历史文章附件列表/（数据科学学习手札134）pyjanitor：为pandas补充更多功能/（数据科学学习手札134）pyjanitor：为pandas补充更多功能.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "99e686c7-2837-488f-bdf2-2935ee560915",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import janitor\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bee3e0fa-45a5-4afc-aea1-489fda9a9437",
   "metadata": {},
   "source": [
    "## 2.1 利用also()方法穿插执行任意函数"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "19bac17a-6f98-4cdb-a60c-edf2e0a60de9",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "a字段<=1的记录有0行\n",
      "字段名：['new_a', 'b']\n"
     ]
    },
    {
     "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>new_a</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   new_a\n",
       "1      2\n",
       "2      3"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = (\n",
    "    # 构造示例数据框\n",
    "    pd.DataFrame({\"a\": [1, 2, 3], \"b\": list(\"abc\")})\n",
    "    .query(\"a > 1\")\n",
    "    # 利用also()插入lambda函数接受上一步的输入对象\n",
    "    .also(lambda df: print(f\"a字段<=1的记录有{df.query('a <= 1').shape[0]}行\"))\n",
    "    .rename(columns={'a': 'new_a'})\n",
    "    # 利用also()实现中间计算结果的导出\n",
    "    .also(lambda df: df.to_csv(\"temp.csv\", index=False))\n",
    "    # 利用also()打印到这一步时数据框计算结果的字段名\n",
    "    .also(\n",
    "        lambda df: print(f\"字段名：{df.columns.tolist()}\")\n",
    "    )\n",
    "    .drop(columns='b')\n",
    ")\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "99b7add4-5361-4ae9-ab5d-7ca904bbfccd",
   "metadata": {},
   "source": [
    "## 2.2 利用case_when()方法实现多条件分支"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "79fe6064-d9a3-4825-a905-d55ef31be015",
   "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>a</th>\n",
       "      <th>b</th>\n",
       "      <th>c</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "      <td>5</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   a  b  c\n",
       "0  0  0  6\n",
       "1  0  3  7\n",
       "2  1  4  8\n",
       "3  2  5  9"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame(\n",
    "    {\n",
    "        \"a\": [0, 0, 1, 2],\n",
    "        \"b\": [0, 3, 4, 5],\n",
    "        \"c\": [6, 7, 8, 9],\n",
    "    }\n",
    ")\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "bfe51f59-f0cc-4e14-ba1c-3a72aedc2575",
   "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>a</th>\n",
       "      <th>b</th>\n",
       "      <th>c</th>\n",
       "      <th>类别</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>类别1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>类别2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>8</td>\n",
       "      <td>类别3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "      <td>5</td>\n",
       "      <td>9</td>\n",
       "      <td>类别3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   a  b  c   类别\n",
       "0  0  0  6  类别1\n",
       "1  0  3  7  类别2\n",
       "2  1  4  8  类别3\n",
       "3  2  5  9  类别3"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.case_when(\n",
    "    ((df.a == 0) & (df.b == 0)), '类别1',\n",
    "    ((df.a == 0) & (df.b != 0)), '类别2',\n",
    "    # 其他情况\n",
    "    '类别3',\n",
    "    column_name=\"类别\",\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "23165d8b-cb5d-42ee-af49-bfed8baf7f86",
   "metadata": {},
   "source": [
    "## 2.3 利用conditional_join()实现条件连接"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "0194e430-c0d8-4801-b051-418eceb2b14a",
   "metadata": {
    "tags": []
   },
   "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>id</th>\n",
       "      <th>left_range_start</th>\n",
       "      <th>left_range_end</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a</td>\n",
       "      <td>2</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>b</td>\n",
       "      <td>9</td>\n",
       "      <td>11</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>c</td>\n",
       "      <td>14</td>\n",
       "      <td>21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>d</td>\n",
       "      <td>30</td>\n",
       "      <td>35</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  id  left_range_start  left_range_end\n",
       "0  a                 2               5\n",
       "1  b                 9              11\n",
       "2  c                14              21\n",
       "3  d                30              35"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 定义示例左表\n",
    "df_left = pd.DataFrame({\n",
    "    'id': list('abcd'),\n",
    "    'left_range_start': [2, 9, 14, 30],\n",
    "    'left_range_end': [5, 11, 21, 35]\n",
    "})\n",
    "df_left"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "8c844ba1-6081-4841-8c98-886f936b52fb",
   "metadata": {
    "tags": []
   },
   "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>id</th>\n",
       "      <th>right_range_start</th>\n",
       "      <th>right_range_end</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>i</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>j</td>\n",
       "      <td>6</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>x</td>\n",
       "      <td>15</td>\n",
       "      <td>18</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>y</td>\n",
       "      <td>28</td>\n",
       "      <td>31</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  id  right_range_start  right_range_end\n",
       "0  i                  2                3\n",
       "1  j                  6               10\n",
       "2  x                 15               18\n",
       "3  y                 28               31"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 定义示例右表\n",
    "df_right = pd.DataFrame({\n",
    "    'id': list('ijxy'),\n",
    "    'right_range_start': [2, 6, 15, 28],\n",
    "    'right_range_end': [3, 10, 18, 31]\n",
    "})\n",
    "df_right"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "c58ee4a8-a86c-4e33-b647-fbdf823a6abd",
   "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 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=\"3\" halign=\"left\">left</th>\n",
       "      <th colspan=\"3\" halign=\"left\">right</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>left_range_start</th>\n",
       "      <th>left_range_end</th>\n",
       "      <th>id</th>\n",
       "      <th>right_range_start</th>\n",
       "      <th>right_range_end</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>a</td>\n",
       "      <td>2</td>\n",
       "      <td>5</td>\n",
       "      <td>i</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>c</td>\n",
       "      <td>14</td>\n",
       "      <td>21</td>\n",
       "      <td>x</td>\n",
       "      <td>15</td>\n",
       "      <td>18</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  left                                 right                                  \n",
       "    id left_range_start left_range_end    id right_range_start right_range_end\n",
       "0    a                2              5     i                 2               3\n",
       "1    c               14             21     x                15              18"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(\n",
    "    df_left\n",
    "    .conditional_join(\n",
    "        df_right,\n",
    "        # 满足left_range_start <= right_range_start\n",
    "        ('left_range_start', 'right_range_start', '<='),\n",
    "        # 且满足left_range_end >= right_range_end\n",
    "        ('left_range_end', 'right_range_end', '>=')\n",
    "    )\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0a3c6628-6b7a-46aa-913e-4e6d61818f91",
   "metadata": {},
   "source": [
    "## 2.4 利用move()方法快捷完成字段位置调整"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "ef4701a6-afc3-4a2c-849b-b2e0e2bad867",
   "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>a</th>\n",
       "      <th>b</th>\n",
       "      <th>c</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6</td>\n",
       "      <td>5</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   a  b  c\n",
       "0  2  1  7\n",
       "1  4  3  8\n",
       "2  6  5  9"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame({\"a\": [2, 4, 6], \"b\": [1, 3, 5], \"c\": [7, 8, 9]})\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "d33f7248-ee7f-4578-9e3d-c3010c2b9cec",
   "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>b</th>\n",
       "      <th>a</th>\n",
       "      <th>c</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   b  a  c\n",
       "0  1  2  7\n",
       "1  3  4  8\n",
       "2  5  6  9"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 将a字段挪动到c字段之前\n",
    "df.move(source=\"a\", target=\"c\", position=\"before\", axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "d94fae24-2eda-4eed-aa21-dcd0ccc4a648",
   "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>b</th>\n",
       "      <th>c</th>\n",
       "      <th>a</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3</td>\n",
       "      <td>8</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5</td>\n",
       "      <td>9</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   b  c  a\n",
       "0  1  7  2\n",
       "1  3  8  4\n",
       "2  5  9  6"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 将a字段挪动到c字段之后\n",
    "df.move(source=\"a\", target=\"c\", position=\"after\", axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4cdb0202-f280-4102-b21b-abe32587cc67",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1539e14f-f498-4569-9d18-52885bc4db9a",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "817ac6f2-ae71-48f5-9e3b-545ad787ed66",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7a522c82-ccbd-49f3-aa65-3214de28796c",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d5733ae4-d755-40b8-886f-f1e34a8ae16d",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}