[Pipe - Method Chaining] #pandas #notebook #pipe

Pandas Pipe - Method Chaining.ipynb

{
  "cells": [
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "import seaborn as sns",
      "execution_count": 1,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df = sns.load_dataset('tips')",
      "execution_count": 2,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df.groupby('day').pipe(get_first_two_rows_in_each_group)",
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 17,
          "data": {
            "text/plain": "    total_bill   tip     sex smoker   day    time  size\n0        16.99  1.01  Female     No   Sun  Dinner     2\n1        10.34  1.66    Male     No   Sun  Dinner     3\n19       20.65  3.35    Male     No   Sat  Dinner     3\n20       17.92  4.08    Male     No   Sat  Dinner     2\n77       27.20  4.00    Male     No  Thur   Lunch     4\n78       22.76  3.00    Male     No  Thur   Lunch     2\n90       28.97  3.00    Male    Yes   Fri  Dinner     2\n91       22.49  3.50    Male     No   Fri  Dinner     2",
            "text/html": "<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>total_bill</th>\n      <th>tip</th>\n      <th>sex</th>\n      <th>smoker</th>\n      <th>day</th>\n      <th>time</th>\n      <th>size</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>16.99</td>\n      <td>1.01</td>\n      <td>Female</td>\n      <td>No</td>\n      <td>Sun</td>\n      <td>Dinner</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>10.34</td>\n      <td>1.66</td>\n      <td>Male</td>\n      <td>No</td>\n      <td>Sun</td>\n      <td>Dinner</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>19</th>\n      <td>20.65</td>\n      <td>3.35</td>\n      <td>Male</td>\n      <td>No</td>\n      <td>Sat</td>\n      <td>Dinner</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>20</th>\n      <td>17.92</td>\n      <td>4.08</td>\n      <td>Male</td>\n      <td>No</td>\n      <td>Sat</td>\n      <td>Dinner</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>77</th>\n      <td>27.20</td>\n      <td>4.00</td>\n      <td>Male</td>\n      <td>No</td>\n      <td>Thur</td>\n      <td>Lunch</td>\n      <td>4</td>\n    </tr>\n    <tr>\n      <th>78</th>\n      <td>22.76</td>\n      <td>3.00</td>\n      <td>Male</td>\n      <td>No</td>\n      <td>Thur</td>\n      <td>Lunch</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>90</th>\n      <td>28.97</td>\n      <td>3.00</td>\n      <td>Male</td>\n      <td>Yes</td>\n      <td>Fri</td>\n      <td>Dinner</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>91</th>\n      <td>22.49</td>\n      <td>3.50</td>\n      <td>Male</td>\n      <td>No</td>\n      <td>Fri</td>\n      <td>Dinner</td>\n      <td>2</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "def get_first_two_rows_in_each_group(df):\n    return df.head(2)",
      "execution_count": 16,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df.groupby('day').pipe(count_rows).pipe(remove_lunch_times)",
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 19,
          "data": {
            "text/plain": "    total_bill   tip     sex smoker  day    time  size\n0        16.99  1.01  Female     No  Sun  Dinner     2\n1        10.34  1.66    Male     No  Sun  Dinner     3\n19       20.65  3.35    Male     No  Sat  Dinner     3\n20       17.92  4.08    Male     No  Sat  Dinner     2\n90       28.97  3.00    Male    Yes  Fri  Dinner     2\n91       22.49  3.50    Male     No  Fri  Dinner     2",
            "text/html": "<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>total_bill</th>\n      <th>tip</th>\n      <th>sex</th>\n      <th>smoker</th>\n      <th>day</th>\n      <th>time</th>\n      <th>size</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>16.99</td>\n      <td>1.01</td>\n      <td>Female</td>\n      <td>No</td>\n      <td>Sun</td>\n      <td>Dinner</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>10.34</td>\n      <td>1.66</td>\n      <td>Male</td>\n      <td>No</td>\n      <td>Sun</td>\n      <td>Dinner</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>19</th>\n      <td>20.65</td>\n      <td>3.35</td>\n      <td>Male</td>\n      <td>No</td>\n      <td>Sat</td>\n      <td>Dinner</td>\n      <td>3</td>\n    </tr>\n    <tr>\n      <th>20</th>\n      <td>17.92</td>\n      <td>4.08</td>\n      <td>Male</td>\n      <td>No</td>\n      <td>Sat</td>\n      <td>Dinner</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>90</th>\n      <td>28.97</td>\n      <td>3.00</td>\n      <td>Male</td>\n      <td>Yes</td>\n      <td>Fri</td>\n      <td>Dinner</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>91</th>\n      <td>22.49</td>\n      <td>3.50</td>\n      <td>Male</td>\n      <td>No</td>\n      <td>Fri</td>\n      <td>Dinner</td>\n      <td>2</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "def remove_lunch_times(df):\n    return df[df['time']!='Lunch']",
      "execution_count": 18,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "(\n    df.groupby('day')\n    .pipe(count_rows)\n    .pipe(remove_lunch_times)\n    .pipe(get_sex, 'Female')\n)",
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 26,
          "data": {
            "text/plain": "   total_bill   tip     sex smoker  day    time  size\n0       16.99  1.01  Female     No  Sun  Dinner     2",
            "text/html": "<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>total_bill</th>\n      <th>tip</th>\n      <th>sex</th>\n      <th>smoker</th>\n      <th>day</th>\n      <th>time</th>\n      <th>size</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>16.99</td>\n      <td>1.01</td>\n      <td>Female</td>\n      <td>No</td>\n      <td>Sun</td>\n      <td>Dinner</td>\n      <td>2</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "def get_sex(df, sex):\n    return df[df['sex']==sex]",
      "execution_count": 25,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "(\n    df.groupby('day')\n    .pipe(count_rows)\n    .pipe(remove_lunch_times)\n    .pipe(get_sex, 'Female')\n    .pipe(select_tip_col)\n)",
      "execution_count": 30,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 30,
          "data": {
            "text/plain": "0    1.01\nName: tip, dtype: float64"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "def select_tip_col(df):\n    return df['tip']",
      "execution_count": 31,
      "outputs": []
    }
  ],
  "metadata": {
    "kernelspec": {
      "name": "py36-test",
      "display_name": "py36-test",
      "language": "python"
    },
    "hide_input": false,
    "language_info": {
      "name": "python",
      "version": "3.6.3",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "gist": {
      "id": "",
      "data": {
        "description": "Pandas Pipe - Method Chaining",
        "public": true
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}