1805 lines
73 KiB
Plaintext
1805 lines
73 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 22,
|
||
"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\n",
|
||
"import numpy as np\n",
|
||
"import itertools\n",
|
||
"import sklearn.utils as sku\n",
|
||
"from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer, HashingVectorizer\n",
|
||
"from sklearn.model_selection import train_test_split\n",
|
||
"from sklearn.preprocessing import MultiLabelBinarizer"
|
||
]
|
||
},
|
||
{
|
||
"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": 3,
|
||
"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": 4,
|
||
"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": 5,
|
||
"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": 5,
|
||
"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": 6,
|
||
"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": 7,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# defining blacklist for modifier emojis:\n",
|
||
"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",
|
||
"])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 21,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# filtering them and the EMOJI keyword out:\n",
|
||
"plain_text = plain_text.str.replace(\"<EMOJI>\",\"\").str.replace(\"[\" + \"\".join(list(emoji_blacklist)) + \"]\",\"\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# making a set of the emoji list:\n",
|
||
"\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"* trying a multi label vectorizer"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 25,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"mlb = MultiLabelBinarizer()\n",
|
||
"\n",
|
||
"labels = mlb.fit_transform(emojis)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"* generating train and test set:"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 30,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"X1, Xt1, y1, yt1 = train_test_split(plain_text, labels, test_size=0.1, random_state=4222)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 31,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"vectorizer = TfidfVectorizer(stop_words='english')\n",
|
||
"vec_train = vectorizer.fit_transform(X1)\n",
|
||
"vec_test = vectorizer.transform(Xt1)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"* train. this can take a very long time..."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 40,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from sklearn.neural_network import MLPClassifier as MLP\n",
|
||
"from sklearn.multiclass import OneVsRestClassifier as OVRC\n",
|
||
"from sklearn.tree import DecisionTreeClassifier as DTC"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 49,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"def train():\n",
|
||
" clf = OVRC(DTC())\n",
|
||
"\n",
|
||
" clf.fit(vec_train[:10000], y1[:10000])\n",
|
||
" \n",
|
||
" return clf"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 50,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 889 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 897 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 898 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 901 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 902 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 903 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 907 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 908 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 909 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 910 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 911 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 913 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 914 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 915 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 918 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 919 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 924 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 925 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 926 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 927 is present in all training examples.\n",
|
||
" str(classes[c]))\n",
|
||
"/home/jonas/.local/lib/python3.6/site-packages/sklearn/multiclass.py:76: UserWarning: Label not 928 is present in all training examples.\n",
|
||
" str(classes[c]))\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"clf = train()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 51,
|
||
"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>predict</th>\n",
|
||
" <th>teacher</th>\n",
|
||
" <th>text</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>57624</th>\n",
|
||
" <td>(💥, 😡)</td>\n",
|
||
" <td>(💥, 😡)</td>\n",
|
||
" <td>@RealRoseTaylor1: IMO A terrorist doesn’t hav...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>58180</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(😒,)</td>\n",
|
||
" <td>@mog7546: NOT BREAKING NEWS - #KELLY's STUPID...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>122719</th>\n",
|
||
" <td>(😂, 🤦)</td>\n",
|
||
" <td>(😂, 🤦)</td>\n",
|
||
" <td>@SpecialMonroe: I’m more of like a “ yes nigg...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>132425</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(🤷,)</td>\n",
|
||
" <td>@xo_sweetttnesss Basically ️</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>95629</th>\n",
|
||
" <td>(😂,)</td>\n",
|
||
" <td>(😂,)</td>\n",
|
||
" <td>@JVino_: Never should of gave niggas technolo...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>144805</th>\n",
|
||
" <td>(😂,)</td>\n",
|
||
" <td>(🤷,)</td>\n",
|
||
" <td>@_Erickaaaaaaa: People mad iffy I’m not aroun...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>50997</th>\n",
|
||
" <td>(💕, 🛫)</td>\n",
|
||
" <td>(💕, 🛫)</td>\n",
|
||
" <td>@MURASAKI_9394: &lt;preview&gt; 171101 ICN@mt...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>52294</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(😍, 😣)</td>\n",
|
||
" <td>@JaDinePhils: Rogue x Gambit x Deadpool No cu...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>57600</th>\n",
|
||
" <td>(⚾, 😬)</td>\n",
|
||
" <td>(💙,)</td>\n",
|
||
" <td>@CailenHanzlik: So hyped watching my former t...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>12709</th>\n",
|
||
" <td>(😂,)</td>\n",
|
||
" <td>(💀,)</td>\n",
|
||
" <td>@C_eazyy @RuthlessLuke_ LMAO DED let a nigga s...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>159921</th>\n",
|
||
" <td>(😍,)</td>\n",
|
||
" <td>(👎,)</td>\n",
|
||
" <td>@ShawnHayes_Real @Mr_Ghostly @CR_Shelton @Rojo...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1297</th>\n",
|
||
" <td>(💀, 😂)</td>\n",
|
||
" <td>(💀, 😂)</td>\n",
|
||
" <td>@Ieansquad: he really solved the equation I c...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>124445</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(😩,)</td>\n",
|
||
" <td>It is really breaking my heart. Imma stick by ...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>150159</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(🐰,)</td>\n",
|
||
" <td>@jikookarchive: : aw sexy~: (jimin your cleav...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>170959</th>\n",
|
||
" <td>(✅, 🔥)</td>\n",
|
||
" <td>(✅, 🍋, 🔥)</td>\n",
|
||
" <td>@Harrys1DEmpire: 1: Like this2: Follow all th...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>46992</th>\n",
|
||
" <td>(🎬, 💋, 🔗)</td>\n",
|
||
" <td>(🎬, 💋, 🔗)</td>\n",
|
||
" <td>@ONGSEONGWU_TH: [] #WANNAONE X Innisfree | On...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>130772</th>\n",
|
||
" <td>(🎃,)</td>\n",
|
||
" <td>(🐺,)</td>\n",
|
||
" <td>@lbtreiman: Well i certainly didn't get 'em a...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>63733</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(🎃,)</td>\n",
|
||
" <td>@gamngbizzle: Follow everyone who retweets t...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>22026</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(💕, 📷)</td>\n",
|
||
" <td>@fshion_me: Love it【@perlinek】Coupon code: zo...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>109588</th>\n",
|
||
" <td>(😍, 😳)</td>\n",
|
||
" <td>(😍,)</td>\n",
|
||
" <td>@SoCuteBabies: Those eyes</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>167358</th>\n",
|
||
" <td>(🎃,)</td>\n",
|
||
" <td>(👻, 😈)</td>\n",
|
||
" <td>@Lepetit626: Happy Halloween from the cutest ...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>132276</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(💀,)</td>\n",
|
||
" <td>@marceoooo shuttup</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>150897</th>\n",
|
||
" <td>(😱, 🙈, 🙉)</td>\n",
|
||
" <td>(🔥, 😈)</td>\n",
|
||
" <td>@instaWANKtube: Drilling babe@mistersex17 @hq...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>15211</th>\n",
|
||
" <td>(🎃,)</td>\n",
|
||
" <td>(🎃,)</td>\n",
|
||
" <td>@G_Eazy: Hopped out of the millennium falcon ...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>58157</th>\n",
|
||
" <td>(⌛, 💊)</td>\n",
|
||
" <td>(⌛, 💊)</td>\n",
|
||
" <td>@NBCNewsNight: Stranger Things Neuro Upside D...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>87036</th>\n",
|
||
" <td>(🔥,)</td>\n",
|
||
" <td>(😂,)</td>\n",
|
||
" <td>I ran a lot harder back then, as well.I join v...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>68909</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(🚗,)</td>\n",
|
||
" <td>@Holy_Boost: SUMMER BOOST case GA! -Like+ ...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>70063</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(😭,)</td>\n",
|
||
" <td>I love you so much meliflua ❤️</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>53508</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(💥,)</td>\n",
|
||
" <td>@SMMmarkeing786: Get FREE CBD OIL Trial Bott...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>91590</th>\n",
|
||
" <td>(👀,)</td>\n",
|
||
" <td>(👀,)</td>\n",
|
||
" <td>@dezidoesit: Shea Moisture did not come to pl...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>...</th>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>82637</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>()</td>\n",
|
||
" <td>@KissaSins: Follow me on Instagram!!</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>151805</th>\n",
|
||
" <td>(👀,)</td>\n",
|
||
" <td>(👀,)</td>\n",
|
||
" <td>@dezidoesit: Shea Moisture did not come to pl...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>25914</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(🔘,)</td>\n",
|
||
" <td>@Heartless600904: He knows how badly he hurt ...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>91602</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(😡,)</td>\n",
|
||
" <td>@1776Stonewall @Frederick99m That's when I kne...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>16911</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(😩,)</td>\n",
|
||
" <td>Not even out of bed yet and I’m ready to get o...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>94798</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(🙃,)</td>\n",
|
||
" <td>nobody gets how lonely and hungry i get</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>112317</th>\n",
|
||
" <td>(💪,)</td>\n",
|
||
" <td>(🤗,)</td>\n",
|
||
" <td>@BIGAC_: new month, new money, new opportunit...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>72241</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(😎,)</td>\n",
|
||
" <td>@ZeeTamil: Happy birthday @iamsrk #ZeeTamil #...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>160551</th>\n",
|
||
" <td>(✨, 💪)</td>\n",
|
||
" <td>(😭,)</td>\n",
|
||
" <td>@WORLDSTARNOW: Drake looks like he entering h...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>151889</th>\n",
|
||
" <td>(👅, 😻)</td>\n",
|
||
" <td>(😍,)</td>\n",
|
||
" <td>@GenderReveaIs: The moment of truth, hoop sty...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>64998</th>\n",
|
||
" <td>(🐶, 💓)</td>\n",
|
||
" <td>(🐶, 💓)</td>\n",
|
||
" <td>@LA_Loving: Baby’s first Halloween</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>138015</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(😂,)</td>\n",
|
||
" <td>@MikeChosen1: When you got a girl who doesn't...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>84447</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(💕,)</td>\n",
|
||
" <td>@LiamPayne @pinkskiesljp @BestSimy @LiamPayne ...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>125899</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(🙏,)</td>\n",
|
||
" <td>@Oh_Ashlaay We just have to pray to the baseba...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>47898</th>\n",
|
||
" <td>(😂,)</td>\n",
|
||
" <td>(😂,)</td>\n",
|
||
" <td>@JVino_: Never should of gave niggas technolo...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>7597</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(😂,)</td>\n",
|
||
" <td>@junkiejunkrat We’re doing goooooood. But fuck...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>173305</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(🌈, 💛)</td>\n",
|
||
" <td>Ohh nice.</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>133827</th>\n",
|
||
" <td>(💙,)</td>\n",
|
||
" <td>(💙,)</td>\n",
|
||
" <td>@JenBluesnake: This is lovely. Unsworth's app...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>157487</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(💻,)</td>\n",
|
||
" <td>@yesyours: : Vehicle Magnet #VehicleMagnet 🖨</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>142977</th>\n",
|
||
" <td>(🌸, 💓)</td>\n",
|
||
" <td>(🌸, 💓)</td>\n",
|
||
" <td>@namkook_daily: they are so cosy and soft ☁</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>47506</th>\n",
|
||
" <td>(😭,)</td>\n",
|
||
" <td>(💙, 🔥)</td>\n",
|
||
" <td>@Juli_SJ13: ••••••2017 SAVED ••••••#BlackSuit</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>164518</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(😜,)</td>\n",
|
||
" <td>@marcogumabao: I hope you like your eggs SUNN...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>96549</th>\n",
|
||
" <td>(🐶, 💓)</td>\n",
|
||
" <td>(🐶, 💓)</td>\n",
|
||
" <td>@LA_Loving: Baby’s first Halloween</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>69134</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(😞, 😡)</td>\n",
|
||
" <td>Reading this @AshcroftBen with many mixed emot...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>116753</th>\n",
|
||
" <td>(💪,)</td>\n",
|
||
" <td>(🍋,)</td>\n",
|
||
" <td>@Caradelevingne: ❤️ NO_ONE EVER REALLY DIES ❤...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>125133</th>\n",
|
||
" <td>(😑,)</td>\n",
|
||
" <td>(🖤, 😉)</td>\n",
|
||
" <td>@DannyTu3250187: @Kriszti7504 @filipina_krueg...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>5081</th>\n",
|
||
" <td>(😔,)</td>\n",
|
||
" <td>(😘,)</td>\n",
|
||
" <td>@brysoxox: rt or gay</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>62088</th>\n",
|
||
" <td>()</td>\n",
|
||
" <td>(💔,)</td>\n",
|
||
" <td>Why do say that hondas are for fboys??</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>32769</th>\n",
|
||
" <td>(😂, 😘, 🙏)</td>\n",
|
||
" <td>(😁,)</td>\n",
|
||
" <td>@menggalurks: Live na ba ang EB today? #ALDU...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>92385</th>\n",
|
||
" <td>(😍,)</td>\n",
|
||
" <td>(💔,)</td>\n",
|
||
" <td>OML, WHAT HAPPENED?!!</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"<p>17634 rows × 3 columns</p>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" predict teacher \\\n",
|
||
"57624 (💥, 😡) (💥, 😡) \n",
|
||
"58180 () (😒,) \n",
|
||
"122719 (😂, 🤦) (😂, 🤦) \n",
|
||
"132425 () (🤷,) \n",
|
||
"95629 (😂,) (😂,) \n",
|
||
"144805 (😂,) (🤷,) \n",
|
||
"50997 (💕, 🛫) (💕, 🛫) \n",
|
||
"52294 () (😍, 😣) \n",
|
||
"57600 (⚾, 😬) (💙,) \n",
|
||
"12709 (😂,) (💀,) \n",
|
||
"159921 (😍,) (👎,) \n",
|
||
"1297 (💀, 😂) (💀, 😂) \n",
|
||
"124445 () (😩,) \n",
|
||
"150159 () (🐰,) \n",
|
||
"170959 (✅, 🔥) (✅, 🍋, 🔥) \n",
|
||
"46992 (🎬, 💋, 🔗) (🎬, 💋, 🔗) \n",
|
||
"130772 (🎃,) (🐺,) \n",
|
||
"63733 () (🎃,) \n",
|
||
"22026 () (💕, 📷) \n",
|
||
"109588 (😍, 😳) (😍,) \n",
|
||
"167358 (🎃,) (👻, 😈) \n",
|
||
"132276 () (💀,) \n",
|
||
"150897 (😱, 🙈, 🙉) (🔥, 😈) \n",
|
||
"15211 (🎃,) (🎃,) \n",
|
||
"58157 (⌛, 💊) (⌛, 💊) \n",
|
||
"87036 (🔥,) (😂,) \n",
|
||
"68909 () (🚗,) \n",
|
||
"70063 () (😭,) \n",
|
||
"53508 () (💥,) \n",
|
||
"91590 (👀,) (👀,) \n",
|
||
"... ... ... \n",
|
||
"82637 () () \n",
|
||
"151805 (👀,) (👀,) \n",
|
||
"25914 () (🔘,) \n",
|
||
"91602 () (😡,) \n",
|
||
"16911 () (😩,) \n",
|
||
"94798 () (🙃,) \n",
|
||
"112317 (💪,) (🤗,) \n",
|
||
"72241 () (😎,) \n",
|
||
"160551 (✨, 💪) (😭,) \n",
|
||
"151889 (👅, 😻) (😍,) \n",
|
||
"64998 (🐶, 💓) (🐶, 💓) \n",
|
||
"138015 () (😂,) \n",
|
||
"84447 () (💕,) \n",
|
||
"125899 () (🙏,) \n",
|
||
"47898 (😂,) (😂,) \n",
|
||
"7597 () (😂,) \n",
|
||
"173305 () (🌈, 💛) \n",
|
||
"133827 (💙,) (💙,) \n",
|
||
"157487 () (💻,) \n",
|
||
"142977 (🌸, 💓) (🌸, 💓) \n",
|
||
"47506 (😭,) (💙, 🔥) \n",
|
||
"164518 () (😜,) \n",
|
||
"96549 (🐶, 💓) (🐶, 💓) \n",
|
||
"69134 () (😞, 😡) \n",
|
||
"116753 (💪,) (🍋,) \n",
|
||
"125133 (😑,) (🖤, 😉) \n",
|
||
"5081 (😔,) (😘,) \n",
|
||
"62088 () (💔,) \n",
|
||
"32769 (😂, 😘, 🙏) (😁,) \n",
|
||
"92385 (😍,) (💔,) \n",
|
||
"\n",
|
||
" text \n",
|
||
"57624 @RealRoseTaylor1: IMO A terrorist doesn’t hav... \n",
|
||
"58180 @mog7546: NOT BREAKING NEWS - #KELLY's STUPID... \n",
|
||
"122719 @SpecialMonroe: I’m more of like a “ yes nigg... \n",
|
||
"132425 @xo_sweetttnesss Basically ️ \n",
|
||
"95629 @JVino_: Never should of gave niggas technolo... \n",
|
||
"144805 @_Erickaaaaaaa: People mad iffy I’m not aroun... \n",
|
||
"50997 @MURASAKI_9394: <preview> 171101 ICN@mt... \n",
|
||
"52294 @JaDinePhils: Rogue x Gambit x Deadpool No cu... \n",
|
||
"57600 @CailenHanzlik: So hyped watching my former t... \n",
|
||
"12709 @C_eazyy @RuthlessLuke_ LMAO DED let a nigga s... \n",
|
||
"159921 @ShawnHayes_Real @Mr_Ghostly @CR_Shelton @Rojo... \n",
|
||
"1297 @Ieansquad: he really solved the equation I c... \n",
|
||
"124445 It is really breaking my heart. Imma stick by ... \n",
|
||
"150159 @jikookarchive: : aw sexy~: (jimin your cleav... \n",
|
||
"170959 @Harrys1DEmpire: 1: Like this2: Follow all th... \n",
|
||
"46992 @ONGSEONGWU_TH: [] #WANNAONE X Innisfree | On... \n",
|
||
"130772 @lbtreiman: Well i certainly didn't get 'em a... \n",
|
||
"63733 @gamngbizzle: Follow everyone who retweets t... \n",
|
||
"22026 @fshion_me: Love it【@perlinek】Coupon code: zo... \n",
|
||
"109588 @SoCuteBabies: Those eyes \n",
|
||
"167358 @Lepetit626: Happy Halloween from the cutest ... \n",
|
||
"132276 @marceoooo shuttup \n",
|
||
"150897 @instaWANKtube: Drilling babe@mistersex17 @hq... \n",
|
||
"15211 @G_Eazy: Hopped out of the millennium falcon ... \n",
|
||
"58157 @NBCNewsNight: Stranger Things Neuro Upside D... \n",
|
||
"87036 I ran a lot harder back then, as well.I join v... \n",
|
||
"68909 @Holy_Boost: SUMMER BOOST case GA! -Like+ ... \n",
|
||
"70063 I love you so much meliflua ❤️ \n",
|
||
"53508 @SMMmarkeing786: Get FREE CBD OIL Trial Bott... \n",
|
||
"91590 @dezidoesit: Shea Moisture did not come to pl... \n",
|
||
"... ... \n",
|
||
"82637 @KissaSins: Follow me on Instagram!! \n",
|
||
"151805 @dezidoesit: Shea Moisture did not come to pl... \n",
|
||
"25914 @Heartless600904: He knows how badly he hurt ... \n",
|
||
"91602 @1776Stonewall @Frederick99m That's when I kne... \n",
|
||
"16911 Not even out of bed yet and I’m ready to get o... \n",
|
||
"94798 nobody gets how lonely and hungry i get \n",
|
||
"112317 @BIGAC_: new month, new money, new opportunit... \n",
|
||
"72241 @ZeeTamil: Happy birthday @iamsrk #ZeeTamil #... \n",
|
||
"160551 @WORLDSTARNOW: Drake looks like he entering h... \n",
|
||
"151889 @GenderReveaIs: The moment of truth, hoop sty... \n",
|
||
"64998 @LA_Loving: Baby’s first Halloween \n",
|
||
"138015 @MikeChosen1: When you got a girl who doesn't... \n",
|
||
"84447 @LiamPayne @pinkskiesljp @BestSimy @LiamPayne ... \n",
|
||
"125899 @Oh_Ashlaay We just have to pray to the baseba... \n",
|
||
"47898 @JVino_: Never should of gave niggas technolo... \n",
|
||
"7597 @junkiejunkrat We’re doing goooooood. But fuck... \n",
|
||
"173305 Ohh nice. \n",
|
||
"133827 @JenBluesnake: This is lovely. Unsworth's app... \n",
|
||
"157487 @yesyours: : Vehicle Magnet #VehicleMagnet 🖨 \n",
|
||
"142977 @namkook_daily: they are so cosy and soft ☁ \n",
|
||
"47506 @Juli_SJ13: ••••••2017 SAVED ••••••#BlackSuit \n",
|
||
"164518 @marcogumabao: I hope you like your eggs SUNN... \n",
|
||
"96549 @LA_Loving: Baby’s first Halloween \n",
|
||
"69134 Reading this @AshcroftBen with many mixed emot... \n",
|
||
"116753 @Caradelevingne: ❤️ NO_ONE EVER REALLY DIES ❤... \n",
|
||
"125133 @DannyTu3250187: @Kriszti7504 @filipina_krueg... \n",
|
||
"5081 @brysoxox: rt or gay \n",
|
||
"62088 Why do say that hondas are for fboys?? \n",
|
||
"32769 @menggalurks: Live na ba ang EB today? #ALDU... \n",
|
||
"92385 OML, WHAT HAPPENED?!! \n",
|
||
"\n",
|
||
"[17634 rows x 3 columns]"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"pred = clf.predict(vectorizer.transform(Xt1))\n",
|
||
"\n",
|
||
"# build a dataframe to visualize test results:\n",
|
||
"testlist = pd.DataFrame({'text': Xt1, 'teacher': mlb.inverse_transform(yt1), 'predict': mlb.inverse_transform(pred)})\n",
|
||
"\n",
|
||
"display(testlist)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 52,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"testlist.to_csv('test.csv')"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 58,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"application/vnd.jupyter.widget-view+json": {
|
||
"model_id": "1e6d156f9beb42ada3790d977beb2b7c",
|
||
"version_major": 2,
|
||
"version_minor": 0
|
||
},
|
||
"text/html": [
|
||
"<p>Failed to display Jupyter Widget of type <code>Text</code>.</p>\n",
|
||
"<p>\n",
|
||
" If you're reading this message in the Jupyter Notebook or JupyterLab Notebook, it may mean\n",
|
||
" that the widgets JavaScript is still loading. If this message persists, it\n",
|
||
" likely means that the widgets JavaScript library is either not installed or\n",
|
||
" not enabled. See the <a href=\"https://ipywidgets.readthedocs.io/en/stable/user_install.html\">Jupyter\n",
|
||
" Widgets Documentation</a> for setup instructions.\n",
|
||
"</p>\n",
|
||
"<p>\n",
|
||
" If you're reading this message in another frontend (for example, a static\n",
|
||
" rendering on GitHub or <a href=\"https://nbviewer.jupyter.org/\">NBViewer</a>),\n",
|
||
" it may mean that your frontend doesn't currently support widgets.\n",
|
||
"</p>\n"
|
||
],
|
||
"text/plain": [
|
||
"Text(value='')"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
},
|
||
{
|
||
"data": {
|
||
"application/vnd.jupyter.widget-view+json": {
|
||
"model_id": "b76a73c0fa7946f28fe91e18240484a4",
|
||
"version_major": 2,
|
||
"version_minor": 0
|
||
},
|
||
"text/html": [
|
||
"<p>Failed to display Jupyter Widget of type <code>VBox</code>.</p>\n",
|
||
"<p>\n",
|
||
" If you're reading this message in the Jupyter Notebook or JupyterLab Notebook, it may mean\n",
|
||
" that the widgets JavaScript is still loading. If this message persists, it\n",
|
||
" likely means that the widgets JavaScript library is either not installed or\n",
|
||
" not enabled. See the <a href=\"https://ipywidgets.readthedocs.io/en/stable/user_install.html\">Jupyter\n",
|
||
" Widgets Documentation</a> for setup instructions.\n",
|
||
"</p>\n",
|
||
"<p>\n",
|
||
" If you're reading this message in another frontend (for example, a static\n",
|
||
" rendering on GitHub or <a href=\"https://nbviewer.jupyter.org/\">NBViewer</a>),\n",
|
||
" it may mean that your frontend doesn't currently support widgets.\n",
|
||
"</p>\n"
|
||
],
|
||
"text/plain": [
|
||
"VBox(children=(Button(description='get smiley', icon='check', style=ButtonStyle(), tooltip='Click me'), Output()))"
|
||
]
|
||
},
|
||
"metadata": {},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"out = widgets.Output()\n",
|
||
"\n",
|
||
"t = widgets.Text()\n",
|
||
"b = widgets.Button(\n",
|
||
" description='get smiley',\n",
|
||
" disabled=False,\n",
|
||
" button_style='', # 'success', 'info', 'warning', 'danger' or ''\n",
|
||
" tooltip='Click me',\n",
|
||
" icon='check'\n",
|
||
")\n",
|
||
"\n",
|
||
"\n",
|
||
"\n",
|
||
"def handle_submit(sender):\n",
|
||
" with out:\n",
|
||
" clear_output()\n",
|
||
" with out:\n",
|
||
" display(Markdown(\"# \" + str(mlb.inverse_transform(clf.predict(vectorizer.transform([t.value])))[0])))\n",
|
||
"\n",
|
||
"b.on_click(handle_submit)\n",
|
||
" \n",
|
||
"display(t)\n",
|
||
"display(widgets.VBox([b, out])) "
|
||
]
|
||
},
|
||
{
|
||
"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": "3.6.5"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 2
|
||
}
|