267.083 NaN NaN 55.431779\n",
"3 AFG 1963 10500.711 NaN NaN 55.335655\n",
"4 AFG 1964 10744.167 NaN NaN 55.181682\n",
"... ... ... ... ... ... ...\n",
"9476 ZWE 2006 11544.326 361.018746 3.118174 54.770759\n",
"9477 ZWE 2007 11443.187 294.536335 3.164092 54.635371\n",
"9478 ZWE 2008 11350.111 275.703327 3.295467 54.418664\n",
"9479 ZWE 2009 11392.629 300.428289 2.937018 54.169175\n",
"9480 ZWE 2010 11651.858 318.804100 3.131205 53.889596\n",
"\n",
"[9481 rows x 6 columns]"
],
"text/html": [
"\n",
" <div id=\"df-9f4f4c85-0aa9-465c-82bb-d50dc837b54e\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>isocode</th>\n",
" <th>year</th>\n",
" <th>POP</th>\n",
" <th>rgdpl</th>\n",
" <th>ki</th>\n",
" <th>L_P</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>AFG</td>\n",
" <td>1960</td>\n",
" <td>9829.450</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.539784</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>AFG</td>\n",
" <td>1961</td>\n",
" <td>10043.473</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.487023</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>AFG</td>\n",
" <td>1962</td>\n",
" <td>10267.083</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.431779</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>AFG</td>\n",
" <td>1963</td>\n",
" <td>10500.711</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.335655</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>AFG</td>\n",
" <td>1964</td>\n",
" <td>10744.167</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.181682</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9476</th>\n",
" <td>ZWE</td>\n",
" <td>2006</td>\n",
" <td>11544.326</td>\n",
" <td>361.018746</td>\n",
" <td>3.118174</td>\n",
" <td>54.770759</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9477</th>\n",
" <td>ZWE</td>\n",
" <td>2007</td>\n",
" <td>11443.187</td>\n",
" <td>294.536335</td>\n",
" <td>3.164092</td>\n",
" <td>54.635371</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9478</th>\n",
" <td>ZWE</td>\n",
" <td>2008</td>\n",
" <td>11350.111</td>\n",
" <td>275.703327</td>\n",
" <td>3.295467</td>\n",
" <td>54.418664</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9479</th>\n",
" <td>ZWE</td>\n",
" <td>2009</td>\n",
" <td>11392.629</td>\n",
" <td>300.428289</td>\n",
" <td>2.937018</td>\n",
" <td>54.169175</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9480</th>\n",
" <td>ZWE</td>\n",
" <td>2010</td>\n",
" <td>11651.858</td>\n",
" <td>318.804100</td>\n",
" <td>3.131205</td>\n",
" <td>53.889596</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>9481 rows × 6 columns</p>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-9f4f4c85-0aa9-465c-82bb-d50dc837b54e')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-9f4f4c85-0aa9-465c-82bb-d50dc837b54e button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-9f4f4c85-0aa9-465c-82bb-d50dc837b54e');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-8925d7c7-3a5c-4e60-984b-2b5b6bf09cd8\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-8925d7c7-3a5c-4e60-984b-2b5b6bf09cd8')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-8925d7c7-3a5c-4e60-984b-2b5b6bf09cd8 button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" <div id=\"id_d676e6d4-119d-42ba-aba7-ac57f480aa58\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('merged_df')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_d676e6d4-119d-42ba-aba7-ac57f480aa58 button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('merged_df');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "merged_df",
"summary": "{\n \"name\": \"merged_df\",\n \"rows\": 9481,\n \"fields\": [\n {\n \"column\": \"isocode\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 190,\n \"samples\": [\n \"TUR\",\n \"GBR\",\n \"MUS\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"year\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 14,\n \"min\": 1960,\n \"max\": 2010,\n \"num_unique_values\": 51,\n \"samples\": [\n 2003,\n 2000,\n 2006\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"POP\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 126362.24960859088,\n \"min\": 9.482,\n \"max\": 1330141.295,\n \"num_unique_values\": 9422,\n \"samples\": [\n 150.508,\n 80313.516,\n 49.888\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rgdpl\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 11350.461032763233,\n \"min\": 160.7972212,\n \"max\": 136311.0084,\n \"num_unique_values\": 8083,\n \"samples\": [\n 2579.061492,\n 10488.47502,\n 15815.04688\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ki\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 11.356085221428252,\n \"min\": -11.49638271,\n \"max\": 93.63680575,\n \"num_unique_values\": 8081,\n \"samples\": [\n 13.18122334,\n 23.99502517,\n 13.63452372\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"L_P\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 6.940328455341578,\n \"min\": 44.77987337,\n \"max\": 86.07924571,\n \"num_unique_values\": 9277,\n \"samples\": [\n 51.89760401,\n 48.68291727,\n 62.43031124\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 12
}
]
},
{
"cell_type": "code",
"source": [
"# Calculate L = P * (L_P / 100)\n",
"merged_df['L'] = merged_df['POP'] * (merged_df['L_P'] / 100)"
],
"metadata": {
"id": "uudLKkxR7jmn"
},
"execution_count": 13,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Merge bl data to rest\n",
"\n",
"merged_df = pd.merge(\n",
" merged_df,\n",
" bl_selected,\n",
" on=['isocode', 'year'],\n",
" how='left'\n",
")"
],
"metadata": {
"id": "f-djokJl_IBe"
},
"execution_count": 14,
"outputs": []
},
{
"cell_type": "code",
"source": [
"merged_df"
],
"metadata": {
"id": "Mg6LpgP-HOwj",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 424
},
"outputId": "f7e50606-fa40-4049-f55f-bf2e50339520"
},
"execution_count": 15,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" isocode year POP rgdpl ki L_P L \\\n",
"0 AFG 1960 9829.450 NaN NaN 55.539784 5459.255307 \n",
"1 AFG 1961 10043.473 NaN NaN 55.487023 5572.824169 \n",
"2 AFG 1962 10267.083 NaN NaN 55.431779 5691.226719 \n",
"3 AFG 1963 10500.711 NaN NaN 55.335655 5810.637255 \n",
"4 AFG 1964 10744.167 NaN NaN 55.181682 5928.812085 \n",
"... ... ... ... ... ... ... ... \n",
"9476 ZWE 2006 11544.326 361.018746 3.118174 54.770759 6322.915007 \n",
"9477 ZWE 2007 11443.187 294.536335 3.164092 54.635371 6252.027655 \n",
"9478 ZWE 2008 11350.111 275.703327 3.295467 54.418664 6176.578825 \n",
"9479 ZWE 2009 11392.629 300.428289 2.937018 54.169175 6171.293169 \n",
"9480 ZWE 2010 11651.858 318.804100 3.131205 53.889596 6279.139248 \n",
"\n",
" H_P H_S \n",
"0 0.286 0.075 \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"... ... ... \n",
"9476 NaN NaN \n",
"9477 NaN NaN \n",
"9478 NaN NaN \n",
"9479 NaN NaN \n",
"9480 5.894 1.944 \n",
"\n",
"[9481 rows x 9 columns]"
],
"text/html": [
"\n",
" <div id=\"df-517df169-65fa-4f8b-ae97-1cb99994be63\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>isocode</th>\n",
" <th>year</th>\n",
" <th>POP</th>\n",
" <th>rgdpl</th>\n",
" <th>ki</th>\n",
" <th>L_P</th>\n",
" <th>L</th>\n",
" <th>H_P</th>\n",
" <th>H_S</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>AFG</td>\n",
" <td>1960</td>\n",
" <td>9829.450</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.539784</td>\n",
" <td>5459.255307</td>\n",
" <td>0.286</td>\n",
" <td>0.075</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>AFG</td>\n",
" <td>1961</td>\n",
" <td>10043.473</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.487023</td>\n",
" <td>5572.824169</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>AFG</td>\n",
" <td>1962</td>\n",
" <td>10267.083</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.431779</td>\n",
" <td>5691.226719</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>AFG</td>\n",
" <td>1963</td>\n",
" <td>10500.711</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.335655</td>\n",
" <td>5810.637255</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>AFG</td>\n",
" <td>1964</td>\n",
" <td>10744.167</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.181682</td>\n",
" <td>5928.812085</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9476</th>\n",
" <td>ZWE</td>\n",
" <td>2006</td>\n",
" <td>11544.326</td>\n",
" <td>361.018746</td>\n",
" <td>3.118174</td>\n",
" <td>54.770759</td>\n",
" <td>6322.915007</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9477</th>\n",
" <td>ZWE</td>\n",
" <td>2007</td>\n",
" <td>11443.187</td>\n",
" <td>294.536335</td>\n",
" <td>3.164092</td>\n",
" <td>54.635371</td>\n",
" <td>6252.027655</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9478</th>\n",
" <td>ZWE</td>\n",
" <td>2008</td>\n",
" <td>11350.111</td>\n",
" <td>275.703327</td>\n",
" <td>3.295467</td>\n",
" <td>54.418664</td>\n",
" <td>6176.578825</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9479</th>\n",
" <td>ZWE</td>\n",
" <td>2009</td>\n",
" <td>11392.629</td>\n",
" <td>300.428289</td>\n",
" <td>2.937018</td>\n",
" <td>54.169175</td>\n",
" <td>6171.293169</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9480</th>\n",
" <td>ZWE</td>\n",
" <td>2010</td>\n",
" <td>11651.858</td>\n",
" <td>318.804100</td>\n",
" <td>3.131205</td>\n",
" <td>53.889596</td>\n",
" <td>6279.139248</td>\n",
" <td>5.894</td>\n",
" <td>1.944</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>9481 rows × 9 columns</p>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-517df169-65fa-4f8b-ae97-1cb99994be63')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-517df169-65fa-4f8b-ae97-1cb99994be63 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-517df169-65fa-4f8b-ae97-1cb99994be63');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-031c92e2-5d88-4007-b170-cf88b4e0195e\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-031c92e2-5d88-4007-b170-cf88b4e0195e')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-031c92e2-5d88-4007-b170-cf88b4e0195e button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" <div id=\"id_087cb0d5-da3c-43dd-9808-16de73b77f9a\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('merged_df')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_087cb0d5-da3c-43dd-9808-16de73b77f9a button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('merged_df');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "merged_df",
"summary": "{\n \"name\": \"merged_df\",\n \"rows\": 9481,\n \"fields\": [\n {\n \"column\": \"isocode\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 190,\n \"samples\": [\n \"TUR\",\n \"GBR\",\n \"MUS\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"year\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 14,\n \"min\": 1960,\n \"max\": 2010,\n \"num_unique_values\": 51,\n \"samples\": [\n 2003,\n 2000,\n 2006\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"POP\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 126362.24960859088,\n \"min\": 9.482,\n \"max\": 1330141.295,\n \"num_unique_values\": 9422,\n \"samples\": [\n 150.508,\n 80313.516,\n 49.888\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rgdpl\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 11350.461032763233,\n \"min\": 160.7972212,\n \"max\": 136311.0084,\n \"num_unique_values\": 8083,\n \"samples\": [\n 2579.061492,\n 10488.47502,\n 15815.04688\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ki\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 11.356085221428252,\n \"min\": -11.49638271,\n \"max\": 93.63680575,\n \"num_unique_values\": 8081,\n \"samples\": [\n 13.18122334,\n 23.99502517,\n 13.63452372\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"L_P\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 6.940328455341578,\n \"min\": 44.77987337,\n \"max\": 86.07924571,\n \"num_unique_values\": 9277,\n \"samples\": [\n 51.89760401,\n 48.68291727,\n 62.43031124\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"L\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 64609.16110926366,\n \"min\": 4.5472644501702,\n \"max\": 970057.1435404308,\n \"num_unique_values\": 9277,\n \"samples\": [\n 3278.9887078233787,\n 3937.6194238910643,\n 1688.4090383924279\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"H_P\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.8513064485947293,\n \"min\": 0.037,\n \"max\": 8.866,\n \"num_unique_values\": 1346,\n \"samples\": [\n 5.825,\n 1.893,\n 8.839\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"H_S\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.5040417150370304,\n \"min\": 0.0,\n \"max\": 6.806,\n \"num_unique_values\": 1268,\n \"samples\": [\n 4.171,\n 2.656,\n 1.753\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 15
}
]
},
{
"cell_type": "code",
"source": [
"merged_df['h_1'] = merged_df['H_P'] + merged_df['H_S']\n"
],
"metadata": {
"id": "YnCPO9KR_XmD"
},
"execution_count": 16,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# h_2 = H_P\n",
"merged_df['h_2'] = merged_df['H_P']\n",
"merged_df"
],
"metadata": {
"id": "evWNKo0O_0BW",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 424
},
"outputId": "287b97ed-35fd-4d1b-a67c-042ba7fb1cab"
},
"execution_count": 17,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" isocode year POP rgdpl ki L_P L \\\n",
"0 AFG 1960 9829.450 NaN NaN 55.539784 5459.255307 \n",
"1 AFG 1961 10043.473 NaN NaN 55.487023 5572.824169 \n",
"2 AFG 1962 10267.083 NaN NaN 55.431779 5691.226719 \n",
"3 AFG 1963 10500.711 NaN NaN 55.335655 5810.637255 \n",
"4 AFG 1964 10744.167 NaN NaN 55.181682 5928.812085 \n",
"... ... ... ... ... ... ... ... \n",
"9476 ZWE 2006 11544.326 361.018746 3.118174 54.770759 6322.915007 \n",
"9477 ZWE 2007 11443.187 294.536335 3.164092 54.635371 6252.027655 \n",
"9478 ZWE 2008 11350.111 275.703327 3.295467 54.418664 6176.578825 \n",
"9479 ZWE 2009 11392.629 300.428289 2.937018 54.169175 6171.293169 \n",
"9480 ZWE 2010 11651.858 318.804100 3.131205 53.889596 6279.139248 \n",
"\n",
" H_P H_S h_1 h_2 \n",
"0 0.286 0.075 0.361 0.286 \n",
"1 NaN NaN NaN NaN \n",
"2 NaN NaN NaN NaN \n",
"3 NaN NaN NaN NaN \n",
"4 NaN NaN NaN NaN \n",
"... ... ... ... ... \n",
"9476 NaN NaN NaN NaN \n",
"9477 NaN NaN NaN NaN \n",
"9478 NaN NaN NaN NaN \n",
"9479 NaN NaN NaN NaN \n",
"9480 5.894 1.944 7.838 5.894 \n",
"\n",
"[9481 rows x 11 columns]"
],
"text/html": [
"\n",
" <div id=\"df-8f114049-0819-410b-8a8a-4c5fa04d7fac\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>isocode</th>\n",
" <th>year</th>\n",
" <th>POP</th>\n",
" <th>rgdpl</th>\n",
" <th>ki</th>\n",
" <th>L_P</th>\n",
" <th>L</th>\n",
" <th>H_P</th>\n",
" <th>H_S</th>\n",
" <th>h_1</th>\n",
" <th>h_2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>AFG</td>\n",
" <td>1960</td>\n",
" <td>9829.450</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.539784</td>\n",
" <td>5459.255307</td>\n",
" <td>0.286</td>\n",
" <td>0.075</td>\n",
" <td>0.361</td>\n",
" <td>0.286</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>AFG</td>\n",
" <td>1961</td>\n",
" <td>10043.473</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.487023</td>\n",
" <td>5572.824169</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>AFG</td>\n",
" <td>1962</td>\n",
" <td>10267.083</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.431779</td>\n",
" <td>5691.226719</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>AFG</td>\n",
" <td>1963</td>\n",
" <td>10500.711</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.335655</td>\n",
" <td>5810.637255</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>AFG</td>\n",
" <td>1964</td>\n",
" <td>10744.167</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.181682</td>\n",
" <td>5928.812085</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9476</th>\n",
" <td>ZWE</td>\n",
" <td>2006</td>\n",
" <td>11544.326</td>\n",
" <td>361.018746</td>\n",
" <td>3.118174</td>\n",
" <td>54.770759</td>\n",
" <td>6322.915007</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9477</th>\n",
" <td>ZWE</td>\n",
" <td>2007</td>\n",
" <td>11443.187</td>\n",
" <td>294.536335</td>\n",
" <td>3.164092</td>\n",
" <td>54.635371</td>\n",
" <td>6252.027655</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9478</th>\n",
" <td>ZWE</td>\n",
" <td>2008</td>\n",
" <td>11350.111</td>\n",
" <td>275.703327</td>\n",
" <td>3.295467</td>\n",
" <td>54.418664</td>\n",
" <td>6176.578825</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9479</th>\n",
" <td>ZWE</td>\n",
" <td>2009</td>\n",
" <td>11392.629</td>\n",
" <td>300.428289</td>\n",
" <td>2.937018</td>\n",
" <td>54.169175</td>\n",
" <td>6171.293169</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9480</th>\n",
" <td>ZWE</td>\n",
" <td>2010</td>\n",
" <td>11651.858</td>\n",
" <td>318.804100</td>\n",
" <td>3.131205</td>\n",
" <td>53.889596</td>\n",
" <td>6279.139248</td>\n",
" <td>5.894</td>\n",
" <td>1.944</td>\n",
" <td>7.838</td>\n",
" <td>5.894</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>9481 rows × 11 columns</p>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-8f114049-0819-410b-8a8a-4c5fa04d7fac')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-8f114049-0819-410b-8a8a-4c5fa04d7fac button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-8f114049-0819-410b-8a8a-4c5fa04d7fac');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-328d9b73-02b8-4af1-ba19-3bbe75e78a70\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-328d9b73-02b8-4af1-ba19-3bbe75e78a70')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-328d9b73-02b8-4af1-ba19-3bbe75e78a70 button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" <div id=\"id_d1bab278-17ec-4358-9c41-cb86dc135548\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('merged_df')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_d1bab278-17ec-4358-9c41-cb86dc135548 button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('merged_df');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "merged_df",
"summary": "{\n \"name\": \"merged_df\",\n \"rows\": 9481,\n \"fields\": [\n {\n \"column\": \"isocode\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 190,\n \"samples\": [\n \"TUR\",\n \"GBR\",\n \"MUS\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"year\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 14,\n \"min\": 1960,\n \"max\": 2010,\n \"num_unique_values\": 51,\n \"samples\": [\n 2003,\n 2000,\n 2006\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"POP\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 126362.24960859088,\n \"min\": 9.482,\n \"max\": 1330141.295,\n \"num_unique_values\": 9422,\n \"samples\": [\n 150.508,\n 80313.516,\n 49.888\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rgdpl\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 11350.461032763233,\n \"min\": 160.7972212,\n \"max\": 136311.0084,\n \"num_unique_values\": 8083,\n \"samples\": [\n 2579.061492,\n 10488.47502,\n 15815.04688\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ki\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 11.356085221428252,\n \"min\": -11.49638271,\n \"max\": 93.63680575,\n \"num_unique_values\": 8081,\n \"samples\": [\n 13.18122334,\n 23.99502517,\n 13.63452372\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"L_P\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 6.940328455341578,\n \"min\": 44.77987337,\n \"max\": 86.07924571,\n \"num_unique_values\": 9277,\n \"samples\": [\n 51.89760401,\n 48.68291727,\n 62.43031124\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"L\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 64609.16110926366,\n \"min\": 4.5472644501702,\n \"max\": 970057.1435404308,\n \"num_unique_values\": 9277,\n \"samples\": [\n 3278.9887078233787,\n 3937.6194238910643,\n 1688.4090383924279\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"H_P\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.8513064485947293,\n \"min\": 0.037,\n \"max\": 8.866,\n \"num_unique_values\": 1346,\n \"samples\": [\n 5.825,\n 1.893,\n 8.839\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"H_S\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.5040417150370304,\n \"min\": 0.0,\n \"max\": 6.806,\n \"num_unique_values\": 1268,\n \"samples\": [\n 4.171,\n 2.656,\n 1.753\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"h_1\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3.0423666509670935,\n \"min\": 0.041999999999999996,\n \"max\": 12.466999999999999,\n \"num_unique_values\": 1435,\n \"samples\": [\n 3.0700000000000003,\n 4.126,\n 4.459\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"h_2\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.8513064485947293,\n \"min\": 0.037,\n \"max\": 8.866,\n \"num_unique_values\": 1346,\n \"samples\": [\n 5.825,\n 1.893,\n 8.839\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 17
}
]
},
{
"cell_type": "code",
"source": [
"merged_df = merged_df[(merged_df['year'] >= 1960) & (merged_df['year'] <= 2010)]\n",
"merged_df"
],
"metadata": {
"id": "KoEv2Qy7I6kU",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 424
},
"outputId": "a1ae6ca6-33c0-49c8-9555-f56ef64c0225"
},
"execution_count": 18,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" isocode year POP rgdpl ki L_P L \\\n",
"0 AFG 1960 9829.450 NaN NaN 55.539784 5459.255307 \n",
"1 AFG 1961 10043.473 NaN NaN 55.487023 5572.824169 \n",
"2 AFG 1962 10267.083 NaN NaN 55.431779 5691.226719 \n",
"3 AFG 1963 10500.711 NaN NaN 55.335655 5810.637255 \n",
"4 AFG 1964 10744.167 NaN NaN 55.181682 5928.812085 \n",
"... ... ... ... ... ... ... ... \n",
"9476 ZWE 2006 11544.326 361.018746 3.118174 54.770759 6322.915007 \n",
"9477 ZWE 2007 11443.187 294.536335 3.164092 54.635371 6252.027655 \n",
"9478 ZWE 2008 11350.111 275.703327 3.295467 54.418664 6176.578825 \n",
"9479 ZWE 2009 11392.629 300.428289 2.937018 54.169175 6171.293169 \n",
"9480 ZWE 2010 11651.858 318.804100 3.131205 53.889596 6279.139248 \n",
"\n",
" H_P H_S h_1 h_2 \n",
"0 0.286 0.075 0.361 0.286 \n",
"1 NaN NaN NaN NaN \n",
"2 NaN NaN NaN NaN \n",
"3 NaN NaN NaN NaN \n",
"4 NaN NaN NaN NaN \n",
"... ... ... ... ... \n",
"9476 NaN NaN NaN NaN \n",
"9477 NaN NaN NaN NaN \n",
"9478 NaN NaN NaN NaN \n",
"9479 NaN NaN NaN NaN \n",
"9480 5.894 1.944 7.838 5.894 \n",
"\n",
"[9481 rows x 11 columns]"
],
"text/html": [
"\n",
" <div id=\"df-4c39a833-0aef-4547-ba78-374c2ee74358\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>isocode</th>\n",
" <th>year</th>\n",
" <th>POP</th>\n",
" <th>rgdpl</th>\n",
" <th>ki</th>\n",
" <th>L_P</th>\n",
" <th>L</th>\n",
" <th>H_P</th>\n",
" <th>H_S</th>\n",
" <th>h_1</th>\n",
" <th>h_2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>AFG</td>\n",
" <td>1960</td>\n",
" <td>9829.450</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.539784</td>\n",
" <td>5459.255307</td>\n",
" <td>0.286</td>\n",
" <td>0.075</td>\n",
" <td>0.361</td>\n",
" <td>0.286</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>AFG</td>\n",
" <td>1961</td>\n",
" <td>10043.473</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.487023</td>\n",
" <td>5572.824169</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>AFG</td>\n",
" <td>1962</td>\n",
" <td>10267.083</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.431779</td>\n",
" <td>5691.226719</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>AFG</td>\n",
" <td>1963</td>\n",
" <td>10500.711</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.335655</td>\n",
" <td>5810.637255</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>AFG</td>\n",
" <td>1964</td>\n",
" <td>10744.167</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.181682</td>\n",
" <td>5928.812085</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9476</th>\n",
" <td>ZWE</td>\n",
" <td>2006</td>\n",
" <td>11544.326</td>\n",
" <td>361.018746</td>\n",
" <td>3.118174</td>\n",
" <td>54.770759</td>\n",
" <td>6322.915007</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9477</th>\n",
" <td>ZWE</td>\n",
" <td>2007</td>\n",
" <td>11443.187</td>\n",
" <td>294.536335</td>\n",
" <td>3.164092</td>\n",
" <td>54.635371</td>\n",
" <td>6252.027655</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9478</th>\n",
" <td>ZWE</td>\n",
" <td>2008</td>\n",
" <td>11350.111</td>\n",
" <td>275.703327</td>\n",
" <td>3.295467</td>\n",
" <td>54.418664</td>\n",
" <td>6176.578825</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9479</th>\n",
" <td>ZWE</td>\n",
" <td>2009</td>\n",
" <td>11392.629</td>\n",
" <td>300.428289</td>\n",
" <td>2.937018</td>\n",
" <td>54.169175</td>\n",
" <td>6171.293169</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9480</th>\n",
" <td>ZWE</td>\n",
" <td>2010</td>\n",
" <td>11651.858</td>\n",
" <td>318.804100</td>\n",
" <td>3.131205</td>\n",
" <td>53.889596</td>\n",
" <td>6279.139248</td>\n",
" <td>5.894</td>\n",
" <td>1.944</td>\n",
" <td>7.838</td>\n",
" <td>5.894</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>9481 rows × 11 columns</p>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-4c39a833-0aef-4547-ba78-374c2ee74358')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-4c39a833-0aef-4547-ba78-374c2ee74358 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-4c39a833-0aef-4547-ba78-374c2ee74358');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-46f59e60-1227-4ae8-9596-1a91e8514226\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-46f59e60-1227-4ae8-9596-1a91e8514226')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-46f59e60-1227-4ae8-9596-1a91e8514226 button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" <div id=\"id_5946a28c-16a6-4db9-ba5b-3b33d1f0822b\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('merged_df')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_5946a28c-16a6-4db9-ba5b-3b33d1f0822b button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('merged_df');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "merged_df",
"summary": "{\n \"name\": \"merged_df\",\n \"rows\": 9481,\n \"fields\": [\n {\n \"column\": \"isocode\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 190,\n \"samples\": [\n \"TUR\",\n \"GBR\",\n \"MUS\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"year\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 14,\n \"min\": 1960,\n \"max\": 2010,\n \"num_unique_values\": 51,\n \"samples\": [\n 2003,\n 2000,\n 2006\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"POP\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 126362.24960859088,\n \"min\": 9.482,\n \"max\": 1330141.295,\n \"num_unique_values\": 9422,\n \"samples\": [\n 150.508,\n 80313.516,\n 49.888\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rgdpl\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 11350.461032763233,\n \"min\": 160.7972212,\n \"max\": 136311.0084,\n \"num_unique_values\": 8083,\n \"samples\": [\n 2579.061492,\n 10488.47502,\n 15815.04688\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ki\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 11.356085221428252,\n \"min\": -11.49638271,\n \"max\": 93.63680575,\n \"num_unique_values\": 8081,\n \"samples\": [\n 13.18122334,\n 23.99502517,\n 13.63452372\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"L_P\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 6.940328455341578,\n \"min\": 44.77987337,\n \"max\": 86.07924571,\n \"num_unique_values\": 9277,\n \"samples\": [\n 51.89760401,\n 48.68291727,\n 62.43031124\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"L\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 64609.16110926366,\n \"min\": 4.5472644501702,\n \"max\": 970057.1435404308,\n \"num_unique_values\": 9277,\n \"samples\": [\n 3278.9887078233787,\n 3937.6194238910643,\n 1688.4090383924279\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"H_P\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.8513064485947293,\n \"min\": 0.037,\n \"max\": 8.866,\n \"num_unique_values\": 1346,\n \"samples\": [\n 5.825,\n 1.893,\n 8.839\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"H_S\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.5040417150370304,\n \"min\": 0.0,\n \"max\": 6.806,\n \"num_unique_values\": 1268,\n \"samples\": [\n 4.171,\n 2.656,\n 1.753\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"h_1\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3.0423666509670935,\n \"min\": 0.041999999999999996,\n \"max\": 12.466999999999999,\n \"num_unique_values\": 1435,\n \"samples\": [\n 3.0700000000000003,\n 4.126,\n 4.459\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"h_2\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.8513064485947293,\n \"min\": 0.037,\n \"max\": 8.866,\n \"num_unique_values\": 1346,\n \"samples\": [\n 5.825,\n 1.893,\n 8.839\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 18
}
]
},
{
"cell_type": "code",
"source": [
"# Sort the DataFrame by country and year\n",
"merged_df.sort_values(['isocode', 'year'], inplace=True)\n",
"\n",
"# Within each country, shift 'L' by -5 years to get L_t+5\n",
"merged_df['L_t+5'] = merged_df.groupby('isocode')['L'].shift(-5)\n",
"merged_df"
],
"metadata": {
"id": "ULzzIxETSbF7",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 424
},
"outputId": "e0c7aee7-9dc2-40d3-dc5f-4590b5120871"
},
"execution_count": 19,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" isocode year POP rgdpl ki L_P L \\\n",
"0 AFG 1960 9829.450 NaN NaN 55.539784 5459.255307 \n",
"1 AFG 1961 10043.473 NaN NaN 55.487023 5572.824169 \n",
"2 AFG 1962 10267.083 NaN NaN 55.431779 5691.226719 \n",
"3 AFG 1963 10500.711 NaN NaN 55.335655 5810.637255 \n",
"4 AFG 1964 10744.167 NaN NaN 55.181682 5928.812085 \n",
"... ... ... ... ... ... ... ... \n",
"9476 ZWE 2006 11544.326 361.018746 3.118174 54.770759 6322.915007 \n",
"9477 ZWE 2007 11443.187 294.536335 3.164092 54.635371 6252.027655 \n",
"9478 ZWE 2008 11350.111 275.703327 3.295467 54.418664 6176.578825 \n",
"9479 ZWE 2009 11392.629 300.428289 2.937018 54.169175 6171.293169 \n",
"9480 ZWE 2010 11651.858 318.804100 3.131205 53.889596 6279.139248 \n",
"\n",
" H_P H_S h_1 h_2 L_t+5 \n",
"0 0.286 0.075 0.361 0.286 6042.966109 \n",
"1 NaN NaN NaN NaN 6155.798480 \n",
"2 NaN NaN NaN NaN 6273.768653 \n",
"3 NaN NaN NaN NaN 6397.454028 \n",
"4 NaN NaN NaN NaN 6525.993579 \n",
"... ... ... ... ... ... \n",
"9476 NaN NaN NaN NaN NaN \n",
"9477 NaN NaN NaN NaN NaN \n",
"9478 NaN NaN NaN NaN NaN \n",
"9479 NaN NaN NaN NaN NaN \n",
"9480 5.894 1.944 7.838 5.894 NaN \n",
"\n",
"[9481 rows x 12 columns]"
],
"text/html": [
"\n",
" <div id=\"df-c414cb39-bf24-4a07-84f9-35c2dacf56d4\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>isocode</th>\n",
" <th>year</th>\n",
" <th>POP</th>\n",
" <th>rgdpl</th>\n",
" <th>ki</th>\n",
" <th>L_P</th>\n",
" <th>L</th>\n",
" <th>H_P</th>\n",
" <th>H_S</th>\n",
" <th>h_1</th>\n",
" <th>h_2</th>\n",
" <th>L_t+5</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>AFG</td>\n",
" <td>1960</td>\n",
" <td>9829.450</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.539784</td>\n",
" <td>5459.255307</td>\n",
" <td>0.286</td>\n",
" <td>0.075</td>\n",
" <td>0.361</td>\n",
" <td>0.286</td>\n",
" <td>6042.966109</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>AFG</td>\n",
" <td>1961</td>\n",
" <td>10043.473</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.487023</td>\n",
" <td>5572.824169</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>6155.798480</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>AFG</td>\n",
" <td>1962</td>\n",
" <td>10267.083</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.431779</td>\n",
" <td>5691.226719</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>6273.768653</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>AFG</td>\n",
" <td>1963</td>\n",
" <td>10500.711</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.335655</td>\n",
" <td>5810.637255</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>6397.454028</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>AFG</td>\n",
" <td>1964</td>\n",
" <td>10744.167</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.181682</td>\n",
" <td>5928.812085</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>6525.993579</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9476</th>\n",
" <td>ZWE</td>\n",
" <td>2006</td>\n",
" <td>11544.326</td>\n",
" <td>361.018746</td>\n",
" <td>3.118174</td>\n",
" <td>54.770759</td>\n",
" <td>6322.915007</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9477</th>\n",
" <td>ZWE</td>\n",
" <td>2007</td>\n",
" <td>11443.187</td>\n",
" <td>294.536335</td>\n",
" <td>3.164092</td>\n",
" <td>54.635371</td>\n",
" <td>6252.027655</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9478</th>\n",
" <td>ZWE</td>\n",
" <td>2008</td>\n",
" <td>11350.111</td>\n",
" <td>275.703327</td>\n",
" <td>3.295467</td>\n",
" <td>54.418664</td>\n",
" <td>6176.578825</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9479</th>\n",
" <td>ZWE</td>\n",
" <td>2009</td>\n",
" <td>11392.629</td>\n",
" <td>300.428289</td>\n",
" <td>2.937018</td>\n",
" <td>54.169175</td>\n",
" <td>6171.293169</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9480</th>\n",
" <td>ZWE</td>\n",
" <td>2010</td>\n",
" <td>11651.858</td>\n",
" <td>318.804100</td>\n",
" <td>3.131205</td>\n",
" <td>53.889596</td>\n",
" <td>6279.139248</td>\n",
" <td>5.894</td>\n",
" <td>1.944</td>\n",
" <td>7.838</td>\n",
" <td>5.894</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>9481 rows × 12 columns</p>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-c414cb39-bf24-4a07-84f9-35c2dacf56d4')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-c414cb39-bf24-4a07-84f9-35c2dacf56d4 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-c414cb39-bf24-4a07-84f9-35c2dacf56d4');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-ab5b041d-1cb7-4ce6-9180-c48c62ec7a0c\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-ab5b041d-1cb7-4ce6-9180-c48c62ec7a0c')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-ab5b041d-1cb7-4ce6-9180-c48c62ec7a0c button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" <div id=\"id_dbadcafa-6ba7-44c9-a584-b7eaa37428db\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('merged_df')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_dbadcafa-6ba7-44c9-a584-b7eaa37428db button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('merged_df');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "merged_df",
"summary": "{\n \"name\": \"merged_df\",\n \"rows\": 9481,\n \"fields\": [\n {\n \"column\": \"isocode\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 190,\n \"samples\": [\n \"UGA\",\n \"VCT\",\n \"MEX\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"year\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 14,\n \"min\": 1960,\n \"max\": 2010,\n \"num_unique_values\": 51,\n \"samples\": [\n 2003,\n 2000,\n 2006\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"POP\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 126362.24960859094,\n \"min\": 9.482,\n \"max\": 1330141.295,\n \"num_unique_values\": 9422,\n \"samples\": [\n 22060.808,\n 7777.709,\n 13787.599\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rgdpl\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 11350.461032763236,\n \"min\": 160.7972212,\n \"max\": 136311.0084,\n \"num_unique_values\": 8083,\n \"samples\": [\n 3393.640334,\n 564.0738132,\n 730.8600207\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ki\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 11.35608522142825,\n \"min\": -11.49638271,\n \"max\": 93.63680575,\n \"num_unique_values\": 8081,\n \"samples\": [\n 20.34722161,\n 18.96776965,\n 26.90751452\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"L_P\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 6.940328455341577,\n \"min\": 44.77987337,\n \"max\": 86.07924571,\n \"num_unique_values\": 9277,\n \"samples\": [\n 55.10767497,\n 48.68291727,\n 49.64907872\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"L\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 64609.161109263725,\n \"min\": 4.5472644501702,\n \"max\": 970057.1435404308,\n \"num_unique_values\": 9277,\n \"samples\": [\n 282.08902417368387,\n 3937.6194238910643,\n 4134.334391982566\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"H_P\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.85130644859473,\n \"min\": 0.037,\n \"max\": 8.866,\n \"num_unique_values\": 1346,\n \"samples\": [\n 2.871,\n 8.469,\n 5.656\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"H_S\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.5040417150370302,\n \"min\": 0.0,\n \"max\": 6.806,\n \"num_unique_values\": 1268,\n \"samples\": [\n 2.409,\n 1.79,\n 1.307\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"h_1\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3.0423666509670926,\n \"min\": 0.041999999999999996,\n \"max\": 12.466999999999999,\n \"num_unique_values\": 1435,\n \"samples\": [\n 4.425,\n 6.414,\n 9.241\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"h_2\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.85130644859473,\n \"min\": 0.037,\n \"max\": 8.866,\n \"num_unique_values\": 1346,\n \"samples\": [\n 2.871,\n 8.469,\n 5.656\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"L_t+5\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 67073.71945809368,\n \"min\": 4.886858225134399,\n \"max\": 970057.1435404308,\n \"num_unique_values\": 8347,\n \"samples\": [\n 2528.1476774625976,\n 39499.124459031045,\n 86.8734947670324\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 19
}
]
},
{
"cell_type": "code",
"source": [
"# Calculate n only where L_t and L_t+5 are available\n",
"merged_df['n'] = np.where(\n",
" merged_df['L_t+5'].notnull(),\n",
" (merged_df['L_t+5'] / merged_df['L']) ** (1/5) - 1,\n",
" np.nan # Assign NaN if L_t+5 is not available\n",
")\n",
"merged_df"
],
"metadata": {
"id": "wC19e9gBScnA",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 424
},
"outputId": "8e75c0ef-5bbf-4d5f-bf6e-b74f5abd5e91"
},
"execution_count": 20,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" isocode year POP rgdpl ki L_P L \\\n",
"0 AFG 1960 9829.450 NaN NaN 55.539784 5459.255307 \n",
"1 AFG 1961 10043.473 NaN NaN 55.487023 5572.824169 \n",
"2 AFG 1962 10267.083 NaN NaN 55.431779 5691.226719 \n",
"3 AFG 1963 10500.711 NaN NaN 55.335655 5810.637255 \n",
"4 AFG 1964 10744.167 NaN NaN 55.181682 5928.812085 \n",
"... ... ... ... ... ... ... ... \n",
"9476 ZWE 2006 11544.326 361.018746 3.118174 54.770759 6322.915007 \n",
"9477 ZWE 2007 11443.187 294.536335 3.164092 54.635371 6252.027655 \n",
"9478 ZWE 2008 11350.111 275.703327 3.295467 54.418664 6176.578825 \n",
"9479 ZWE 2009 11392.629 300.428289 2.937018 54.169175 6171.293169 \n",
"9480 ZWE 2010 11651.858 318.804100 3.131205 53.889596 6279.139248 \n",
"\n",
" H_P H_S h_1 h_2 L_t+5 n \n",
"0 0.286 0.075 0.361 0.286 6042.966109 0.020524 \n",
"1 NaN NaN NaN NaN 6155.798480 0.020098 \n",
"2 NaN NaN NaN NaN 6273.768653 0.019681 \n",
"3 NaN NaN NaN NaN 6397.454028 0.019428 \n",
"4 NaN NaN NaN NaN 6525.993579 0.019379 \n",
"... ... ... ... ... ... ... \n",
"9476 NaN NaN NaN NaN NaN NaN \n",
"9477 NaN NaN NaN NaN NaN NaN \n",
"9478 NaN NaN NaN NaN NaN NaN \n",
"9479 NaN NaN NaN NaN NaN NaN \n",
"9480 5.894 1.944 7.838 5.894 NaN NaN \n",
"\n",
"[9481 rows x 13 columns]"
],
"text/html": [
"\n",
" <div id=\"df-f853a020-a3cf-4b95-978e-8223e69c3d4e\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>isocode</th>\n",
" <th>year</th>\n",
" <th>POP</th>\n",
" <th>rgdpl</th>\n",
" <th>ki</th>\n",
" <th>L_P</th>\n",
" <th>L</th>\n",
" <th>H_P</th>\n",
" <th>H_S</th>\n",
" <th>h_1</th>\n",
" <th>h_2</th>\n",
" <th>L_t+5</th>\n",
" <th>n</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>AFG</td>\n",
" <td>1960</td>\n",
" <td>9829.450</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.539784</td>\n",
" <td>5459.255307</td>\n",
" <td>0.286</td>\n",
" <td>0.075</td>\n",
" <td>0.361</td>\n",
" <td>0.286</td>\n",
" <td>6042.966109</td>\n",
" <td>0.020524</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>AFG</td>\n",
" <td>1961</td>\n",
" <td>10043.473</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.487023</td>\n",
" <td>5572.824169</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>6155.798480</td>\n",
" <td>0.020098</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>AFG</td>\n",
" <td>1962</td>\n",
" <td>10267.083</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.431779</td>\n",
" <td>5691.226719</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>6273.768653</td>\n",
" <td>0.019681</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>AFG</td>\n",
" <td>1963</td>\n",
" <td>10500.711</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.335655</td>\n",
" <td>5810.637255</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>6397.454028</td>\n",
" <td>0.019428</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>AFG</td>\n",
" <td>1964</td>\n",
" <td>10744.167</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.181682</td>\n",
" <td>5928.812085</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>6525.993579</td>\n",
" <td>0.019379</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9476</th>\n",
" <td>ZWE</td>\n",
" <td>2006</td>\n",
" <td>11544.326</td>\n",
" <td>361.018746</td>\n",
" <td>3.118174</td>\n",
" <td>54.770759</td>\n",
" <td>6322.915007</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9477</th>\n",
" <td>ZWE</td>\n",
" <td>2007</td>\n",
" <td>11443.187</td>\n",
" <td>294.536335</td>\n",
" <td>3.164092</td>\n",
" <td>54.635371</td>\n",
" <td>6252.027655</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9478</th>\n",
" <td>ZWE</td>\n",
" <td>2008</td>\n",
" <td>11350.111</td>\n",
" <td>275.703327</td>\n",
" <td>3.295467</td>\n",
" <td>54.418664</td>\n",
" <td>6176.578825</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9479</th>\n",
" <td>ZWE</td>\n",
" <td>2009</td>\n",
" <td>11392.629</td>\n",
" <td>300.428289</td>\n",
" <td>2.937018</td>\n",
" <td>54.169175</td>\n",
" <td>6171.293169</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9480</th>\n",
" <td>ZWE</td>\n",
" <td>2010</td>\n",
" <td>11651.858</td>\n",
" <td>318.804100</td>\n",
" <td>3.131205</td>\n",
" <td>53.889596</td>\n",
" <td>6279.139248</td>\n",
" <td>5.894</td>\n",
" <td>1.944</td>\n",
" <td>7.838</td>\n",
" <td>5.894</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>9481 rows × 13 columns</p>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-f853a020-a3cf-4b95-978e-8223e69c3d4e')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-f853a020-a3cf-4b95-978e-8223e69c3d4e button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-f853a020-a3cf-4b95-978e-8223e69c3d4e');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-bad67d9d-b865-4a4a-9bbe-481dfbc8fb00\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-bad67d9d-b865-4a4a-9bbe-481dfbc8fb00')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-bad67d9d-b865-4a4a-9bbe-481dfbc8fb00 button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" <div id=\"id_8a37c827-6ab8-49b2-8c30-13b90e48e586\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('merged_df')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_8a37c827-6ab8-49b2-8c30-13b90e48e586 button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('merged_df');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "merged_df",
"summary": "{\n \"name\": \"merged_df\",\n \"rows\": 9481,\n \"fields\": [\n {\n \"column\": \"isocode\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 190,\n \"samples\": [\n \"UGA\",\n \"VCT\",\n \"MEX\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"year\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 14,\n \"min\": 1960,\n \"max\": 2010,\n \"num_unique_values\": 51,\n \"samples\": [\n 2003,\n 2000,\n 2006\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"POP\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 126362.24960859094,\n \"min\": 9.482,\n \"max\": 1330141.295,\n \"num_unique_values\": 9422,\n \"samples\": [\n 22060.808,\n 7777.709,\n 13787.599\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rgdpl\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 11350.461032763236,\n \"min\": 160.7972212,\n \"max\": 136311.0084,\n \"num_unique_values\": 8083,\n \"samples\": [\n 3393.640334,\n 564.0738132,\n 730.8600207\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ki\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 11.35608522142825,\n \"min\": -11.49638271,\n \"max\": 93.63680575,\n \"num_unique_values\": 8081,\n \"samples\": [\n 20.34722161,\n 18.96776965,\n 26.90751452\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"L_P\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 6.940328455341577,\n \"min\": 44.77987337,\n \"max\": 86.07924571,\n \"num_unique_values\": 9277,\n \"samples\": [\n 55.10767497,\n 48.68291727,\n 49.64907872\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"L\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 64609.161109263725,\n \"min\": 4.5472644501702,\n \"max\": 970057.1435404308,\n \"num_unique_values\": 9277,\n \"samples\": [\n 282.08902417368387,\n 3937.6194238910643,\n 4134.334391982566\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"H_P\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.85130644859473,\n \"min\": 0.037,\n \"max\": 8.866,\n \"num_unique_values\": 1346,\n \"samples\": [\n 2.871,\n 8.469,\n 5.656\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"H_S\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.5040417150370302,\n \"min\": 0.0,\n \"max\": 6.806,\n \"num_unique_values\": 1268,\n \"samples\": [\n 2.409,\n 1.79,\n 1.307\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"h_1\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3.0423666509670926,\n \"min\": 0.041999999999999996,\n \"max\": 12.466999999999999,\n \"num_unique_values\": 1435,\n \"samples\": [\n 4.425,\n 6.414,\n 9.241\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"h_2\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.85130644859473,\n \"min\": 0.037,\n \"max\": 8.866,\n \"num_unique_values\": 1346,\n \"samples\": [\n 2.871,\n 8.469,\n 5.656\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"L_t+5\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 67073.71945809368,\n \"min\": 4.886858225134399,\n \"max\": 970057.1435404308,\n \"num_unique_values\": 8347,\n \"samples\": [\n 2528.1476774625976,\n 39499.124459031045,\n 86.8734947670324\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"n\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.01629660582911869,\n \"min\": -0.11825851087714279,\n \"max\": 0.1781193746249352,\n \"num_unique_values\": 8347,\n \"samples\": [\n 0.008592904321928385,\n 0.026705905110226746,\n 0.02558583348239485\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 20
}
]
},
{
"cell_type": "code",
"source": [
"# Calculate total GDP (Y)\n",
"merged_df['Y'] = merged_df['rgdpl'] * merged_df['POP']\n",
"\n",
"# Calculate Y_L = Y / L\n",
"merged_df['Y_L'] = merged_df['Y'] / merged_df['L']\n",
"\n",
"# Convert ki from percentage\n",
"merged_df['Sk'] = merged_df['ki'] / 100\n",
"merged_df"
],
"metadata": {
"id": "rH2hG-eXWdf_",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 424
},
"outputId": "e194b045-4593-45a8-fd70-323d95f3f612"
},
"execution_count": 21,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" isocode year POP rgdpl ki L_P L \\\n",
"0 AFG 1960 9829.450 NaN NaN 55.539784 5459.255307 \n",
"1 AFG 1961 10043.473 NaN NaN 55.487023 5572.824169 \n",
"2 AFG 1962 10267.083 NaN NaN 55.431779 5691.226719 \n",
"3 AFG 1963 10500.711 NaN NaN 55.335655 5810.637255 \n",
"4 AFG 1964 10744.167 NaN NaN 55.181682 5928.812085 \n",
"... ... ... ... ... ... ... ... \n",
"9476 ZWE 2006 11544.326 361.018746 3.118174 54.770759 6322.915007 \n",
"9477 ZWE 2007 11443.187 294.536335 3.164092 54.635371 6252.027655 \n",
"9478 ZWE 2008 11350.111 275.703327 3.295467 54.418664 6176.578825 \n",
"9479 ZWE 2009 11392.629 300.428289 2.937018 54.169175 6171.293169 \n",
"9480 ZWE 2010 11651.858 318.804100 3.131205 53.889596 6279.139248 \n",
"\n",
" H_P H_S h_1 h_2 L_t+5 n Y \\\n",
"0 0.286 0.075 0.361 0.286 6042.966109 0.020524 NaN \n",
"1 NaN NaN NaN NaN 6155.798480 0.020098 NaN \n",
"2 NaN NaN NaN NaN 6273.768653 0.019681 NaN \n",
"3 NaN NaN NaN NaN 6397.454028 0.019428 NaN \n",
"4 NaN NaN NaN NaN 6525.993579 0.019379 NaN \n",
"... ... ... ... ... ... ... ... \n",
"9476 NaN NaN NaN NaN NaN NaN 4.167718e+06 \n",
"9477 NaN NaN NaN NaN NaN NaN 3.370434e+06 \n",
"9478 NaN NaN NaN NaN NaN NaN 3.129263e+06 \n",
"9479 NaN NaN NaN NaN NaN NaN 3.422668e+06 \n",
"9480 5.894 1.944 7.838 5.894 NaN NaN 3.714660e+06 \n",
"\n",
" Y_L Sk \n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"... ... ... \n",
"9476 659.145045 0.031182 \n",
"9477 539.094602 0.031641 \n",
"9478 506.633762 0.032955 \n",
"9479 554.611156 0.029370 \n",
"9480 591.587471 0.031312 \n",
"\n",
"[9481 rows x 16 columns]"
],
"text/html": [
"\n",
" <div id=\"df-0b76801e-703f-499d-97fb-855c78381d06\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>isocode</th>\n",
" <th>year</th>\n",
" <th>POP</th>\n",
" <th>rgdpl</th>\n",
" <th>ki</th>\n",
" <th>L_P</th>\n",
" <th>L</th>\n",
" <th>H_P</th>\n",
" <th>H_S</th>\n",
" <th>h_1</th>\n",
" <th>h_2</th>\n",
" <th>L_t+5</th>\n",
" <th>n</th>\n",
" <th>Y</th>\n",
" <th>Y_L</th>\n",
" <th>Sk</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>AFG</td>\n",
" <td>1960</td>\n",
" <td>9829.450</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.539784</td>\n",
" <td>5459.255307</td>\n",
" <td>0.286</td>\n",
" <td>0.075</td>\n",
" <td>0.361</td>\n",
" <td>0.286</td>\n",
" <td>6042.966109</td>\n",
" <td>0.020524</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>AFG</td>\n",
" <td>1961</td>\n",
" <td>10043.473</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.487023</td>\n",
" <td>5572.824169</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>6155.798480</td>\n",
" <td>0.020098</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>AFG</td>\n",
" <td>1962</td>\n",
" <td>10267.083</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.431779</td>\n",
" <td>5691.226719</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>6273.768653</td>\n",
" <td>0.019681</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>AFG</td>\n",
" <td>1963</td>\n",
" <td>10500.711</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.335655</td>\n",
" <td>5810.637255</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>6397.454028</td>\n",
" <td>0.019428</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>AFG</td>\n",
" <td>1964</td>\n",
" <td>10744.167</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>55.181682</td>\n",
" <td>5928.812085</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>6525.993579</td>\n",
" <td>0.019379</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9476</th>\n",
" <td>ZWE</td>\n",
" <td>2006</td>\n",
" <td>11544.326</td>\n",
" <td>361.018746</td>\n",
" <td>3.118174</td>\n",
" <td>54.770759</td>\n",
" <td>6322.915007</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.167718e+06</td>\n",
" <td>659.145045</td>\n",
" <td>0.031182</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9477</th>\n",
" <td>ZWE</td>\n",
" <td>2007</td>\n",
" <td>11443.187</td>\n",
" <td>294.536335</td>\n",
" <td>3.164092</td>\n",
" <td>54.635371</td>\n",
" <td>6252.027655</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>3.370434e+06</td>\n",
" <td>539.094602</td>\n",
" <td>0.031641</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9478</th>\n",
" <td>ZWE</td>\n",
" <td>2008</td>\n",
" <td>11350.111</td>\n",
" <td>275.703327</td>\n",
" <td>3.295467</td>\n",
" <td>54.418664</td>\n",
" <td>6176.578825</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>3.129263e+06</td>\n",
" <td>506.633762</td>\n",
" <td>0.032955</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9479</th>\n",
" <td>ZWE</td>\n",
" <td>2009</td>\n",
" <td>11392.629</td>\n",
" <td>300.428289</td>\n",
" <td>2.937018</td>\n",
" <td>54.169175</td>\n",
" <td>6171.293169</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>3.422668e+06</td>\n",
" <td>554.611156</td>\n",
" <td>0.029370</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9480</th>\n",
" <td>ZWE</td>\n",
" <td>2010</td>\n",
" <td>11651.858</td>\n",
" <td>318.804100</td>\n",
" <td>3.131205</td>\n",
" <td>53.889596</td>\n",
" <td>6279.139248</td>\n",
" <td>5.894</td>\n",
" <td>1.944</td>\n",
" <td>7.838</td>\n",
" <td>5.894</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>3.714660e+06</td>\n",
" <td>591.587471</td>\n",
" <td>0.031312</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>9481 rows × 16 columns</p>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-0b76801e-703f-499d-97fb-855c78381d06')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-0b76801e-703f-499d-97fb-855c78381d06 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-0b76801e-703f-499d-97fb-855c78381d06');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-7c6ed942-c069-4664-8b42-8a5e5474a666\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-7c6ed942-c069-4664-8b42-8a5e5474a666')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-7c6ed942-c069-4664-8b42-8a5e5474a666 button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" <div id=\"id_5c567210-2353-4287-a322-46d90db1b198\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('merged_df')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_5c567210-2353-4287-a322-46d90db1b198 button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('merged_df');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "merged_df",
"summary": "{\n \"name\": \"merged_df\",\n \"rows\": 9481,\n \"fields\": [\n {\n \"column\": \"isocode\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 190,\n \"samples\": [\n \"UGA\",\n \"VCT\",\n \"MEX\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"year\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 14,\n \"min\": 1960,\n \"max\": 2010,\n \"num_unique_values\": 51,\n \"samples\": [\n 2003,\n 2000,\n 2006\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"POP\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 126362.24960859094,\n \"min\": 9.482,\n \"max\": 1330141.295,\n \"num_unique_values\": 9422,\n \"samples\": [\n 22060.808,\n 7777.709,\n 13787.599\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"rgdpl\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 11350.461032763236,\n \"min\": 160.7972212,\n \"max\": 136311.0084,\n \"num_unique_values\": 8083,\n \"samples\": [\n 3393.640334,\n 564.0738132,\n 730.8600207\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ki\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 11.35608522142825,\n \"min\": -11.49638271,\n \"max\": 93.63680575,\n \"num_unique_values\": 8081,\n \"samples\": [\n 20.34722161,\n 18.96776965,\n 26.90751452\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"L_P\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 6.940328455341577,\n \"min\": 44.77987337,\n \"max\": 86.07924571,\n \"num_unique_values\": 9277,\n \"samples\": [\n 55.10767497,\n 48.68291727,\n 49.64907872\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"L\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 64609.161109263725,\n \"min\": 4.5472644501702,\n \"max\": 970057.1435404308,\n \"num_unique_values\": 9277,\n \"samples\": [\n 282.08902417368387,\n 3937.6194238910643,\n 4134.334391982566\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"H_P\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.85130644859473,\n \"min\": 0.037,\n \"max\": 8.866,\n \"num_unique_values\": 1346,\n \"samples\": [\n 2.871,\n 8.469,\n 5.656\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"H_S\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.5040417150370302,\n \"min\": 0.0,\n \"max\": 6.806,\n \"num_unique_values\": 1268,\n \"samples\": [\n 2.409,\n 1.79,\n 1.307\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"h_1\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3.0423666509670926,\n \"min\": 0.041999999999999996,\n \"max\": 12.466999999999999,\n \"num_unique_values\": 1435,\n \"samples\": [\n 4.425,\n 6.414,\n 9.241\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"h_2\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.85130644859473,\n \"min\": 0.037,\n \"max\": 8.866,\n \"num_unique_values\": 1346,\n \"samples\": [\n 2.871,\n 8.469,\n 5.656\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"L_t+5\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 67073.71945809368,\n \"min\": 4.886858225134399,\n \"max\": 970057.1435404308,\n \"num_unique_values\": 8347,\n \"samples\": [\n 2528.1476774625976,\n 39499.124459031045,\n 86.8734947670324\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"n\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.01629660582911869,\n \"min\": -0.11825851087714279,\n \"max\": 0.1781193746249352,\n \"num_unique_values\": 8347,\n \"samples\": [\n 0.008592904321928385,\n 0.026705905110226746,\n 0.02558583348239485\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Y\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 815661844.1853056,\n \"min\": 83485.81917044881,\n \"max\": 13123931539.879808,\n \"num_unique_values\": 8083,\n \"samples\": [\n 211802926.91267416,\n 11489294.030480584,\n 19563276.60172671\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Y_L\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 16703.16159924237,\n \"min\": 296.1609935422071,\n \"max\": 167451.5330628864,\n \"num_unique_values\": 7889,\n \"samples\": [\n 9335.639567305667,\n 3803.0811266756,\n 14012.39503774634\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Sk\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.11356085221428214,\n \"min\": -0.11496382710000001,\n \"max\": 0.9363680575,\n \"num_unique_values\": 8081,\n \"samples\": [\n 0.2034722161,\n 0.18967769650000002,\n 0.2690751452\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 21
}
]
},
{
"cell_type": "code",
"source": [
"# # Group by country and 5-year periods, then calculate the average\n",
"merged_df['year_group'] = (merged_df['year'] // 5) * 5\n",
"\n",
"# List of variables to aggregate\n",
"variables_to_average = ['Y_L', 'Sk', 'n', 'h_1', 'h_2']\n",
"\n",
"# Aggregate data by country and year_group\n",
"merged_df = merged_df.groupby(['isocode', 'year_group'])[variables_to_average].mean().reset_index()\n",
"merged_df"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 424
},
"id": "zI8U6weTP_56",
"outputId": "d2bca823-379d-4d7f-ca92-ee01ae036736"
},
"execution_count": 22,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" isocode year_group Y_L Sk n h_1 h_2\n",
"0 AFG 1960 NaN NaN 0.019822 0.361 0.286\n",
"1 AFG 1965 NaN NaN 0.020521 0.409 0.315\n",
"2 AFG 1970 1885.435178 0.146990 0.021697 0.662 0.477\n",
"3 AFG 1975 2218.826921 0.212154 -0.025493 0.881 0.622\n",
"4 AFG 1980 2682.034132 0.221990 -0.004059 1.173 0.816\n",
"... ... ... ... ... ... ... ...\n",
"2072 ZWE 1990 930.456587 0.035493 0.026490 5.845 3.737\n",
"2073 ZWE 1995 772.957023 0.037646 0.015152 6.766 4.460\n",
"2074 ZWE 2000 658.720907 0.046580 -0.008076 7.230 5.051\n",
"2075 ZWE 2005 569.594484 0.032197 -0.003608 7.626 5.498\n",
"2076 ZWE 2010 591.587471 0.031312 NaN 7.838 5.894\n",
"\n",
"[2077 rows x 7 columns]"
],
"text/html": [
"\n",
" <div id=\"df-81b313fc-3db5-425c-bfb9-96482d55ec21\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>isocode</th>\n",
" <th>year_group</th>\n",
" <th>Y_L</th>\n",
" <th>Sk</th>\n",
" <th>n</th>\n",
" <th>h_1</th>\n",
" <th>h_2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>AFG</td>\n",
" <td>1960</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.019822</td>\n",
" <td>0.361</td>\n",
" <td>0.286</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>AFG</td>\n",
" <td>1965</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.020521</td>\n",
" <td>0.409</td>\n",
" <td>0.315</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>AFG</td>\n",
" <td>1970</td>\n",
" <td>1885.435178</td>\n",
" <td>0.146990</td>\n",
" <td>0.021697</td>\n",
" <td>0.662</td>\n",
" <td>0.477</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>AFG</td>\n",
" <td>1975</td>\n",
" <td>2218.826921</td>\n",
" <td>0.212154</td>\n",
" <td>-0.025493</td>\n",
" <td>0.881</td>\n",
" <td>0.622</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>AFG</td>\n",
" <td>1980</td>\n",
" <td>2682.034132</td>\n",
" <td>0.221990</td>\n",
" <td>-0.004059</td>\n",
" <td>1.173</td>\n",
" <td>0.816</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2072</th>\n",
" <td>ZWE</td>\n",
" <td>1990</td>\n",
" <td>930.456587</td>\n",
" <td>0.035493</td>\n",
" <td>0.026490</td>\n",
" <td>5.845</td>\n",
" <td>3.737</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2073</th>\n",
" <td>ZWE</td>\n",
" <td>1995</td>\n",
" <td>772.957023</td>\n",
" <td>0.037646</td>\n",
" <td>0.015152</td>\n",
" <td>6.766</td>\n",
" <td>4.460</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2074</th>\n",
" <td>ZWE</td>\n",
" <td>2000</td>\n",
" <td>658.720907</td>\n",
" <td>0.046580</td>\n",
" <td>-0.008076</td>\n",
" <td>7.230</td>\n",
" <td>5.051</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2075</th>\n",
" <td>ZWE</td>\n",
" <td>2005</td>\n",
" <td>569.594484</td>\n",
" <td>0.032197</td>\n",
" <td>-0.003608</td>\n",
" <td>7.626</td>\n",
" <td>5.498</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2076</th>\n",
" <td>ZWE</td>\n",
" <td>2010</td>\n",
" <td>591.587471</td>\n",
" <td>0.031312</td>\n",
" <td>NaN</td>\n",
" <td>7.838</td>\n",
" <td>5.894</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>2077 rows × 7 columns</p>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-81b313fc-3db5-425c-bfb9-96482d55ec21')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-81b313fc-3db5-425c-bfb9-96482d55ec21 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-81b313fc-3db5-425c-bfb9-96482d55ec21');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-cdfdb75c-ee7c-443b-b40d-6e01f36f5ee3\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-cdfdb75c-ee7c-443b-b40d-6e01f36f5ee3')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-cdfdb75c-ee7c-443b-b40d-6e01f36f5ee3 button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" <div id=\"id_ac5cea3c-56da-4518-9de5-22dbcc12e1ed\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('merged_df')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_ac5cea3c-56da-4518-9de5-22dbcc12e1ed button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('merged_df');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "merged_df",
"summary": "{\n \"name\": \"merged_df\",\n \"rows\": 2077,\n \"fields\": [\n {\n \"column\": \"isocode\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 190,\n \"samples\": [\n \"UGA\",\n \"VCT\",\n \"MEX\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"year_group\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 15,\n \"min\": 1960,\n \"max\": 2010,\n \"num_unique_values\": 11,\n \"samples\": [\n 1985,\n 1960,\n 2005\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Y_L\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 17268.167868437817,\n \"min\": 492.1387380205191,\n \"max\": 159755.37670729982,\n \"num_unique_values\": 1762,\n \"samples\": [\n 2219.485666244532,\n 12181.772726682928,\n 3260.0550664063444\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Sk\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.10879439693647254,\n \"min\": 0.014610665466,\n \"max\": 0.7651136179,\n \"num_unique_values\": 1804,\n \"samples\": [\n 0.15129481954,\n 0.24791211025999998,\n 0.3441268188\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"n\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.016191456367199594,\n \"min\": -0.05828859411436917,\n \"max\": 0.16166784574782586,\n \"num_unique_values\": 1842,\n \"samples\": [\n 0.0036542434287929913,\n 0.009176803876019957,\n 0.03311363385116635\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"h_1\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3.0423666509670926,\n \"min\": 0.041999999999999996,\n \"max\": 12.466999999999999,\n \"num_unique_values\": 1435,\n \"samples\": [\n 4.425,\n 6.414,\n 9.241\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"h_2\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.85130644859473,\n \"min\": 0.037,\n \"max\": 8.866,\n \"num_unique_values\": 1346,\n \"samples\": [\n 2.871,\n 8.469,\n 5.656\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 22
}
]
},
{
"cell_type": "code",
"source": [
"# Calculate n + g + delta\n",
"merged_df['n_g_delta'] = merged_df['n'] + 0.05\n",
"merged_df"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 424
},
"id": "mvFXIcVYQh3b",
"outputId": "34096361-732d-4af6-f072-8024ce60a6be"
},
"execution_count": 23,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" isocode year_group Y_L Sk n h_1 h_2 \\\n",
"0 AFG 1960 NaN NaN 0.019822 0.361 0.286 \n",
"1 AFG 1965 NaN NaN 0.020521 0.409 0.315 \n",
"2 AFG 1970 1885.435178 0.146990 0.021697 0.662 0.477 \n",
"3 AFG 1975 2218.826921 0.212154 -0.025493 0.881 0.622 \n",
"4 AFG 1980 2682.034132 0.221990 -0.004059 1.173 0.816 \n",
"... ... ... ... ... ... ... ... \n",
"2072 ZWE 1990 930.456587 0.035493 0.026490 5.845 3.737 \n",
"2073 ZWE 1995 772.957023 0.037646 0.015152 6.766 4.460 \n",
"2074 ZWE 2000 658.720907 0.046580 -0.008076 7.230 5.051 \n",
"2075 ZWE 2005 569.594484 0.032197 -0.003608 7.626 5.498 \n",
"2076 ZWE 2010 591.587471 0.031312 NaN 7.838 5.894 \n",
"\n",
" n_g_delta \n",
"0 0.069822 \n",
"1 0.070521 \n",
"2 0.071697 \n",
"3 0.024507 \n",
"4 0.045941 \n",
"... ... \n",
"2072 0.076490 \n",
"2073 0.065152 \n",
"2074 0.041924 \n",
"2075 0.046392 \n",
"2076 NaN \n",
"\n",
"[2077 rows x 8 columns]"
],
"text/html": [
"\n",
" <div id=\"df-ca55af5a-78d3-43c7-9f22-46a402aa1bf8\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>isocode</th>\n",
" <th>year_group</th>\n",
" <th>Y_L</th>\n",
" <th>Sk</th>\n",
" <th>n</th>\n",
" <th>h_1</th>\n",
" <th>h_2</th>\n",
" <th>n_g_delta</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>AFG</td>\n",
" <td>1960</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.019822</td>\n",
" <td>0.361</td>\n",
" <td>0.286</td>\n",
" <td>0.069822</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>AFG</td>\n",
" <td>1965</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.020521</td>\n",
" <td>0.409</td>\n",
" <td>0.315</td>\n",
" <td>0.070521</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>AFG</td>\n",
" <td>1970</td>\n",
" <td>1885.435178</td>\n",
" <td>0.146990</td>\n",
" <td>0.021697</td>\n",
" <td>0.662</td>\n",
" <td>0.477</td>\n",
" <td>0.071697</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>AFG</td>\n",
" <td>1975</td>\n",
" <td>2218.826921</td>\n",
" <td>0.212154</td>\n",
" <td>-0.025493</td>\n",
" <td>0.881</td>\n",
" <td>0.622</td>\n",
" <td>0.024507</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>AFG</td>\n",
" <td>1980</td>\n",
" <td>2682.034132</td>\n",
" <td>0.221990</td>\n",
" <td>-0.004059</td>\n",
" <td>1.173</td>\n",
" <td>0.816</td>\n",
" <td>0.045941</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2072</th>\n",
" <td>ZWE</td>\n",
" <td>1990</td>\n",
" <td>930.456587</td>\n",
" <td>0.035493</td>\n",
" <td>0.026490</td>\n",
" <td>5.845</td>\n",
" <td>3.737</td>\n",
" <td>0.076490</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2073</th>\n",
" <td>ZWE</td>\n",
" <td>1995</td>\n",
" <td>772.957023</td>\n",
" <td>0.037646</td>\n",
" <td>0.015152</td>\n",
" <td>6.766</td>\n",
" <td>4.460</td>\n",
" <td>0.065152</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2074</th>\n",
" <td>ZWE</td>\n",
" <td>2000</td>\n",
" <td>658.720907</td>\n",
" <td>0.046580</td>\n",
" <td>-0.008076</td>\n",
" <td>7.230</td>\n",
" <td>5.051</td>\n",
" <td>0.041924</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2075</th>\n",
" <td>ZWE</td>\n",
" <td>2005</td>\n",
" <td>569.594484</td>\n",
" <td>0.032197</td>\n",
" <td>-0.003608</td>\n",
" <td>7.626</td>\n",
" <td>5.498</td>\n",
" <td>0.046392</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2076</th>\n",
" <td>ZWE</td>\n",
" <td>2010</td>\n",
" <td>591.587471</td>\n",
" <td>0.031312</td>\n",
" <td>NaN</td>\n",
" <td>7.838</td>\n",
" <td>5.894</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>2077 rows × 8 columns</p>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-ca55af5a-78d3-43c7-9f22-46a402aa1bf8')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-ca55af5a-78d3-43c7-9f22-46a402aa1bf8 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-ca55af5a-78d3-43c7-9f22-46a402aa1bf8');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-9f49dd1a-709a-4947-93d4-c79e779855c5\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-9f49dd1a-709a-4947-93d4-c79e779855c5')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-9f49dd1a-709a-4947-93d4-c79e779855c5 button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" <div id=\"id_af56fac2-f3aa-48b9-a6ae-b407e0651884\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('merged_df')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_af56fac2-f3aa-48b9-a6ae-b407e0651884 button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('merged_df');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "merged_df",
"summary": "{\n \"name\": \"merged_df\",\n \"rows\": 2077,\n \"fields\": [\n {\n \"column\": \"isocode\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 190,\n \"samples\": [\n \"UGA\",\n \"VCT\",\n \"MEX\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"year_group\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 15,\n \"min\": 1960,\n \"max\": 2010,\n \"num_unique_values\": 11,\n \"samples\": [\n 1985,\n 1960,\n 2005\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Y_L\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 17268.167868437817,\n \"min\": 492.1387380205191,\n \"max\": 159755.37670729982,\n \"num_unique_values\": 1762,\n \"samples\": [\n 2219.485666244532,\n 12181.772726682928,\n 3260.0550664063444\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Sk\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.10879439693647254,\n \"min\": 0.014610665466,\n \"max\": 0.7651136179,\n \"num_unique_values\": 1804,\n \"samples\": [\n 0.15129481954,\n 0.24791211025999998,\n 0.3441268188\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"n\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.016191456367199594,\n \"min\": -0.05828859411436917,\n \"max\": 0.16166784574782586,\n \"num_unique_values\": 1842,\n \"samples\": [\n 0.0036542434287929913,\n 0.009176803876019957,\n 0.03311363385116635\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"h_1\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3.0423666509670926,\n \"min\": 0.041999999999999996,\n \"max\": 12.466999999999999,\n \"num_unique_values\": 1435,\n \"samples\": [\n 4.425,\n 6.414,\n 9.241\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"h_2\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.85130644859473,\n \"min\": 0.037,\n \"max\": 8.866,\n \"num_unique_values\": 1346,\n \"samples\": [\n 2.871,\n 8.469,\n 5.656\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"n_g_delta\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.016191456367199576,\n \"min\": -0.00828859411436917,\n \"max\": 0.21166784574782588,\n \"num_unique_values\": 1842,\n \"samples\": [\n 0.05365424342879299,\n 0.05917680387601996,\n 0.08311363385116635\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 23
}
]
},
{
"cell_type": "code",
"source": [
"# Calculate logs of variables\n",
"\n",
"# List of variables to take logs of\n",
"log_vars = ['Y_L', 'Sk', 'n_g_delta', 'h_1', 'h_2']\n",
"\n",
"# Calculate logs, handling zeros or negative values\n",
"for var in log_vars:\n",
" merged_df['ln_' + var] = np.log(merged_df[var].replace(0, np.nan))\n",
"\n",
"# Remove nan rows when there's missing data.\n",
"initial_row_count = merged_df.shape[0]\n",
"merged_df = merged_df.dropna(subset=['ln_Y_L', 'ln_Sk', 'ln_n_g_delta', 'ln_h_1', 'ln_h_2'])\n",
"rows_removed = initial_row_count - merged_df.shape[0]\n",
"print(f'{rows_removed} rows out of {initial_row_count} were deleted because of missing data')"
],
"metadata": {
"id": "Sbg0nY9iU1kb",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "19fb0d2b-fb39-46c0-ebd0-725b801746ff"
},
"execution_count": 24,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"885 rows out of 2077 were deleted because of missing data\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.10/dist-packages/pandas/core/arraylike.py:399: RuntimeWarning: invalid value encountered in log\n",
" result = getattr(ufunc, method)(*inputs, **kwargs)\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"merged_df.to_csv(\"merged.csv\")\n",
"merged_df"
],
"metadata": {
"id": "E9isi9NzU44w",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 424
},
"outputId": "2a11e13d-98b6-4405-b59e-b8d1fb5f1716"
},
"execution_count": 25,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
" isocode year_group Y_L Sk n h_1 h_2 \\\n",
"2 AFG 1970 1885.435178 0.146990 0.021697 0.662 0.477 \n",
"3 AFG 1975 2218.826921 0.212154 -0.025493 0.881 0.622 \n",
"4 AFG 1980 2682.034132 0.221990 -0.004059 1.173 0.816 \n",
"5 AFG 1985 2650.605259 0.222138 0.027930 1.583 1.162 \n",
"6 AFG 1990 1597.933937 0.223036 0.055501 1.888 1.440 \n",
"... ... ... ... ... ... ... ... \n",
"2071 ZWE 1985 879.491214 0.030909 0.043270 4.719 3.219 \n",
"2072 ZWE 1990 930.456587 0.035493 0.026490 5.845 3.737 \n",
"2073 ZWE 1995 772.957023 0.037646 0.015152 6.766 4.460 \n",
"2074 ZWE 2000 658.720907 0.046580 -0.008076 7.230 5.051 \n",
"2075 ZWE 2005 569.594484 0.032197 -0.003608 7.626 5.498 \n",
"\n",
" n_g_delta ln_Y_L ln_Sk ln_n_g_delta ln_h_1 ln_h_2 \n",
"2 0.071697 7.541914 -1.917390 -2.635311 -0.412490 -0.740239 \n",
"3 0.024507 7.704734 -1.550444 -3.708815 -0.126698 -0.474815 \n",
"4 0.045941 7.894331 -1.505123 -3.080393 0.159565 -0.203341 \n",
"5 0.077930 7.882543 -1.504456 -2.551941 0.459322 0.150143 \n",
"6 0.105501 7.376467 -1.500424 -2.249033 0.635518 0.364643 \n",
"... ... ... ... ... ... ... \n",
"2071 0.093270 6.779344 -3.476721 -2.372262 1.551597 1.169071 \n",
"2072 0.076490 6.835675 -3.338414 -2.570594 1.765587 1.318283 \n",
"2073 0.065152 6.650223 -3.279541 -2.731037 1.911910 1.495149 \n",
"2074 0.041924 6.490300 -3.066584 -3.171886 1.978239 1.619586 \n",
"2075 0.046392 6.344925 -3.435879 -3.070620 2.031563 1.704384 \n",
"\n",
"[1192 rows x 13 columns]"
],
"text/html": [
"\n",
" <div id=\"df-cf54e975-ff35-4e12-b395-e5405ab35ac4\" class=\"colab-df-container\">\n",
" <div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>isocode</th>\n",
" <th>year_group</th>\n",
" <th>Y_L</th>\n",
" <th>Sk</th>\n",
" <th>n</th>\n",
" <th>h_1</th>\n",
" <th>h_2</th>\n",
" <th>n_g_delta</th>\n",
" <th>ln_Y_L</th>\n",
" <th>ln_Sk</th>\n",
" <th>ln_n_g_delta</th>\n",
" <th>ln_h_1</th>\n",
" <th>ln_h_2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>AFG</td>\n",
" <td>1970</td>\n",
" <td>1885.435178</td>\n",
" <td>0.146990</td>\n",
" <td>0.021697</td>\n",
" <td>0.662</td>\n",
" <td>0.477</td>\n",
" <td>0.071697</td>\n",
" <td>7.541914</td>\n",
" <td>-1.917390</td>\n",
" <td>-2.635311</td>\n",
" <td>-0.412490</td>\n",
" <td>-0.740239</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>AFG</td>\n",
" <td>1975</td>\n",
" <td>2218.826921</td>\n",
" <td>0.212154</td>\n",
" <td>-0.025493</td>\n",
" <td>0.881</td>\n",
" <td>0.622</td>\n",
" <td>0.024507</td>\n",
" <td>7.704734</td>\n",
" <td>-1.550444</td>\n",
" <td>-3.708815</td>\n",
" <td>-0.126698</td>\n",
" <td>-0.474815</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>AFG</td>\n",
" <td>1980</td>\n",
" <td>2682.034132</td>\n",
" <td>0.221990</td>\n",
" <td>-0.004059</td>\n",
" <td>1.173</td>\n",
" <td>0.816</td>\n",
" <td>0.045941</td>\n",
" <td>7.894331</td>\n",
" <td>-1.505123</td>\n",
" <td>-3.080393</td>\n",
" <td>0.159565</td>\n",
" <td>-0.203341</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>AFG</td>\n",
" <td>1985</td>\n",
" <td>2650.605259</td>\n",
" <td>0.222138</td>\n",
" <td>0.027930</td>\n",
" <td>1.583</td>\n",
" <td>1.162</td>\n",
" <td>0.077930</td>\n",
" <td>7.882543</td>\n",
" <td>-1.504456</td>\n",
" <td>-2.551941</td>\n",
" <td>0.459322</td>\n",
" <td>0.150143</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>AFG</td>\n",
" <td>1990</td>\n",
" <td>1597.933937</td>\n",
" <td>0.223036</td>\n",
" <td>0.055501</td>\n",
" <td>1.888</td>\n",
" <td>1.440</td>\n",
" <td>0.105501</td>\n",
" <td>7.376467</td>\n",
" <td>-1.500424</td>\n",
" <td>-2.249033</td>\n",
" <td>0.635518</td>\n",
" <td>0.364643</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2071</th>\n",
" <td>ZWE</td>\n",
" <td>1985</td>\n",
" <td>879.491214</td>\n",
" <td>0.030909</td>\n",
" <td>0.043270</td>\n",
" <td>4.719</td>\n",
" <td>3.219</td>\n",
" <td>0.093270</td>\n",
" <td>6.779344</td>\n",
" <td>-3.476721</td>\n",
" <td>-2.372262</td>\n",
" <td>1.551597</td>\n",
" <td>1.169071</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2072</th>\n",
" <td>ZWE</td>\n",
" <td>1990</td>\n",
" <td>930.456587</td>\n",
" <td>0.035493</td>\n",
" <td>0.026490</td>\n",
" <td>5.845</td>\n",
" <td>3.737</td>\n",
" <td>0.076490</td>\n",
" <td>6.835675</td>\n",
" <td>-3.338414</td>\n",
" <td>-2.570594</td>\n",
" <td>1.765587</td>\n",
" <td>1.318283</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2073</th>\n",
" <td>ZWE</td>\n",
" <td>1995</td>\n",
" <td>772.957023</td>\n",
" <td>0.037646</td>\n",
" <td>0.015152</td>\n",
" <td>6.766</td>\n",
" <td>4.460</td>\n",
" <td>0.065152</td>\n",
" <td>6.650223</td>\n",
" <td>-3.279541</td>\n",
" <td>-2.731037</td>\n",
" <td>1.911910</td>\n",
" <td>1.495149</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2074</th>\n",
" <td>ZWE</td>\n",
" <td>2000</td>\n",
" <td>658.720907</td>\n",
" <td>0.046580</td>\n",
" <td>-0.008076</td>\n",
" <td>7.230</td>\n",
" <td>5.051</td>\n",
" <td>0.041924</td>\n",
" <td>6.490300</td>\n",
" <td>-3.066584</td>\n",
" <td>-3.171886</td>\n",
" <td>1.978239</td>\n",
" <td>1.619586</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2075</th>\n",
" <td>ZWE</td>\n",
" <td>2005</td>\n",
" <td>569.594484</td>\n",
" <td>0.032197</td>\n",
" <td>-0.003608</td>\n",
" <td>7.626</td>\n",
" <td>5.498</td>\n",
" <td>0.046392</td>\n",
" <td>6.344925</td>\n",
" <td>-3.435879</td>\n",
" <td>-3.070620</td>\n",
" <td>2.031563</td>\n",
" <td>1.704384</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1192 rows × 13 columns</p>\n",
"</div>\n",
" <div class=\"colab-df-buttons\">\n",
"\n",
" <div class=\"colab-df-container\">\n",
" <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-cf54e975-ff35-4e12-b395-e5405ab35ac4')\"\n",
" title=\"Convert this dataframe to an interactive table.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
" <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
" </svg>\n",
" </button>\n",
"\n",
" <style>\n",
" .colab-df-container {\n",
" display:flex;\n",
" gap: 12px;\n",
" }\n",
"\n",
" .colab-df-convert {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-convert:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" .colab-df-buttons div {\n",
" margin-bottom: 4px;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-convert:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
"\n",
" <script>\n",
" const buttonEl =\n",
" document.querySelector('#df-cf54e975-ff35-4e12-b395-e5405ab35ac4 button.colab-df-convert');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" async function convertToInteractive(key) {\n",
" const element = document.querySelector('#df-cf54e975-ff35-4e12-b395-e5405ab35ac4');\n",
" const dataTable =\n",
" await google.colab.kernel.invokeFunction('convertToInteractive',\n",
" [key], {});\n",
" if (!dataTable) return;\n",
"\n",
" const docLinkHtml = 'Like what you see? Visit the ' +\n",
" '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
" + ' to learn more about interactive tables.';\n",
" element.innerHTML = '';\n",
" dataTable['output_type'] = 'display_data';\n",
" await google.colab.output.renderOutput(dataTable, element);\n",
" const docLink = document.createElement('div');\n",
" docLink.innerHTML = docLinkHtml;\n",
" element.appendChild(docLink);\n",
" }\n",
" </script>\n",
" </div>\n",
"\n",
"\n",
"<div id=\"df-eb52618e-013b-4022-b51c-6a874f08bc33\">\n",
" <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-eb52618e-013b-4022-b51c-6a874f08bc33')\"\n",
" title=\"Suggest charts\"\n",
" style=\"display:none;\">\n",
"\n",
"<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <g>\n",
" <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
" </g>\n",
"</svg>\n",
" </button>\n",
"\n",
"<style>\n",
" .colab-df-quickchart {\n",
" --bg-color: #E8F0FE;\n",
" --fill-color: #1967D2;\n",
" --hover-bg-color: #E2EBFA;\n",
" --hover-fill-color: #174EA6;\n",
" --disabled-fill-color: #AAA;\n",
" --disabled-bg-color: #DDD;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-quickchart {\n",
" --bg-color: #3B4455;\n",
" --fill-color: #D2E3FC;\n",
" --hover-bg-color: #434B5C;\n",
" --hover-fill-color: #FFFFFF;\n",
" --disabled-bg-color: #3B4455;\n",
" --disabled-fill-color: #666;\n",
" }\n",
"\n",
" .colab-df-quickchart {\n",
" background-color: var(--bg-color);\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: var(--fill-color);\n",
" height: 32px;\n",
" padding: 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-quickchart:hover {\n",
" background-color: var(--hover-bg-color);\n",
" box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: var(--button-hover-fill-color);\n",
" }\n",
"\n",
" .colab-df-quickchart-complete:disabled,\n",
" .colab-df-quickchart-complete:disabled:hover {\n",
" background-color: var(--disabled-bg-color);\n",
" fill: var(--disabled-fill-color);\n",
" box-shadow: none;\n",
" }\n",
"\n",
" .colab-df-spinner {\n",
" border: 2px solid var(--fill-color);\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" animation:\n",
" spin 1s steps(1) infinite;\n",
" }\n",
"\n",
" @keyframes spin {\n",
" 0% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" border-left-color: var(--fill-color);\n",
" }\n",
" 20% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 30% {\n",
" border-color: transparent;\n",
" border-left-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 40% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-top-color: var(--fill-color);\n",
" }\n",
" 60% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" }\n",
" 80% {\n",
" border-color: transparent;\n",
" border-right-color: var(--fill-color);\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" 90% {\n",
" border-color: transparent;\n",
" border-bottom-color: var(--fill-color);\n",
" }\n",
" }\n",
"</style>\n",
"\n",
" <script>\n",
" async function quickchart(key) {\n",
" const quickchartButtonEl =\n",
" document.querySelector('#' + key + ' button');\n",
" quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
" quickchartButtonEl.classList.add('colab-df-spinner');\n",
" try {\n",
" const charts = await google.colab.kernel.invokeFunction(\n",
" 'suggestCharts', [key], {});\n",
" } catch (error) {\n",
" console.error('Error during call to suggestCharts:', error);\n",
" }\n",
" quickchartButtonEl.classList.remove('colab-df-spinner');\n",
" quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
" }\n",
" (() => {\n",
" let quickchartButtonEl =\n",
" document.querySelector('#df-eb52618e-013b-4022-b51c-6a874f08bc33 button');\n",
" quickchartButtonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
" })();\n",
" </script>\n",
"</div>\n",
"\n",
" <div id=\"id_434dcfbb-2ec4-4b79-9a20-03fe05e2c42b\">\n",
" <style>\n",
" .colab-df-generate {\n",
" background-color: #E8F0FE;\n",
" border: none;\n",
" border-radius: 50%;\n",
" cursor: pointer;\n",
" display: none;\n",
" fill: #1967D2;\n",
" height: 32px;\n",
" padding: 0 0 0 0;\n",
" width: 32px;\n",
" }\n",
"\n",
" .colab-df-generate:hover {\n",
" background-color: #E2EBFA;\n",
" box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
" fill: #174EA6;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate {\n",
" background-color: #3B4455;\n",
" fill: #D2E3FC;\n",
" }\n",
"\n",
" [theme=dark] .colab-df-generate:hover {\n",
" background-color: #434B5C;\n",
" box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
" filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
" fill: #FFFFFF;\n",
" }\n",
" </style>\n",
" <button class=\"colab-df-generate\" onclick=\"generateWithVariable('merged_df')\"\n",
" title=\"Generate code using this dataframe.\"\n",
" style=\"display:none;\">\n",
"\n",
" <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
" width=\"24px\">\n",
" <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
" </svg>\n",
" </button>\n",
" <script>\n",
" (() => {\n",
" const buttonEl =\n",
" document.querySelector('#id_434dcfbb-2ec4-4b79-9a20-03fe05e2c42b button.colab-df-generate');\n",
" buttonEl.style.display =\n",
" google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
"\n",
" buttonEl.onclick = () => {\n",
" google.colab.notebook.generateWithVariable('merged_df');\n",
" }\n",
" })();\n",
" </script>\n",
" </div>\n",
"\n",
" </div>\n",
" </div>\n"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "dataframe",
"variable_name": "merged_df",
"summary": "{\n \"name\": \"merged_df\",\n \"rows\": 1192,\n \"fields\": [\n {\n \"column\": \"isocode\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 139,\n \"samples\": [\n \"YEM\",\n \"KEN\",\n \"CZE\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"year_group\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 14,\n \"min\": 1960,\n \"max\": 2005,\n \"num_unique_values\": 10,\n \"samples\": [\n 1960,\n 1975,\n 1995\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Y_L\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 17536.94745706398,\n \"min\": 492.1387380205191,\n \"max\": 139890.32674061361,\n \"num_unique_values\": 1192,\n \"samples\": [\n 5946.178747815115,\n 13705.962021081219,\n 11180.180192767106\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Sk\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.10028118162989348,\n \"min\": 0.014610665466,\n \"max\": 0.64661407486,\n \"num_unique_values\": 1192,\n \"samples\": [\n 0.15348151022,\n 0.19655868742,\n 0.025924289\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"n\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.014131283020716994,\n \"min\": -0.039143629360799716,\n \"max\": 0.11427771900496353,\n \"num_unique_values\": 1192,\n \"samples\": [\n 0.023451535071641105,\n 0.035155641691527385,\n 0.0021613231748056627\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"h_1\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3.003726601865529,\n \"min\": 0.134,\n \"max\": 12.466999999999999,\n \"num_unique_values\": 1149,\n \"samples\": [\n 11.152000000000001,\n 2.951,\n 3.834\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"h_2\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.8195945747459197,\n \"min\": 0.083,\n \"max\": 8.866,\n \"num_unique_values\": 1098,\n \"samples\": [\n 5.879,\n 2.228,\n 0.815\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"n_g_delta\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.01413128302071699,\n \"min\": 0.010856370639200287,\n \"max\": 0.16427771900496352,\n \"num_unique_values\": 1192,\n \"samples\": [\n 0.07345153507164111,\n 0.0851556416915274,\n 0.052161323174805665\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ln_Y_L\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.22235703159943,\n \"min\": 6.198760664587792,\n \"max\": 11.848614014164465,\n \"num_unique_values\": 1192,\n \"samples\": [\n 8.690504064965447,\n 9.525586201171642,\n 9.321897864000235\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ln_Sk\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.5403985341945052,\n \"min\": -4.22600350559154,\n \"max\": -0.4360056464362188,\n \"num_unique_values\": 1192,\n \"samples\": [\n -1.8741751738029562,\n -1.6267942285489374,\n -3.6525749505078133\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ln_n_g_delta\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.20995447576544116,\n \"min\": -4.523003215617462,\n \"max\": -1.8061968747907369,\n \"num_unique_values\": 1192,\n \"samples\": [\n -2.611129477034815,\n -2.463274618148978,\n -2.9534139940703525\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ln_h_1\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.7375719919877776,\n \"min\": -2.0099154790312257,\n \"max\": 2.523085153362838,\n \"num_unique_values\": 1144,\n \"samples\": [\n 1.3668566672274156,\n -1.305636458102436,\n 1.023170093501251\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ln_h_2\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.6675952126899195,\n \"min\": -2.488914671185539,\n \"max\": 2.182223736322862,\n \"num_unique_values\": 1098,\n \"samples\": [\n 1.7713866794201178,\n 0.8011043220650377,\n -0.2045671657412744\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
}
},
"metadata": {},
"execution_count": 25
}
]
},
{
"cell_type": "code",
"source": [
"# Regression without human capital\n",
"import statsmodels.api as sm\n",
"\n",
"# Prepare data\n",
"df_reg = merged_df.copy()\n",
"X = df_reg[['ln_Sk', 'ln_n_g_delta']]\n",
"y = df_reg['ln_Y_L']\n",
"X = sm.add_constant(X) # Adds a constant term to the predictor\n",
"\n",
"# Run OLS regression\n",
"model = sm.OLS(y, X).fit()\n",
"\n",
"# Print results\n",
"print(model.summary())"
],
"metadata": {
"id": "wYtiSvmHX11a",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "0f9e7576-749d-4331-d4e9-e77117026eb3"
},
"execution_count": 26,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
" OLS Regression Results \n",
"==============================================================================\n",
"Dep. Variable: ln_Y_L R-squared: 0.226\n",
"Model: OLS Adj. R-squared: 0.225\n",
"Method: Least Squares F-statistic: 173.7\n",
"Date: Mon, 18 Nov 2024 Prob (F-statistic): 6.61e-67\n",
"Time: 09:00:19 Log-Likelihood: -1777.4\n",
"No. Observations: 1192 AIC: 3561.\n",
"Df Residuals: 1189 BIC: 3576.\n",
"Df Model: 2 \n",
"Covariance Type: nonrobust \n",
"================================================================================\n",
" coef std err t P>|t| [0.025 0.975]\n",
"--------------------------------------------------------------------------------\n",
"const 5.5285 0.409 13.525 0.000 4.726 6.330\n",
"ln_Sk 0.8179 0.058 14.171 0.000 0.705 0.931\n",
"ln_n_g_delta -1.7664 0.149 -11.891 0.000 -2.058 -1.475\n",
"==============================================================================\n",
"Omnibus: 13.680 Durbin-Watson: 0.378\n",
"Prob(Omnibus): 0.001 Jarque-Bera (JB): 16.130\n",
"Skew: 0.179 Prob(JB): 0.000314\n",
"Kurtosis: 3.444 Cond. No. 45.8\n",
"==============================================================================\n",
"\n",
"Notes:\n",
"[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Regression with h_1\n",
"df_reg = merged_df.copy()\n",
"X = df_reg[['ln_Sk', 'ln_h_1', 'ln_n_g_delta']]\n",
"y = df_reg['ln_Y_L']\n",
"X = sm.add_constant(X)\n",
"\n",
"model_h1 = sm.OLS(y, X).fit()\n",
"\n",
"print(model_h1.summary())"
],
"metadata": {
"id": "pqptFV8HYNoe",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "a0e81d25-2705-47bb-a160-ea009c454798"
},
"execution_count": 27,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
" OLS Regression Results \n",
"==============================================================================\n",
"Dep. Variable: ln_Y_L R-squared: 0.498\n",
"Model: OLS Adj. R-squared: 0.497\n",
"Method: Least Squares F-statistic: 392.7\n",
"Date: Mon, 18 Nov 2024 Prob (F-statistic): 3.45e-177\n",
"Time: 09:00:19 Log-Likelihood: -1519.5\n",
"No. Observations: 1192 AIC: 3047.\n",
"Df Residuals: 1188 BIC: 3067.\n",
"Df Model: 3 \n",
"Covariance Type: nonrobust \n",
"================================================================================\n",
" coef std err t P>|t| [0.025 0.975]\n",
"--------------------------------------------------------------------------------\n",
"const 6.5185 0.332 19.653 0.000 5.868 7.169\n",
"ln_Sk 0.3858 0.050 7.789 0.000 0.289 0.483\n",
"ln_h_1 0.9832 0.039 25.362 0.000 0.907 1.059\n",
"ln_n_g_delta -0.5664 0.129 -4.401 0.000 -0.819 -0.314\n",
"==============================================================================\n",
"Omnibus: 3.897 Durbin-Watson: 0.325\n",
"Prob(Omnibus): 0.142 Jarque-Bera (JB): 4.322\n",
"Skew: 0.048 Prob(JB): 0.115\n",
"Kurtosis: 3.279 Cond. No. 51.1\n",
"==============================================================================\n",
"\n",
"Notes:\n",
"[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Regression with h_2\n",
"df_reg = merged_df.copy()\n",
"X = df_reg[['ln_Sk', 'ln_h_2', 'ln_n_g_delta']]\n",
"y = df_reg['ln_Y_L']\n",
"X = sm.add_constant(X)\n",
"\n",
"model_h2 = sm.OLS(y, X).fit()\n",
"\n",
"print(model_h2.summary())"
],
"metadata": {
"id": "63vsEk7QYavv",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "ce23e9d6-0193-4663-b5ac-7620b9aac6dc"
},
"execution_count": 28,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
" OLS Regression Results \n",
"==============================================================================\n",
"Dep. Variable: ln_Y_L R-squared: 0.443\n",
"Model: OLS Adj. R-squared: 0.441\n",
"Method: Least Squares F-statistic: 314.6\n",
"Date: Mon, 18 Nov 2024 Prob (F-statistic): 2.72e-150\n",
"Time: 09:00:19 Log-Likelihood: -1581.7\n",
"No. Observations: 1192 AIC: 3171.\n",
"Df Residuals: 1188 BIC: 3192.\n",
"Df Model: 3 \n",
"Covariance Type: nonrobust \n",
"================================================================================\n",
" coef std err t P>|t| [0.025 0.975]\n",
"--------------------------------------------------------------------------------\n",
"const 6.3586 0.349 18.211 0.000 5.674 7.044\n",
"ln_Sk 0.4311 0.052 8.259 0.000 0.329 0.534\n",
"ln_h_2 0.9594 0.045 21.488 0.000 0.872 1.047\n",
"ln_n_g_delta -0.7949 0.134 -5.933 0.000 -1.058 -0.532\n",
"==============================================================================\n",
"Omnibus: 13.319 Durbin-Watson: 0.323\n",
"Prob(Omnibus): 0.001 Jarque-Bera (JB): 16.144\n",
"Skew: 0.165 Prob(JB): 0.000312\n",
"Kurtosis: 3.465 Cond. No. 49.1\n",
"==============================================================================\n",
"\n",
"Notes:\n",
"[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"## 1985 Regression"
],
"metadata": {
"id": "rqiMQayCF4CT"
}
},
{
"cell_type": "code",
"source": [
"# Withouth human capital\n",
"df_reg = merged_df.loc[merged_df['year_group'] == 1985]\n",
"X = df_reg[['ln_Sk', 'ln_n_g_delta']]\n",
"y = df_reg['ln_Y_L']\n",
"X = sm.add_constant(X) # Adds a constant term to the predictor\n",
"\n",
"# Run OLS regression\n",
"model = sm.OLS(y, X).fit()\n",
"\n",
"# Print results\n",
"print(model.summary())"
],
"metadata": {
"id": "pOc6CwfOvB-5",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "f6c28b50-74c2-49de-eb99-949b31a53456"
},
"execution_count": 29,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
" OLS Regression Results \n",
"==============================================================================\n",
"Dep. Variable: ln_Y_L R-squared: 0.206\n",
"Model: OLS Adj. R-squared: 0.193\n",
"Method: Least Squares F-statistic: 15.79\n",
"Date: Mon, 18 Nov 2024 Prob (F-statistic): 7.98e-07\n",
"Time: 09:00:19 Log-Likelihood: -185.84\n",
"No. Observations: 125 AIC: 377.7\n",
"Df Residuals: 122 BIC: 386.2\n",
"Df Model: 2 \n",
"Covariance Type: nonrobust \n",
"================================================================================\n",
" coef std err t P>|t| [0.025 0.975]\n",
"--------------------------------------------------------------------------------\n",
"const 6.9812 0.970 7.197 0.000 5.061 8.902\n",
"ln_Sk 0.7907 0.175 4.513 0.000 0.444 1.138\n",
"ln_n_g_delta -1.2452 0.351 -3.545 0.001 -1.941 -0.550\n",
"==============================================================================\n",
"Omnibus: 0.058 Durbin-Watson: 1.940\n",
"Prob(Omnibus): 0.972 Jarque-Bera (JB): 0.054\n",
"Skew: 0.041 Prob(JB): 0.973\n",
"Kurtosis: 2.939 Cond. No. 35.2\n",
"==============================================================================\n",
"\n",
"Notes:\n",
"[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Predicted values\n",
"predicted = model.fittedvalues\n",
"\n",
"# Actual values\n",
"actual = df_reg['ln_Y_L']\n",
"\n",
"# Plot actual vs. predicted\n",
"plt.figure(figsize=(8, 6))\n",
"sns.scatterplot(x=actual, y=predicted, alpha=0.5)\n",
"plt.plot([actual.min(), actual.max()], [actual.min(), actual.max()], 'r--')\n",
"plt.title('Actual vs. Predicted ln(Y/L)')\n",
"plt.xlabel('Actual ln(Y/L)')\n",
"plt.ylabel('Predicted ln(Y/L)')\n",
"plt.show()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 564
},
"id": "NnuIDFxoHD6G",
"outputId": "c54895fc-0cbc-4e84-a760-015d158b35f2"
},
"execution_count": 30,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
}
]
},
{
"cell_type": "code",
"source": [
"# With human capital\n",
"df_reg = merged_df.loc[merged_df['year_group'] == 1985]\n",
"X = df_reg[['ln_Sk', 'ln_h_1', 'ln_n_g_delta']]\n",
"y = df_reg['ln_Y_L']\n",
"X = sm.add_constant(X)\n",
"\n",
"model_h1 = sm.OLS(y, X).fit()\n",
"\n",
"print(model_h1.summary())"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "ee_yArSYGP1I",
"outputId": "52cd8fd9-ccc1-4957-b758-d35bb07b2cef"
},
"execution_count": 31,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
" OLS Regression Results \n",
"==============================================================================\n",
"Dep. Variable: ln_Y_L R-squared: 0.527\n",
"Model: OLS Adj. R-squared: 0.516\n",
"Method: Least Squares F-statistic: 44.99\n",
"Date: Mon, 18 Nov 2024 Prob (F-statistic): 1.33e-19\n",
"Time: 09:00:19 Log-Likelihood: -153.39\n",
"No. Observations: 125 AIC: 314.8\n",
"Df Residuals: 121 BIC: 326.1\n",
"Df Model: 3 \n",
"Covariance Type: nonrobust \n",
"================================================================================\n",
" coef std err t P>|t| [0.025 0.975]\n",
"--------------------------------------------------------------------------------\n",
"const 5.9467 0.760 7.825 0.000 4.442 7.451\n",
"ln_Sk 0.2368 0.149 1.591 0.114 -0.058 0.531\n",
"ln_h_1 1.3179 0.145 9.074 0.000 1.030 1.605\n",
"ln_n_g_delta -0.4958 0.284 -1.744 0.084 -1.059 0.067\n",
"==============================================================================\n",
"Omnibus: 2.644 Durbin-Watson: 2.105\n",
"Prob(Omnibus): 0.267 Jarque-Bera (JB): 2.132\n",
"Skew: 0.223 Prob(JB): 0.344\n",
"Kurtosis: 3.459 Cond. No. 39.2\n",
"==============================================================================\n",
"\n",
"Notes:\n",
"[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Predicted values\n",
"predicted = model_h1.fittedvalues\n",
"\n",
"# Actual values\n",
"actual = df_reg['ln_Y_L']\n",
"\n",
"# Plot actual vs. predicted\n",
"plt.figure(figsize=(8, 6))\n",
"sns.scatterplot(x=actual, y=predicted, alpha=0.5)\n",
"plt.plot([actual.min(), actual.max()], [actual.min(), actual.max()], 'r--')\n",
"plt.title('Actual vs. Predicted ln(Y/L)')\n",
"plt.xlabel('Actual ln(Y/L)')\n",
"plt.ylabel('Predicted ln(Y/L)')\n",
"plt.show()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 564
},
"id": "3_-inCNBoPfI",
"outputId": "5018a724-870e-4afe-f896-1f8a259c23e5"
},
"execution_count": 32,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
}
]
},
{
"cell_type": "code",
"source": [
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"\n",
"# Set Seaborn style\n",
"sns.set_style('whitegrid')\n",
"\n",
"# Scatter plot of ln_Y_L vs. ln_Sk with regression line\n",
"plt.figure(figsize=(8, 6))\n",
"sns.regplot(x='ln_Sk', y='ln_Y_L', data=merged_df, scatter_kws={'alpha':0.5})\n",
"plt.title('Log Output per Worker vs. Log Physical Capital Investment Rate')\n",
"plt.xlabel('ln(Sk)')\n",
"plt.ylabel('ln(Y/L)')\n",
"plt.show()\n",
"\n",
"# Scatter plot of ln_Y_L vs. ln_h_1 with regression line\n",
"plt.figure(figsize=(8, 6))\n",
"sns.regplot(x='ln_h_1', y='ln_Y_L', data=merged_df, scatter_kws={'alpha':0.5}, color='green')\n",
"plt.title('Log Output per Worker vs. Log Human Capital Stock (h_1)')\n",
"plt.xlabel('ln(h_1)')\n",
"plt.ylabel('ln(Y/L)')\n",
"plt.show()\n",
"\n",
"# Scatter plot of ln_Y_L vs. ln_n_g_delta with regression line\n",
"plt.figure(figsize=(8, 6))\n",
"sns.regplot(x='ln_n_g_delta', y='ln_Y_L', data=merged_df, scatter_kws={'alpha':0.5}, color='red')\n",
"plt.title('Log Output per Worker vs. Log(n + g + δ)')\n",
"plt.xlabel('ln(n + g + δ)')\n",
"plt.ylabel('ln(Y/L)')\n",
"plt.show()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"id": "OceDOfX5Gi7y",
"outputId": "a5bb2841-2a84-4c96-b338-9e0394276eb8"
},
"execution_count": 33,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
],
"image/png": "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\n"
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
],
"image/png": "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
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment