历史文章附件列表/（数据科学学习手札97）掌握pandas中的transform/（数据科学学习手札97）详解pandas中的transform.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-14T09:56:07.614204Z",
     "iopub.status.busy": "2020-10-14T09:56:07.614204Z",
     "iopub.status.idle": "2020-10-14T09:56:07.618193Z",
     "shell.execute_reply": "2020-10-14T09:56:07.618193Z",
     "shell.execute_reply.started": "2020-10-14T09:56:07.614204Z"
    }
   },
   "outputs": [],
   "source": [
    "import warnings\n",
    "\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 2 pandas中的transform"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2.1 transform作用于Series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-14T09:56:07.623210Z",
     "iopub.status.busy": "2020-10-14T09:56:07.623210Z",
     "iopub.status.idle": "2020-10-14T09:56:07.641130Z",
     "shell.execute_reply": "2020-10-14T09:56:07.641130Z",
     "shell.execute_reply.started": "2020-10-14T09:56:07.623210Z"
    }
   },
   "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>species</th>\n",
       "      <th>island</th>\n",
       "      <th>bill_length_mm</th>\n",
       "      <th>bill_depth_mm</th>\n",
       "      <th>flipper_length_mm</th>\n",
       "      <th>body_mass_g</th>\n",
       "      <th>sex</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>Torgersen</td>\n",
       "      <td>39.1</td>\n",
       "      <td>18.7</td>\n",
       "      <td>181.0</td>\n",
       "      <td>3750.0</td>\n",
       "      <td>male</td>\n",
       "      <td>2007</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>Torgersen</td>\n",
       "      <td>39.5</td>\n",
       "      <td>17.4</td>\n",
       "      <td>186.0</td>\n",
       "      <td>3800.0</td>\n",
       "      <td>female</td>\n",
       "      <td>2007</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>Torgersen</td>\n",
       "      <td>40.3</td>\n",
       "      <td>18.0</td>\n",
       "      <td>195.0</td>\n",
       "      <td>3250.0</td>\n",
       "      <td>female</td>\n",
       "      <td>2007</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>Torgersen</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2007</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Adelie</td>\n",
       "      <td>Torgersen</td>\n",
       "      <td>36.7</td>\n",
       "      <td>19.3</td>\n",
       "      <td>193.0</td>\n",
       "      <td>3450.0</td>\n",
       "      <td>female</td>\n",
       "      <td>2007</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>339</th>\n",
       "      <td>Chinstrap</td>\n",
       "      <td>Dream</td>\n",
       "      <td>55.8</td>\n",
       "      <td>19.8</td>\n",
       "      <td>207.0</td>\n",
       "      <td>4000.0</td>\n",
       "      <td>male</td>\n",
       "      <td>2009</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>340</th>\n",
       "      <td>Chinstrap</td>\n",
       "      <td>Dream</td>\n",
       "      <td>43.5</td>\n",
       "      <td>18.1</td>\n",
       "      <td>202.0</td>\n",
       "      <td>3400.0</td>\n",
       "      <td>female</td>\n",
       "      <td>2009</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>341</th>\n",
       "      <td>Chinstrap</td>\n",
       "      <td>Dream</td>\n",
       "      <td>49.6</td>\n",
       "      <td>18.2</td>\n",
       "      <td>193.0</td>\n",
       "      <td>3775.0</td>\n",
       "      <td>male</td>\n",
       "      <td>2009</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>342</th>\n",
       "      <td>Chinstrap</td>\n",
       "      <td>Dream</td>\n",
       "      <td>50.8</td>\n",
       "      <td>19.0</td>\n",
       "      <td>210.0</td>\n",
       "      <td>4100.0</td>\n",
       "      <td>male</td>\n",
       "      <td>2009</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>343</th>\n",
       "      <td>Chinstrap</td>\n",
       "      <td>Dream</td>\n",
       "      <td>50.2</td>\n",
       "      <td>18.7</td>\n",
       "      <td>198.0</td>\n",
       "      <td>3775.0</td>\n",
       "      <td>female</td>\n",
       "      <td>2009</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>344 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       species     island  bill_length_mm  bill_depth_mm  flipper_length_mm  \\\n",
       "0       Adelie  Torgersen            39.1           18.7              181.0   \n",
       "1       Adelie  Torgersen            39.5           17.4              186.0   \n",
       "2       Adelie  Torgersen            40.3           18.0              195.0   \n",
       "3       Adelie  Torgersen             NaN            NaN                NaN   \n",
       "4       Adelie  Torgersen            36.7           19.3              193.0   \n",
       "..         ...        ...             ...            ...                ...   \n",
       "339  Chinstrap      Dream            55.8           19.8              207.0   \n",
       "340  Chinstrap      Dream            43.5           18.1              202.0   \n",
       "341  Chinstrap      Dream            49.6           18.2              193.0   \n",
       "342  Chinstrap      Dream            50.8           19.0              210.0   \n",
       "343  Chinstrap      Dream            50.2           18.7              198.0   \n",
       "\n",
       "     body_mass_g     sex  year  \n",
       "0         3750.0    male  2007  \n",
       "1         3800.0  female  2007  \n",
       "2         3250.0  female  2007  \n",
       "3            NaN     NaN  2007  \n",
       "4         3450.0  female  2007  \n",
       "..           ...     ...   ...  \n",
       "339       4000.0    male  2009  \n",
       "340       3400.0  female  2009  \n",
       "341       3775.0    male  2009  \n",
       "342       4100.0    male  2009  \n",
       "343       3775.0  female  2009  \n",
       "\n",
       "[344 rows x 8 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "# 读入数据并去除含有缺失值的行\n",
    "penguins = pd.read_csv('penguins.csv')\n",
    "penguins"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- **单个变换函数**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-14T09:56:07.642127Z",
     "iopub.status.busy": "2020-10-14T09:56:07.642127Z",
     "iopub.status.idle": "2020-10-14T09:56:07.650107Z",
     "shell.execute_reply": "2020-10-14T09:56:07.649110Z",
     "shell.execute_reply.started": "2020-10-14T09:56:07.642127Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0      3.666122\n",
       "1      3.676301\n",
       "2      3.696351\n",
       "3           NaN\n",
       "4      3.602777\n",
       "         ...   \n",
       "339    4.021774\n",
       "340    3.772761\n",
       "341    3.903991\n",
       "342    3.927896\n",
       "343    3.916015\n",
       "Name: bill_length_mm, Length: 344, dtype: float64"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 对数化\n",
    "penguins['bill_length_mm'].transform(np.log)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-14T09:56:07.651105Z",
     "iopub.status.busy": "2020-10-14T09:56:07.651105Z",
     "iopub.status.idle": "2020-10-14T09:56:07.658083Z",
     "shell.execute_reply": "2020-10-14T09:56:07.658083Z",
     "shell.execute_reply.started": "2020-10-14T09:56:07.651105Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0      40.1\n",
       "1      40.5\n",
       "2      41.3\n",
       "3       NaN\n",
       "4      37.7\n",
       "       ... \n",
       "339    56.8\n",
       "340    44.5\n",
       "341    50.6\n",
       "342    51.8\n",
       "343    51.2\n",
       "Name: bill_length_mm, Length: 344, dtype: float64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# lambda函数\n",
    "penguins['bill_length_mm'].transform(lambda s: s+1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- **多个变换函数**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-14T09:56:07.660078Z",
     "iopub.status.busy": "2020-10-14T09:56:07.659081Z",
     "iopub.status.idle": "2020-10-14T09:56:07.671049Z",
     "shell.execute_reply": "2020-10-14T09:56:07.670052Z",
     "shell.execute_reply.started": "2020-10-14T09:56:07.660078Z"
    }
   },
   "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>log</th>\n",
       "      <th>&lt;lambda&gt;</th>\n",
       "      <th>sqrt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3.666122</td>\n",
       "      <td>40.1</td>\n",
       "      <td>6.252999</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3.676301</td>\n",
       "      <td>40.5</td>\n",
       "      <td>6.284903</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3.696351</td>\n",
       "      <td>41.3</td>\n",
       "      <td>6.348228</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3.602777</td>\n",
       "      <td>37.7</td>\n",
       "      <td>6.058052</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>339</th>\n",
       "      <td>4.021774</td>\n",
       "      <td>56.8</td>\n",
       "      <td>7.469940</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>340</th>\n",
       "      <td>3.772761</td>\n",
       "      <td>44.5</td>\n",
       "      <td>6.595453</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>341</th>\n",
       "      <td>3.903991</td>\n",
       "      <td>50.6</td>\n",
       "      <td>7.042727</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>342</th>\n",
       "      <td>3.927896</td>\n",
       "      <td>51.8</td>\n",
       "      <td>7.127412</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>343</th>\n",
       "      <td>3.916015</td>\n",
       "      <td>51.2</td>\n",
       "      <td>7.085196</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>344 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          log  <lambda>      sqrt\n",
       "0    3.666122      40.1  6.252999\n",
       "1    3.676301      40.5  6.284903\n",
       "2    3.696351      41.3  6.348228\n",
       "3         NaN       NaN       NaN\n",
       "4    3.602777      37.7  6.058052\n",
       "..        ...       ...       ...\n",
       "339  4.021774      56.8  7.469940\n",
       "340  3.772761      44.5  6.595453\n",
       "341  3.903991      50.6  7.042727\n",
       "342  3.927896      51.8  7.127412\n",
       "343  3.916015      51.2  7.085196\n",
       "\n",
       "[344 rows x 3 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "penguins['bill_length_mm'].transform([np.log, \n",
    "                                      lambda s: s+1, \n",
    "                                      np.sqrt])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-14T09:56:07.672047Z",
     "iopub.status.busy": "2020-10-14T09:56:07.672047Z",
     "iopub.status.idle": "2020-10-14T09:56:07.685045Z",
     "shell.execute_reply": "2020-10-14T09:56:07.685045Z",
     "shell.execute_reply.started": "2020-10-14T09:56:07.672047Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     -0.883205\n",
       "1     -0.809939\n",
       "2     -0.663408\n",
       "3           NaN\n",
       "4     -1.322799\n",
       "         ...   \n",
       "339    2.175637\n",
       "340   -0.077282\n",
       "341    1.040019\n",
       "342    1.259816\n",
       "343    1.149917\n",
       "Name: bill_length_mm, Length: 344, dtype: float64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 利用transform进行数据标准化\n",
    "penguins['bill_length_mm'].transform(lambda s: (s - s.mean()) / s.std())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2.2 transform作用于DataFrame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-14T09:56:07.686006Z",
     "iopub.status.busy": "2020-10-14T09:56:07.686006Z",
     "iopub.status.idle": "2020-10-14T09:56:07.705952Z",
     "shell.execute_reply": "2020-10-14T09:56:07.704958Z",
     "shell.execute_reply.started": "2020-10-14T09:56:07.686006Z"
    }
   },
   "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>bill_length_mm</th>\n",
       "      <th>bill_depth_mm</th>\n",
       "      <th>flipper_length_mm</th>\n",
       "      <th>body_mass_g</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-0.883205</td>\n",
       "      <td>0.784300</td>\n",
       "      <td>-1.416272</td>\n",
       "      <td>-0.563317</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-0.809939</td>\n",
       "      <td>0.126003</td>\n",
       "      <td>-1.060696</td>\n",
       "      <td>-0.500969</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-0.663408</td>\n",
       "      <td>0.429833</td>\n",
       "      <td>-0.420660</td>\n",
       "      <td>-1.186793</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\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>-1.322799</td>\n",
       "      <td>1.088129</td>\n",
       "      <td>-0.562890</td>\n",
       "      <td>-0.937403</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>339</th>\n",
       "      <td>2.175637</td>\n",
       "      <td>1.341320</td>\n",
       "      <td>0.432721</td>\n",
       "      <td>-0.251578</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>340</th>\n",
       "      <td>-0.077282</td>\n",
       "      <td>0.480471</td>\n",
       "      <td>0.077145</td>\n",
       "      <td>-0.999750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>341</th>\n",
       "      <td>1.040019</td>\n",
       "      <td>0.531109</td>\n",
       "      <td>-0.562890</td>\n",
       "      <td>-0.532143</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>342</th>\n",
       "      <td>1.259816</td>\n",
       "      <td>0.936215</td>\n",
       "      <td>0.646066</td>\n",
       "      <td>-0.126883</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>343</th>\n",
       "      <td>1.149917</td>\n",
       "      <td>0.784300</td>\n",
       "      <td>-0.207315</td>\n",
       "      <td>-0.532143</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>344 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     bill_length_mm  bill_depth_mm  flipper_length_mm  body_mass_g\n",
       "0         -0.883205       0.784300          -1.416272    -0.563317\n",
       "1         -0.809939       0.126003          -1.060696    -0.500969\n",
       "2         -0.663408       0.429833          -0.420660    -1.186793\n",
       "3               NaN            NaN                NaN          NaN\n",
       "4         -1.322799       1.088129          -0.562890    -0.937403\n",
       "..              ...            ...                ...          ...\n",
       "339        2.175637       1.341320           0.432721    -0.251578\n",
       "340       -0.077282       0.480471           0.077145    -0.999750\n",
       "341        1.040019       0.531109          -0.562890    -0.532143\n",
       "342        1.259816       0.936215           0.646066    -0.126883\n",
       "343        1.149917       0.784300          -0.207315    -0.532143\n",
       "\n",
       "[344 rows x 4 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 分别对每列进行标准化\n",
    "(\n",
    "    penguins\n",
    "    .loc[:, 'bill_length_mm': 'body_mass_g']\n",
    "    .transform(lambda s: (s - s.mean()) / s.std())\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-14T09:56:07.706950Z",
     "iopub.status.busy": "2020-10-14T09:56:07.706950Z",
     "iopub.status.idle": "2020-10-14T09:56:07.735872Z",
     "shell.execute_reply": "2020-10-14T09:56:07.735872Z",
     "shell.execute_reply.started": "2020-10-14T09:56:07.706950Z"
    }
   },
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"2\" halign=\"left\">bill_length_mm</th>\n",
       "      <th colspan=\"2\" halign=\"left\">bill_depth_mm</th>\n",
       "      <th colspan=\"2\" halign=\"left\">flipper_length_mm</th>\n",
       "      <th colspan=\"2\" halign=\"left\">body_mass_g</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>log</th>\n",
       "      <th>&lt;lambda_0&gt;</th>\n",
       "      <th>log</th>\n",
       "      <th>&lt;lambda_0&gt;</th>\n",
       "      <th>log</th>\n",
       "      <th>&lt;lambda_0&gt;</th>\n",
       "      <th>log</th>\n",
       "      <th>&lt;lambda_0&gt;</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3.666122</td>\n",
       "      <td>40.1</td>\n",
       "      <td>2.928524</td>\n",
       "      <td>19.7</td>\n",
       "      <td>5.198497</td>\n",
       "      <td>182.0</td>\n",
       "      <td>8.229511</td>\n",
       "      <td>3751.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3.676301</td>\n",
       "      <td>40.5</td>\n",
       "      <td>2.856470</td>\n",
       "      <td>18.4</td>\n",
       "      <td>5.225747</td>\n",
       "      <td>187.0</td>\n",
       "      <td>8.242756</td>\n",
       "      <td>3801.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3.696351</td>\n",
       "      <td>41.3</td>\n",
       "      <td>2.890372</td>\n",
       "      <td>19.0</td>\n",
       "      <td>5.273000</td>\n",
       "      <td>196.0</td>\n",
       "      <td>8.086410</td>\n",
       "      <td>3251.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3.602777</td>\n",
       "      <td>37.7</td>\n",
       "      <td>2.960105</td>\n",
       "      <td>20.3</td>\n",
       "      <td>5.262690</td>\n",
       "      <td>194.0</td>\n",
       "      <td>8.146130</td>\n",
       "      <td>3451.0</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>339</th>\n",
       "      <td>4.021774</td>\n",
       "      <td>56.8</td>\n",
       "      <td>2.985682</td>\n",
       "      <td>20.8</td>\n",
       "      <td>5.332719</td>\n",
       "      <td>208.0</td>\n",
       "      <td>8.294050</td>\n",
       "      <td>4001.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>340</th>\n",
       "      <td>3.772761</td>\n",
       "      <td>44.5</td>\n",
       "      <td>2.895912</td>\n",
       "      <td>19.1</td>\n",
       "      <td>5.308268</td>\n",
       "      <td>203.0</td>\n",
       "      <td>8.131531</td>\n",
       "      <td>3401.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>341</th>\n",
       "      <td>3.903991</td>\n",
       "      <td>50.6</td>\n",
       "      <td>2.901422</td>\n",
       "      <td>19.2</td>\n",
       "      <td>5.262690</td>\n",
       "      <td>194.0</td>\n",
       "      <td>8.236156</td>\n",
       "      <td>3776.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>342</th>\n",
       "      <td>3.927896</td>\n",
       "      <td>51.8</td>\n",
       "      <td>2.944439</td>\n",
       "      <td>20.0</td>\n",
       "      <td>5.347108</td>\n",
       "      <td>211.0</td>\n",
       "      <td>8.318742</td>\n",
       "      <td>4101.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>343</th>\n",
       "      <td>3.916015</td>\n",
       "      <td>51.2</td>\n",
       "      <td>2.928524</td>\n",
       "      <td>19.7</td>\n",
       "      <td>5.288267</td>\n",
       "      <td>199.0</td>\n",
       "      <td>8.236156</td>\n",
       "      <td>3776.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>344 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    bill_length_mm            bill_depth_mm            flipper_length_mm  \\\n",
       "               log <lambda_0>           log <lambda_0>               log   \n",
       "0         3.666122       40.1      2.928524       19.7          5.198497   \n",
       "1         3.676301       40.5      2.856470       18.4          5.225747   \n",
       "2         3.696351       41.3      2.890372       19.0          5.273000   \n",
       "3              NaN        NaN           NaN        NaN               NaN   \n",
       "4         3.602777       37.7      2.960105       20.3          5.262690   \n",
       "..             ...        ...           ...        ...               ...   \n",
       "339       4.021774       56.8      2.985682       20.8          5.332719   \n",
       "340       3.772761       44.5      2.895912       19.1          5.308268   \n",
       "341       3.903991       50.6      2.901422       19.2          5.262690   \n",
       "342       3.927896       51.8      2.944439       20.0          5.347108   \n",
       "343       3.916015       51.2      2.928524       19.7          5.288267   \n",
       "\n",
       "               body_mass_g             \n",
       "    <lambda_0>         log <lambda_0>  \n",
       "0        182.0    8.229511     3751.0  \n",
       "1        187.0    8.242756     3801.0  \n",
       "2        196.0    8.086410     3251.0  \n",
       "3          NaN         NaN        NaN  \n",
       "4        194.0    8.146130     3451.0  \n",
       "..         ...         ...        ...  \n",
       "339      208.0    8.294050     4001.0  \n",
       "340      203.0    8.131531     3401.0  \n",
       "341      194.0    8.236156     3776.0  \n",
       "342      211.0    8.318742     4101.0  \n",
       "343      199.0    8.236156     3776.0  \n",
       "\n",
       "[344 rows x 8 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(\n",
    "    penguins\n",
    "    .loc[:, 'bill_length_mm': 'body_mass_g']\n",
    "    .transform([np.log, lambda s: s+1])\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-14T09:56:07.737902Z",
     "iopub.status.busy": "2020-10-14T09:56:07.737902Z",
     "iopub.status.idle": "2020-10-14T09:56:07.757839Z",
     "shell.execute_reply": "2020-10-14T09:56:07.757839Z",
     "shell.execute_reply.started": "2020-10-14T09:56:07.737902Z"
    }
   },
   "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 tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>bill_length_mm</th>\n",
       "      <th>bill_depth_mm</th>\n",
       "      <th>flipper_length_mm</th>\n",
       "      <th colspan=\"2\" halign=\"left\">body_mass_g</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>log</th>\n",
       "      <th>&lt;lambda&gt;</th>\n",
       "      <th>log</th>\n",
       "      <th>log</th>\n",
       "      <th>sqrt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3.666122</td>\n",
       "      <td>0.784300</td>\n",
       "      <td>5.198497</td>\n",
       "      <td>8.229511</td>\n",
       "      <td>61.237244</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3.676301</td>\n",
       "      <td>0.126003</td>\n",
       "      <td>5.225747</td>\n",
       "      <td>8.242756</td>\n",
       "      <td>61.644140</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3.696351</td>\n",
       "      <td>0.429833</td>\n",
       "      <td>5.273000</td>\n",
       "      <td>8.086410</td>\n",
       "      <td>57.008771</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\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>4</th>\n",
       "      <td>3.602777</td>\n",
       "      <td>1.088129</td>\n",
       "      <td>5.262690</td>\n",
       "      <td>8.146130</td>\n",
       "      <td>58.736701</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>339</th>\n",
       "      <td>4.021774</td>\n",
       "      <td>1.341320</td>\n",
       "      <td>5.332719</td>\n",
       "      <td>8.294050</td>\n",
       "      <td>63.245553</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>340</th>\n",
       "      <td>3.772761</td>\n",
       "      <td>0.480471</td>\n",
       "      <td>5.308268</td>\n",
       "      <td>8.131531</td>\n",
       "      <td>58.309519</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>341</th>\n",
       "      <td>3.903991</td>\n",
       "      <td>0.531109</td>\n",
       "      <td>5.262690</td>\n",
       "      <td>8.236156</td>\n",
       "      <td>61.441029</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>342</th>\n",
       "      <td>3.927896</td>\n",
       "      <td>0.936215</td>\n",
       "      <td>5.347108</td>\n",
       "      <td>8.318742</td>\n",
       "      <td>64.031242</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>343</th>\n",
       "      <td>3.916015</td>\n",
       "      <td>0.784300</td>\n",
       "      <td>5.288267</td>\n",
       "      <td>8.236156</td>\n",
       "      <td>61.441029</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>344 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    bill_length_mm bill_depth_mm flipper_length_mm body_mass_g           \n",
       "               log      <lambda>               log         log       sqrt\n",
       "0         3.666122      0.784300          5.198497    8.229511  61.237244\n",
       "1         3.676301      0.126003          5.225747    8.242756  61.644140\n",
       "2         3.696351      0.429833          5.273000    8.086410  57.008771\n",
       "3              NaN           NaN               NaN         NaN        NaN\n",
       "4         3.602777      1.088129          5.262690    8.146130  58.736701\n",
       "..             ...           ...               ...         ...        ...\n",
       "339       4.021774      1.341320          5.332719    8.294050  63.245553\n",
       "340       3.772761      0.480471          5.308268    8.131531  58.309519\n",
       "341       3.903991      0.531109          5.262690    8.236156  61.441029\n",
       "342       3.927896      0.936215          5.347108    8.318742  64.031242\n",
       "343       3.916015      0.784300          5.288267    8.236156  61.441029\n",
       "\n",
       "[344 rows x 5 columns]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 根据字典为不同的列配置不同的变换函数\n",
    "(\n",
    "    penguins\n",
    "    .loc[:, 'bill_length_mm': 'body_mass_g']\n",
    "    .transform({'bill_length_mm': np.log,\n",
    "                'bill_depth_mm': lambda s: (s - s.mean()) / s.std(),\n",
    "                'flipper_length_mm': np.log,\n",
    "                'body_mass_g': [np.log, np.sqrt]})\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 2.3 transform作用于DataFrame的分组过程"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-10-14T09:56:07.759806Z",
     "iopub.status.busy": "2020-10-14T09:56:07.758808Z",
     "iopub.status.idle": "2020-10-14T09:56:07.783742Z",
     "shell.execute_reply": "2020-10-14T09:56:07.783742Z",
     "shell.execute_reply.started": "2020-10-14T09:56:07.759806Z"
    }
   },
   "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>bill_length_mm</th>\n",
       "      <th>bill_depth_mm</th>\n",
       "      <th>flipper_length_mm</th>\n",
       "      <th>body_mass_g</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>39.10</td>\n",
       "      <td>18.70</td>\n",
       "      <td>181.00</td>\n",
       "      <td>3750.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>39.50</td>\n",
       "      <td>17.40</td>\n",
       "      <td>186.00</td>\n",
       "      <td>3800.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>40.30</td>\n",
       "      <td>18.00</td>\n",
       "      <td>195.00</td>\n",
       "      <td>3250.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>38.79</td>\n",
       "      <td>18.35</td>\n",
       "      <td>189.95</td>\n",
       "      <td>3700.66</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>36.70</td>\n",
       "      <td>19.30</td>\n",
       "      <td>193.00</td>\n",
       "      <td>3450.00</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>339</th>\n",
       "      <td>55.80</td>\n",
       "      <td>19.80</td>\n",
       "      <td>207.00</td>\n",
       "      <td>4000.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>340</th>\n",
       "      <td>43.50</td>\n",
       "      <td>18.10</td>\n",
       "      <td>202.00</td>\n",
       "      <td>3400.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>341</th>\n",
       "      <td>49.60</td>\n",
       "      <td>18.20</td>\n",
       "      <td>193.00</td>\n",
       "      <td>3775.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>342</th>\n",
       "      <td>50.80</td>\n",
       "      <td>19.00</td>\n",
       "      <td>210.00</td>\n",
       "      <td>4100.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>343</th>\n",
       "      <td>50.20</td>\n",
       "      <td>18.70</td>\n",
       "      <td>198.00</td>\n",
       "      <td>3775.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>344 rows × 4 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     bill_length_mm  bill_depth_mm  flipper_length_mm  body_mass_g\n",
       "0             39.10          18.70             181.00      3750.00\n",
       "1             39.50          17.40             186.00      3800.00\n",
       "2             40.30          18.00             195.00      3250.00\n",
       "3             38.79          18.35             189.95      3700.66\n",
       "4             36.70          19.30             193.00      3450.00\n",
       "..              ...            ...                ...          ...\n",
       "339           55.80          19.80             207.00      4000.00\n",
       "340           43.50          18.10             202.00      3400.00\n",
       "341           49.60          18.20             193.00      3775.00\n",
       "342           50.80          19.00             210.00      4100.00\n",
       "343           50.20          18.70             198.00      3775.00\n",
       "\n",
       "[344 rows x 4 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 分组进行缺失值均值填充\n",
    "(\n",
    "    penguins\n",
    "    .groupby('species')[['bill_length_mm', 'bill_depth_mm', \n",
    "                         'flipper_length_mm', 'body_mass_g']]\n",
    "    .transform(lambda s: s.fillna(s.mean().round(2)))\n",
    ")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.9"
  },
  "widgets": {
   "application/vnd.jupyter.widget-state+json": {
    "state": {},
    "version_major": 2,
    "version_minor": 0
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}