chapter2.ipynb · quantlabor/pandas_for_everyone-master

forked from 赵加栋/pandas_for_everyone-master

加入 Gitee

与超过 1200万开发者一起发现、参与优秀开源项目，私有仓库也完全免费：）

文件

该仓库未声明开源许可证文件（LICENSE），使用请关注具体项目描述及其代码上游依赖。

克隆/下载

chapter2.ipynb 73.24 KB

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    banana\n",
       "1        42\n",
       "dtype: object"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd \n",
    "# Series\n",
    "pd.Series(['banana', 42])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Person         Wes Mckinney\n",
       "Who       Creator of Pandas\n",
       "dtype: object"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.Series(['Wes Mckinney', 'Creator of Pandas'],\n",
    "         index=['Person','Who'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>Age</th>\n",
       "      <th>Born</th>\n",
       "      <th>Died</th>\n",
       "      <th>Name</th>\n",
       "      <th>Occupation</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>37</td>\n",
       "      <td>1920-07-25</td>\n",
       "      <td>1958-04-16</td>\n",
       "      <td>Rosaline Franklin</td>\n",
       "      <td>Chemist</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>61</td>\n",
       "      <td>1876-06-13</td>\n",
       "      <td>1937-10-16</td>\n",
       "      <td>Willam Gosset</td>\n",
       "      <td>Statistican</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Age        Born        Died               Name   Occupation\n",
       "0   37  1920-07-25  1958-04-16  Rosaline Franklin      Chemist\n",
       "1   61  1876-06-13  1937-10-16      Willam Gosset  Statistican"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 创建DataFrame\n",
    "pd.DataFrame({\n",
    "    \"Name\":['Rosaline Franklin', \"Willam Gosset\"],\n",
    "    \"Occupation\":['Chemist', 'Statistican'],\n",
    "    \"Born\":['1920-07-25','1876-06-13'],\n",
    "    'Died':['1958-04-16', '1937-10-16'],\n",
    "    'Age':[37,61]\n",
    "})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "scientists = pd.DataFrame({\n",
    "    \"Name\":['Rosaline Franklin', \"Willam Gosset\"],\n",
    "    \"Occupation\":['Chemist', 'Statistican'],\n",
    "    \"Born\":['1920-07-25','1876-06-13'],\n",
    "    'Died':['1958-04-16', '1937-10-16'],\n",
    "    'Age':[37,61]\n",
    "},\n",
    "index=['Rosaline Franklin', \"Willam Gosset\"],\n",
    "columns=['Occupation', 'Born', 'Died','Age'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "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>Occupation</th>\n",
       "      <th>Born</th>\n",
       "      <th>Died</th>\n",
       "      <th>Age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Rosaline Franklin</td>\n",
       "      <td>Chemist</td>\n",
       "      <td>1920-07-25</td>\n",
       "      <td>1958-04-16</td>\n",
       "      <td>37</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Willam Gosset</td>\n",
       "      <td>Statistican</td>\n",
       "      <td>1876-06-13</td>\n",
       "      <td>1937-10-16</td>\n",
       "      <td>61</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                Name   Occupation        Born        Died  Age\n",
       "0  Rosaline Franklin      Chemist  1920-07-25  1958-04-16   37\n",
       "1      Willam Gosset  Statistican  1876-06-13  1937-10-16   61"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from collections import OrderedDict\n",
    "pd.DataFrame(OrderedDict([\n",
    "    (\"Name\",['Rosaline Franklin', \"Willam Gosset\"]),\n",
    "    (\"Occupation\",['Chemist', 'Statistican']),\n",
    "    (\"Born\",['1920-07-25','1876-06-13']),\n",
    "    ('Died',['1958-04-16', '1937-10-16']),\n",
    "    ('Age',[37,61])\n",
    "]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Occupation    Statistican\n",
       "Born           1876-06-13\n",
       "Died           1937-10-16\n",
       "Age                    61\n",
       "Name: Willam Gosset, dtype: object"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 道行\n",
    "scientists.loc[\"Willam Gosset\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Occupation', 'Born', 'Died', 'Age'], dtype='object')"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "scientists.loc[\"Willam Gosset\"].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Statistican', '1876-06-13', '1937-10-16', 61], dtype=object)"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "scientists.loc[\"Willam Gosset\"].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Occupation', 'Born', 'Died', 'Age'], dtype='object')"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "scientists.loc[\"Willam Gosset\"].keys()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Rosaline Franklin    37\n",
       "Willam Gosset        61\n",
       "Name: Age, dtype: int64"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "scientists[\"Age\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "49.0 61 37 16.97056274847714\n"
     ]
    }
   ],
   "source": [
    "print(scientists[\"Age\"].mean(), scientists[\"Age\"].max(), scientists[\"Age\"].min(),scientists[\"Age\"].std())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "sc = pd.read_csv('../data/scientists.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    37\n",
       "1    61\n",
       "2    90\n",
       "3    66\n",
       "4    56\n",
       "5    45\n",
       "6    41\n",
       "7    77\n",
       "Name: Age, dtype: int64"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sc[\"Age\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count     8.000000\n",
       "mean     59.125000\n",
       "std      18.325918\n",
       "min      37.000000\n",
       "25%      44.000000\n",
       "50%      58.500000\n",
       "75%      68.750000\n",
       "max      90.000000\n",
       "Name: Age, dtype: float64"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sc[\"Age\"].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1    61\n",
       "2    90\n",
       "3    66\n",
       "7    77\n",
       "Name: Age, dtype: int64"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sc[\"Age\"][sc[\"Age\"]>sc[\"Age\"].mean()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0     38.0\n",
      "1    161.0\n",
      "2      NaN\n",
      "3      NaN\n",
      "4      NaN\n",
      "5      NaN\n",
      "6      NaN\n",
      "7      NaN\n",
      "dtype: float64\n"
     ]
    }
   ],
   "source": [
    "print(sc[\"Age\"] + pd.Series([1,100]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "operands could not be broadcast together with shapes (8,) (2,) ",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-27-917d71b5d468>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mnumpy\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0msc\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"Age\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0marray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m100\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m/media/vd1/zjd/venv/lib/python3.5/site-packages/pandas/core/ops.py\u001b[0m in \u001b[0;36mwrapper\u001b[0;34m(left, right)\u001b[0m\n\u001b[1;32m   1581\u001b[0m             \u001b[0mrvalues\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mrvalues\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1582\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1583\u001b[0;31m         \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msafe_na_op\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlvalues\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrvalues\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1584\u001b[0m         return construct_result(left, result,\n\u001b[1;32m   1585\u001b[0m                                 index=left.index, name=res_name, dtype=None)\n",
      "\u001b[0;32m/media/vd1/zjd/venv/lib/python3.5/site-packages/pandas/core/ops.py\u001b[0m in \u001b[0;36msafe_na_op\u001b[0;34m(lvalues, rvalues)\u001b[0m\n\u001b[1;32m   1527\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1528\u001b[0m             \u001b[0;32mwith\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0merrstate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mall\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'ignore'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1529\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mna_op\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlvalues\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrvalues\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1530\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1531\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mis_object_dtype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlvalues\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/media/vd1/zjd/venv/lib/python3.5/site-packages/pandas/core/ops.py\u001b[0m in \u001b[0;36mna_op\u001b[0;34m(x, y)\u001b[0m\n\u001b[1;32m   1503\u001b[0m         \u001b[0;32mimport\u001b[0m \u001b[0mpandas\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcore\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcomputation\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexpressions\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mexpressions\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1504\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1505\u001b[0;31m             \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mexpressions\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mevaluate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mop\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstr_rep\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0meval_kwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1506\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1507\u001b[0m             \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmasked_arith_op\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mop\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/media/vd1/zjd/venv/lib/python3.5/site-packages/pandas/core/computation/expressions.py\u001b[0m in \u001b[0;36mevaluate\u001b[0;34m(op, op_str, a, b, use_numexpr, **eval_kwargs)\u001b[0m\n\u001b[1;32m    206\u001b[0m     \u001b[0muse_numexpr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0muse_numexpr\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0m_bool_arith_check\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mop_str\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0ma\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mb\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    207\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0muse_numexpr\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 208\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0m_evaluate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mop\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mop_str\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0ma\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mb\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0meval_kwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    209\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0m_evaluate_standard\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mop\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mop_str\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0ma\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mb\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    210\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/media/vd1/zjd/venv/lib/python3.5/site-packages/pandas/core/computation/expressions.py\u001b[0m in \u001b[0;36m_evaluate_standard\u001b[0;34m(op, op_str, a, b, **eval_kwargs)\u001b[0m\n\u001b[1;32m     66\u001b[0m         \u001b[0m_store_test_result\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     67\u001b[0m     \u001b[0;32mwith\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0merrstate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mall\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'ignore'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 68\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mop\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0ma\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mb\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     69\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     70\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mValueError\u001b[0m: operands could not be broadcast together with shapes (8,) (2,) "
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "sc[\"Age\"] + np.array([1,100])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "ages = sc[\"Age\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "7    77\n",
      "6    41\n",
      "5    45\n",
      "4    56\n",
      "3    66\n",
      "2    90\n",
      "1    61\n",
      "0    37\n",
      "Name: Age, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "rev_ages = ages.sort_index(ascending=False)\n",
    "print(rev_ages)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     74\n",
       "1    122\n",
       "2    180\n",
       "3    132\n",
       "4    112\n",
       "5     90\n",
       "6     82\n",
       "7    154\n",
       "Name: Age, dtype: int64"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ages +rev_ages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     74\n",
       "1    122\n",
       "2    180\n",
       "3    132\n",
       "4    112\n",
       "5     90\n",
       "6     82\n",
       "7    154\n",
       "Name: Age, dtype: int64"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ages*2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "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>Born</th>\n",
       "      <th>Died</th>\n",
       "      <th>Age</th>\n",
       "      <th>Occupation</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>William Gosset</td>\n",
       "      <td>1876-06-13</td>\n",
       "      <td>1937-10-16</td>\n",
       "      <td>61</td>\n",
       "      <td>Statistician</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Florence Nightingale</td>\n",
       "      <td>1820-05-12</td>\n",
       "      <td>1910-08-13</td>\n",
       "      <td>90</td>\n",
       "      <td>Nurse</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Marie Curie</td>\n",
       "      <td>1867-11-07</td>\n",
       "      <td>1934-07-04</td>\n",
       "      <td>66</td>\n",
       "      <td>Chemist</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Johann Gauss</td>\n",
       "      <td>1777-04-30</td>\n",
       "      <td>1855-02-23</td>\n",
       "      <td>77</td>\n",
       "      <td>Mathematician</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   Name        Born        Died  Age     Occupation\n",
       "1        William Gosset  1876-06-13  1937-10-16   61   Statistician\n",
       "2  Florence Nightingale  1820-05-12  1910-08-13   90          Nurse\n",
       "3           Marie Curie  1867-11-07  1934-07-04   66        Chemist\n",
       "7          Johann Gauss  1777-04-30  1855-02-23   77  Mathematician"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sc[sc[\"Age\"]>sc[\"Age\"].mean()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "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>Born</th>\n",
       "      <th>Died</th>\n",
       "      <th>Age</th>\n",
       "      <th>Occupation</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Rosaline Franklin</td>\n",
       "      <td>1920-07-25</td>\n",
       "      <td>1958-04-16</td>\n",
       "      <td>37</td>\n",
       "      <td>Chemist</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>William Gosset</td>\n",
       "      <td>1876-06-13</td>\n",
       "      <td>1937-10-16</td>\n",
       "      <td>61</td>\n",
       "      <td>Statistician</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Florence Nightingale</td>\n",
       "      <td>1820-05-12</td>\n",
       "      <td>1910-08-13</td>\n",
       "      <td>90</td>\n",
       "      <td>Nurse</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Marie Curie</td>\n",
       "      <td>1867-11-07</td>\n",
       "      <td>1934-07-04</td>\n",
       "      <td>66</td>\n",
       "      <td>Chemist</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   Name        Born        Died  Age    Occupation\n",
       "0     Rosaline Franklin  1920-07-25  1958-04-16   37       Chemist\n",
       "1        William Gosset  1876-06-13  1937-10-16   61  Statistician\n",
       "2  Florence Nightingale  1820-05-12  1910-08-13   90         Nurse\n",
       "3           Marie Curie  1867-11-07  1934-07-04   66       Chemist"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sc[:4]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "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>Born</th>\n",
       "      <th>Died</th>\n",
       "      <th>Age</th>\n",
       "      <th>Occupation</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Rachel Carson</td>\n",
       "      <td>1907-05-27</td>\n",
       "      <td>1964-04-14</td>\n",
       "      <td>56</td>\n",
       "      <td>Biologist</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>John Snow</td>\n",
       "      <td>1813-03-15</td>\n",
       "      <td>1858-06-16</td>\n",
       "      <td>45</td>\n",
       "      <td>Physician</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Alan Turing</td>\n",
       "      <td>1912-06-23</td>\n",
       "      <td>1954-06-07</td>\n",
       "      <td>41</td>\n",
       "      <td>Computer Scientist</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Johann Gauss</td>\n",
       "      <td>1777-04-30</td>\n",
       "      <td>1855-02-23</td>\n",
       "      <td>77</td>\n",
       "      <td>Mathematician</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            Name        Born        Died  Age          Occupation\n",
       "4  Rachel Carson  1907-05-27  1964-04-14   56           Biologist\n",
       "5      John Snow  1813-03-15  1858-06-16   45           Physician\n",
       "6    Alan Turing  1912-06-23  1954-06-07   41  Computer Scientist\n",
       "7   Johann Gauss  1777-04-30  1855-02-23   77       Mathematician"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sc[4:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "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>Born</th>\n",
       "      <th>Died</th>\n",
       "      <th>Age</th>\n",
       "      <th>Occupation</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Rosaline FranklinRosaline Franklin</td>\n",
       "      <td>1920-07-251920-07-25</td>\n",
       "      <td>1958-04-161958-04-16</td>\n",
       "      <td>74</td>\n",
       "      <td>ChemistChemist</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>William GossetWilliam Gosset</td>\n",
       "      <td>1876-06-131876-06-13</td>\n",
       "      <td>1937-10-161937-10-16</td>\n",
       "      <td>122</td>\n",
       "      <td>StatisticianStatistician</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Florence NightingaleFlorence Nightingale</td>\n",
       "      <td>1820-05-121820-05-12</td>\n",
       "      <td>1910-08-131910-08-13</td>\n",
       "      <td>180</td>\n",
       "      <td>NurseNurse</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Marie CurieMarie Curie</td>\n",
       "      <td>1867-11-071867-11-07</td>\n",
       "      <td>1934-07-041934-07-04</td>\n",
       "      <td>132</td>\n",
       "      <td>ChemistChemist</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Rachel CarsonRachel Carson</td>\n",
       "      <td>1907-05-271907-05-27</td>\n",
       "      <td>1964-04-141964-04-14</td>\n",
       "      <td>112</td>\n",
       "      <td>BiologistBiologist</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>John SnowJohn Snow</td>\n",
       "      <td>1813-03-151813-03-15</td>\n",
       "      <td>1858-06-161858-06-16</td>\n",
       "      <td>90</td>\n",
       "      <td>PhysicianPhysician</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Alan TuringAlan Turing</td>\n",
       "      <td>1912-06-231912-06-23</td>\n",
       "      <td>1954-06-071954-06-07</td>\n",
       "      <td>82</td>\n",
       "      <td>Computer ScientistComputer Scientist</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Johann GaussJohann Gauss</td>\n",
       "      <td>1777-04-301777-04-30</td>\n",
       "      <td>1855-02-231855-02-23</td>\n",
       "      <td>154</td>\n",
       "      <td>MathematicianMathematician</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                       Name                  Born  \\\n",
       "0        Rosaline FranklinRosaline Franklin  1920-07-251920-07-25   \n",
       "1              William GossetWilliam Gosset  1876-06-131876-06-13   \n",
       "2  Florence NightingaleFlorence Nightingale  1820-05-121820-05-12   \n",
       "3                    Marie CurieMarie Curie  1867-11-071867-11-07   \n",
       "4                Rachel CarsonRachel Carson  1907-05-271907-05-27   \n",
       "5                        John SnowJohn Snow  1813-03-151813-03-15   \n",
       "6                    Alan TuringAlan Turing  1912-06-231912-06-23   \n",
       "7                  Johann GaussJohann Gauss  1777-04-301777-04-30   \n",
       "\n",
       "                   Died  Age                            Occupation  \n",
       "0  1958-04-161958-04-16   74                        ChemistChemist  \n",
       "1  1937-10-161937-10-16  122              StatisticianStatistician  \n",
       "2  1910-08-131910-08-13  180                            NurseNurse  \n",
       "3  1934-07-041934-07-04  132                        ChemistChemist  \n",
       "4  1964-04-141964-04-14  112                    BiologistBiologist  \n",
       "5  1858-06-161858-06-16   90                    PhysicianPhysician  \n",
       "6  1954-06-071954-06-07   82  Computer ScientistComputer Scientist  \n",
       "7  1855-02-231855-02-23  154            MathematicianMathematician  "
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sc*2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0   1920-07-25\n",
       "1   1876-06-13\n",
       "2   1820-05-12\n",
       "3   1867-11-07\n",
       "4   1907-05-27\n",
       "5   1813-03-15\n",
       "6   1912-06-23\n",
       "7   1777-04-30\n",
       "Name: Born, dtype: datetime64[ns]"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.to_datetime(sc['Born'], format = '%Y-%m-%d')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [],
   "source": [
    "sc['born_dt'],sc['died_dt'] = (pd.to_datetime(sc['Born'], format = '%Y-%m-%d'), pd.to_datetime(sc['Died'], format = '%Y-%m-%d'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "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>Born</th>\n",
       "      <th>Died</th>\n",
       "      <th>Age</th>\n",
       "      <th>Occupation</th>\n",
       "      <th>born_dt</th>\n",
       "      <th>died_dt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Rosaline Franklin</td>\n",
       "      <td>1920-07-25</td>\n",
       "      <td>1958-04-16</td>\n",
       "      <td>37</td>\n",
       "      <td>Chemist</td>\n",
       "      <td>1920-07-25</td>\n",
       "      <td>1958-04-16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>William Gosset</td>\n",
       "      <td>1876-06-13</td>\n",
       "      <td>1937-10-16</td>\n",
       "      <td>61</td>\n",
       "      <td>Statistician</td>\n",
       "      <td>1876-06-13</td>\n",
       "      <td>1937-10-16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Florence Nightingale</td>\n",
       "      <td>1820-05-12</td>\n",
       "      <td>1910-08-13</td>\n",
       "      <td>90</td>\n",
       "      <td>Nurse</td>\n",
       "      <td>1820-05-12</td>\n",
       "      <td>1910-08-13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Marie Curie</td>\n",
       "      <td>1867-11-07</td>\n",
       "      <td>1934-07-04</td>\n",
       "      <td>66</td>\n",
       "      <td>Chemist</td>\n",
       "      <td>1867-11-07</td>\n",
       "      <td>1934-07-04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Rachel Carson</td>\n",
       "      <td>1907-05-27</td>\n",
       "      <td>1964-04-14</td>\n",
       "      <td>56</td>\n",
       "      <td>Biologist</td>\n",
       "      <td>1907-05-27</td>\n",
       "      <td>1964-04-14</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   Name        Born        Died  Age    Occupation    born_dt  \\\n",
       "0     Rosaline Franklin  1920-07-25  1958-04-16   37       Chemist 1920-07-25   \n",
       "1        William Gosset  1876-06-13  1937-10-16   61  Statistician 1876-06-13   \n",
       "2  Florence Nightingale  1820-05-12  1910-08-13   90         Nurse 1820-05-12   \n",
       "3           Marie Curie  1867-11-07  1934-07-04   66       Chemist 1867-11-07   \n",
       "4         Rachel Carson  1907-05-27  1964-04-14   56     Biologist 1907-05-27   \n",
       "\n",
       "     died_dt  \n",
       "0 1958-04-16  \n",
       "1 1937-10-16  \n",
       "2 1910-08-13  \n",
       "3 1934-07-04  \n",
       "4 1964-04-14  "
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sc.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/lib/python3.5/random.py:272: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
      "  x[i], x[j] = x[j], x[i]\n"
     ]
    }
   ],
   "source": [
    "import random\n",
    "random.seed(42)\n",
    "random.shuffle(sc[\"Age\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "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>Born</th>\n",
       "      <th>Died</th>\n",
       "      <th>Age</th>\n",
       "      <th>Occupation</th>\n",
       "      <th>born_dt</th>\n",
       "      <th>died_dt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Rosaline Franklin</td>\n",
       "      <td>1920-07-25</td>\n",
       "      <td>1958-04-16</td>\n",
       "      <td>66</td>\n",
       "      <td>Chemist</td>\n",
       "      <td>1920-07-25</td>\n",
       "      <td>1958-04-16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>William Gosset</td>\n",
       "      <td>1876-06-13</td>\n",
       "      <td>1937-10-16</td>\n",
       "      <td>56</td>\n",
       "      <td>Statistician</td>\n",
       "      <td>1876-06-13</td>\n",
       "      <td>1937-10-16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Florence Nightingale</td>\n",
       "      <td>1820-05-12</td>\n",
       "      <td>1910-08-13</td>\n",
       "      <td>41</td>\n",
       "      <td>Nurse</td>\n",
       "      <td>1820-05-12</td>\n",
       "      <td>1910-08-13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Marie Curie</td>\n",
       "      <td>1867-11-07</td>\n",
       "      <td>1934-07-04</td>\n",
       "      <td>77</td>\n",
       "      <td>Chemist</td>\n",
       "      <td>1867-11-07</td>\n",
       "      <td>1934-07-04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Rachel Carson</td>\n",
       "      <td>1907-05-27</td>\n",
       "      <td>1964-04-14</td>\n",
       "      <td>90</td>\n",
       "      <td>Biologist</td>\n",
       "      <td>1907-05-27</td>\n",
       "      <td>1964-04-14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>John Snow</td>\n",
       "      <td>1813-03-15</td>\n",
       "      <td>1858-06-16</td>\n",
       "      <td>45</td>\n",
       "      <td>Physician</td>\n",
       "      <td>1813-03-15</td>\n",
       "      <td>1858-06-16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Alan Turing</td>\n",
       "      <td>1912-06-23</td>\n",
       "      <td>1954-06-07</td>\n",
       "      <td>37</td>\n",
       "      <td>Computer Scientist</td>\n",
       "      <td>1912-06-23</td>\n",
       "      <td>1954-06-07</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Johann Gauss</td>\n",
       "      <td>1777-04-30</td>\n",
       "      <td>1855-02-23</td>\n",
       "      <td>61</td>\n",
       "      <td>Mathematician</td>\n",
       "      <td>1777-04-30</td>\n",
       "      <td>1855-02-23</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   Name        Born        Died  Age          Occupation  \\\n",
       "0     Rosaline Franklin  1920-07-25  1958-04-16   66             Chemist   \n",
       "1        William Gosset  1876-06-13  1937-10-16   56        Statistician   \n",
       "2  Florence Nightingale  1820-05-12  1910-08-13   41               Nurse   \n",
       "3           Marie Curie  1867-11-07  1934-07-04   77             Chemist   \n",
       "4         Rachel Carson  1907-05-27  1964-04-14   90           Biologist   \n",
       "5             John Snow  1813-03-15  1858-06-16   45           Physician   \n",
       "6           Alan Turing  1912-06-23  1954-06-07   37  Computer Scientist   \n",
       "7          Johann Gauss  1777-04-30  1855-02-23   61       Mathematician   \n",
       "\n",
       "     born_dt    died_dt  \n",
       "0 1920-07-25 1958-04-16  \n",
       "1 1876-06-13 1937-10-16  \n",
       "2 1820-05-12 1910-08-13  \n",
       "3 1867-11-07 1934-07-04  \n",
       "4 1907-05-27 1964-04-14  \n",
       "5 1813-03-15 1858-06-16  \n",
       "6 1912-06-23 1954-06-07  \n",
       "7 1777-04-30 1855-02-23  "
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "sc[\"Age\"] = sc['Age'].sample(len(sc[\"Age\"]), random_state=24).reset_index(drop=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "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>Born</th>\n",
       "      <th>Died</th>\n",
       "      <th>Age</th>\n",
       "      <th>Occupation</th>\n",
       "      <th>born_dt</th>\n",
       "      <th>died_dt</th>\n",
       "      <th>age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Rosaline Franklin</td>\n",
       "      <td>1920-07-25</td>\n",
       "      <td>1958-04-16</td>\n",
       "      <td>61</td>\n",
       "      <td>Chemist</td>\n",
       "      <td>1920-07-25</td>\n",
       "      <td>1958-04-16</td>\n",
       "      <td>61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>William Gosset</td>\n",
       "      <td>1876-06-13</td>\n",
       "      <td>1937-10-16</td>\n",
       "      <td>45</td>\n",
       "      <td>Statistician</td>\n",
       "      <td>1876-06-13</td>\n",
       "      <td>1937-10-16</td>\n",
       "      <td>45</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Florence Nightingale</td>\n",
       "      <td>1820-05-12</td>\n",
       "      <td>1910-08-13</td>\n",
       "      <td>37</td>\n",
       "      <td>Nurse</td>\n",
       "      <td>1820-05-12</td>\n",
       "      <td>1910-08-13</td>\n",
       "      <td>37</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Marie Curie</td>\n",
       "      <td>1867-11-07</td>\n",
       "      <td>1934-07-04</td>\n",
       "      <td>90</td>\n",
       "      <td>Chemist</td>\n",
       "      <td>1867-11-07</td>\n",
       "      <td>1934-07-04</td>\n",
       "      <td>90</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Rachel Carson</td>\n",
       "      <td>1907-05-27</td>\n",
       "      <td>1964-04-14</td>\n",
       "      <td>56</td>\n",
       "      <td>Biologist</td>\n",
       "      <td>1907-05-27</td>\n",
       "      <td>1964-04-14</td>\n",
       "      <td>56</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>John Snow</td>\n",
       "      <td>1813-03-15</td>\n",
       "      <td>1858-06-16</td>\n",
       "      <td>66</td>\n",
       "      <td>Physician</td>\n",
       "      <td>1813-03-15</td>\n",
       "      <td>1858-06-16</td>\n",
       "      <td>66</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Alan Turing</td>\n",
       "      <td>1912-06-23</td>\n",
       "      <td>1954-06-07</td>\n",
       "      <td>77</td>\n",
       "      <td>Computer Scientist</td>\n",
       "      <td>1912-06-23</td>\n",
       "      <td>1954-06-07</td>\n",
       "      <td>77</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Johann Gauss</td>\n",
       "      <td>1777-04-30</td>\n",
       "      <td>1855-02-23</td>\n",
       "      <td>41</td>\n",
       "      <td>Mathematician</td>\n",
       "      <td>1777-04-30</td>\n",
       "      <td>1855-02-23</td>\n",
       "      <td>41</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   Name        Born        Died  Age          Occupation  \\\n",
       "0     Rosaline Franklin  1920-07-25  1958-04-16   61             Chemist   \n",
       "1        William Gosset  1876-06-13  1937-10-16   45        Statistician   \n",
       "2  Florence Nightingale  1820-05-12  1910-08-13   37               Nurse   \n",
       "3           Marie Curie  1867-11-07  1934-07-04   90             Chemist   \n",
       "4         Rachel Carson  1907-05-27  1964-04-14   56           Biologist   \n",
       "5             John Snow  1813-03-15  1858-06-16   66           Physician   \n",
       "6           Alan Turing  1912-06-23  1954-06-07   77  Computer Scientist   \n",
       "7          Johann Gauss  1777-04-30  1855-02-23   41       Mathematician   \n",
       "\n",
       "     born_dt    died_dt  age  \n",
       "0 1920-07-25 1958-04-16   61  \n",
       "1 1876-06-13 1937-10-16   45  \n",
       "2 1820-05-12 1910-08-13   37  \n",
       "3 1867-11-07 1934-07-04   90  \n",
       "4 1907-05-27 1964-04-14   56  \n",
       "5 1813-03-15 1858-06-16   66  \n",
       "6 1912-06-23 1954-06-07   77  \n",
       "7 1777-04-30 1855-02-23   41  "
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "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>Born</th>\n",
       "      <th>Died</th>\n",
       "      <th>Age</th>\n",
       "      <th>Occupation</th>\n",
       "      <th>born_dt</th>\n",
       "      <th>died_dt</th>\n",
       "      <th>age</th>\n",
       "      <th>age_days_dt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Rosaline Franklin</td>\n",
       "      <td>1920-07-25</td>\n",
       "      <td>1958-04-16</td>\n",
       "      <td>61</td>\n",
       "      <td>Chemist</td>\n",
       "      <td>1920-07-25</td>\n",
       "      <td>1958-04-16</td>\n",
       "      <td>61</td>\n",
       "      <td>13779 days</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>William Gosset</td>\n",
       "      <td>1876-06-13</td>\n",
       "      <td>1937-10-16</td>\n",
       "      <td>45</td>\n",
       "      <td>Statistician</td>\n",
       "      <td>1876-06-13</td>\n",
       "      <td>1937-10-16</td>\n",
       "      <td>45</td>\n",
       "      <td>22404 days</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Florence Nightingale</td>\n",
       "      <td>1820-05-12</td>\n",
       "      <td>1910-08-13</td>\n",
       "      <td>37</td>\n",
       "      <td>Nurse</td>\n",
       "      <td>1820-05-12</td>\n",
       "      <td>1910-08-13</td>\n",
       "      <td>37</td>\n",
       "      <td>32964 days</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Marie Curie</td>\n",
       "      <td>1867-11-07</td>\n",
       "      <td>1934-07-04</td>\n",
       "      <td>90</td>\n",
       "      <td>Chemist</td>\n",
       "      <td>1867-11-07</td>\n",
       "      <td>1934-07-04</td>\n",
       "      <td>90</td>\n",
       "      <td>24345 days</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Rachel Carson</td>\n",
       "      <td>1907-05-27</td>\n",
       "      <td>1964-04-14</td>\n",
       "      <td>56</td>\n",
       "      <td>Biologist</td>\n",
       "      <td>1907-05-27</td>\n",
       "      <td>1964-04-14</td>\n",
       "      <td>56</td>\n",
       "      <td>20777 days</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>John Snow</td>\n",
       "      <td>1813-03-15</td>\n",
       "      <td>1858-06-16</td>\n",
       "      <td>66</td>\n",
       "      <td>Physician</td>\n",
       "      <td>1813-03-15</td>\n",
       "      <td>1858-06-16</td>\n",
       "      <td>66</td>\n",
       "      <td>16529 days</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Alan Turing</td>\n",
       "      <td>1912-06-23</td>\n",
       "      <td>1954-06-07</td>\n",
       "      <td>77</td>\n",
       "      <td>Computer Scientist</td>\n",
       "      <td>1912-06-23</td>\n",
       "      <td>1954-06-07</td>\n",
       "      <td>77</td>\n",
       "      <td>15324 days</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Johann Gauss</td>\n",
       "      <td>1777-04-30</td>\n",
       "      <td>1855-02-23</td>\n",
       "      <td>41</td>\n",
       "      <td>Mathematician</td>\n",
       "      <td>1777-04-30</td>\n",
       "      <td>1855-02-23</td>\n",
       "      <td>41</td>\n",
       "      <td>28422 days</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   Name        Born        Died  Age          Occupation  \\\n",
       "0     Rosaline Franklin  1920-07-25  1958-04-16   61             Chemist   \n",
       "1        William Gosset  1876-06-13  1937-10-16   45        Statistician   \n",
       "2  Florence Nightingale  1820-05-12  1910-08-13   37               Nurse   \n",
       "3           Marie Curie  1867-11-07  1934-07-04   90             Chemist   \n",
       "4         Rachel Carson  1907-05-27  1964-04-14   56           Biologist   \n",
       "5             John Snow  1813-03-15  1858-06-16   66           Physician   \n",
       "6           Alan Turing  1912-06-23  1954-06-07   77  Computer Scientist   \n",
       "7          Johann Gauss  1777-04-30  1855-02-23   41       Mathematician   \n",
       "\n",
       "     born_dt    died_dt  age age_days_dt  \n",
       "0 1920-07-25 1958-04-16   61  13779 days  \n",
       "1 1876-06-13 1937-10-16   45  22404 days  \n",
       "2 1820-05-12 1910-08-13   37  32964 days  \n",
       "3 1867-11-07 1934-07-04   90  24345 days  \n",
       "4 1907-05-27 1964-04-14   56  20777 days  \n",
       "5 1813-03-15 1858-06-16   66  16529 days  \n",
       "6 1912-06-23 1954-06-07   77  15324 days  \n",
       "7 1777-04-30 1855-02-23   41  28422 days  "
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sc['age_days_dt'] = (sc['died_dt'] - sc['born_dt'])\n",
    "sc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "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>Born</th>\n",
       "      <th>Died</th>\n",
       "      <th>Age</th>\n",
       "      <th>Occupation</th>\n",
       "      <th>born_dt</th>\n",
       "      <th>died_dt</th>\n",
       "      <th>age</th>\n",
       "      <th>age_days_dt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Rosaline Franklin</td>\n",
       "      <td>1920-07-25</td>\n",
       "      <td>1958-04-16</td>\n",
       "      <td>61</td>\n",
       "      <td>Chemist</td>\n",
       "      <td>1920-07-25</td>\n",
       "      <td>1958-04-16</td>\n",
       "      <td>61</td>\n",
       "      <td>37.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>William Gosset</td>\n",
       "      <td>1876-06-13</td>\n",
       "      <td>1937-10-16</td>\n",
       "      <td>45</td>\n",
       "      <td>Statistician</td>\n",
       "      <td>1876-06-13</td>\n",
       "      <td>1937-10-16</td>\n",
       "      <td>45</td>\n",
       "      <td>61.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Florence Nightingale</td>\n",
       "      <td>1820-05-12</td>\n",
       "      <td>1910-08-13</td>\n",
       "      <td>37</td>\n",
       "      <td>Nurse</td>\n",
       "      <td>1820-05-12</td>\n",
       "      <td>1910-08-13</td>\n",
       "      <td>37</td>\n",
       "      <td>90.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Marie Curie</td>\n",
       "      <td>1867-11-07</td>\n",
       "      <td>1934-07-04</td>\n",
       "      <td>90</td>\n",
       "      <td>Chemist</td>\n",
       "      <td>1867-11-07</td>\n",
       "      <td>1934-07-04</td>\n",
       "      <td>90</td>\n",
       "      <td>66.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Rachel Carson</td>\n",
       "      <td>1907-05-27</td>\n",
       "      <td>1964-04-14</td>\n",
       "      <td>56</td>\n",
       "      <td>Biologist</td>\n",
       "      <td>1907-05-27</td>\n",
       "      <td>1964-04-14</td>\n",
       "      <td>56</td>\n",
       "      <td>56.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>John Snow</td>\n",
       "      <td>1813-03-15</td>\n",
       "      <td>1858-06-16</td>\n",
       "      <td>66</td>\n",
       "      <td>Physician</td>\n",
       "      <td>1813-03-15</td>\n",
       "      <td>1858-06-16</td>\n",
       "      <td>66</td>\n",
       "      <td>45.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Alan Turing</td>\n",
       "      <td>1912-06-23</td>\n",
       "      <td>1954-06-07</td>\n",
       "      <td>77</td>\n",
       "      <td>Computer Scientist</td>\n",
       "      <td>1912-06-23</td>\n",
       "      <td>1954-06-07</td>\n",
       "      <td>77</td>\n",
       "      <td>41.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Johann Gauss</td>\n",
       "      <td>1777-04-30</td>\n",
       "      <td>1855-02-23</td>\n",
       "      <td>41</td>\n",
       "      <td>Mathematician</td>\n",
       "      <td>1777-04-30</td>\n",
       "      <td>1855-02-23</td>\n",
       "      <td>41</td>\n",
       "      <td>77.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   Name        Born        Died  Age          Occupation  \\\n",
       "0     Rosaline Franklin  1920-07-25  1958-04-16   61             Chemist   \n",
       "1        William Gosset  1876-06-13  1937-10-16   45        Statistician   \n",
       "2  Florence Nightingale  1820-05-12  1910-08-13   37               Nurse   \n",
       "3           Marie Curie  1867-11-07  1934-07-04   90             Chemist   \n",
       "4         Rachel Carson  1907-05-27  1964-04-14   56           Biologist   \n",
       "5             John Snow  1813-03-15  1858-06-16   66           Physician   \n",
       "6           Alan Turing  1912-06-23  1954-06-07   77  Computer Scientist   \n",
       "7          Johann Gauss  1777-04-30  1855-02-23   41       Mathematician   \n",
       "\n",
       "     born_dt    died_dt  age  age_days_dt  \n",
       "0 1920-07-25 1958-04-16   61         37.0  \n",
       "1 1876-06-13 1937-10-16   45         61.0  \n",
       "2 1820-05-12 1910-08-13   37         90.0  \n",
       "3 1867-11-07 1934-07-04   90         66.0  \n",
       "4 1907-05-27 1964-04-14   56         56.0  \n",
       "5 1813-03-15 1858-06-16   66         45.0  \n",
       "6 1912-06-23 1954-06-07   77         41.0  \n",
       "7 1777-04-30 1855-02-23   41         77.0  "
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sc['age_days_dt'] = sc['age_days_dt'].astype('timedelta64[Y]')\n",
    "sc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "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>Born</th>\n",
       "      <th>Died</th>\n",
       "      <th>Age</th>\n",
       "      <th>Occupation</th>\n",
       "      <th>born_dt</th>\n",
       "      <th>died_dt</th>\n",
       "      <th>age_days_dt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Rosaline Franklin</td>\n",
       "      <td>1920-07-25</td>\n",
       "      <td>1958-04-16</td>\n",
       "      <td>61</td>\n",
       "      <td>Chemist</td>\n",
       "      <td>1920-07-25</td>\n",
       "      <td>1958-04-16</td>\n",
       "      <td>37.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>William Gosset</td>\n",
       "      <td>1876-06-13</td>\n",
       "      <td>1937-10-16</td>\n",
       "      <td>45</td>\n",
       "      <td>Statistician</td>\n",
       "      <td>1876-06-13</td>\n",
       "      <td>1937-10-16</td>\n",
       "      <td>61.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Florence Nightingale</td>\n",
       "      <td>1820-05-12</td>\n",
       "      <td>1910-08-13</td>\n",
       "      <td>37</td>\n",
       "      <td>Nurse</td>\n",
       "      <td>1820-05-12</td>\n",
       "      <td>1910-08-13</td>\n",
       "      <td>90.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Marie Curie</td>\n",
       "      <td>1867-11-07</td>\n",
       "      <td>1934-07-04</td>\n",
       "      <td>90</td>\n",
       "      <td>Chemist</td>\n",
       "      <td>1867-11-07</td>\n",
       "      <td>1934-07-04</td>\n",
       "      <td>66.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Rachel Carson</td>\n",
       "      <td>1907-05-27</td>\n",
       "      <td>1964-04-14</td>\n",
       "      <td>56</td>\n",
       "      <td>Biologist</td>\n",
       "      <td>1907-05-27</td>\n",
       "      <td>1964-04-14</td>\n",
       "      <td>56.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>John Snow</td>\n",
       "      <td>1813-03-15</td>\n",
       "      <td>1858-06-16</td>\n",
       "      <td>66</td>\n",
       "      <td>Physician</td>\n",
       "      <td>1813-03-15</td>\n",
       "      <td>1858-06-16</td>\n",
       "      <td>45.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Alan Turing</td>\n",
       "      <td>1912-06-23</td>\n",
       "      <td>1954-06-07</td>\n",
       "      <td>77</td>\n",
       "      <td>Computer Scientist</td>\n",
       "      <td>1912-06-23</td>\n",
       "      <td>1954-06-07</td>\n",
       "      <td>41.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Johann Gauss</td>\n",
       "      <td>1777-04-30</td>\n",
       "      <td>1855-02-23</td>\n",
       "      <td>41</td>\n",
       "      <td>Mathematician</td>\n",
       "      <td>1777-04-30</td>\n",
       "      <td>1855-02-23</td>\n",
       "      <td>77.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   Name        Born        Died  Age          Occupation  \\\n",
       "0     Rosaline Franklin  1920-07-25  1958-04-16   61             Chemist   \n",
       "1        William Gosset  1876-06-13  1937-10-16   45        Statistician   \n",
       "2  Florence Nightingale  1820-05-12  1910-08-13   37               Nurse   \n",
       "3           Marie Curie  1867-11-07  1934-07-04   90             Chemist   \n",
       "4         Rachel Carson  1907-05-27  1964-04-14   56           Biologist   \n",
       "5             John Snow  1813-03-15  1858-06-16   66           Physician   \n",
       "6           Alan Turing  1912-06-23  1954-06-07   77  Computer Scientist   \n",
       "7          Johann Gauss  1777-04-30  1855-02-23   41       Mathematician   \n",
       "\n",
       "     born_dt    died_dt  age_days_dt  \n",
       "0 1920-07-25 1958-04-16         37.0  \n",
       "1 1876-06-13 1937-10-16         61.0  \n",
       "2 1820-05-12 1910-08-13         90.0  \n",
       "3 1867-11-07 1934-07-04         66.0  \n",
       "4 1907-05-27 1964-04-14         56.0  \n",
       "5 1813-03-15 1858-06-16         45.0  \n",
       "6 1912-06-23 1954-06-07         41.0  \n",
       "7 1777-04-30 1855-02-23         77.0  "
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sc.drop(['age'], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 保存Series 二进制\n",
    "sc['Name'].to_pickle('../sc_names_series.pickle') "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 保存DataFrame 二进制\n",
    "sc.to_pickle('../sc_names_dt.pickle') "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "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>Born</th>\n",
       "      <th>Died</th>\n",
       "      <th>Age</th>\n",
       "      <th>Occupation</th>\n",
       "      <th>born_dt</th>\n",
       "      <th>died_dt</th>\n",
       "      <th>age</th>\n",
       "      <th>age_days_dt</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Rosaline Franklin</td>\n",
       "      <td>1920-07-25</td>\n",
       "      <td>1958-04-16</td>\n",
       "      <td>61</td>\n",
       "      <td>Chemist</td>\n",
       "      <td>1920-07-25</td>\n",
       "      <td>1958-04-16</td>\n",
       "      <td>61</td>\n",
       "      <td>37.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>William Gosset</td>\n",
       "      <td>1876-06-13</td>\n",
       "      <td>1937-10-16</td>\n",
       "      <td>45</td>\n",
       "      <td>Statistician</td>\n",
       "      <td>1876-06-13</td>\n",
       "      <td>1937-10-16</td>\n",
       "      <td>45</td>\n",
       "      <td>61.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Florence Nightingale</td>\n",
       "      <td>1820-05-12</td>\n",
       "      <td>1910-08-13</td>\n",
       "      <td>37</td>\n",
       "      <td>Nurse</td>\n",
       "      <td>1820-05-12</td>\n",
       "      <td>1910-08-13</td>\n",
       "      <td>37</td>\n",
       "      <td>90.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Marie Curie</td>\n",
       "      <td>1867-11-07</td>\n",
       "      <td>1934-07-04</td>\n",
       "      <td>90</td>\n",
       "      <td>Chemist</td>\n",
       "      <td>1867-11-07</td>\n",
       "      <td>1934-07-04</td>\n",
       "      <td>90</td>\n",
       "      <td>66.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Rachel Carson</td>\n",
       "      <td>1907-05-27</td>\n",
       "      <td>1964-04-14</td>\n",
       "      <td>56</td>\n",
       "      <td>Biologist</td>\n",
       "      <td>1907-05-27</td>\n",
       "      <td>1964-04-14</td>\n",
       "      <td>56</td>\n",
       "      <td>56.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>John Snow</td>\n",
       "      <td>1813-03-15</td>\n",
       "      <td>1858-06-16</td>\n",
       "      <td>66</td>\n",
       "      <td>Physician</td>\n",
       "      <td>1813-03-15</td>\n",
       "      <td>1858-06-16</td>\n",
       "      <td>66</td>\n",
       "      <td>45.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Alan Turing</td>\n",
       "      <td>1912-06-23</td>\n",
       "      <td>1954-06-07</td>\n",
       "      <td>77</td>\n",
       "      <td>Computer Scientist</td>\n",
       "      <td>1912-06-23</td>\n",
       "      <td>1954-06-07</td>\n",
       "      <td>77</td>\n",
       "      <td>41.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Johann Gauss</td>\n",
       "      <td>1777-04-30</td>\n",
       "      <td>1855-02-23</td>\n",
       "      <td>41</td>\n",
       "      <td>Mathematician</td>\n",
       "      <td>1777-04-30</td>\n",
       "      <td>1855-02-23</td>\n",
       "      <td>41</td>\n",
       "      <td>77.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                   Name        Born        Died  Age          Occupation  \\\n",
       "0     Rosaline Franklin  1920-07-25  1958-04-16   61             Chemist   \n",
       "1        William Gosset  1876-06-13  1937-10-16   45        Statistician   \n",
       "2  Florence Nightingale  1820-05-12  1910-08-13   37               Nurse   \n",
       "3           Marie Curie  1867-11-07  1934-07-04   90             Chemist   \n",
       "4         Rachel Carson  1907-05-27  1964-04-14   56           Biologist   \n",
       "5             John Snow  1813-03-15  1858-06-16   66           Physician   \n",
       "6           Alan Turing  1912-06-23  1954-06-07   77  Computer Scientist   \n",
       "7          Johann Gauss  1777-04-30  1855-02-23   41       Mathematician   \n",
       "\n",
       "     born_dt    died_dt  age  age_days_dt  \n",
       "0 1920-07-25 1958-04-16   61         37.0  \n",
       "1 1876-06-13 1937-10-16   45         61.0  \n",
       "2 1820-05-12 1910-08-13   37         90.0  \n",
       "3 1867-11-07 1934-07-04   90         66.0  \n",
       "4 1907-05-27 1964-04-14   56         56.0  \n",
       "5 1813-03-15 1858-06-16   66         45.0  \n",
       "6 1912-06-23 1954-06-07   77         41.0  \n",
       "7 1777-04-30 1855-02-23   41         77.0  "
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.read_pickle('../sc_names_dt.pickle')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [],
   "source": [
    "# CSV\n",
    "sc.to_csv('../sc_df.tsv', sep='\\t', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[33mDEPRECATION: Python 3.5 reached the end of its life on September 13th, 2020. Please upgrade your Python as Python 3.5 is no longer maintained. pip 21.0 will drop support for Python 3.5 in January 2021. pip 21.0 will remove support for this functionality.\u001b[0m\n",
      "Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple\n",
      "Collecting openpyxl\n",
      "  Downloading https://pypi.tuna.tsinghua.edu.cn/packages/d6/26/eb28e975b7a37aad38d7ec4f7a0f652bdee6ecf36e6bd06f473c5af9b87b/openpyxl-2.6.4.tar.gz (173 kB)\n",
      "\u001b[K     |████████████████████████████████| 173 kB 235 kB/s eta 0:00:01\n",
      "\u001b[?25hCollecting jdcal\n",
      "  Downloading https://pypi.tuna.tsinghua.edu.cn/packages/f0/da/572cbc0bc582390480bbd7c4e93d14dc46079778ed915b505dc494b37c57/jdcal-1.4.1-py2.py3-none-any.whl (9.5 kB)\n",
      "Collecting et_xmlfile\n",
      "  Downloading https://pypi.tuna.tsinghua.edu.cn/packages/22/28/a99c42aea746e18382ad9fb36f64c1c1f04216f41797f2f0fa567da11388/et_xmlfile-1.0.1.tar.gz (8.4 kB)\n",
      "Building wheels for collected packages: et-xmlfile, openpyxl\n",
      "  Building wheel for et-xmlfile (setup.py) ... \u001b[?25ldone\n",
      "\u001b[?25h  Created wheel for et-xmlfile: filename=et_xmlfile-1.0.1-py3-none-any.whl size=8915 sha256=340b49429c4cfeee6c43d1980d5bf8343f34db68a387cb4be88249e63bcf206a\n",
      "  Stored in directory: /home/zjd/.cache/pip/wheels/1d/87/75/719778cb32c1db76fbce9c683a159fa2a8e6aa02405227c42d\n",
      "  Building wheel for openpyxl (setup.py) ... \u001b[?25ldone\n",
      "\u001b[?25h  Created wheel for openpyxl: filename=openpyxl-2.6.4-py2.py3-none-any.whl size=245679 sha256=645265870277f66305ef7e84cc697a362d495e0d232def958e842304d0535a3f\n",
      "  Stored in directory: /home/zjd/.cache/pip/wheels/54/4a/55/b940db2abb76710cc9a0c1e132039dab46cff7a8c55a6cd8a9\n",
      "Successfully built et-xmlfile openpyxl\n",
      "Installing collected packages: jdcal, et-xmlfile, openpyxl\n",
      "Successfully installed et-xmlfile-1.0.1 jdcal-1.4.1 openpyxl-2.6.4\n"
     ]
    }
   ],
   "source": [
    "!pip install openpyxl"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Excel\n",
    "import openpyxl\n",
    "sc.to_excel('../sc_df.xlsx', sheet_name='sc', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [],
   "source": [
    "# feather格式 传递给R方便\n",
    "# !pip install feather-format\n",
    "#import feather-format\n",
    "sc.to_feather('../sc_df.xl')"
   ]
  },
  {
   "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}

一键复制编辑原始数据按行查看历史

提交于 2022-04-05 08:04 . 提交

马建仓 AI 助手

尝试更多

代码解读

代码找茬

代码优化

Python

https://gitee.com/quantlabor/pandas_for_everyone-master.git

git@gitee.com:quantlabor/pandas_for_everyone-master.git

quantlabor

pandas_for_everyone-master

master

quantlabor/pandas_for_everyone-master

简介

发行版

贡献者

近期动态

quantlabor/pandas_for_everyone-master .gitee-modal { width: 500px !important; }

简介

发行版

贡献者

近期动态

搜索帮助

quantlabor/pandas_for_everyone-master