{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e91239ad",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "5803418b",
   "metadata": {},
   "outputs": [],
   "source": [
    "# rowdata = {\n",
    "#     \"电影名称\": ['功夫熊猫', '叶问3', '伦敦陷落', '代理情人', '新步步惊心', '谍影重重', '功夫熊猫', '美人鱼', '宝贝当家', '唐人街探案'],\n",
    "#     \"搞笑镜头\": [39,3,2,9,8,5,39,21,45,23],\n",
    "#     \"拥抱镜头\": [0,2,3,38,34,2,0,17,2,3],\n",
    "#     \"打斗镜头\": [31,65,55,2,17,57,31,5,9,17],\n",
    "#     \"电影类型\": [\"喜剧片\", \"动作片\", \"动作片\", \"爱情片\", \"爱情片\", \"动作片\", \"喜剧片\", \"喜剧片\", \"喜剧片\"]\n",
    "# }\n",
    "rowdata = {\n",
    "    \"电影名称\": ['功夫熊猫', '叶问3', '伦敦陷落', '代理情人', '新步步惊心', '谍影重重', '功夫熊猫', '美人鱼', '宝贝当家'],\n",
    "    \"搞笑镜头\": [39,3,2,9,8,5,39,21,45],\n",
    "    \"拥抱镜头\": [0,2,3,38,34,2,0,17,2],\n",
    "    \"打斗镜头\": [31,65,55,2,17,57,31,5,9],\n",
    "    \"电影类型\": [\"喜剧片\", \"动作片\", \"动作片\", \"爱情片\", \"爱情片\", \"动作片\", \"喜剧片\", \"喜剧片\", \"喜剧片\"]\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "e1d2a6c4",
   "metadata": {},
   "outputs": [],
   "source": [
    "movie_data = pd.DataFrame(rowdata)\n",
    "# print(movie_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "7e0058cc",
   "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>电影名称</th>\n",
       "      <th>搞笑镜头</th>\n",
       "      <th>拥抱镜头</th>\n",
       "      <th>打斗镜头</th>\n",
       "      <th>电影类型</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>功夫熊猫</td>\n",
       "      <td>39</td>\n",
       "      <td>0</td>\n",
       "      <td>31</td>\n",
       "      <td>喜剧片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>叶问3</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>65</td>\n",
       "      <td>动作片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>伦敦陷落</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>55</td>\n",
       "      <td>动作片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>代理情人</td>\n",
       "      <td>9</td>\n",
       "      <td>38</td>\n",
       "      <td>2</td>\n",
       "      <td>爱情片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>新步步惊心</td>\n",
       "      <td>8</td>\n",
       "      <td>34</td>\n",
       "      <td>17</td>\n",
       "      <td>爱情片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>谍影重重</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>57</td>\n",
       "      <td>动作片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>功夫熊猫</td>\n",
       "      <td>39</td>\n",
       "      <td>0</td>\n",
       "      <td>31</td>\n",
       "      <td>喜剧片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>美人鱼</td>\n",
       "      <td>21</td>\n",
       "      <td>17</td>\n",
       "      <td>5</td>\n",
       "      <td>喜剧片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>宝贝当家</td>\n",
       "      <td>45</td>\n",
       "      <td>2</td>\n",
       "      <td>9</td>\n",
       "      <td>喜剧片</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    电影名称  搞笑镜头  拥抱镜头  打斗镜头 电影类型\n",
       "0   功夫熊猫    39     0    31  喜剧片\n",
       "1    叶问3     3     2    65  动作片\n",
       "2   伦敦陷落     2     3    55  动作片\n",
       "3   代理情人     9    38     2  爱情片\n",
       "4  新步步惊心     8    34    17  爱情片\n",
       "5   谍影重重     5     2    57  动作片\n",
       "6   功夫熊猫    39     0    31  喜剧片\n",
       "7    美人鱼    21    17     5  喜剧片\n",
       "8   宝贝当家    45     2     9  喜剧片"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "movie_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "id": "0b06ed25",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    21.470911\n",
       "1    52.009614\n",
       "2    43.416587\n",
       "3    40.570926\n",
       "4    34.438351\n",
       "5    43.874822\n",
       "6    21.470911\n",
       "7    18.547237\n",
       "8    23.430749\n",
       "dtype: float64"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_data = [23, 3, 17]\n",
    "data = ((movie_data.iloc[:9, 1:4] - new_data) ** 2).sum(1) ** 0.5\n",
    "data\n",
    "# dist = "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "id": "59e75138",
   "metadata": {},
   "outputs": [],
   "source": [
    "# movie_data.iloc[:9, 4]\n",
    "k = 5\n",
    "data_l = pd.DataFrame({\n",
    "    \"data\": data,\n",
    "    \"labels\": (movie_data.iloc[:9, 4]),\n",
    "})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "0092d0e3",
   "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>data</th>\n",
       "      <th>labels</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>21.470911</td>\n",
       "      <td>喜剧片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>52.009614</td>\n",
       "      <td>动作片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>43.416587</td>\n",
       "      <td>动作片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>40.570926</td>\n",
       "      <td>爱情片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>34.438351</td>\n",
       "      <td>爱情片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>43.874822</td>\n",
       "      <td>动作片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>21.470911</td>\n",
       "      <td>喜剧片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>18.547237</td>\n",
       "      <td>喜剧片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>23.430749</td>\n",
       "      <td>喜剧片</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        data labels\n",
       "0  21.470911    喜剧片\n",
       "1  52.009614    动作片\n",
       "2  43.416587    动作片\n",
       "3  40.570926    爱情片\n",
       "4  34.438351    爱情片\n",
       "5  43.874822    动作片\n",
       "6  21.470911    喜剧片\n",
       "7  18.547237    喜剧片\n",
       "8  23.430749    喜剧片"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_l"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "e448a633",
   "metadata": {},
   "outputs": [],
   "source": [
    "sort_data = data_l.sort_values(by=\"data\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "59fc7986",
   "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>data</th>\n",
       "      <th>labels</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>18.547237</td>\n",
       "      <td>喜剧片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>21.470911</td>\n",
       "      <td>喜剧片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>21.470911</td>\n",
       "      <td>喜剧片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>23.430749</td>\n",
       "      <td>喜剧片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>34.438351</td>\n",
       "      <td>爱情片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>40.570926</td>\n",
       "      <td>爱情片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>43.416587</td>\n",
       "      <td>动作片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>43.874822</td>\n",
       "      <td>动作片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>52.009614</td>\n",
       "      <td>动作片</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        data labels\n",
       "7  18.547237    喜剧片\n",
       "0  21.470911    喜剧片\n",
       "6  21.470911    喜剧片\n",
       "8  23.430749    喜剧片\n",
       "4  34.438351    爱情片\n",
       "3  40.570926    爱情片\n",
       "2  43.416587    动作片\n",
       "5  43.874822    动作片\n",
       "1  52.009614    动作片"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sort_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "c424e45d",
   "metadata": {},
   "outputs": [],
   "source": [
    "select_k = sort_data[:k]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "b1b4d542",
   "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>data</th>\n",
       "      <th>labels</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>18.547237</td>\n",
       "      <td>喜剧片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>21.470911</td>\n",
       "      <td>喜剧片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>21.470911</td>\n",
       "      <td>喜剧片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>23.430749</td>\n",
       "      <td>喜剧片</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>34.438351</td>\n",
       "      <td>爱情片</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        data labels\n",
       "7  18.547237    喜剧片\n",
       "0  21.470911    喜剧片\n",
       "6  21.470911    喜剧片\n",
       "8  23.430749    喜剧片\n",
       "4  34.438351    爱情片"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "select_k"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "aa754a73",
   "metadata": {},
   "outputs": [],
   "source": [
    "frequency1 = select_k.loc[:, \"labels\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "id": "0a4855f3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "7    喜剧片\n",
       "0    喜剧片\n",
       "6    喜剧片\n",
       "8    喜剧片\n",
       "4    爱情片\n",
       "Name: labels, dtype: object"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "frequency1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "id": "d2a8eda4",
   "metadata": {},
   "outputs": [],
   "source": [
    "result = frequency1.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "id": "905e2b9e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "喜剧片    4\n",
       "爱情片    1\n",
       "Name: labels, dtype: int64"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "id": "75b0b58c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'喜剧片'"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result.index[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0d463a29",
   "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": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}