{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## NLP处理实例\n",
    "\n",
    "### 数据集: Disasters on social media\n",
    "\n",
    "推特（社交媒体）上有许多的信息，其中有关于灾难，疾病，暴乱的，有些只是开玩笑或者是电影情节，我们该如何让机器能分辨出这两种讨论呢？"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 为什么这很重要\n",
    "我们将努力正确预测有关灾难的推文。这是一个非常相关的问题，因为：\n",
    "\n",
    "* 对于任何试图从噪音中获取信号的人来说，这都是可以采取行动的(比如警察部门在这种情况下)。\n",
    "* 这是很棘手的，因为依赖关键字比在大多数情况下像垃圾邮件更难。"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "###  任务\n",
    "对文本数据进行分类，并分析找到相关归因。"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sklearn\n",
    "from tensorflow import keras\n",
    "import nltk\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import re\n",
    "import codecs"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 数据输入\n",
    "需要对数据做一下编码处理"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "input_file = codecs.open(\"data/socialmedia_relevant_cols.csv\", \"r\",encoding='utf-8', errors='replace')\n",
    "output_file = open(\"data/socialmedia_relevant_cols_clean.csv\", \"w\",encoding='utf-8')\n",
    "\n",
    "def sanitize_characters(raw, clean):    \n",
    "    for line in input_file:\n",
    "        out = line\n",
    "        output_file.write(line)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "sanitize_characters(input_file, output_file)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 数据预处理"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "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>text</th>\n",
       "      <th>choose_one</th>\n",
       "      <th>class_label</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Just happened a terrible car crash</td>\n",
       "      <td>Relevant</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Our Deeds are the Reason of this #earthquake M...</td>\n",
       "      <td>Relevant</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Heard about #earthquake is different cities, s...</td>\n",
       "      <td>Relevant</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>there is a forest fire at spot pond, geese are...</td>\n",
       "      <td>Relevant</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Forest fire near La Ronge Sask. Canada</td>\n",
       "      <td>Relevant</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                text choose_one  class_label\n",
       "0                 Just happened a terrible car crash   Relevant            1\n",
       "1  Our Deeds are the Reason of this #earthquake M...   Relevant            1\n",
       "2  Heard about #earthquake is different cities, s...   Relevant            1\n",
       "3  there is a forest fire at spot pond, geese are...   Relevant            1\n",
       "4             Forest fire near La Ronge Sask. Canada   Relevant            1"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "questions = pd.read_csv(\"data/socialmedia_relevant_cols_clean.csv\")\n",
    "questions.columns=['text', 'choose_one', 'class_label']\n",
    "questions.head()"
   ]
  },
  {
   "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}