intro.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 538,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import missingno as msno\n",
    "import numpy as np\n",
    "import emoji\n",
    "import regex\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 539,
   "metadata": {},
   "outputs": [],
   "source": [
    "headers = [\"Comment\", \"Comment ID\", \"Reply Count\", \"Like Count\", \"Viewer Rating\"]\n",
    "\n",
    "def read_in_csvs(list_filenames):\n",
    "    return pd.concat([pd.read_csv(filename+\".csv\", names=headers) for filename in list_filenames])\n",
    "\n",
    "filenames = [\"aya_blackpink_time_3\", \"aya_blackpink_time_4\", \n",
    "             \"normal_blackpink_time_3\", \"normal_blackpink_time_4\"]\n",
    "\n",
    "blackpink = read_in_csvs(filenames)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 540,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(3320, 5)"
      ]
     },
     "execution_count": 540,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "blackpink.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 541,
   "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>Comment</th>\n",
       "      <th>Comment ID</th>\n",
       "      <th>Reply Count</th>\n",
       "      <th>Like Count</th>\n",
       "      <th>Viewer Rating</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>곡이 지난곡을 재생산하는느낌은지울수가없네요. 변화가필요합니다.</td>\n",
       "      <td>UgzZok9hFyZ6KXL7dx54AaABAg</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Yay already 10 M likes</td>\n",
       "      <td>UgwGx_T_qoH8wfxyACV4AaABAg</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>#RESPECTLISA STOP WITH THE BULLYING</td>\n",
       "      <td>Ugztt7qshUYp2Eprybh4AaABAg</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>does no one wanna talk about Rosé with balacla...</td>\n",
       "      <td>UgxJvrhriUipNrhc9Nl4AaABAg</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>I HOPE THE YG CEO LET  BLACKPINK AND OTHER ART...</td>\n",
       "      <td>UgymlRqv2PpCO_oOzYd4AaABAg</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                             Comment  \\\n",
       "0                 곡이 지난곡을 재생산하는느낌은지울수가없네요. 변화가필요합니다.   \n",
       "1                             Yay already 10 M likes   \n",
       "2                #RESPECTLISA STOP WITH THE BULLYING   \n",
       "3  does no one wanna talk about Rosé with balacla...   \n",
       "4  I HOPE THE YG CEO LET  BLACKPINK AND OTHER ART...   \n",
       "\n",
       "                   Comment ID  Reply Count  Like Count  Viewer Rating  \n",
       "0  UgzZok9hFyZ6KXL7dx54AaABAg            0           0            NaN  \n",
       "1  UgwGx_T_qoH8wfxyACV4AaABAg            0           0            NaN  \n",
       "2  Ugztt7qshUYp2Eprybh4AaABAg            0           0            NaN  \n",
       "3  UgxJvrhriUipNrhc9Nl4AaABAg            0           0            NaN  \n",
       "4  UgymlRqv2PpCO_oOzYd4AaABAg            0           0            NaN  "
      ]
     },
     "execution_count": 541,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "blackpink.head()"
   ]
  }
 ],
 "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}