{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Reindexing Series&DataFrame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from pandas import Series, DataFrame"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Series reindex"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "A    1\n",
       "B    2\n",
       "C    3\n",
       "D    4\n",
       "dtype: int64"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s1 = pd.Series([1, 2, 3, 4], index=['A', 'B', 'C', 'D'])\n",
    "s1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "A    1.0\n",
       "B    2.0\n",
       "C    3.0\n",
       "D    4.0\n",
       "E    NaN\n",
       "dtype: float64"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 按住 Shift + Tab 可以查看帮助\n",
    "s1.reindex(index=['A', 'B', 'C', 'D', 'E'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "A     1\n",
       "B     2\n",
       "C     3\n",
       "D     4\n",
       "E    10\n",
       "dtype: int64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s1.reindex(index=['A', 'B', 'C', 'D', 'E'], fill_value=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1    A\n",
       "3    B\n",
       "5    C\n",
       "dtype: object"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s2 = pd.Series(['A', 'B', 'C'], index=[1, 3, 5])\n",
    "s2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    NaN\n",
       "1      A\n",
       "2    NaN\n",
       "3      B\n",
       "4    NaN\n",
       "5      C\n",
       "6    NaN\n",
       "dtype: object"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s2.reindex(index=range(7))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    NaN\n",
       "1      A\n",
       "2      A\n",
       "3      B\n",
       "4      B\n",
       "5      C\n",
       "6      C\n",
       "dtype: object"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#  method='ffill' 表示根据已有的值自动填充为 NaN 的值\n",
    "s2.reindex(index=range(7), method='ffill')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## DataFrame reindex"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "scrolled": true
   },
   "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>c1</th>\n",
       "      <th>c2</th>\n",
       "      <th>c3</th>\n",
       "      <th>c4</th>\n",
       "      <th>c5</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>0.861122</td>\n",
       "      <td>0.266480</td>\n",
       "      <td>0.699760</td>\n",
       "      <td>0.940892</td>\n",
       "      <td>0.068831</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>0.249055</td>\n",
       "      <td>0.542753</td>\n",
       "      <td>0.606975</td>\n",
       "      <td>0.961807</td>\n",
       "      <td>0.598670</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>D</th>\n",
       "      <td>0.701571</td>\n",
       "      <td>0.971356</td>\n",
       "      <td>0.629673</td>\n",
       "      <td>0.319623</td>\n",
       "      <td>0.747501</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>E</th>\n",
       "      <td>0.192507</td>\n",
       "      <td>0.125178</td>\n",
       "      <td>0.598555</td>\n",
       "      <td>0.254121</td>\n",
       "      <td>0.455577</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>F</th>\n",
       "      <td>0.982085</td>\n",
       "      <td>0.521312</td>\n",
       "      <td>0.906348</td>\n",
       "      <td>0.912376</td>\n",
       "      <td>0.352556</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         c1        c2        c3        c4        c5\n",
       "A  0.861122  0.266480  0.699760  0.940892  0.068831\n",
       "B  0.249055  0.542753  0.606975  0.961807  0.598670\n",
       "D  0.701571  0.971356  0.629673  0.319623  0.747501\n",
       "E  0.192507  0.125178  0.598555  0.254121  0.455577\n",
       "F  0.982085  0.521312  0.906348  0.912376  0.352556"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1 = pd.DataFrame(np.random.rand(25).reshape([5, 5]), index=['A', 'B', 'D', 'E', 'F'], columns=['c1', 'c2', 'c3', 'c4', 'c5'])\n",
    "df1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "scrolled": true
   },
   "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>c1</th>\n",
       "      <th>c2</th>\n",
       "      <th>c3</th>\n",
       "      <th>c4</th>\n",
       "      <th>c5</th>\n",
       "      <th>c6</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>D</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>E</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",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   c1  c2  c3  c4  c5  c6\n",
       "A NaN NaN NaN NaN NaN NaN\n",
       "B NaN NaN NaN NaN NaN NaN\n",
       "C NaN NaN NaN NaN NaN NaN\n",
       "D NaN NaN NaN NaN NaN NaN\n",
       "E NaN NaN NaN NaN NaN NaN"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.reindex(index=[['A', 'B', 'C', 'D', 'E']], columns=['c1', 'c2', 'c3', 'c4', 'c5', 'c6'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "C    3\n",
       "D    4\n",
       "dtype: int64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s1.reindex(index=['C', 'D'])"
   ]
  },
  {
   "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>c1</th>\n",
       "      <th>c2</th>\n",
       "      <th>c3</th>\n",
       "      <th>c4</th>\n",
       "      <th>c5</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <td>0.352591</td>\n",
       "      <td>0.437914</td>\n",
       "      <td>0.131892</td>\n",
       "      <td>0.273035</td>\n",
       "      <td>0.463063</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>0.367352</td>\n",
       "      <td>0.245098</td>\n",
       "      <td>0.081478</td>\n",
       "      <td>0.744348</td>\n",
       "      <td>0.990410</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         c1        c2        c3        c4        c5\n",
       "A  0.352591  0.437914  0.131892  0.273035  0.463063\n",
       "B  0.367352  0.245098  0.081478  0.744348  0.990410"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df1.reindex(index=['A', 'B'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "B    2\n",
       "C    3\n",
       "D    4\n",
       "dtype: int64"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s1.drop('A')"
   ]
  },
  {
   "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>c1</th>\n",
       "      <th>c2</th>\n",
       "      <th>c3</th>\n",
       "      <th>c4</th>\n",
       "      <th>c5</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>B</th>\n",
       "      <td>0.367352</td>\n",
       "      <td>0.245098</td>\n",
       "      <td>0.081478</td>\n",
       "      <td>0.744348</td>\n",
       "      <td>0.990410</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>D</th>\n",
       "      <td>0.364244</td>\n",
       "      <td>0.751367</td>\n",
       "      <td>0.782257</td>\n",
       "      <td>0.443011</td>\n",
       "      <td>0.688876</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>E</th>\n",
       "      <td>0.615851</td>\n",
       "      <td>0.725409</td>\n",
       "      <td>0.741932</td>\n",
       "      <td>0.791803</td>\n",
       "      <td>0.576622</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>F</th>\n",
       "      <td>0.599175</td>\n",
       "      <td>0.543432</td>\n",
       "      <td>0.443125</td>\n",
       "      <td>0.471929</td>\n",
       "      <td>0.436654</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         c1        c2        c3        c4        c5\n",
       "B  0.367352  0.245098  0.081478  0.744348  0.990410\n",
       "D  0.364244  0.751367  0.782257  0.443011  0.688876\n",
       "E  0.615851  0.725409  0.741932  0.791803  0.576622\n",
       "F  0.599175  0.543432  0.443125  0.471929  0.436654"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# axis 表示行和列\n",
    "# 0 表示行\n",
    "# 1 表示列\n",
    "df1.drop('A', axis=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.6.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}