[GEOParse] Non-breaking change compatible with pandas 1.3.0 and 2.2.2

README.md

• Issue: Failing test: test_merge_and_average fails with a TypeError with pandas 2.0.3
• Pull request: Fix failing tests: Add compatibility with pandas 2

The notebooks in this Gist compare the following operations and demonstrate their equivalent outputs:

For pandas 1.3.0:

input_data.groupby(group_by_column).mean()[[expression_column]]

For pandas 1.3.0 and 2.2.2:

input_data.groupby(group_by_column).mean(numeric_only=True)[[expression_column]]

input_data.groupby(group_by_column)[[expression_column]].mean()

check_pandas_1.3.0.ipynb

check_pandas_2.2.2.ipynb

{
 "cells": [
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": "# Test in pandas 2.2.2",
   "id": "db1ed92a11514652"
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-07-27T15:25:27.766948Z",
     "start_time": "2024-07-27T15:25:27.757169Z"
    }
   },
   "cell_type": "code",
   "source": [
    "import sys\n",
    "import pandas as pd\n",
    "\n",
    "print(f\"Python: {sys.version}\")\n",
    "print(f\"pandas: {pd. __version__}\")"
   ],
   "id": "5lrKnkdADhp9",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Python: 3.12.4 (tags/v3.12.4:8e8a4ba, Jun  6 2024, 19:30:16) [MSC v.1940 64 bit (AMD64)]\n",
      "pandas: 2.2.2\n"
     ]
    }
   ],
   "execution_count": 7
  },
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": "### 1. Get the test data",
   "id": "1a6db4c5e0c6f656"
  },
  {
   "cell_type": "code",
   "source": [
    "expression_column = 'VALUE'\n",
    "group_by_column = 'GB_ACC'\n",
    "\n",
    "input_data = pd.read_csv(\"test_data/pandas2_compatibility_input.csv\")\n",
    "expected_result = pd.read_csv(\"test_data/pandas2_compatibility_output.csv\").set_index(group_by_column)"
   ],
   "metadata": {
    "id": "8pyVzJcJVRaI",
    "ExecuteTime": {
     "end_time": "2024-07-27T15:25:27.781181Z",
     "start_time": "2024-07-27T15:25:27.766948Z"
    }
   },
   "id": "8pyVzJcJVRaI",
   "outputs": [],
   "execution_count": 8
  },
  {
   "cell_type": "markdown",
   "source": "### 2. Calculate the results using different methods",
   "metadata": {
    "id": "3DCfwFkkWeMF"
   },
   "id": "3DCfwFkkWeMF"
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-07-27T15:25:27.791868Z",
     "start_time": "2024-07-27T15:25:27.781181Z"
    }
   },
   "cell_type": "code",
   "source": [
    "# df_previous_code = input_data.groupby(group_by_column).mean()[[expression_column]] \n",
    "# TypeError: agg function failed [how->mean,dtype->object]\n",
    "\n",
    "df_updated_code_1 = input_data.groupby(group_by_column).mean(numeric_only=True)[[expression_column]]\n",
    "\n",
    "df_updated_code_2 = input_data.groupby(group_by_column)[[expression_column]].mean()"
   ],
   "id": "d8e96f4c2487acfa",
   "outputs": [],
   "execution_count": 9
  },
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": "### 3. Check the equivalence",
   "id": "9e36328f4bb15a69"
  },
  {
   "cell_type": "code",
   "source": [
    "from pandas.testing import assert_frame_equal\n",
    "\n",
    "print(\"Testing the equivalence of pandas dataframes...\")\n",
    "\n",
    "assert_frame_equal(df_updated_code_1, expected_result)\n",
    "assert_frame_equal(df_updated_code_2, expected_result)\n",
    "\n",
    "print(\"OK\")"
   ],
   "metadata": {
    "id": "cEO0QoYNVrrL",
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "outputId": "81f72033-c6ee-4b2c-cf61-d3eb231560d1",
    "ExecuteTime": {
     "end_time": "2024-07-27T15:25:27.808393Z",
     "start_time": "2024-07-27T15:25:27.791868Z"
    }
   },
   "id": "cEO0QoYNVrrL",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Testing the equivalence of pandas dataframes...\n",
      "OK\n"
     ]
    }
   ],
   "execution_count": 10
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.4"
  },
  "colab": {
   "provenance": []
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}

pandas2_compatibility_input.csv

pandas2_compatibility_output.csv