{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Dplyr's across: Replicating within Pandas"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "[dplyr](https://dplyr.tidyverse.org/index.html) has the [across](https://dplyr.tidyverse.org/reference/across.html) function, which is meant to make column wise processing easy. Pandas has always supported column-wise operations, and in a relatively simple manner. \n",
    "\n",
    "This article aims to replicate solutions in the dplyr [column-wise operations](https://dplyr.tidyverse.org/articles/colwise.html) vignette with Pandas."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's load in the relevant libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " pandas version : 2.2.2 \n",
      " numpy version : 2.0.0 \n",
      " python version : 3.12.4 | packaged by conda-forge | (main, Jun 17 2024, 10:13:44) [Clang 16.0.6 ]\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import sys\n",
    "\n",
    "print(\" pandas version :\", pd.__version__,\"\\n\", \n",
    "      \"numpy version :\", np.__version__, \"\\n\", \n",
    "      \"python version :\", sys.version)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>name</th>\n",
       "      <th>height</th>\n",
       "      <th>mass</th>\n",
       "      <th>hair_color</th>\n",
       "      <th>skin_color</th>\n",
       "      <th>eye_color</th>\n",
       "      <th>birth_year</th>\n",
       "      <th>sex</th>\n",
       "      <th>gender</th>\n",
       "      <th>homeworld</th>\n",
       "      <th>species</th>\n",
       "      <th>films</th>\n",
       "      <th>vehicles</th>\n",
       "      <th>starships</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Luke Skywalker</td>\n",
       "      <td>172.0</td>\n",
       "      <td>77.0</td>\n",
       "      <td>blond</td>\n",
       "      <td>fair</td>\n",
       "      <td>blue</td>\n",
       "      <td>19.0</td>\n",
       "      <td>male</td>\n",
       "      <td>masculine</td>\n",
       "      <td>Tatooine</td>\n",
       "      <td>Human</td>\n",
       "      <td>A New Hope, The Empire Strikes Back, Return of...</td>\n",
       "      <td>Snowspeeder, Imperial Speeder Bike</td>\n",
       "      <td>X-wing, Imperial shuttle</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>C-3PO</td>\n",
       "      <td>167.0</td>\n",
       "      <td>75.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>gold</td>\n",
       "      <td>yellow</td>\n",
       "      <td>112.0</td>\n",
       "      <td>none</td>\n",
       "      <td>masculine</td>\n",
       "      <td>Tatooine</td>\n",
       "      <td>Droid</td>\n",
       "      <td>A New Hope, The Empire Strikes Back, Return of...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>R2-D2</td>\n",
       "      <td>96.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>white, blue</td>\n",
       "      <td>red</td>\n",
       "      <td>33.0</td>\n",
       "      <td>none</td>\n",
       "      <td>masculine</td>\n",
       "      <td>Naboo</td>\n",
       "      <td>Droid</td>\n",
       "      <td>A New Hope, The Empire Strikes Back, Return of...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Darth Vader</td>\n",
       "      <td>202.0</td>\n",
       "      <td>136.0</td>\n",
       "      <td>none</td>\n",
       "      <td>white</td>\n",
       "      <td>yellow</td>\n",
       "      <td>41.9</td>\n",
       "      <td>male</td>\n",
       "      <td>masculine</td>\n",
       "      <td>Tatooine</td>\n",
       "      <td>Human</td>\n",
       "      <td>A New Hope, The Empire Strikes Back, Return of...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>TIE Advanced x1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Leia Organa</td>\n",
       "      <td>150.0</td>\n",
       "      <td>49.0</td>\n",
       "      <td>brown</td>\n",
       "      <td>light</td>\n",
       "      <td>brown</td>\n",
       "      <td>19.0</td>\n",
       "      <td>female</td>\n",
       "      <td>feminine</td>\n",
       "      <td>Alderaan</td>\n",
       "      <td>Human</td>\n",
       "      <td>A New Hope, The Empire Strikes Back, Return of...</td>\n",
       "      <td>Imperial Speeder Bike</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             name  height   mass hair_color   skin_color eye_color  \\\n",
       "0  Luke Skywalker   172.0   77.0      blond         fair      blue   \n",
       "1           C-3PO   167.0   75.0        NaN         gold    yellow   \n",
       "2           R2-D2    96.0   32.0        NaN  white, blue       red   \n",
       "3     Darth Vader   202.0  136.0       none        white    yellow   \n",
       "4     Leia Organa   150.0   49.0      brown        light     brown   \n",
       "\n",
       "   birth_year     sex     gender homeworld species  \\\n",
       "0        19.0    male  masculine  Tatooine   Human   \n",
       "1       112.0    none  masculine  Tatooine   Droid   \n",
       "2        33.0    none  masculine     Naboo   Droid   \n",
       "3        41.9    male  masculine  Tatooine   Human   \n",
       "4        19.0  female   feminine  Alderaan   Human   \n",
       "\n",
       "                                               films  \\\n",
       "0  A New Hope, The Empire Strikes Back, Return of...   \n",
       "1  A New Hope, The Empire Strikes Back, Return of...   \n",
       "2  A New Hope, The Empire Strikes Back, Return of...   \n",
       "3  A New Hope, The Empire Strikes Back, Return of...   \n",
       "4  A New Hope, The Empire Strikes Back, Return of...   \n",
       "\n",
       "                             vehicles                 starships  \n",
       "0  Snowspeeder, Imperial Speeder Bike  X-wing, Imperial shuttle  \n",
       "1                                 NaN                       NaN  \n",
       "2                                 NaN                       NaN  \n",
       "3                                 NaN           TIE Advanced x1  \n",
       "4               Imperial Speeder Bike                       NaN  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "url = \"https://raw.githubusercontent.com/tidyverse/dplyr/main/data-raw/starwars.csv\"\n",
    "starwars = pd.read_csv(url)\n",
    "starwars.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "name          87\n",
       "hair_color    12\n",
       "skin_color    31\n",
       "eye_color     15\n",
       "sex            5\n",
       "gender         3\n",
       "homeworld     49\n",
       "species       38\n",
       "films         24\n",
       "vehicles      11\n",
       "starships     16\n",
       "dtype: int64"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# dplyr : \n",
    "# starwars %>% \n",
    "#   summarise(across(where(is.character), n_distinct))\n",
    "(starwars\n",
    ".select_dtypes('object')\n",
    ".nunique(dropna=False))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# dplyr :\n",
    "# starwars %>% \n",
    "#   group_by(species) %>% \n",
    "#   filter(n() > 1) %>% \n",
    "#   summarise(across(c(sex, gender, homeworld), n_distinct))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>sex</th>\n",
       "      <th>gender</th>\n",
       "      <th>homeworld</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>species</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Droid</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Gungan</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Human</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Kaminoan</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mirialan</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Twi'lek</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Wookiee</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zabrak</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          sex  gender  homeworld\n",
       "species                         \n",
       "Droid       1       2          3\n",
       "Gungan      1       1          1\n",
       "Human       2       2         15\n",
       "Kaminoan    2       2          1\n",
       "Mirialan    1       1          1\n",
       "Twi'lek     2       2          1\n",
       "Wookiee     1       1          1\n",
       "Zabrak      1       1          2"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grp = starwars.groupby('species')\n",
    "\n",
    "(grp[['sex', 'gender', 'homeworld']]\n",
    " .nunique(dropna=False)\n",
    " .loc[grp.size().gt(1)]\n",
    " )"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Another approach is with the [pipe](https://pandas.pydata.org/docs/reference/api/pandas.core.groupby.GroupBy.pipe.html) function:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>sex</th>\n",
       "      <th>gender</th>\n",
       "      <th>homeworld</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>species</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Droid</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Gungan</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Human</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Kaminoan</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mirialan</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Twi'lek</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Wookiee</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Zabrak</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          sex  gender  homeworld\n",
       "species                         \n",
       "Droid       1       2          3\n",
       "Gungan      1       1          1\n",
       "Human       2       2         15\n",
       "Kaminoan    2       2          1\n",
       "Mirialan    1       1          1\n",
       "Twi'lek     2       2          1\n",
       "Wookiee     1       1          1\n",
       "Zabrak      1       1          2"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(starwars\n",
    ".filter(['species', 'sex', 'gender', 'homeworld'])\n",
    ".groupby('species')\n",
    ".pipe(lambda df: df.nunique(dropna = False).loc[df.size().gt(1)])\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# dplyr : \n",
    "# starwars %>% \n",
    "#   group_by(homeworld) %>% \n",
    "#   filter(n() > 1) %>% \n",
    "#   summarise(across(where(is.numeric), ~ mean(.x, na.rm = TRUE)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>height</th>\n",
       "      <th>mass</th>\n",
       "      <th>birth_year</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>homeworld</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Alderaan</th>\n",
       "      <td>176.333333</td>\n",
       "      <td>64.000000</td>\n",
       "      <td>43.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Corellia</th>\n",
       "      <td>175.000000</td>\n",
       "      <td>78.500000</td>\n",
       "      <td>25.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Coruscant</th>\n",
       "      <td>173.666667</td>\n",
       "      <td>50.000000</td>\n",
       "      <td>91.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Kamino</th>\n",
       "      <td>208.333333</td>\n",
       "      <td>83.100000</td>\n",
       "      <td>31.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Kashyyyk</th>\n",
       "      <td>231.000000</td>\n",
       "      <td>124.000000</td>\n",
       "      <td>200.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mirial</th>\n",
       "      <td>168.000000</td>\n",
       "      <td>53.100000</td>\n",
       "      <td>49.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Naboo</th>\n",
       "      <td>177.272727</td>\n",
       "      <td>64.166667</td>\n",
       "      <td>55.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ryloth</th>\n",
       "      <td>179.000000</td>\n",
       "      <td>55.000000</td>\n",
       "      <td>48.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Tatooine</th>\n",
       "      <td>169.800000</td>\n",
       "      <td>85.375000</td>\n",
       "      <td>54.644444</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               height        mass  birth_year\n",
       "homeworld                                    \n",
       "Alderaan   176.333333   64.000000   43.000000\n",
       "Corellia   175.000000   78.500000   25.000000\n",
       "Coruscant  173.666667   50.000000   91.000000\n",
       "Kamino     208.333333   83.100000   31.500000\n",
       "Kashyyyk   231.000000  124.000000  200.000000\n",
       "Mirial     168.000000   53.100000   49.000000\n",
       "Naboo      177.272727   64.166667   55.000000\n",
       "Ryloth     179.000000   55.000000   48.000000\n",
       "Tatooine   169.800000   85.375000   54.644444"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# get the grouper\n",
    "grp = starwars.set_index('homeworld').select_dtypes('number').groupby('homeworld')\n",
    "# get the size:\n",
    "n = grp.size()\n",
    "# filter averages with the size:\n",
    "grp.mean().loc[n.gt(1)]"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "With the [pipe](https://pandas.pydata.org/docs/reference/api/pandas.core.groupby.GroupBy.pipe.html) function:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>height</th>\n",
       "      <th>mass</th>\n",
       "      <th>birth_year</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>homeworld</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Alderaan</th>\n",
       "      <td>176.333333</td>\n",
       "      <td>64.000000</td>\n",
       "      <td>43.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Corellia</th>\n",
       "      <td>175.000000</td>\n",
       "      <td>78.500000</td>\n",
       "      <td>25.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Coruscant</th>\n",
       "      <td>173.666667</td>\n",
       "      <td>50.000000</td>\n",
       "      <td>91.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Kamino</th>\n",
       "      <td>208.333333</td>\n",
       "      <td>83.100000</td>\n",
       "      <td>31.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Kashyyyk</th>\n",
       "      <td>231.000000</td>\n",
       "      <td>124.000000</td>\n",
       "      <td>200.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mirial</th>\n",
       "      <td>168.000000</td>\n",
       "      <td>53.100000</td>\n",
       "      <td>49.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Naboo</th>\n",
       "      <td>177.272727</td>\n",
       "      <td>64.166667</td>\n",
       "      <td>55.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ryloth</th>\n",
       "      <td>179.000000</td>\n",
       "      <td>55.000000</td>\n",
       "      <td>48.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Tatooine</th>\n",
       "      <td>169.800000</td>\n",
       "      <td>85.375000</td>\n",
       "      <td>54.644444</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               height        mass  birth_year\n",
       "homeworld                                    \n",
       "Alderaan   176.333333   64.000000   43.000000\n",
       "Corellia   175.000000   78.500000   25.000000\n",
       "Coruscant  173.666667   50.000000   91.000000\n",
       "Kamino     208.333333   83.100000   31.500000\n",
       "Kashyyyk   231.000000  124.000000  200.000000\n",
       "Mirial     168.000000   53.100000   49.000000\n",
       "Naboo      177.272727   64.166667   55.000000\n",
       "Ryloth     179.000000   55.000000   48.000000\n",
       "Tatooine   169.800000   85.375000   54.644444"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(starwars\n",
    ".set_index('homeworld')\n",
    ".select_dtypes('number')\n",
    ".groupby('homeworld')\n",
    ".pipe(lambda df: df.mean().loc[df.size().gt(1)])\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "An alternate approach, where the groupby is reused, is with [pyjanitor's](https://pyjanitor-devs.github.io/pyjanitor/) [get_columns](https://pyjanitor-devs.github.io/pyjanitor/api/functions/#janitor.functions.utils.get_columns) function:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>height</th>\n",
       "      <th>mass</th>\n",
       "      <th>birth_year</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>homeworld</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Alderaan</th>\n",
       "      <td>176.333333</td>\n",
       "      <td>64.000000</td>\n",
       "      <td>43.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Corellia</th>\n",
       "      <td>175.000000</td>\n",
       "      <td>78.500000</td>\n",
       "      <td>25.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Coruscant</th>\n",
       "      <td>173.666667</td>\n",
       "      <td>50.000000</td>\n",
       "      <td>91.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Kamino</th>\n",
       "      <td>208.333333</td>\n",
       "      <td>83.100000</td>\n",
       "      <td>31.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Kashyyyk</th>\n",
       "      <td>231.000000</td>\n",
       "      <td>124.000000</td>\n",
       "      <td>200.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mirial</th>\n",
       "      <td>168.000000</td>\n",
       "      <td>53.100000</td>\n",
       "      <td>49.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Naboo</th>\n",
       "      <td>177.272727</td>\n",
       "      <td>64.166667</td>\n",
       "      <td>55.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Ryloth</th>\n",
       "      <td>179.000000</td>\n",
       "      <td>55.000000</td>\n",
       "      <td>48.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Tatooine</th>\n",
       "      <td>169.800000</td>\n",
       "      <td>85.375000</td>\n",
       "      <td>54.644444</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               height        mass  birth_year\n",
       "homeworld                                    \n",
       "Alderaan   176.333333   64.000000   43.000000\n",
       "Corellia   175.000000   78.500000   25.000000\n",
       "Coruscant  173.666667   50.000000   91.000000\n",
       "Kamino     208.333333   83.100000   31.500000\n",
       "Kashyyyk   231.000000  124.000000  200.000000\n",
       "Mirial     168.000000   53.100000   49.000000\n",
       "Naboo      177.272727   64.166667   55.000000\n",
       "Ryloth     179.000000   55.000000   48.000000\n",
       "Tatooine   169.800000   85.375000   54.644444"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from janitor import get_columns\n",
    "from pandas.api.types import is_numeric_dtype\n",
    "\n",
    "grp = starwars.groupby('homeworld')\n",
    "(grp\n",
    " .pipe(get_columns, is_numeric_dtype)\n",
    " .mean()\n",
    " .loc[grp.size().gt(1)]\n",
    " )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>hair_color</th>\n",
       "      <th>skin_color</th>\n",
       "      <th>eye_color</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>blond</td>\n",
       "      <td>fair</td>\n",
       "      <td>blue</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>NaN</td>\n",
       "      <td>gold</td>\n",
       "      <td>yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>NaN</td>\n",
       "      <td>white, blue</td>\n",
       "      <td>red</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>none</td>\n",
       "      <td>white</td>\n",
       "      <td>yellow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>brown</td>\n",
       "      <td>light</td>\n",
       "      <td>brown</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>80</th>\n",
       "      <td>none</td>\n",
       "      <td>pale</td>\n",
       "      <td>white</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>82</th>\n",
       "      <td>black</td>\n",
       "      <td>dark</td>\n",
       "      <td>dark</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>83</th>\n",
       "      <td>brown</td>\n",
       "      <td>light</td>\n",
       "      <td>hazel</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>85</th>\n",
       "      <td>none</td>\n",
       "      <td>none</td>\n",
       "      <td>black</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>86</th>\n",
       "      <td>none</td>\n",
       "      <td>none</td>\n",
       "      <td>unknown</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>67 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   hair_color   skin_color eye_color\n",
       "0       blond         fair      blue\n",
       "1         NaN         gold    yellow\n",
       "2         NaN  white, blue       red\n",
       "3        none        white    yellow\n",
       "4       brown        light     brown\n",
       "..        ...          ...       ...\n",
       "80       none         pale     white\n",
       "82      black         dark      dark\n",
       "83      brown        light     hazel\n",
       "85       none         none     black\n",
       "86       none         none   unknown\n",
       "\n",
       "[67 rows x 3 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# dplyr:\n",
    "# starwars %>% distinct(across(contains(\"color\")))\n",
    "starwars.filter(like='color').drop_duplicates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "hair_color    skin_color  eye_color\n",
       "brown         light       brown        6\n",
       "              fair        blue         4\n",
       "none          grey        black        4\n",
       "black         dark        brown        3\n",
       "blond         fair        blue         3\n",
       "                                      ..\n",
       "none          dark        brown        1\n",
       "              green       black        1\n",
       "auburn, grey  fair        blue         1\n",
       "none          green       red          1\n",
       "NaN           white, red  red          1\n",
       "Name: count, Length: 67, dtype: int64"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# dplyr\n",
    "# starwars %>% count(across(contains(\"color\")), sort = TRUE)\n",
    "starwars.filter(like='color').value_counts(dropna = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>name</th>\n",
       "      <th>height</th>\n",
       "      <th>mass</th>\n",
       "      <th>hair_color</th>\n",
       "      <th>skin_color</th>\n",
       "      <th>eye_color</th>\n",
       "      <th>birth_year</th>\n",
       "      <th>sex</th>\n",
       "      <th>gender</th>\n",
       "      <th>homeworld</th>\n",
       "      <th>species</th>\n",
       "      <th>films</th>\n",
       "      <th>vehicles</th>\n",
       "      <th>starships</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Luke Skywalker</td>\n",
       "      <td>172.0</td>\n",
       "      <td>77.0</td>\n",
       "      <td>blond</td>\n",
       "      <td>fair</td>\n",
       "      <td>blue</td>\n",
       "      <td>19.0</td>\n",
       "      <td>male</td>\n",
       "      <td>masculine</td>\n",
       "      <td>Tatooine</td>\n",
       "      <td>Human</td>\n",
       "      <td>A New Hope, The Empire Strikes Back, Return of...</td>\n",
       "      <td>Snowspeeder, Imperial Speeder Bike</td>\n",
       "      <td>X-wing, Imperial shuttle</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>C-3PO</td>\n",
       "      <td>167.0</td>\n",
       "      <td>75.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>gold</td>\n",
       "      <td>yellow</td>\n",
       "      <td>112.0</td>\n",
       "      <td>none</td>\n",
       "      <td>masculine</td>\n",
       "      <td>Tatooine</td>\n",
       "      <td>Droid</td>\n",
       "      <td>A New Hope, The Empire Strikes Back, Return of...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>R2-D2</td>\n",
       "      <td>96.0</td>\n",
       "      <td>32.0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>white, blue</td>\n",
       "      <td>red</td>\n",
       "      <td>33.0</td>\n",
       "      <td>none</td>\n",
       "      <td>masculine</td>\n",
       "      <td>Naboo</td>\n",
       "      <td>Droid</td>\n",
       "      <td>A New Hope, The Empire Strikes Back, Return of...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Darth Vader</td>\n",
       "      <td>202.0</td>\n",
       "      <td>136.0</td>\n",
       "      <td>none</td>\n",
       "      <td>white</td>\n",
       "      <td>yellow</td>\n",
       "      <td>41.9</td>\n",
       "      <td>male</td>\n",
       "      <td>masculine</td>\n",
       "      <td>Tatooine</td>\n",
       "      <td>Human</td>\n",
       "      <td>A New Hope, The Empire Strikes Back, Return of...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>TIE Advanced x1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Leia Organa</td>\n",
       "      <td>150.0</td>\n",
       "      <td>49.0</td>\n",
       "      <td>brown</td>\n",
       "      <td>light</td>\n",
       "      <td>brown</td>\n",
       "      <td>19.0</td>\n",
       "      <td>female</td>\n",
       "      <td>feminine</td>\n",
       "      <td>Alderaan</td>\n",
       "      <td>Human</td>\n",
       "      <td>A New Hope, The Empire Strikes Back, Return of...</td>\n",
       "      <td>Imperial Speeder Bike</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>82</th>\n",
       "      <td>Finn</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>black</td>\n",
       "      <td>dark</td>\n",
       "      <td>dark</td>\n",
       "      <td>NaN</td>\n",
       "      <td>male</td>\n",
       "      <td>masculine</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Human</td>\n",
       "      <td>The Force Awakens</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>83</th>\n",
       "      <td>Rey</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>brown</td>\n",
       "      <td>light</td>\n",
       "      <td>hazel</td>\n",
       "      <td>NaN</td>\n",
       "      <td>female</td>\n",
       "      <td>feminine</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Human</td>\n",
       "      <td>The Force Awakens</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>84</th>\n",
       "      <td>Poe Dameron</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>brown</td>\n",
       "      <td>light</td>\n",
       "      <td>brown</td>\n",
       "      <td>NaN</td>\n",
       "      <td>male</td>\n",
       "      <td>masculine</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Human</td>\n",
       "      <td>The Force Awakens</td>\n",
       "      <td>NaN</td>\n",
       "      <td>X-wing</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>85</th>\n",
       "      <td>BB8</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>none</td>\n",
       "      <td>none</td>\n",
       "      <td>black</td>\n",
       "      <td>NaN</td>\n",
       "      <td>none</td>\n",
       "      <td>masculine</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Droid</td>\n",
       "      <td>The Force Awakens</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>86</th>\n",
       "      <td>Captain Phasma</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>none</td>\n",
       "      <td>none</td>\n",
       "      <td>unknown</td>\n",
       "      <td>NaN</td>\n",
       "      <td>female</td>\n",
       "      <td>feminine</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Human</td>\n",
       "      <td>The Force Awakens</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>87 rows × 14 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "              name  height   mass hair_color   skin_color eye_color  \\\n",
       "0   Luke Skywalker   172.0   77.0      blond         fair      blue   \n",
       "1            C-3PO   167.0   75.0        NaN         gold    yellow   \n",
       "2            R2-D2    96.0   32.0        NaN  white, blue       red   \n",
       "3      Darth Vader   202.0  136.0       none        white    yellow   \n",
       "4      Leia Organa   150.0   49.0      brown        light     brown   \n",
       "..             ...     ...    ...        ...          ...       ...   \n",
       "82            Finn     NaN    NaN      black         dark      dark   \n",
       "83             Rey     NaN    NaN      brown        light     hazel   \n",
       "84     Poe Dameron     NaN    NaN      brown        light     brown   \n",
       "85             BB8     NaN    NaN       none         none     black   \n",
       "86  Captain Phasma     NaN    NaN       none         none   unknown   \n",
       "\n",
       "    birth_year     sex     gender homeworld species  \\\n",
       "0         19.0    male  masculine  Tatooine   Human   \n",
       "1        112.0    none  masculine  Tatooine   Droid   \n",
       "2         33.0    none  masculine     Naboo   Droid   \n",
       "3         41.9    male  masculine  Tatooine   Human   \n",
       "4         19.0  female   feminine  Alderaan   Human   \n",
       "..         ...     ...        ...       ...     ...   \n",
       "82         NaN    male  masculine       NaN   Human   \n",
       "83         NaN  female   feminine       NaN   Human   \n",
       "84         NaN    male  masculine       NaN   Human   \n",
       "85         NaN    none  masculine       NaN   Droid   \n",
       "86         NaN  female   feminine       NaN   Human   \n",
       "\n",
       "                                                films  \\\n",
       "0   A New Hope, The Empire Strikes Back, Return of...   \n",
       "1   A New Hope, The Empire Strikes Back, Return of...   \n",
       "2   A New Hope, The Empire Strikes Back, Return of...   \n",
       "3   A New Hope, The Empire Strikes Back, Return of...   \n",
       "4   A New Hope, The Empire Strikes Back, Return of...   \n",
       "..                                                ...   \n",
       "82                                  The Force Awakens   \n",
       "83                                  The Force Awakens   \n",
       "84                                  The Force Awakens   \n",
       "85                                  The Force Awakens   \n",
       "86                                  The Force Awakens   \n",
       "\n",
       "                              vehicles                 starships  \n",
       "0   Snowspeeder, Imperial Speeder Bike  X-wing, Imperial shuttle  \n",
       "1                                  NaN                       NaN  \n",
       "2                                  NaN                       NaN  \n",
       "3                                  NaN           TIE Advanced x1  \n",
       "4                Imperial Speeder Bike                       NaN  \n",
       "..                                 ...                       ...  \n",
       "82                                 NaN                       NaN  \n",
       "83                                 NaN                       NaN  \n",
       "84                                 NaN                    X-wing  \n",
       "85                                 NaN                       NaN  \n",
       "86                                 NaN                       NaN  \n",
       "\n",
       "[87 rows x 14 columns]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# starwars %>% \n",
    "#   filter(if_any(everything(), ~ !is.na(.x)))\n",
    "starwars.loc[starwars.notna().any(axis=1)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>name</th>\n",
       "      <th>height</th>\n",
       "      <th>mass</th>\n",
       "      <th>hair_color</th>\n",
       "      <th>skin_color</th>\n",
       "      <th>eye_color</th>\n",
       "      <th>birth_year</th>\n",
       "      <th>sex</th>\n",
       "      <th>gender</th>\n",
       "      <th>homeworld</th>\n",
       "      <th>species</th>\n",
       "      <th>films</th>\n",
       "      <th>vehicles</th>\n",
       "      <th>starships</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Luke Skywalker</td>\n",
       "      <td>172.0</td>\n",
       "      <td>77.0</td>\n",
       "      <td>blond</td>\n",
       "      <td>fair</td>\n",
       "      <td>blue</td>\n",
       "      <td>19.0</td>\n",
       "      <td>male</td>\n",
       "      <td>masculine</td>\n",
       "      <td>Tatooine</td>\n",
       "      <td>Human</td>\n",
       "      <td>A New Hope, The Empire Strikes Back, Return of...</td>\n",
       "      <td>Snowspeeder, Imperial Speeder Bike</td>\n",
       "      <td>X-wing, Imperial shuttle</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Obi-Wan Kenobi</td>\n",
       "      <td>182.0</td>\n",
       "      <td>77.0</td>\n",
       "      <td>auburn, white</td>\n",
       "      <td>fair</td>\n",
       "      <td>blue-gray</td>\n",
       "      <td>57.0</td>\n",
       "      <td>male</td>\n",
       "      <td>masculine</td>\n",
       "      <td>Stewjon</td>\n",
       "      <td>Human</td>\n",
       "      <td>A New Hope, The Empire Strikes Back, Return of...</td>\n",
       "      <td>Tribubble bongo</td>\n",
       "      <td>Jedi starfighter, Trade Federation cruiser, Na...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Anakin Skywalker</td>\n",
       "      <td>188.0</td>\n",
       "      <td>84.0</td>\n",
       "      <td>blond</td>\n",
       "      <td>fair</td>\n",
       "      <td>blue</td>\n",
       "      <td>41.9</td>\n",
       "      <td>male</td>\n",
       "      <td>masculine</td>\n",
       "      <td>Tatooine</td>\n",
       "      <td>Human</td>\n",
       "      <td>The Phantom Menace, Attack of the Clones, Reve...</td>\n",
       "      <td>Zephyr-G swoop bike, XJ-6 airspeeder</td>\n",
       "      <td>Naboo fighter, Trade Federation cruiser, Jedi ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Chewbacca</td>\n",
       "      <td>228.0</td>\n",
       "      <td>112.0</td>\n",
       "      <td>brown</td>\n",
       "      <td>unknown</td>\n",
       "      <td>blue</td>\n",
       "      <td>200.0</td>\n",
       "      <td>male</td>\n",
       "      <td>masculine</td>\n",
       "      <td>Kashyyyk</td>\n",
       "      <td>Wookiee</td>\n",
       "      <td>A New Hope, The Empire Strikes Back, Return of...</td>\n",
       "      <td>AT-ST</td>\n",
       "      <td>Millennium Falcon, Imperial shuttle</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>Wedge Antilles</td>\n",
       "      <td>170.0</td>\n",
       "      <td>77.0</td>\n",
       "      <td>brown</td>\n",
       "      <td>fair</td>\n",
       "      <td>hazel</td>\n",
       "      <td>21.0</td>\n",
       "      <td>male</td>\n",
       "      <td>masculine</td>\n",
       "      <td>Corellia</td>\n",
       "      <td>Human</td>\n",
       "      <td>A New Hope, The Empire Strikes Back, Return of...</td>\n",
       "      <td>Snowspeeder</td>\n",
       "      <td>X-wing</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42</th>\n",
       "      <td>Darth Maul</td>\n",
       "      <td>175.0</td>\n",
       "      <td>80.0</td>\n",
       "      <td>none</td>\n",
       "      <td>red</td>\n",
       "      <td>yellow</td>\n",
       "      <td>54.0</td>\n",
       "      <td>male</td>\n",
       "      <td>masculine</td>\n",
       "      <td>Dathomir</td>\n",
       "      <td>Zabrak</td>\n",
       "      <td>The Phantom Menace</td>\n",
       "      <td>Sith speeder</td>\n",
       "      <td>Scimitar</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                name  height   mass     hair_color skin_color  eye_color  \\\n",
       "0     Luke Skywalker   172.0   77.0          blond       fair       blue   \n",
       "9     Obi-Wan Kenobi   182.0   77.0  auburn, white       fair  blue-gray   \n",
       "10  Anakin Skywalker   188.0   84.0          blond       fair       blue   \n",
       "12         Chewbacca   228.0  112.0          brown    unknown       blue   \n",
       "16    Wedge Antilles   170.0   77.0          brown       fair      hazel   \n",
       "42        Darth Maul   175.0   80.0           none        red     yellow   \n",
       "\n",
       "    birth_year   sex     gender homeworld  species  \\\n",
       "0         19.0  male  masculine  Tatooine    Human   \n",
       "9         57.0  male  masculine   Stewjon    Human   \n",
       "10        41.9  male  masculine  Tatooine    Human   \n",
       "12       200.0  male  masculine  Kashyyyk  Wookiee   \n",
       "16        21.0  male  masculine  Corellia    Human   \n",
       "42        54.0  male  masculine  Dathomir   Zabrak   \n",
       "\n",
       "                                                films  \\\n",
       "0   A New Hope, The Empire Strikes Back, Return of...   \n",
       "9   A New Hope, The Empire Strikes Back, Return of...   \n",
       "10  The Phantom Menace, Attack of the Clones, Reve...   \n",
       "12  A New Hope, The Empire Strikes Back, Return of...   \n",
       "16  A New Hope, The Empire Strikes Back, Return of...   \n",
       "42                                 The Phantom Menace   \n",
       "\n",
       "                                vehicles  \\\n",
       "0     Snowspeeder, Imperial Speeder Bike   \n",
       "9                        Tribubble bongo   \n",
       "10  Zephyr-G swoop bike, XJ-6 airspeeder   \n",
       "12                                 AT-ST   \n",
       "16                           Snowspeeder   \n",
       "42                          Sith speeder   \n",
       "\n",
       "                                            starships  \n",
       "0                            X-wing, Imperial shuttle  \n",
       "9   Jedi starfighter, Trade Federation cruiser, Na...  \n",
       "10  Naboo fighter, Trade Federation cruiser, Jedi ...  \n",
       "12                Millennium Falcon, Imperial shuttle  \n",
       "16                                             X-wing  \n",
       "42                                           Scimitar  "
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# starwars %>% \n",
    "#   filter(if_any(everything(), ~ !is.na(.x)))\n",
    "starwars.loc[starwars.notna().all(axis=1)]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Output for the above is different from the vignette's because Pandas treats none as NaN, and dplyr does not (at least in the vignette)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's look at another solution, from [Stack Overflow](https://stackoverflow.com/questions/63200530/python-pandas-equivalent-to-dplyr-1-0-0-summarizeacross):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>model</th>\n",
       "      <th>mpg</th>\n",
       "      <th>cyl</th>\n",
       "      <th>disp</th>\n",
       "      <th>hp</th>\n",
       "      <th>drat</th>\n",
       "      <th>wt</th>\n",
       "      <th>qsec</th>\n",
       "      <th>vs</th>\n",
       "      <th>am</th>\n",
       "      <th>gear</th>\n",
       "      <th>carb</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Mazda RX4</td>\n",
       "      <td>21.0</td>\n",
       "      <td>6</td>\n",
       "      <td>160.0</td>\n",
       "      <td>110</td>\n",
       "      <td>3.90</td>\n",
       "      <td>2.620</td>\n",
       "      <td>16.46</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Mazda RX4 Wag</td>\n",
       "      <td>21.0</td>\n",
       "      <td>6</td>\n",
       "      <td>160.0</td>\n",
       "      <td>110</td>\n",
       "      <td>3.90</td>\n",
       "      <td>2.875</td>\n",
       "      <td>17.02</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Datsun 710</td>\n",
       "      <td>22.8</td>\n",
       "      <td>4</td>\n",
       "      <td>108.0</td>\n",
       "      <td>93</td>\n",
       "      <td>3.85</td>\n",
       "      <td>2.320</td>\n",
       "      <td>18.61</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Hornet 4 Drive</td>\n",
       "      <td>21.4</td>\n",
       "      <td>6</td>\n",
       "      <td>258.0</td>\n",
       "      <td>110</td>\n",
       "      <td>3.08</td>\n",
       "      <td>3.215</td>\n",
       "      <td>19.44</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Hornet Sportabout</td>\n",
       "      <td>18.7</td>\n",
       "      <td>8</td>\n",
       "      <td>360.0</td>\n",
       "      <td>175</td>\n",
       "      <td>3.15</td>\n",
       "      <td>3.440</td>\n",
       "      <td>17.02</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               model   mpg  cyl   disp   hp  drat     wt   qsec  vs  am  gear  \\\n",
       "0          Mazda RX4  21.0    6  160.0  110  3.90  2.620  16.46   0   1     4   \n",
       "1      Mazda RX4 Wag  21.0    6  160.0  110  3.90  2.875  17.02   0   1     4   \n",
       "2         Datsun 710  22.8    4  108.0   93  3.85  2.320  18.61   1   1     4   \n",
       "3     Hornet 4 Drive  21.4    6  258.0  110  3.08  3.215  19.44   1   0     3   \n",
       "4  Hornet Sportabout  18.7    8  360.0  175  3.15  3.440  17.02   0   0     3   \n",
       "\n",
       "   carb  \n",
       "0     4  \n",
       "1     4  \n",
       "2     1  \n",
       "3     1  \n",
       "4     2  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "url = \"https://gist.githubusercontent.com/seankross/a412dfbd88b3db70b74b/raw/5f23f993cd87c283ce766e7ac6b329ee7cc2e1d1/mtcars.csv\"\n",
    "cars = pd.read_csv(url)\n",
    "cars.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>disp</th>\n",
       "      <th>hp</th>\n",
       "      <th>drat</th>\n",
       "      <th>wt</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>cyl</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1156.5</td>\n",
       "      <td>909</td>\n",
       "      <td>4.070909</td>\n",
       "      <td>2.285727</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>1283.2</td>\n",
       "      <td>856</td>\n",
       "      <td>3.585714</td>\n",
       "      <td>3.117143</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>4943.4</td>\n",
       "      <td>2929</td>\n",
       "      <td>3.229286</td>\n",
       "      <td>3.999214</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       disp    hp      drat        wt\n",
       "cyl                                  \n",
       "4    1156.5   909  4.070909  2.285727\n",
       "6    1283.2   856  3.585714  3.117143\n",
       "8    4943.4  2929  3.229286  3.999214"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# dplyr:\n",
    "# dat <- group_by(mtcars, cyl) \n",
    "# summarize(dat, across(ends_with('p'), sum), across(ends_with('t'), mean))\n",
    "aggs = {key:\"mean\" if key.endswith(\"t\") else \"sum\" for key in cars if key.endswith(('p', 't'))}\n",
    "cars.groupby('cyl').agg(aggs)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "An alternate approach, where the groupby is reused, is with [pyjanitor's](https://pyjanitor-devs.github.io/pyjanitor/) [get_columns](https://pyjanitor-devs.github.io/pyjanitor/api/functions/#janitor.functions.utils.get_columns) function:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>disp</th>\n",
       "      <th>hp</th>\n",
       "      <th>drat</th>\n",
       "      <th>wt</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>cyl</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1156.5</td>\n",
       "      <td>909</td>\n",
       "      <td>4.070909</td>\n",
       "      <td>2.285727</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>1283.2</td>\n",
       "      <td>856</td>\n",
       "      <td>3.585714</td>\n",
       "      <td>3.117143</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>4943.4</td>\n",
       "      <td>2929</td>\n",
       "      <td>3.229286</td>\n",
       "      <td>3.999214</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       disp    hp      drat        wt\n",
       "cyl                                  \n",
       "4    1156.5   909  4.070909  2.285727\n",
       "6    1283.2   856  3.585714  3.117143\n",
       "8    4943.4  2929  3.229286  3.999214"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grp = cars.groupby('cyl')\n",
    "summary = [get_columns(grp, '*p').sum(), get_columns(grp, '*t').mean()]\n",
    "pd.concat(summary, axis = 1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Comments\n",
    "<script src=\"https://utteranc.es/client.js\"\n",
    "        repo=\"samukweku/data-wrangling-blog\"\n",
    "        issue-term=\"title\"\n",
    "        theme=\"github-light\"\n",
    "        crossorigin=\"anonymous\"\n",
    "        async>\n",
    "</script>"
   ]
  }
 ],
 "metadata": {
  "jupytext": {
   "formats": "ipynb,md"
  },
  "kernelspec": {
   "display_name": "blogger",
   "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": "3.10.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}