Affective_analysis_model.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Building prefix dict from the default dictionary ...\n",
      "Loading model from cache C:\\Users\\ASUS\\AppData\\Local\\Temp\\jieba.cache\n",
      "Loading model cost 1.734 seconds.\n",
      "Prefix dict has been built successfully.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>评论</th>\n",
       "      <th>款式</th>\n",
       "      <th>时间</th>\n",
       "      <th>cut_comment</th>\n",
       "      <th>snlp_result</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>['两款智能手机采用了麒麟990芯片组，该芯片组采用了前沿的7nm架构，支持GPU涡轮增压和...</td>\n",
       "      <td>['网络类型:SA/NSA双模(5G);机身颜色:亮黑色;套餐类型:官方标配;存储容量:6+...</td>\n",
       "      <td>['2020-11-10 21:00:57']</td>\n",
       "      <td>[ ' 两款 智能手机 采用 了 麒麟 990 芯片组 ， 该 芯片组 采用 了 前沿 的 ...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>['手机外观炫彩夺目， 像素特别清楚 手感非常好 机子还可以根据自己的使用习惯设置手势。这点...</td>\n",
       "      <td>['网络类型:SA/NSA双模(5G);机身颜色:零度白;套餐类型:官方标配;存储容量:8+...</td>\n",
       "      <td>['2020-11-15 15:14:51']</td>\n",
       "      <td>[ ' 手机 外观 炫彩 夺目 ，   像素 特别 清楚   手感 非常 好   机子 还 ...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>['第一买华为的手机、感觉还不错，屏幕全屏。我手小，机身刚好适合。外观优雅、商务以及质感很好...</td>\n",
       "      <td>['网络类型:SA/NSA双模(5G);机身颜色:晨曦金;套餐类型:官方标配;存储容量:8+...</td>\n",
       "      <td>['2020-11-01 09:40:45']</td>\n",
       "      <td>[ ' 第一 买 华为 的 手机 、 感觉 还 不错 ， 屏幕 全屏 。 我手 小 ， 机身...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>['手机使用流畅，运行速度也快，冲了一会电，也蛮快的，整体比较给力，价格也合适。后置广角摄像...</td>\n",
       "      <td>['网络类型:SA/NSA双模(5G);机身颜色:亮黑色;套餐类型:官方标配;存储容量:8+...</td>\n",
       "      <td>['2020-11-12 16:51:54']</td>\n",
       "      <td>[ ' 手机 使用 流畅 ， 运行 速度 也 快 ， 冲 了 一会 电 ， 也 蛮 快 的 ...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>['手机很好看，大小合适，速度很快，电池待机时间也持久，非常适合女生用颜色，买之前我还犹豫了...</td>\n",
       "      <td>['网络类型:SA/NSA双模(5G);机身颜色:晨曦金;套餐类型:官方标配;存储容量:8+...</td>\n",
       "      <td>['2020-11-16 14:56:13']</td>\n",
       "      <td>[ ' 手机 很 好看 ， 大小 合适 ， 速度 很快 ， 电池 待机时间 也 持久 ， 非...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1595</td>\n",
       "      <td>['娴娴服务好']</td>\n",
       "      <td>['网络类型:SA/NSA双模(5G);机身颜色:零度白;套餐类型:官方标配;存储容量:6+...</td>\n",
       "      <td>['2020-04-29 09:47:06']</td>\n",
       "      <td>[ ' 娴娴 服务 好 ' ]</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1596</td>\n",
       "      <td>['给老妈买的！到手十分喜欢，说拍摄比原来的小米清楚多了，内存也大可以存好多视频，曲子和照片...</td>\n",
       "      <td>['网络类型:SA/NSA双模(5G);机身颜色:零度白;套餐类型:官方标配;存储容量:8+...</td>\n",
       "      <td>['2020-04-28 12:37:09']</td>\n",
       "      <td>[ ' 给 老妈 买 的 ！ 到手 十分 喜欢 ， 说 拍摄 比 原来 的 小米 清楚 多 ...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1597</td>\n",
       "      <td>['物流很快 第一天下单 第二天就到了 也挺好的 手机充电是真的快 再也不怕手机没电了 拍照...</td>\n",
       "      <td>['网络类型:SA/NSA双模(5G);机身颜色:P40 pro【零度白】;套餐类型:官方标...</td>\n",
       "      <td>['2020-09-12 14:26:09']</td>\n",
       "      <td>[ ' 物流 很快   第一天 下单   第二天 就 到 了   也 挺 好 的   手机 ...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1598</td>\n",
       "      <td>['不错']</td>\n",
       "      <td>['网络类型:SA/NSA双模(5G);机身颜色:冰霜银;套餐类型:官方标配;存储容量:8+...</td>\n",
       "      <td>['2020-04-23 08:49:45']</td>\n",
       "      <td>[ ' 不错 ' ]</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1599</td>\n",
       "      <td>['手机外观时尚，漂亮，运行很流畅，客服迪丽热巴，小美，衡衡，都特别的热情，有问必答，下次还...</td>\n",
       "      <td>['网络类型:SA/NSA双模(5G);机身颜色:深海蓝;套餐类型:官方标配;存储容量:8+...</td>\n",
       "      <td>['2020-05-21 16:27:11']</td>\n",
       "      <td>[ ' 手机 外观 时尚 ， 漂亮 ， 运行 很 流畅 ， 客服 迪丽 热巴 ， 小美 ， ...</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1600 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                     评论  \\\n",
       "0     ['两款智能手机采用了麒麟990芯片组，该芯片组采用了前沿的7nm架构，支持GPU涡轮增压和...   \n",
       "1     ['手机外观炫彩夺目， 像素特别清楚 手感非常好 机子还可以根据自己的使用习惯设置手势。这点...   \n",
       "2     ['第一买华为的手机、感觉还不错，屏幕全屏。我手小，机身刚好适合。外观优雅、商务以及质感很好...   \n",
       "3     ['手机使用流畅，运行速度也快，冲了一会电，也蛮快的，整体比较给力，价格也合适。后置广角摄像...   \n",
       "4     ['手机很好看，大小合适，速度很快，电池待机时间也持久，非常适合女生用颜色，买之前我还犹豫了...   \n",
       "...                                                 ...   \n",
       "1595                                          ['娴娴服务好']   \n",
       "1596  ['给老妈买的！到手十分喜欢，说拍摄比原来的小米清楚多了，内存也大可以存好多视频，曲子和照片...   \n",
       "1597  ['物流很快 第一天下单 第二天就到了 也挺好的 手机充电是真的快 再也不怕手机没电了 拍照...   \n",
       "1598                                             ['不错']   \n",
       "1599  ['手机外观时尚，漂亮，运行很流畅，客服迪丽热巴，小美，衡衡，都特别的热情，有问必答，下次还...   \n",
       "\n",
       "                                                     款式  \\\n",
       "0     ['网络类型:SA/NSA双模(5G);机身颜色:亮黑色;套餐类型:官方标配;存储容量:6+...   \n",
       "1     ['网络类型:SA/NSA双模(5G);机身颜色:零度白;套餐类型:官方标配;存储容量:8+...   \n",
       "2     ['网络类型:SA/NSA双模(5G);机身颜色:晨曦金;套餐类型:官方标配;存储容量:8+...   \n",
       "3     ['网络类型:SA/NSA双模(5G);机身颜色:亮黑色;套餐类型:官方标配;存储容量:8+...   \n",
       "4     ['网络类型:SA/NSA双模(5G);机身颜色:晨曦金;套餐类型:官方标配;存储容量:8+...   \n",
       "...                                                 ...   \n",
       "1595  ['网络类型:SA/NSA双模(5G);机身颜色:零度白;套餐类型:官方标配;存储容量:6+...   \n",
       "1596  ['网络类型:SA/NSA双模(5G);机身颜色:零度白;套餐类型:官方标配;存储容量:8+...   \n",
       "1597  ['网络类型:SA/NSA双模(5G);机身颜色:P40 pro【零度白】;套餐类型:官方标...   \n",
       "1598  ['网络类型:SA/NSA双模(5G);机身颜色:冰霜银;套餐类型:官方标配;存储容量:8+...   \n",
       "1599  ['网络类型:SA/NSA双模(5G);机身颜色:深海蓝;套餐类型:官方标配;存储容量:8+...   \n",
       "\n",
       "                           时间  \\\n",
       "0     ['2020-11-10 21:00:57']   \n",
       "1     ['2020-11-15 15:14:51']   \n",
       "2     ['2020-11-01 09:40:45']   \n",
       "3     ['2020-11-12 16:51:54']   \n",
       "4     ['2020-11-16 14:56:13']   \n",
       "...                       ...   \n",
       "1595  ['2020-04-29 09:47:06']   \n",
       "1596  ['2020-04-28 12:37:09']   \n",
       "1597  ['2020-09-12 14:26:09']   \n",
       "1598  ['2020-04-23 08:49:45']   \n",
       "1599  ['2020-05-21 16:27:11']   \n",
       "\n",
       "                                            cut_comment  snlp_result  \n",
       "0     [ ' 两款 智能手机 采用 了 麒麟 990 芯片组 ， 该 芯片组 采用 了 前沿 的 ...            1  \n",
       "1     [ ' 手机 外观 炫彩 夺目 ，   像素 特别 清楚   手感 非常 好   机子 还 ...            1  \n",
       "2     [ ' 第一 买 华为 的 手机 、 感觉 还 不错 ， 屏幕 全屏 。 我手 小 ， 机身...            1  \n",
       "3     [ ' 手机 使用 流畅 ， 运行 速度 也 快 ， 冲 了 一会 电 ， 也 蛮 快 的 ...            1  \n",
       "4     [ ' 手机 很 好看 ， 大小 合适 ， 速度 很快 ， 电池 待机时间 也 持久 ， 非...            1  \n",
       "...                                                 ...          ...  \n",
       "1595                                    [ ' 娴娴 服务 好 ' ]            1  \n",
       "1596  [ ' 给 老妈 买 的 ！ 到手 十分 喜欢 ， 说 拍摄 比 原来 的 小米 清楚 多 ...            1  \n",
       "1597  [ ' 物流 很快   第一天 下单   第二天 就 到 了   也 挺 好 的   手机 ...            1  \n",
       "1598                                         [ ' 不错 ' ]            1  \n",
       "1599  [ ' 手机 外观 时尚 ， 漂亮 ， 运行 很 流畅 ， 客服 迪丽 热巴 ， 小美 ， ...            1  \n",
       "\n",
       "[1600 rows x 5 columns]"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import jieba\n",
    "import pandas as pd\n",
    "from snownlp import SnowNLP\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "data = pd.read_csv('D:/comments.csv')\n",
    "\n",
    "def cut_words(mytext):\n",
    "    return \" \".join(jieba.cut(mytext))\n",
    "data['cut_comment'] = data['评论'].apply(cut_words)\n",
    "\n",
    "def snow_result(comemnt):\n",
    "    s = SnowNLP(comemnt)\n",
    "    if s.sentiments >= 0.6:\n",
    "        return 1\n",
    "    else:\n",
    "        return 0\n",
    "    \n",
    "data['snlp_result'] = data['评论'].apply(snow_result)\n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_stopwords(stopwords_file_path):\n",
    "    with open(stopwords_file_path,'r',encoding='utf-8') as f:\n",
    "        stopwords = f.read()\n",
    "    stopwords_list = stopwords.strip()\n",
    "    stopwords_list = [i for i in stopwords_list]\n",
    "    return stopwords_list\n",
    "\n",
    "stopwords_file_path = './stopwords/my_stopwords.txt'\n",
    "stopwords_list = get_stopwords(stopwords_file_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": 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>app</th>\n",
       "      <th>hellip</th>\n",
       "      <th>ldquo</th>\n",
       "      <th>nbsp</th>\n",
       "      <th>nice</th>\n",
       "      <th>ok</th>\n",
       "      <th>oppo</th>\n",
       "      <th>p20</th>\n",
       "      <th>p40</th>\n",
       "      <th>rdquo</th>\n",
       "      <th>...</th>\n",
       "      <th>顺畅</th>\n",
       "      <th>颜值</th>\n",
       "      <th>颜色</th>\n",
       "      <th>飞燕</th>\n",
       "      <th>马上</th>\n",
       "      <th>骄傲</th>\n",
       "      <th>高清</th>\n",
       "      <th>高端</th>\n",
       "      <th>麻烦</th>\n",
       "      <th>黑色</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 673 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   app  hellip  ldquo  nbsp  nice  ok  oppo  p20  p40  rdquo  ...  顺畅  颜值  颜色  \\\n",
       "0    0       0      0     0     0   0     0    0    0      0  ...   0   0   0   \n",
       "1    0       0      0     0     0   0     0    0    0      0  ...   0   1   0   \n",
       "2    0       0      0     0     0   0     0    0    0      0  ...   0   0   0   \n",
       "3    0       0      0     0     0   0     0    0    0      0  ...   0   0   0   \n",
       "4    0       0      0     0     0   0     0    0    0      0  ...   0   0   0   \n",
       "\n",
       "   飞燕  马上  骄傲  高清  高端  麻烦  黑色  \n",
       "0   0   0   0   0   0   0   0  \n",
       "1   0   1   0   0   0   0   0  \n",
       "2   0   0   0   0   0   0   0  \n",
       "3   0   0   0   0   0   0   0  \n",
       "4   0   0   0   0   0   0   0  \n",
       "\n",
       "[5 rows x 673 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X = data['cut_comment'] #分词后的评论\n",
    "y = data['snlp_result'] #SnowNLP(text).sentiments\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=22)\n",
    "\n",
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "\n",
    "vect = CountVectorizer(max_df = 0.8, \n",
    "                       min_df = 3, \n",
    "                       token_pattern=u'(?u)\\\\b[^\\\\d\\\\W]\\\\w+\\\\b', \n",
    "                       stop_words=frozenset(stopwords_list))\n",
    "\n",
    "test = pd.DataFrame(vect.fit_transform(X_train).toarray(), columns=vect.get_feature_names())\n",
    "test.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8703125\n"
     ]
    }
   ],
   "source": [
    "from sklearn.naive_bayes import MultinomialNB\n",
    "nb = MultinomialNB()\n",
    "\n",
    "X_train_vect = vect.fit_transform(X_train)\n",
    "nb.fit(X_train_vect, y_train)\n",
    "train_score = nb.score(X_train_vect, y_train)\n",
    "print(train_score)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.85625\n"
     ]
    }
   ],
   "source": [
    "X_test_vect = vect.transform(X_test)\n",
    "print(nb.score(X_test_vect, y_test))"
   ]
  },
  {
   "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}