added simple approach
This commit is contained in:
		
							
								
								
									
										6
									
								
								Project/simple_approach/README.md
									
									
									
									
									
										Normal file
									
								
							
							
						
						
									
										6
									
								
								Project/simple_approach/README.md
									
									
									
									
									
										Normal file
									
								
							| @ -0,0 +1,6 @@ | ||||
| # Simple Approach | ||||
|  | ||||
| ---- | ||||
|  | ||||
| just a slightly better approach than the naive one 💁 | ||||
|  | ||||
							
								
								
									
										990
									
								
								Project/simple_approach/simple_twitter_learning.ipynb
									
									
									
									
									
										Normal file
									
								
							
							
						
						
									
										990
									
								
								Project/simple_approach/simple_twitter_learning.ipynb
									
									
									
									
									
										Normal file
									
								
							| @ -0,0 +1,990 @@ | ||||
| { | ||||
|  "cells": [ | ||||
|   { | ||||
|    "cell_type": "code", | ||||
|    "execution_count": 13, | ||||
|    "metadata": {}, | ||||
|    "outputs": [], | ||||
|    "source": [ | ||||
|     "import pandas as pd\n", | ||||
|     "from IPython.display import clear_output, Markdown, Math\n", | ||||
|     "import ipywidgets as widgets\n", | ||||
|     "import os\n", | ||||
|     "import glob\n", | ||||
|     "import json" | ||||
|    ] | ||||
|   }, | ||||
|   { | ||||
|    "cell_type": "markdown", | ||||
|    "metadata": {}, | ||||
|    "source": [ | ||||
|     "# simple twitter approach\n", | ||||
|     "*for learning emoji usage by single (in the meaning of unconnected) twitter messages*" | ||||
|    ] | ||||
|   }, | ||||
|   { | ||||
|    "cell_type": "markdown", | ||||
|    "metadata": {}, | ||||
|    "source": [ | ||||
|     "## loading train data" | ||||
|    ] | ||||
|   }, | ||||
|   { | ||||
|    "cell_type": "code", | ||||
|    "execution_count": 9, | ||||
|    "metadata": {}, | ||||
|    "outputs": [], | ||||
|    "source": [ | ||||
|     "data_root_folder = \"./data_en/\" # i created a symlink here" | ||||
|    ] | ||||
|   }, | ||||
|   { | ||||
|    "cell_type": "markdown", | ||||
|    "metadata": {}, | ||||
|    "source": [ | ||||
|     "* get all json files in `data_root_folder`" | ||||
|    ] | ||||
|   }, | ||||
|   { | ||||
|    "cell_type": "code", | ||||
|    "execution_count": 10, | ||||
|    "metadata": {}, | ||||
|    "outputs": [], | ||||
|    "source": [ | ||||
|     "json_files = sorted(glob.glob(data_root_folder + \"/*.json\"))" | ||||
|    ] | ||||
|   }, | ||||
|   { | ||||
|    "cell_type": "markdown", | ||||
|    "metadata": {}, | ||||
|    "source": [ | ||||
|     "----" | ||||
|    ] | ||||
|   }, | ||||
|   { | ||||
|    "cell_type": "markdown", | ||||
|    "metadata": {}, | ||||
|    "source": [ | ||||
|     "* so far, only load the first file" | ||||
|    ] | ||||
|   }, | ||||
|   { | ||||
|    "cell_type": "code", | ||||
|    "execution_count": 16, | ||||
|    "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>EMOJI</th>\n", | ||||
|        "      <th>datetime</th>\n", | ||||
|        "      <th>id</th>\n", | ||||
|        "      <th>lang</th>\n", | ||||
|        "      <th>person</th>\n", | ||||
|        "      <th>reply_to</th>\n", | ||||
|        "      <th>text</th>\n", | ||||
|        "    </tr>\n", | ||||
|        "  </thead>\n", | ||||
|        "  <tbody>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>0</th>\n", | ||||
|        "      <td>[🔥, 👏]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:00</td>\n", | ||||
|        "      <td>925716304635547600</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>31507978</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>fashionbombdaily's photo  <EMOJI><EMOJI>🏼</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>1</th>\n", | ||||
|        "      <td>[🤦]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:00</td>\n", | ||||
|        "      <td>925716304664911900</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>231994649</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>It’s scary how on point my horoscope be <EMOJI...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>2</th>\n", | ||||
|        "      <td>[🤧]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:00</td>\n", | ||||
|        "      <td>925716304652308500</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>78123421</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@mvyn_: Them boring ass licks, you supposed t...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>3</th>\n", | ||||
|        "      <td>[🐯, 🐥, 💕]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:01</td>\n", | ||||
|        "      <td>925716308846661600</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>860396470540705800</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@taehyungpic: #vmin ‘s unit shoot  <EMOJI><EM...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>4</th>\n", | ||||
|        "      <td>[👍, 👍, 👍]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:02</td>\n", | ||||
|        "      <td>925716313015586800</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>775381892321333200</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@risa_del: Can I just say how much Meng respe...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>5</th>\n", | ||||
|        "      <td>[😒]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:02</td>\n", | ||||
|        "      <td>925716313032364000</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>3244140547</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@Melodia_Muse: omg did y'all just cut off Red...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>6</th>\n", | ||||
|        "      <td>[✅, 🍟]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:02</td>\n", | ||||
|        "      <td>925716313036722200</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>4891498023</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@Harrys1DEmpire: Follow everyone who LIKES th...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>7</th>\n", | ||||
|        "      <td>[👶]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:03</td>\n", | ||||
|        "      <td>925716317243555800</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>2660072274</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@taehyungpic: he is so smollll <EMOJI>©rocket...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>8</th>\n", | ||||
|        "      <td>[😄]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:03</td>\n", | ||||
|        "      <td>925716317214089200</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>2592765104</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>Woooaaaahhh <EMOJI></td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>9</th>\n", | ||||
|        "      <td>[🌟, 🌟]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:03</td>\n", | ||||
|        "      <td>925716317218508800</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>3011085514</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@mymermaidIagoon: <EMOJI> HURRY! For your cha...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>10</th>\n", | ||||
|        "      <td>[📷]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:04</td>\n", | ||||
|        "      <td>925716321416949800</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>278737933</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td><EMOJI> vivalcli: Portraits by Zhao Guojing an...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>11</th>\n", | ||||
|        "      <td>[🚨, 🚨, 🚨, 🚨, 🚨, 🚨]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:05</td>\n", | ||||
|        "      <td>925716325615439900</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>876587129077477400</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@BillRatchet: <EMOJI><EMOJI><EMOJI>NO NUT NOV...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>12</th>\n", | ||||
|        "      <td>[💕]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:05</td>\n", | ||||
|        "      <td>925716325615505400</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>2402588155</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@mysweetapplexxx: ❤️Happy Birthday, @GoodGalC...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>13</th>\n", | ||||
|        "      <td>[🙏]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:06</td>\n", | ||||
|        "      <td>925716329797054500</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>1546678166</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@pourlui: @realDonaldTrump @SSNjl @foxandfrie...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>14</th>\n", | ||||
|        "      <td>[😩, 😩]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:06</td>\n", | ||||
|        "      <td>925716329801310200</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>824586253634981900</td>\n", | ||||
|        "      <td>9.257162e+17</td>\n", | ||||
|        "      <td>@hiphopphiIes i wanna know too<EMOJI><EMOJI></td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>15</th>\n", | ||||
|        "      <td>[😭, 💓]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:02</td>\n", | ||||
|        "      <td>925716313019965400</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>1581953814</td>\n", | ||||
|        "      <td>9.257088e+17</td>\n", | ||||
|        "      <td>@WizMommma veda was yoda too <EMOJI><EMOJI></td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>16</th>\n", | ||||
|        "      <td>[🙏, 🤕, 😂]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:06</td>\n", | ||||
|        "      <td>925716329801371600</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>1737878390</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@TiagoIlori4: Me and my family are humbled by...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>17</th>\n", | ||||
|        "      <td>[😂]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:05</td>\n", | ||||
|        "      <td>925716325607133200</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>1001999683</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>I’m less stressed about turning 30 now <EMOJI>...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>18</th>\n", | ||||
|        "      <td>[💯]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:07</td>\n", | ||||
|        "      <td>925716334008082400</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>745222369183043600</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>Full charged. <EMOJI></td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>19</th>\n", | ||||
|        "      <td>[🙄]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:09</td>\n", | ||||
|        "      <td>925716342401052700</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>798557155217539100</td>\n", | ||||
|        "      <td>9.257147e+17</td>\n", | ||||
|        "      <td>@SeaDimon That’s part of the problem, (they) @...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>20</th>\n", | ||||
|        "      <td>[😟, 😥, 😢]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:10</td>\n", | ||||
|        "      <td>925716346570240000</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>744396039126421500</td>\n", | ||||
|        "      <td>9.250629e+17</td>\n", | ||||
|        "      <td>@Ian_khetye got me emotional there<EMOJI><EMOJ...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>21</th>\n", | ||||
|        "      <td>[😂, 😂, 😂]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:10</td>\n", | ||||
|        "      <td>925716346603753500</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>2428265479</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@30SECONDFlGHTS: BRUHHH <EMOJI><EMOJI><EMOJI></td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>22</th>\n", | ||||
|        "      <td>[👀]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:10</td>\n", | ||||
|        "      <td>925716346595434500</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>2523596372</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@BasebaIINation: Game 7 who you got?<EMOJI> f...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>23</th>\n", | ||||
|        "      <td>[🔎]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:11</td>\n", | ||||
|        "      <td>925716350764331000</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>2315896393</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@JudicialWatch: JW says DOJ &amp; Congress ar...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>24</th>\n", | ||||
|        "      <td>[📣, 💖]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:12</td>\n", | ||||
|        "      <td>925716354988236800</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>2316464875</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@cssconfau: ✍🏻 <EMOJI> Ever thought about spe...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>25</th>\n", | ||||
|        "      <td>[✨, 💖]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:12</td>\n", | ||||
|        "      <td>925716354975465500</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>2614916743</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@btspat_:  Deal for Young Forever: Night Vers...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>26</th>\n", | ||||
|        "      <td>[💪]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:13</td>\n", | ||||
|        "      <td>925716359153041400</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>2887539044</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@DFC_SARAVANA: @dhanushkraja Reached 6 Millio...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>27</th>\n", | ||||
|        "      <td>[🌻]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:13</td>\n", | ||||
|        "      <td>925716359182520300</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>721490010118205400</td>\n", | ||||
|        "      <td>8.965900e+17</td>\n", | ||||
|        "      <td>back to the yellow <EMOJI></td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>28</th>\n", | ||||
|        "      <td>[🍁, 🌺, 🍂]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:15</td>\n", | ||||
|        "      <td>925716367558545400</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>520536723</td>\n", | ||||
|        "      <td>9.257159e+17</td>\n", | ||||
|        "      <td>@Dimafadma Happy month to you and your loved o...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>29</th>\n", | ||||
|        "      <td>[🍃]</td>\n", | ||||
|        "      <td>2017-11-01 13:29:16</td>\n", | ||||
|        "      <td>925716371735900200</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>850852815941517300</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>Maxx and Patricia. Family hangs at For Good He...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>...</th>\n", | ||||
|        "      <td>...</td>\n", | ||||
|        "      <td>...</td>\n", | ||||
|        "      <td>...</td>\n", | ||||
|        "      <td>...</td>\n", | ||||
|        "      <td>...</td>\n", | ||||
|        "      <td>...</td>\n", | ||||
|        "      <td>...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176302</th>\n", | ||||
|        "      <td>[😭, 😭, 💘]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:31</td>\n", | ||||
|        "      <td>925624327755591700</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>845085544589672400</td>\n", | ||||
|        "      <td>9.256009e+17</td>\n", | ||||
|        "      <td>@peachshua1230 Awww <EMOJI> Ajsksjdjd im smili...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176303</th>\n", | ||||
|        "      <td>[🤣, 🤣, 🤣, 🤣]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:33</td>\n", | ||||
|        "      <td>925624336156938200</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>1154786048</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@playboinathann: MY LIL BRO ATE AN EDIBLE THI...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176304</th>\n", | ||||
|        "      <td>[😫, ✋]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:34</td>\n", | ||||
|        "      <td>925624340342812700</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>924752524871131100</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>I hate when I send a text or snap n I'm so anx...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176305</th>\n", | ||||
|        "      <td>[👻, 🎃]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:34</td>\n", | ||||
|        "      <td>925624340334501900</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>868681065308631000</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@LDNNOISE: Happy Halloween <EMOJI><EMOJI></td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176306</th>\n", | ||||
|        "      <td>[😂, 🙁]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:34</td>\n", | ||||
|        "      <td>925624340355280900</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>419493819</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>The answer is no I have no plans and I never l...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176307</th>\n", | ||||
|        "      <td>[😭]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:34</td>\n", | ||||
|        "      <td>925624340346937300</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>2457745952</td>\n", | ||||
|        "      <td>9.256219e+17</td>\n", | ||||
|        "      <td>@BeachBoy_Gab LMAOOO I'm so proud <EMOJI></td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176308</th>\n", | ||||
|        "      <td>[😢, 💔]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:34</td>\n", | ||||
|        "      <td>925624340338507800</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>1955767531</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>My cousin/little sister is leaving to San Fran...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176309</th>\n", | ||||
|        "      <td>[🙃]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:35</td>\n", | ||||
|        "      <td>925624344524361700</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>796490344581898200</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>Can't be alone w my thoughts tonight so just g...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176310</th>\n", | ||||
|        "      <td>[✨]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:35</td>\n", | ||||
|        "      <td>925624344511897600</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>825346617620328400</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@ohmygirlpcs: Jine <EMOJI></td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176311</th>\n", | ||||
|        "      <td>[😂, 😂, 😂, 😂, 😂]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:36</td>\n", | ||||
|        "      <td>925624348710285300</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>907808317124177900</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td><EMOJI><EMOJI><EMOJI><EMOJI><EMOJI> ambot!!!</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176312</th>\n", | ||||
|        "      <td>[🚀]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:37</td>\n", | ||||
|        "      <td>925624352921608200</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>1605371160</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@WestHamUtd: It wasn't the result we wanted, ...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176313</th>\n", | ||||
|        "      <td>[👌, 👊, 🙌]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:37</td>\n", | ||||
|        "      <td>925624352929910800</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>262162415</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td><EMOJI>🏽<EMOJI>🏽 1st of the month!!Happy 1st o...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176314</th>\n", | ||||
|        "      <td>[😴]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:41</td>\n", | ||||
|        "      <td>925624369715515400</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>574882525</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>#WednesdayWisdom ... stay in bed <EMOJI></td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176315</th>\n", | ||||
|        "      <td>[💀, 🖤]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:42</td>\n", | ||||
|        "      <td>925624373905707000</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>2694136560</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@Brandonwoelfel: Happy Halloween friends!<EMO...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176316</th>\n", | ||||
|        "      <td>[🔴]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:43</td>\n", | ||||
|        "      <td>925624378078851100</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>799982767886872600</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@carras16: Good win tonight and great to see ...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176317</th>\n", | ||||
|        "      <td>[😂, 😂, 😂, 😂]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:44</td>\n", | ||||
|        "      <td>925624382269124600</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>556175173</td>\n", | ||||
|        "      <td>9.254038e+17</td>\n", | ||||
|        "      <td>@Louis_Tomlinson @NiallOfficial THIS IS GOLD. ...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176318</th>\n", | ||||
|        "      <td>[💖, 💗, 💞, 💕, 💘]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:44</td>\n", | ||||
|        "      <td>925624382281547800</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>837324291637051400</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@95duet: i love them sm☹️<EMOJI><EMOJI><EMOJI...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176319</th>\n", | ||||
|        "      <td>[😀]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:45</td>\n", | ||||
|        "      <td>925624386455031800</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>1610265588</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td><EMOJI> thank you for the kind compliment</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176320</th>\n", | ||||
|        "      <td>[😎]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:45</td>\n", | ||||
|        "      <td>925624386454937600</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>4760724450</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>Enjoyed the silence <EMOJI></td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176321</th>\n", | ||||
|        "      <td>[✨]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:46</td>\n", | ||||
|        "      <td>925624390657572900</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>882858115636514800</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>OS: Spiderman Homecoming <EMOJI></td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176322</th>\n", | ||||
|        "      <td>[🤷]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:46</td>\n", | ||||
|        "      <td>925624390682849300</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>188129628</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>Go to hell <EMOJI>🏽♀️</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176323</th>\n", | ||||
|        "      <td>[😘]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:46</td>\n", | ||||
|        "      <td>925624390666129400</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>2473135939</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>Thank you Yomi! <EMOJI></td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176324</th>\n", | ||||
|        "      <td>[😂]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:46</td>\n", | ||||
|        "      <td>925624390670106600</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>2373584209</td>\n", | ||||
|        "      <td>9.256241e+17</td>\n", | ||||
|        "      <td>@discopiggu Lol. Just enjoy the stars. Music K...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176325</th>\n", | ||||
|        "      <td>[🙏]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:47</td>\n", | ||||
|        "      <td>925624394860453900</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>40709255</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@INS_Ecosystem: We are honored to have @eyal ...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176326</th>\n", | ||||
|        "      <td>[🔥]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:48</td>\n", | ||||
|        "      <td>925624399063117800</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>889503742474768400</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@EmiNiPr: I just love twitterMan's not hot <E...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176327</th>\n", | ||||
|        "      <td>[🙏]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:50</td>\n", | ||||
|        "      <td>925624407459971100</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>181689756</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>Thoughts and prayers for NY<EMOJI>🏻 #NYCStrong</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176328</th>\n", | ||||
|        "      <td>[💁]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:50</td>\n", | ||||
|        "      <td>925624407460057100</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>60160788</td>\n", | ||||
|        "      <td>9.254610e+17</td>\n", | ||||
|        "      <td>@BrianyH I searched COCK, PENIS, SHLONG, WINKY...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176329</th>\n", | ||||
|        "      <td>[🌠, 🎇, 🌠, 🌙]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:51</td>\n", | ||||
|        "      <td>925624411620646900</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>4915042321</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@eyesnoselips99: 170930 KMF  <EMOJI>☄<EMOJI> ...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176330</th>\n", | ||||
|        "      <td>[🍃, 🌻, 🌻, 🍃, 🍃, 💐, 💐, 🍃, 🙋]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:53</td>\n", | ||||
|        "      <td>925624420022063100</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>3792290725</td>\n", | ||||
|        "      <td>9.256215e+17</td>\n", | ||||
|        "      <td>@amitbarman520 Thank you so much<EMOJI><EMOJI>...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "    <tr>\n", | ||||
|        "      <th>176331</th>\n", | ||||
|        "      <td>[😻, 😫, 🤔, 💦, 💦, 💦]</td>\n", | ||||
|        "      <td>2017-11-01 07:23:57</td>\n", | ||||
|        "      <td>925624436799049700</td>\n", | ||||
|        "      <td>en</td>\n", | ||||
|        "      <td>612733752</td>\n", | ||||
|        "      <td>NaN</td>\n", | ||||
|        "      <td>@DarrionDaDon_: Vocals ? <EMOJI>High Notes ? ...</td>\n", | ||||
|        "    </tr>\n", | ||||
|        "  </tbody>\n", | ||||
|        "</table>\n", | ||||
|        "<p>176332 rows × 7 columns</p>\n", | ||||
|        "</div>" | ||||
|       ], | ||||
|       "text/plain": [ | ||||
|        "                              EMOJI            datetime                  id  \\\n", | ||||
|        "0                            [🔥, 👏] 2017-11-01 13:29:00  925716304635547600   \n", | ||||
|        "1                               [🤦] 2017-11-01 13:29:00  925716304664911900   \n", | ||||
|        "2                               [🤧] 2017-11-01 13:29:00  925716304652308500   \n", | ||||
|        "3                         [🐯, 🐥, 💕] 2017-11-01 13:29:01  925716308846661600   \n", | ||||
|        "4                         [👍, 👍, 👍] 2017-11-01 13:29:02  925716313015586800   \n", | ||||
|        "5                               [😒] 2017-11-01 13:29:02  925716313032364000   \n", | ||||
|        "6                            [✅, 🍟] 2017-11-01 13:29:02  925716313036722200   \n", | ||||
|        "7                               [👶] 2017-11-01 13:29:03  925716317243555800   \n", | ||||
|        "8                               [😄] 2017-11-01 13:29:03  925716317214089200   \n", | ||||
|        "9                            [🌟, 🌟] 2017-11-01 13:29:03  925716317218508800   \n", | ||||
|        "10                              [📷] 2017-11-01 13:29:04  925716321416949800   \n", | ||||
|        "11               [🚨, 🚨, 🚨, 🚨, 🚨, 🚨] 2017-11-01 13:29:05  925716325615439900   \n", | ||||
|        "12                              [💕] 2017-11-01 13:29:05  925716325615505400   \n", | ||||
|        "13                              [🙏] 2017-11-01 13:29:06  925716329797054500   \n", | ||||
|        "14                           [😩, 😩] 2017-11-01 13:29:06  925716329801310200   \n", | ||||
|        "15                           [😭, 💓] 2017-11-01 13:29:02  925716313019965400   \n", | ||||
|        "16                        [🙏, 🤕, 😂] 2017-11-01 13:29:06  925716329801371600   \n", | ||||
|        "17                              [😂] 2017-11-01 13:29:05  925716325607133200   \n", | ||||
|        "18                              [💯] 2017-11-01 13:29:07  925716334008082400   \n", | ||||
|        "19                              [🙄] 2017-11-01 13:29:09  925716342401052700   \n", | ||||
|        "20                        [😟, 😥, 😢] 2017-11-01 13:29:10  925716346570240000   \n", | ||||
|        "21                        [😂, 😂, 😂] 2017-11-01 13:29:10  925716346603753500   \n", | ||||
|        "22                              [👀] 2017-11-01 13:29:10  925716346595434500   \n", | ||||
|        "23                              [🔎] 2017-11-01 13:29:11  925716350764331000   \n", | ||||
|        "24                           [📣, 💖] 2017-11-01 13:29:12  925716354988236800   \n", | ||||
|        "25                           [✨, 💖] 2017-11-01 13:29:12  925716354975465500   \n", | ||||
|        "26                              [💪] 2017-11-01 13:29:13  925716359153041400   \n", | ||||
|        "27                              [🌻] 2017-11-01 13:29:13  925716359182520300   \n", | ||||
|        "28                        [🍁, 🌺, 🍂] 2017-11-01 13:29:15  925716367558545400   \n", | ||||
|        "29                              [🍃] 2017-11-01 13:29:16  925716371735900200   \n", | ||||
|        "...                             ...                 ...                 ...   \n", | ||||
|        "176302                    [😭, 😭, 💘] 2017-11-01 07:23:31  925624327755591700   \n", | ||||
|        "176303                 [🤣, 🤣, 🤣, 🤣] 2017-11-01 07:23:33  925624336156938200   \n", | ||||
|        "176304                       [😫, ✋] 2017-11-01 07:23:34  925624340342812700   \n", | ||||
|        "176305                       [👻, 🎃] 2017-11-01 07:23:34  925624340334501900   \n", | ||||
|        "176306                       [😂, 🙁] 2017-11-01 07:23:34  925624340355280900   \n", | ||||
|        "176307                          [😭] 2017-11-01 07:23:34  925624340346937300   \n", | ||||
|        "176308                       [😢, 💔] 2017-11-01 07:23:34  925624340338507800   \n", | ||||
|        "176309                          [🙃] 2017-11-01 07:23:35  925624344524361700   \n", | ||||
|        "176310                          [✨] 2017-11-01 07:23:35  925624344511897600   \n", | ||||
|        "176311              [😂, 😂, 😂, 😂, 😂] 2017-11-01 07:23:36  925624348710285300   \n", | ||||
|        "176312                          [🚀] 2017-11-01 07:23:37  925624352921608200   \n", | ||||
|        "176313                    [👌, 👊, 🙌] 2017-11-01 07:23:37  925624352929910800   \n", | ||||
|        "176314                          [😴] 2017-11-01 07:23:41  925624369715515400   \n", | ||||
|        "176315                       [💀, 🖤] 2017-11-01 07:23:42  925624373905707000   \n", | ||||
|        "176316                          [🔴] 2017-11-01 07:23:43  925624378078851100   \n", | ||||
|        "176317                 [😂, 😂, 😂, 😂] 2017-11-01 07:23:44  925624382269124600   \n", | ||||
|        "176318              [💖, 💗, 💞, 💕, 💘] 2017-11-01 07:23:44  925624382281547800   \n", | ||||
|        "176319                          [😀] 2017-11-01 07:23:45  925624386455031800   \n", | ||||
|        "176320                          [😎] 2017-11-01 07:23:45  925624386454937600   \n", | ||||
|        "176321                          [✨] 2017-11-01 07:23:46  925624390657572900   \n", | ||||
|        "176322                          [🤷] 2017-11-01 07:23:46  925624390682849300   \n", | ||||
|        "176323                          [😘] 2017-11-01 07:23:46  925624390666129400   \n", | ||||
|        "176324                          [😂] 2017-11-01 07:23:46  925624390670106600   \n", | ||||
|        "176325                          [🙏] 2017-11-01 07:23:47  925624394860453900   \n", | ||||
|        "176326                          [🔥] 2017-11-01 07:23:48  925624399063117800   \n", | ||||
|        "176327                          [🙏] 2017-11-01 07:23:50  925624407459971100   \n", | ||||
|        "176328                          [💁] 2017-11-01 07:23:50  925624407460057100   \n", | ||||
|        "176329                 [🌠, 🎇, 🌠, 🌙] 2017-11-01 07:23:51  925624411620646900   \n", | ||||
|        "176330  [🍃, 🌻, 🌻, 🍃, 🍃, 💐, 💐, 🍃, 🙋] 2017-11-01 07:23:53  925624420022063100   \n", | ||||
|        "176331           [😻, 😫, 🤔, 💦, 💦, 💦] 2017-11-01 07:23:57  925624436799049700   \n", | ||||
|        "\n", | ||||
|        "       lang              person      reply_to  \\\n", | ||||
|        "0        en            31507978           NaN   \n", | ||||
|        "1        en           231994649           NaN   \n", | ||||
|        "2        en            78123421           NaN   \n", | ||||
|        "3        en  860396470540705800           NaN   \n", | ||||
|        "4        en  775381892321333200           NaN   \n", | ||||
|        "5        en          3244140547           NaN   \n", | ||||
|        "6        en          4891498023           NaN   \n", | ||||
|        "7        en          2660072274           NaN   \n", | ||||
|        "8        en          2592765104           NaN   \n", | ||||
|        "9        en          3011085514           NaN   \n", | ||||
|        "10       en           278737933           NaN   \n", | ||||
|        "11       en  876587129077477400           NaN   \n", | ||||
|        "12       en          2402588155           NaN   \n", | ||||
|        "13       en          1546678166           NaN   \n", | ||||
|        "14       en  824586253634981900  9.257162e+17   \n", | ||||
|        "15       en          1581953814  9.257088e+17   \n", | ||||
|        "16       en          1737878390           NaN   \n", | ||||
|        "17       en          1001999683           NaN   \n", | ||||
|        "18       en  745222369183043600           NaN   \n", | ||||
|        "19       en  798557155217539100  9.257147e+17   \n", | ||||
|        "20       en  744396039126421500  9.250629e+17   \n", | ||||
|        "21       en          2428265479           NaN   \n", | ||||
|        "22       en          2523596372           NaN   \n", | ||||
|        "23       en          2315896393           NaN   \n", | ||||
|        "24       en          2316464875           NaN   \n", | ||||
|        "25       en          2614916743           NaN   \n", | ||||
|        "26       en          2887539044           NaN   \n", | ||||
|        "27       en  721490010118205400  8.965900e+17   \n", | ||||
|        "28       en           520536723  9.257159e+17   \n", | ||||
|        "29       en  850852815941517300           NaN   \n", | ||||
|        "...     ...                 ...           ...   \n", | ||||
|        "176302   en  845085544589672400  9.256009e+17   \n", | ||||
|        "176303   en          1154786048           NaN   \n", | ||||
|        "176304   en  924752524871131100           NaN   \n", | ||||
|        "176305   en  868681065308631000           NaN   \n", | ||||
|        "176306   en           419493819           NaN   \n", | ||||
|        "176307   en          2457745952  9.256219e+17   \n", | ||||
|        "176308   en          1955767531           NaN   \n", | ||||
|        "176309   en  796490344581898200           NaN   \n", | ||||
|        "176310   en  825346617620328400           NaN   \n", | ||||
|        "176311   en  907808317124177900           NaN   \n", | ||||
|        "176312   en          1605371160           NaN   \n", | ||||
|        "176313   en           262162415           NaN   \n", | ||||
|        "176314   en           574882525           NaN   \n", | ||||
|        "176315   en          2694136560           NaN   \n", | ||||
|        "176316   en  799982767886872600           NaN   \n", | ||||
|        "176317   en           556175173  9.254038e+17   \n", | ||||
|        "176318   en  837324291637051400           NaN   \n", | ||||
|        "176319   en          1610265588           NaN   \n", | ||||
|        "176320   en          4760724450           NaN   \n", | ||||
|        "176321   en  882858115636514800           NaN   \n", | ||||
|        "176322   en           188129628           NaN   \n", | ||||
|        "176323   en          2473135939           NaN   \n", | ||||
|        "176324   en          2373584209  9.256241e+17   \n", | ||||
|        "176325   en            40709255           NaN   \n", | ||||
|        "176326   en  889503742474768400           NaN   \n", | ||||
|        "176327   en           181689756           NaN   \n", | ||||
|        "176328   en            60160788  9.254610e+17   \n", | ||||
|        "176329   en          4915042321           NaN   \n", | ||||
|        "176330   en          3792290725  9.256215e+17   \n", | ||||
|        "176331   en           612733752           NaN   \n", | ||||
|        "\n", | ||||
|        "                                                     text  \n", | ||||
|        "0               fashionbombdaily's photo  <EMOJI><EMOJI>🏼  \n", | ||||
|        "1       It’s scary how on point my horoscope be <EMOJI...  \n", | ||||
|        "2        @mvyn_: Them boring ass licks, you supposed t...  \n", | ||||
|        "3        @taehyungpic: #vmin ‘s unit shoot  <EMOJI><EM...  \n", | ||||
|        "4        @risa_del: Can I just say how much Meng respe...  \n", | ||||
|        "5        @Melodia_Muse: omg did y'all just cut off Red...  \n", | ||||
|        "6        @Harrys1DEmpire: Follow everyone who LIKES th...  \n", | ||||
|        "7        @taehyungpic: he is so smollll <EMOJI>©rocket...  \n", | ||||
|        "8                                    Woooaaaahhh <EMOJI>   \n", | ||||
|        "9        @mymermaidIagoon: <EMOJI> HURRY! For your cha...  \n", | ||||
|        "10      <EMOJI> vivalcli: Portraits by Zhao Guojing an...  \n", | ||||
|        "11       @BillRatchet: <EMOJI><EMOJI><EMOJI>NO NUT NOV...  \n", | ||||
|        "12       @mysweetapplexxx: ❤️Happy Birthday, @GoodGalC...  \n", | ||||
|        "13       @pourlui: @realDonaldTrump @SSNjl @foxandfrie...  \n", | ||||
|        "14           @hiphopphiIes i wanna know too<EMOJI><EMOJI>  \n", | ||||
|        "15            @WizMommma veda was yoda too <EMOJI><EMOJI>  \n", | ||||
|        "16       @TiagoIlori4: Me and my family are humbled by...  \n", | ||||
|        "17      I’m less stressed about turning 30 now <EMOJI>...  \n", | ||||
|        "18                                  Full charged. <EMOJI>  \n", | ||||
|        "19      @SeaDimon That’s part of the problem, (they) @...  \n", | ||||
|        "20      @Ian_khetye got me emotional there<EMOJI><EMOJ...  \n", | ||||
|        "21         @30SECONDFlGHTS: BRUHHH <EMOJI><EMOJI><EMOJI>   \n", | ||||
|        "22       @BasebaIINation: Game 7 who you got?<EMOJI> f...  \n", | ||||
|        "23       @JudicialWatch: JW says DOJ & Congress ar...  \n", | ||||
|        "24       @cssconfau: ✍🏻 <EMOJI> Ever thought about spe...  \n", | ||||
|        "25       @btspat_:  Deal for Young Forever: Night Vers...  \n", | ||||
|        "26       @DFC_SARAVANA: @dhanushkraja Reached 6 Millio...  \n", | ||||
|        "27                            back to the yellow <EMOJI>   \n", | ||||
|        "28      @Dimafadma Happy month to you and your loved o...  \n", | ||||
|        "29      Maxx and Patricia. Family hangs at For Good He...  \n", | ||||
|        "...                                                   ...  \n", | ||||
|        "176302  @peachshua1230 Awww <EMOJI> Ajsksjdjd im smili...  \n", | ||||
|        "176303   @playboinathann: MY LIL BRO ATE AN EDIBLE THI...  \n", | ||||
|        "176304  I hate when I send a text or snap n I'm so anx...  \n", | ||||
|        "176305         @LDNNOISE: Happy Halloween <EMOJI><EMOJI>   \n", | ||||
|        "176306  The answer is no I have no plans and I never l...  \n", | ||||
|        "176307          @BeachBoy_Gab LMAOOO I'm so proud <EMOJI>  \n", | ||||
|        "176308  My cousin/little sister is leaving to San Fran...  \n", | ||||
|        "176309  Can't be alone w my thoughts tonight so just g...  \n", | ||||
|        "176310                        @ohmygirlpcs: Jine <EMOJI>   \n", | ||||
|        "176311      <EMOJI><EMOJI><EMOJI><EMOJI><EMOJI> ambot!!!   \n", | ||||
|        "176312   @WestHamUtd: It wasn't the result we wanted, ...  \n", | ||||
|        "176313  <EMOJI>🏽<EMOJI>🏽 1st of the month!!Happy 1st o...  \n", | ||||
|        "176314           #WednesdayWisdom ... stay in bed <EMOJI>  \n", | ||||
|        "176315   @Brandonwoelfel: Happy Halloween friends!<EMO...  \n", | ||||
|        "176316   @carras16: Good win tonight and great to see ...  \n", | ||||
|        "176317  @Louis_Tomlinson @NiallOfficial THIS IS GOLD. ...  \n", | ||||
|        "176318   @95duet: i love them sm☹️<EMOJI><EMOJI><EMOJI...  \n", | ||||
|        "176319         <EMOJI> thank you for the kind compliment   \n", | ||||
|        "176320                        Enjoyed the silence <EMOJI>  \n", | ||||
|        "176321                   OS: Spiderman Homecoming <EMOJI>  \n", | ||||
|        "176322                            Go to hell <EMOJI>🏽♀️   \n", | ||||
|        "176323                           Thank you Yomi! <EMOJI>   \n", | ||||
|        "176324  @discopiggu Lol. Just enjoy the stars. Music K...  \n", | ||||
|        "176325   @INS_Ecosystem: We are honored to have @eyal ...  \n", | ||||
|        "176326   @EmiNiPr: I just love twitterMan's not hot <E...  \n", | ||||
|        "176327     Thoughts and prayers for NY<EMOJI>🏻 #NYCStrong  \n", | ||||
|        "176328  @BrianyH I searched COCK, PENIS, SHLONG, WINKY...  \n", | ||||
|        "176329   @eyesnoselips99: 170930 KMF  <EMOJI>☄<EMOJI> ...  \n", | ||||
|        "176330  @amitbarman520 Thank you so much<EMOJI><EMOJI>...  \n", | ||||
|        "176331   @DarrionDaDon_: Vocals ? <EMOJI>High Notes ? ...  \n", | ||||
|        "\n", | ||||
|        "[176332 rows x 7 columns]" | ||||
|       ] | ||||
|      }, | ||||
|      "execution_count": 16, | ||||
|      "metadata": {}, | ||||
|      "output_type": "execute_result" | ||||
|     } | ||||
|    ], | ||||
|    "source": [ | ||||
|     "twitter_data = pd.read_json(json_files[0])\n", | ||||
|     "twitter_data" | ||||
|    ] | ||||
|   }, | ||||
|   { | ||||
|    "cell_type": "markdown", | ||||
|    "metadata": {}, | ||||
|    "source": [ | ||||
|     "* extracting emojis and text" | ||||
|    ] | ||||
|   }, | ||||
|   { | ||||
|    "cell_type": "code", | ||||
|    "execution_count": 20, | ||||
|    "metadata": {}, | ||||
|    "outputs": [], | ||||
|    "source": [ | ||||
|     "emojis = twitter_data['EMOJI']\n", | ||||
|     "plain_text = twitter_data['text']" | ||||
|    ] | ||||
|   }, | ||||
|   { | ||||
|    "cell_type": "markdown", | ||||
|    "metadata": {}, | ||||
|    "source": [ | ||||
|     "* make our plain text more \"plain\":\n", | ||||
|     "    * removing the keyword `<EMOJI>` (just for the beginning)\n", | ||||
|     "    * removing remaining useless emojis, like skin modifier etc." | ||||
|    ] | ||||
|   }, | ||||
|   { | ||||
|    "cell_type": "code", | ||||
|    "execution_count": 21, | ||||
|    "metadata": {}, | ||||
|    "outputs": [], | ||||
|    "source": [ | ||||
|     "emoji_blacklist = set([\n", | ||||
|     "    chr(0x1F3FB),\n", | ||||
|     "    chr(0x1F3FC),\n", | ||||
|     "    chr(0x1F3FD),\n", | ||||
|     "    chr(0x1F3FE),\n", | ||||
|     "    chr(0x1F3FF),\n", | ||||
|     "    chr(0x2642),\n", | ||||
|     "    chr(0x2640)\n", | ||||
|     "])" | ||||
|    ] | ||||
|   } | ||||
|  ], | ||||
|  "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": "3.6.5" | ||||
|   } | ||||
|  }, | ||||
|  "nbformat": 4, | ||||
|  "nbformat_minor": 2 | ||||
| } | ||||
		Reference in New Issue
	
	Block a user