├── .circleci
    └── config.yml
├── .gitignore
├── 01_data_cleaning.ipynb
├── 02_data_cleaning.ipynb
├── 03_depression_detector.ipynb
├── README.md
└── config.yml


/.circleci/config.yml:
--------------------------------------------------------------------------------
 1 | # Use the latest 2.1 version of CircleCI pipeline process engine. See: https://circleci.com/docs/2.0/configuration-reference
 2 | version: 2.1
 3 | # Use a package of configuration called an orb.
 4 | orbs:
 5 |   # Declare a dependency on the welcome-orb
 6 |   welcome: circleci/welcome-orb@0.4.1
 7 | # Orchestrate or schedule a set of jobs
 8 | workflows:
 9 |   # Name the workflow "welcome"
10 |   welcome:
11 |     # Run the welcome/run job in its own container
12 |     jobs:
13 |       - welcome/run
14 | 


--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
  1 | # Byte-compiled / optimized / DLL files
  2 | __pycache__/
  3 | *.py[cod]
  4 | *$py.class
  5 | 
  6 | # C extensions
  7 | *.so
  8 | 
  9 | # Distribution / packaging
 10 | .Python
 11 | build/
 12 | develop-eggs/
 13 | dist/
 14 | downloads/
 15 | eggs/
 16 | .eggs/
 17 | lib/
 18 | lib64/
 19 | parts/
 20 | sdist/
 21 | var/
 22 | wheels/
 23 | pip-wheel-metadata/
 24 | share/python-wheels/
 25 | *.egg-info/
 26 | .installed.cfg
 27 | *.egg
 28 | MANIFEST
 29 | 
 30 | # PyInstaller
 31 | #  Usually these files are written by a python script from a template
 32 | #  before PyInstaller builds the exe, so as to inject date/other infos into it.
 33 | *.manifest
 34 | *.spec
 35 | 
 36 | # Installer logs
 37 | pip-log.txt
 38 | pip-delete-this-directory.txt
 39 | 
 40 | # Unit test / coverage reports
 41 | htmlcov/
 42 | .tox/
 43 | .nox/
 44 | .coverage
 45 | .coverage.*
 46 | .cache
 47 | nosetests.xml
 48 | coverage.xml
 49 | *.cover
 50 | *.py,cover
 51 | .hypothesis/
 52 | .pytest_cache/
 53 | 
 54 | # Translations
 55 | *.mo
 56 | *.pot
 57 | 
 58 | # Django stuff:
 59 | *.log
 60 | local_settings.py
 61 | db.sqlite3
 62 | db.sqlite3-journal
 63 | 
 64 | # Flask stuff:
 65 | instance/
 66 | .webassets-cache
 67 | 
 68 | # Scrapy stuff:
 69 | .scrapy
 70 | 
 71 | # Sphinx documentation
 72 | docs/_build/
 73 | 
 74 | # PyBuilder
 75 | target/
 76 | 
 77 | # Jupyter Notebook
 78 | .ipynb_checkpoints
 79 | 
 80 | # IPython
 81 | profile_default/
 82 | ipython_config.py
 83 | 
 84 | # pyenv
 85 | .python-version
 86 | 
 87 | # pipenv
 88 | #   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
 89 | #   However, in case of collaboration, if having platform-specific dependencies or dependencies
 90 | #   having no cross-platform support, pipenv may install dependencies that don't work, or not
 91 | #   install all needed dependencies.
 92 | #Pipfile.lock
 93 | 
 94 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow
 95 | __pypackages__/
 96 | 
 97 | # Celery stuff
 98 | celerybeat-schedule
 99 | celerybeat.pid
100 | 
101 | # SageMath parsed files
102 | *.sage.py
103 | 
104 | # Environments
105 | .env
106 | .venv
107 | env/
108 | venv/
109 | ENV/
110 | env.bak/
111 | venv.bak/
112 | 
113 | # Spyder project settings
114 | .spyderproject
115 | .spyproject
116 | 
117 | # Rope project settings
118 | .ropeproject
119 | 
120 | # mkdocs documentation
121 | /site
122 | 
123 | # mypy
124 | .mypy_cache/
125 | .dmypy.json
126 | dmypy.json
127 | 
128 | # Pyre type checker
129 | .pyre/
130 | 


--------------------------------------------------------------------------------
/01_data_cleaning.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "code",
   5 |    "execution_count": 1,
   6 |    "metadata": {},
   7 |    "outputs": [],
   8 |    "source": [
   9 |     "import pandas as pd\n",
  10 |     "import numpy as np\n",
  11 |     "\n",
  12 |     "import pandas as pd  \n",
  13 |     "import numpy as np\n",
  14 |     "import matplotlib.pyplot as plt\n",
  15 |     "plt.style.use('fivethirtyeight')\n",
  16 |     "\n",
  17 |     "%matplotlib inline\n",
  18 |     "%config InlineBackend.figure_format = 'retina'\n",
  19 |     "import re\n",
  20 |     "from bs4 import BeautifulSoup\n",
  21 |     "from nltk.tokenize import WordPunctTokenizer\n",
  22 |     "tok = WordPunctTokenizer()"
  23 |    ]
  24 |   },
  25 |   {
  26 |    "cell_type": "code",
  27 |    "execution_count": 2,
  28 |    "metadata": {},
  29 |    "outputs": [],
  30 |    "source": [
  31 |     "depressive_tweets_df = pd.read_csv('depression/depressive_unigram_tweets.csv')"
  32 |    ]
  33 |   },
  34 |   {
  35 |    "cell_type": "code",
  36 |    "execution_count": 3,
  37 |    "metadata": {},
  38 |    "outputs": [
  39 |     {
  40 |      "output_type": "execute_result",
  41 |      "data": {
  42 |       "text/plain": [
  43 |        "  Unnamed: 0           id      time  \\\n",
  44 |        "0          0  1.15135E+18  21:25:13   \n",
  45 |        "1          1  1.15135E+18  21:25:07   \n",
  46 |        "2          2  1.15135E+18  21:25:06   \n",
  47 |        "3          3  1.15135E+18  21:24:55   \n",
  48 |        "4          4  1.15135E+18  21:24:51   \n",
  49 |        "\n",
  50 |        "                                               tweet  \\\n",
  51 |        "0  Wow, my dad yday: “you don’t take those stupid...   \n",
  52 |        "1  what part of this was really harmfult of a lot...   \n",
  53 |        "2  one of the ways I got through my #depression i...   \n",
  54 |        "3  see i wanna do one of them but they all say th...   \n",
  55 |        "4  IS IT clinical depression or is it the palpabl...   \n",
  56 |        "\n",
  57 |        "                                            hashtags cashtags  \n",
  58 |        "0                                                 []       []  \n",
  59 |        "1                                                 []       []  \n",
  60 |        "2  ['#depression', '#uncoveringthenewu', '#change...       []  \n",
  61 |        "3                                                 []       []  \n",
  62 |        "4                                                 []       []  "
  63 |       ],
  64 |       "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>Unnamed: 0</th>\n      <th>id</th>\n      <th>time</th>\n      <th>tweet</th>\n      <th>hashtags</th>\n      <th>cashtags</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>0</td>\n      <td>1.15135E+18</td>\n      <td>21:25:13</td>\n      <td>Wow, my dad yday: “you don’t take those stupid...</td>\n      <td>[]</td>\n      <td>[]</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>1</td>\n      <td>1.15135E+18</td>\n      <td>21:25:07</td>\n      <td>what part of this was really harmfult of a lot...</td>\n      <td>[]</td>\n      <td>[]</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>2</td>\n      <td>1.15135E+18</td>\n      <td>21:25:06</td>\n      <td>one of the ways I got through my #depression i...</td>\n      <td>['#depression', '#uncoveringthenewu', '#change...</td>\n      <td>[]</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>3</td>\n      <td>1.15135E+18</td>\n      <td>21:24:55</td>\n      <td>see i wanna do one of them but they all say th...</td>\n      <td>[]</td>\n      <td>[]</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>4</td>\n      <td>1.15135E+18</td>\n      <td>21:24:51</td>\n      <td>IS IT clinical depression or is it the palpabl...</td>\n      <td>[]</td>\n      <td>[]</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
  65 |      },
  66 |      "metadata": {},
  67 |      "execution_count": 3
  68 |     }
  69 |    ],
  70 |    "source": [
  71 |     "depressive_tweets_df.head()"
  72 |    ]
  73 |   },
  74 |   {
  75 |    "cell_type": "code",
  76 |    "execution_count": null,
  77 |    "metadata": {},
  78 |    "outputs": [],
  79 |    "source": [
  80 |     "#depression_tweets_df = pd.read_csv('depression/depressive_unigram_tweets.csv')"
  81 |    ]
  82 |   },
  83 |   {
  84 |    "cell_type": "code",
  85 |    "execution_count": 4,
  86 |    "metadata": {},
  87 |    "outputs": [
  88 |     {
  89 |      "data": {
  90 |       "text/html": [
  91 |        "<div>\n",
  92 |        "<style scoped>\n",
  93 |        "    .dataframe tbody tr th:only-of-type {\n",
  94 |        "        vertical-align: middle;\n",
  95 |        "    }\n",
  96 |        "\n",
  97 |        "    .dataframe tbody tr th {\n",
  98 |        "        vertical-align: top;\n",
  99 |        "    }\n",
 100 |        "\n",
 101 |        "    .dataframe thead th {\n",
 102 |        "        text-align: right;\n",
 103 |        "    }\n",
 104 |        "</style>\n",
 105 |        "<table border=\"1\" class=\"dataframe\">\n",
 106 |        "  <thead>\n",
 107 |        "    <tr style=\"text-align: right;\">\n",
 108 |        "      <th></th>\n",
 109 |        "      <th>id</th>\n",
 110 |        "      <th>conversation_id</th>\n",
 111 |        "      <th>created_at</th>\n",
 112 |        "      <th>date</th>\n",
 113 |        "      <th>time</th>\n",
 114 |        "      <th>timezone</th>\n",
 115 |        "      <th>user_id</th>\n",
 116 |        "      <th>username</th>\n",
 117 |        "      <th>name</th>\n",
 118 |        "      <th>place</th>\n",
 119 |        "      <th>...</th>\n",
 120 |        "      <th>likes_count</th>\n",
 121 |        "      <th>hashtags</th>\n",
 122 |        "      <th>cashtags</th>\n",
 123 |        "      <th>link</th>\n",
 124 |        "      <th>retweet</th>\n",
 125 |        "      <th>quote_url</th>\n",
 126 |        "      <th>video</th>\n",
 127 |        "      <th>user_rt_id</th>\n",
 128 |        "      <th>near</th>\n",
 129 |        "      <th>geo</th>\n",
 130 |        "    </tr>\n",
 131 |        "  </thead>\n",
 132 |        "  <tbody>\n",
 133 |        "    <tr>\n",
 134 |        "      <th>0</th>\n",
 135 |        "      <td>1151347096966041603</td>\n",
 136 |        "      <td>1151347096966041603</td>\n",
 137 |        "      <td>1563337513000</td>\n",
 138 |        "      <td>2019-07-16</td>\n",
 139 |        "      <td>21:25:13</td>\n",
 140 |        "      <td>PDT</td>\n",
 141 |        "      <td>68141680</td>\n",
 142 |        "      <td>paulsonmyheart</td>\n",
 143 |        "      <td>wit ☾ h♥️</td>\n",
 144 |        "      <td>NaN</td>\n",
 145 |        "      <td>...</td>\n",
 146 |        "      <td>0</td>\n",
 147 |        "      <td>[]</td>\n",
 148 |        "      <td>[]</td>\n",
 149 |        "      <td>https://twitter.com/PaulsonMyHeart/status/1151...</td>\n",
 150 |        "      <td>NaN</td>\n",
 151 |        "      <td>NaN</td>\n",
 152 |        "      <td>0</td>\n",
 153 |        "      <td>NaN</td>\n",
 154 |        "      <td>NaN</td>\n",
 155 |        "      <td>NaN</td>\n",
 156 |        "    </tr>\n",
 157 |        "    <tr>\n",
 158 |        "      <th>1</th>\n",
 159 |        "      <td>1151347069627576320</td>\n",
 160 |        "      <td>1150980638247231489</td>\n",
 161 |        "      <td>1563337507000</td>\n",
 162 |        "      <td>2019-07-16</td>\n",
 163 |        "      <td>21:25:07</td>\n",
 164 |        "      <td>PDT</td>\n",
 165 |        "      <td>1125157678957907970</td>\n",
 166 |        "      <td>gaymiyas</td>\n",
 167 |        "      <td>robin</td>\n",
 168 |        "      <td>NaN</td>\n",
 169 |        "      <td>...</td>\n",
 170 |        "      <td>0</td>\n",
 171 |        "      <td>[]</td>\n",
 172 |        "      <td>[]</td>\n",
 173 |        "      <td>https://twitter.com/gaymiyas/status/1151347069...</td>\n",
 174 |        "      <td>NaN</td>\n",
 175 |        "      <td>NaN</td>\n",
 176 |        "      <td>0</td>\n",
 177 |        "      <td>NaN</td>\n",
 178 |        "      <td>NaN</td>\n",
 179 |        "      <td>NaN</td>\n",
 180 |        "    </tr>\n",
 181 |        "    <tr>\n",
 182 |        "      <th>2</th>\n",
 183 |        "      <td>1151347066255396865</td>\n",
 184 |        "      <td>1151347066255396865</td>\n",
 185 |        "      <td>1563337506000</td>\n",
 186 |        "      <td>2019-07-16</td>\n",
 187 |        "      <td>21:25:06</td>\n",
 188 |        "      <td>PDT</td>\n",
 189 |        "      <td>988965488918253568</td>\n",
 190 |        "      <td>authornesiewing</td>\n",
 191 |        "      <td>Author Nesi Ewing</td>\n",
 192 |        "      <td>NaN</td>\n",
 193 |        "      <td>...</td>\n",
 194 |        "      <td>0</td>\n",
 195 |        "      <td>['#depression', '#uncoveringthenewu', '#change...</td>\n",
 196 |        "      <td>[]</td>\n",
 197 |        "      <td>https://twitter.com/AuthorNesiEwing/status/115...</td>\n",
 198 |        "      <td>NaN</td>\n",
 199 |        "      <td>NaN</td>\n",
 200 |        "      <td>0</td>\n",
 201 |        "      <td>NaN</td>\n",
 202 |        "      <td>NaN</td>\n",
 203 |        "      <td>NaN</td>\n",
 204 |        "    </tr>\n",
 205 |        "    <tr>\n",
 206 |        "      <th>3</th>\n",
 207 |        "      <td>1151347022789611520</td>\n",
 208 |        "      <td>1151343977267892225</td>\n",
 209 |        "      <td>1563337495000</td>\n",
 210 |        "      <td>2019-07-16</td>\n",
 211 |        "      <td>21:24:55</td>\n",
 212 |        "      <td>PDT</td>\n",
 213 |        "      <td>794267753179992064</td>\n",
 214 |        "      <td>sebsmish</td>\n",
 215 |        "      <td>andaluna 🌙</td>\n",
 216 |        "      <td>NaN</td>\n",
 217 |        "      <td>...</td>\n",
 218 |        "      <td>0</td>\n",
 219 |        "      <td>[]</td>\n",
 220 |        "      <td>[]</td>\n",
 221 |        "      <td>https://twitter.com/sebsmish/status/1151347022...</td>\n",
 222 |        "      <td>NaN</td>\n",
 223 |        "      <td>NaN</td>\n",
 224 |        "      <td>0</td>\n",
 225 |        "      <td>NaN</td>\n",
 226 |        "      <td>NaN</td>\n",
 227 |        "      <td>NaN</td>\n",
 228 |        "    </tr>\n",
 229 |        "    <tr>\n",
 230 |        "      <th>4</th>\n",
 231 |        "      <td>1151347006406893568</td>\n",
 232 |        "      <td>1151347006406893568</td>\n",
 233 |        "      <td>1563337491000</td>\n",
 234 |        "      <td>2019-07-16</td>\n",
 235 |        "      <td>21:24:51</td>\n",
 236 |        "      <td>PDT</td>\n",
 237 |        "      <td>1121246242401660928</td>\n",
 238 |        "      <td>gbrrants</td>\n",
 239 |        "      <td>femme brulee 2</td>\n",
 240 |        "      <td>NaN</td>\n",
 241 |        "      <td>...</td>\n",
 242 |        "      <td>0</td>\n",
 243 |        "      <td>[]</td>\n",
 244 |        "      <td>[]</td>\n",
 245 |        "      <td>https://twitter.com/gbrrants/status/1151347006...</td>\n",
 246 |        "      <td>NaN</td>\n",
 247 |        "      <td>NaN</td>\n",
 248 |        "      <td>0</td>\n",
 249 |        "      <td>NaN</td>\n",
 250 |        "      <td>NaN</td>\n",
 251 |        "      <td>NaN</td>\n",
 252 |        "    </tr>\n",
 253 |        "  </tbody>\n",
 254 |        "</table>\n",
 255 |        "<p>5 rows × 26 columns</p>\n",
 256 |        "</div>"
 257 |       ],
 258 |       "text/plain": [
 259 |        "                    id      conversation_id     created_at        date  \\\n",
 260 |        "0  1151347096966041603  1151347096966041603  1563337513000  2019-07-16   \n",
 261 |        "1  1151347069627576320  1150980638247231489  1563337507000  2019-07-16   \n",
 262 |        "2  1151347066255396865  1151347066255396865  1563337506000  2019-07-16   \n",
 263 |        "3  1151347022789611520  1151343977267892225  1563337495000  2019-07-16   \n",
 264 |        "4  1151347006406893568  1151347006406893568  1563337491000  2019-07-16   \n",
 265 |        "\n",
 266 |        "       time timezone              user_id         username               name  \\\n",
 267 |        "0  21:25:13      PDT             68141680   paulsonmyheart          wit ☾ h♥️   \n",
 268 |        "1  21:25:07      PDT  1125157678957907970         gaymiyas              robin   \n",
 269 |        "2  21:25:06      PDT   988965488918253568  authornesiewing  Author Nesi Ewing   \n",
 270 |        "3  21:24:55      PDT   794267753179992064         sebsmish         andaluna 🌙   \n",
 271 |        "4  21:24:51      PDT  1121246242401660928         gbrrants     femme brulee 2   \n",
 272 |        "\n",
 273 |        "  place  ... likes_count                                           hashtags  \\\n",
 274 |        "0   NaN  ...           0                                                 []   \n",
 275 |        "1   NaN  ...           0                                                 []   \n",
 276 |        "2   NaN  ...           0  ['#depression', '#uncoveringthenewu', '#change...   \n",
 277 |        "3   NaN  ...           0                                                 []   \n",
 278 |        "4   NaN  ...           0                                                 []   \n",
 279 |        "\n",
 280 |        "  cashtags                                               link  retweet  \\\n",
 281 |        "0       []  https://twitter.com/PaulsonMyHeart/status/1151...      NaN   \n",
 282 |        "1       []  https://twitter.com/gaymiyas/status/1151347069...      NaN   \n",
 283 |        "2       []  https://twitter.com/AuthorNesiEwing/status/115...      NaN   \n",
 284 |        "3       []  https://twitter.com/sebsmish/status/1151347022...      NaN   \n",
 285 |        "4       []  https://twitter.com/gbrrants/status/1151347006...      NaN   \n",
 286 |        "\n",
 287 |        "   quote_url  video user_rt_id near geo  \n",
 288 |        "0        NaN      0        NaN  NaN NaN  \n",
 289 |        "1        NaN      0        NaN  NaN NaN  \n",
 290 |        "2        NaN      0        NaN  NaN NaN  \n",
 291 |        "3        NaN      0        NaN  NaN NaN  \n",
 292 |        "4        NaN      0        NaN  NaN NaN  \n",
 293 |        "\n",
 294 |        "[5 rows x 26 columns]"
 295 |       ]
 296 |      },
 297 |      "execution_count": 4,
 298 |      "metadata": {},
 299 |      "output_type": "execute_result"
 300 |     }
 301 |    ],
 302 |    "source": [
 303 |     "#depression_tweets_df.head()"
 304 |    ]
 305 |   },
 306 |   {
 307 |    "cell_type": "code",
 308 |    "execution_count": 6,
 309 |    "metadata": {},
 310 |    "outputs": [],
 311 |    "source": [
 312 |     "#depression_tweets_df.drop(['date', 'timezone', 'username', 'name', 'conversation_id', 'created_at', 'user_id', 'place', 'likes_count', 'link', 'retweet', 'quote_url', 'video', 'user_rt_id', 'near', 'geo', 'mentions', 'urls', 'photos', 'replies_count', 'retweets_count'], axis = 1, inplace = True)"
 313 |    ]
 314 |   },
 315 |   {
 316 |    "cell_type": "code",
 317 |    "execution_count": 7,
 318 |    "metadata": {},
 319 |    "outputs": [
 320 |     {
 321 |      "data": {
 322 |       "text/html": [
 323 |        "<div>\n",
 324 |        "<style scoped>\n",
 325 |        "    .dataframe tbody tr th:only-of-type {\n",
 326 |        "        vertical-align: middle;\n",
 327 |        "    }\n",
 328 |        "\n",
 329 |        "    .dataframe tbody tr th {\n",
 330 |        "        vertical-align: top;\n",
 331 |        "    }\n",
 332 |        "\n",
 333 |        "    .dataframe thead th {\n",
 334 |        "        text-align: right;\n",
 335 |        "    }\n",
 336 |        "</style>\n",
 337 |        "<table border=\"1\" class=\"dataframe\">\n",
 338 |        "  <thead>\n",
 339 |        "    <tr style=\"text-align: right;\">\n",
 340 |        "      <th></th>\n",
 341 |        "      <th>id</th>\n",
 342 |        "      <th>time</th>\n",
 343 |        "      <th>tweet</th>\n",
 344 |        "      <th>hashtags</th>\n",
 345 |        "      <th>cashtags</th>\n",
 346 |        "    </tr>\n",
 347 |        "  </thead>\n",
 348 |        "  <tbody>\n",
 349 |        "    <tr>\n",
 350 |        "      <th>0</th>\n",
 351 |        "      <td>1151347096966041603</td>\n",
 352 |        "      <td>21:25:13</td>\n",
 353 |        "      <td>Wow, my dad yday: “you don’t take those stupid...</td>\n",
 354 |        "      <td>[]</td>\n",
 355 |        "      <td>[]</td>\n",
 356 |        "    </tr>\n",
 357 |        "    <tr>\n",
 358 |        "      <th>1</th>\n",
 359 |        "      <td>1151347069627576320</td>\n",
 360 |        "      <td>21:25:07</td>\n",
 361 |        "      <td>what part of this was really harmfult of a lot...</td>\n",
 362 |        "      <td>[]</td>\n",
 363 |        "      <td>[]</td>\n",
 364 |        "    </tr>\n",
 365 |        "    <tr>\n",
 366 |        "      <th>2</th>\n",
 367 |        "      <td>1151347066255396865</td>\n",
 368 |        "      <td>21:25:06</td>\n",
 369 |        "      <td>one of the ways I got through my #depression i...</td>\n",
 370 |        "      <td>['#depression', '#uncoveringthenewu', '#change...</td>\n",
 371 |        "      <td>[]</td>\n",
 372 |        "    </tr>\n",
 373 |        "    <tr>\n",
 374 |        "      <th>3</th>\n",
 375 |        "      <td>1151347022789611520</td>\n",
 376 |        "      <td>21:24:55</td>\n",
 377 |        "      <td>see i wanna do one of them but they all say th...</td>\n",
 378 |        "      <td>[]</td>\n",
 379 |        "      <td>[]</td>\n",
 380 |        "    </tr>\n",
 381 |        "    <tr>\n",
 382 |        "      <th>4</th>\n",
 383 |        "      <td>1151347006406893568</td>\n",
 384 |        "      <td>21:24:51</td>\n",
 385 |        "      <td>IS IT clinical depression or is it the palpabl...</td>\n",
 386 |        "      <td>[]</td>\n",
 387 |        "      <td>[]</td>\n",
 388 |        "    </tr>\n",
 389 |        "  </tbody>\n",
 390 |        "</table>\n",
 391 |        "</div>"
 392 |       ],
 393 |       "text/plain": [
 394 |        "                    id      time  \\\n",
 395 |        "0  1151347096966041603  21:25:13   \n",
 396 |        "1  1151347069627576320  21:25:07   \n",
 397 |        "2  1151347066255396865  21:25:06   \n",
 398 |        "3  1151347022789611520  21:24:55   \n",
 399 |        "4  1151347006406893568  21:24:51   \n",
 400 |        "\n",
 401 |        "                                               tweet  \\\n",
 402 |        "0  Wow, my dad yday: “you don’t take those stupid...   \n",
 403 |        "1  what part of this was really harmfult of a lot...   \n",
 404 |        "2  one of the ways I got through my #depression i...   \n",
 405 |        "3  see i wanna do one of them but they all say th...   \n",
 406 |        "4  IS IT clinical depression or is it the palpabl...   \n",
 407 |        "\n",
 408 |        "                                            hashtags cashtags  \n",
 409 |        "0                                                 []       []  \n",
 410 |        "1                                                 []       []  \n",
 411 |        "2  ['#depression', '#uncoveringthenewu', '#change...       []  \n",
 412 |        "3                                                 []       []  \n",
 413 |        "4                                                 []       []  "
 414 |       ]
 415 |      },
 416 |      "execution_count": 7,
 417 |      "metadata": {},
 418 |      "output_type": "execute_result"
 419 |     }
 420 |    ],
 421 |    "source": [
 422 |     "#depression_tweets_df.head()"
 423 |    ]
 424 |   },
 425 |   {
 426 |    "cell_type": "code",
 427 |    "execution_count": null,
 428 |    "metadata": {},
 429 |    "outputs": [],
 430 |    "source": []
 431 |   },
 432 |   {
 433 |    "cell_type": "code",
 434 |    "execution_count": 8,
 435 |    "metadata": {},
 436 |    "outputs": [],
 437 |    "source": [
 438 |     "#depressed_tweets_df = pd.read_csv('depressed/tweets.csv')"
 439 |    ]
 440 |   },
 441 |   {
 442 |    "cell_type": "code",
 443 |    "execution_count": 9,
 444 |    "metadata": {},
 445 |    "outputs": [
 446 |     {
 447 |      "data": {
 448 |       "text/html": [
 449 |        "<div>\n",
 450 |        "<style scoped>\n",
 451 |        "    .dataframe tbody tr th:only-of-type {\n",
 452 |        "        vertical-align: middle;\n",
 453 |        "    }\n",
 454 |        "\n",
 455 |        "    .dataframe tbody tr th {\n",
 456 |        "        vertical-align: top;\n",
 457 |        "    }\n",
 458 |        "\n",
 459 |        "    .dataframe thead th {\n",
 460 |        "        text-align: right;\n",
 461 |        "    }\n",
 462 |        "</style>\n",
 463 |        "<table border=\"1\" class=\"dataframe\">\n",
 464 |        "  <thead>\n",
 465 |        "    <tr style=\"text-align: right;\">\n",
 466 |        "      <th></th>\n",
 467 |        "      <th>id</th>\n",
 468 |        "      <th>conversation_id</th>\n",
 469 |        "      <th>created_at</th>\n",
 470 |        "      <th>date</th>\n",
 471 |        "      <th>time</th>\n",
 472 |        "      <th>timezone</th>\n",
 473 |        "      <th>user_id</th>\n",
 474 |        "      <th>username</th>\n",
 475 |        "      <th>name</th>\n",
 476 |        "      <th>place</th>\n",
 477 |        "      <th>...</th>\n",
 478 |        "      <th>likes_count</th>\n",
 479 |        "      <th>hashtags</th>\n",
 480 |        "      <th>cashtags</th>\n",
 481 |        "      <th>link</th>\n",
 482 |        "      <th>retweet</th>\n",
 483 |        "      <th>quote_url</th>\n",
 484 |        "      <th>video</th>\n",
 485 |        "      <th>user_rt_id</th>\n",
 486 |        "      <th>near</th>\n",
 487 |        "      <th>geo</th>\n",
 488 |        "    </tr>\n",
 489 |        "  </thead>\n",
 490 |        "  <tbody>\n",
 491 |        "    <tr>\n",
 492 |        "      <th>0</th>\n",
 493 |        "      <td>1151315262748205057</td>\n",
 494 |        "      <td>1151313086525116421</td>\n",
 495 |        "      <td>1563329923000</td>\n",
 496 |        "      <td>2019-07-16</td>\n",
 497 |        "      <td>19:18:43</td>\n",
 498 |        "      <td>PDT</td>\n",
 499 |        "      <td>930813312786366464</td>\n",
 500 |        "      <td>keytodepress</td>\n",
 501 |        "      <td>Cupid</td>\n",
 502 |        "      <td>NaN</td>\n",
 503 |        "      <td>...</td>\n",
 504 |        "      <td>0</td>\n",
 505 |        "      <td>[]</td>\n",
 506 |        "      <td>[]</td>\n",
 507 |        "      <td>https://twitter.com/KeytoDepress/status/115131...</td>\n",
 508 |        "      <td>NaN</td>\n",
 509 |        "      <td>NaN</td>\n",
 510 |        "      <td>0</td>\n",
 511 |        "      <td>NaN</td>\n",
 512 |        "      <td>NaN</td>\n",
 513 |        "      <td>NaN</td>\n",
 514 |        "    </tr>\n",
 515 |        "    <tr>\n",
 516 |        "      <th>1</th>\n",
 517 |        "      <td>1151315254615400448</td>\n",
 518 |        "      <td>1151314716091985920</td>\n",
 519 |        "      <td>1563329921000</td>\n",
 520 |        "      <td>2019-07-16</td>\n",
 521 |        "      <td>19:18:41</td>\n",
 522 |        "      <td>PDT</td>\n",
 523 |        "      <td>771371705063370752</td>\n",
 524 |        "      <td>_ron_247</td>\n",
 525 |        "      <td>MCKAY SEASON SZN (52-39)</td>\n",
 526 |        "      <td>NaN</td>\n",
 527 |        "      <td>...</td>\n",
 528 |        "      <td>0</td>\n",
 529 |        "      <td>[]</td>\n",
 530 |        "      <td>[]</td>\n",
 531 |        "      <td>https://twitter.com/_ron_247/status/1151315254...</td>\n",
 532 |        "      <td>NaN</td>\n",
 533 |        "      <td>NaN</td>\n",
 534 |        "      <td>0</td>\n",
 535 |        "      <td>NaN</td>\n",
 536 |        "      <td>NaN</td>\n",
 537 |        "      <td>NaN</td>\n",
 538 |        "    </tr>\n",
 539 |        "    <tr>\n",
 540 |        "      <th>2</th>\n",
 541 |        "      <td>1151315222692429825</td>\n",
 542 |        "      <td>1151315222692429825</td>\n",
 543 |        "      <td>1563329914000</td>\n",
 544 |        "      <td>2019-07-16</td>\n",
 545 |        "      <td>19:18:34</td>\n",
 546 |        "      <td>PDT</td>\n",
 547 |        "      <td>1020503873369194496</td>\n",
 548 |        "      <td>jan550n</td>\n",
 549 |        "      <td>elizabeth</td>\n",
 550 |        "      <td>NaN</td>\n",
 551 |        "      <td>...</td>\n",
 552 |        "      <td>0</td>\n",
 553 |        "      <td>[]</td>\n",
 554 |        "      <td>[]</td>\n",
 555 |        "      <td>https://twitter.com/jan550n/status/11513152226...</td>\n",
 556 |        "      <td>NaN</td>\n",
 557 |        "      <td>NaN</td>\n",
 558 |        "      <td>0</td>\n",
 559 |        "      <td>NaN</td>\n",
 560 |        "      <td>NaN</td>\n",
 561 |        "      <td>NaN</td>\n",
 562 |        "    </tr>\n",
 563 |        "    <tr>\n",
 564 |        "      <th>3</th>\n",
 565 |        "      <td>1151315218011549696</td>\n",
 566 |        "      <td>1151315218011549696</td>\n",
 567 |        "      <td>1563329913000</td>\n",
 568 |        "      <td>2019-07-16</td>\n",
 569 |        "      <td>19:18:33</td>\n",
 570 |        "      <td>PDT</td>\n",
 571 |        "      <td>2812237658</td>\n",
 572 |        "      <td>ran_engbot</td>\n",
 573 |        "      <td>Ran Yakumo</td>\n",
 574 |        "      <td>NaN</td>\n",
 575 |        "      <td>...</td>\n",
 576 |        "      <td>0</td>\n",
 577 |        "      <td>[]</td>\n",
 578 |        "      <td>[]</td>\n",
 579 |        "      <td>https://twitter.com/ran_engbot/status/11513152...</td>\n",
 580 |        "      <td>NaN</td>\n",
 581 |        "      <td>NaN</td>\n",
 582 |        "      <td>0</td>\n",
 583 |        "      <td>NaN</td>\n",
 584 |        "      <td>NaN</td>\n",
 585 |        "      <td>NaN</td>\n",
 586 |        "    </tr>\n",
 587 |        "    <tr>\n",
 588 |        "      <th>4</th>\n",
 589 |        "      <td>1151315209413386240</td>\n",
 590 |        "      <td>1151315209413386240</td>\n",
 591 |        "      <td>1563329910000</td>\n",
 592 |        "      <td>2019-07-16</td>\n",
 593 |        "      <td>19:18:30</td>\n",
 594 |        "      <td>PDT</td>\n",
 595 |        "      <td>4833251469</td>\n",
 596 |        "      <td>sasstelligence</td>\n",
 597 |        "      <td>Stressed, Depressed Espressos</td>\n",
 598 |        "      <td>NaN</td>\n",
 599 |        "      <td>...</td>\n",
 600 |        "      <td>1</td>\n",
 601 |        "      <td>[]</td>\n",
 602 |        "      <td>[]</td>\n",
 603 |        "      <td>https://twitter.com/Sasstelligence/status/1151...</td>\n",
 604 |        "      <td>NaN</td>\n",
 605 |        "      <td>NaN</td>\n",
 606 |        "      <td>0</td>\n",
 607 |        "      <td>NaN</td>\n",
 608 |        "      <td>NaN</td>\n",
 609 |        "      <td>NaN</td>\n",
 610 |        "    </tr>\n",
 611 |        "  </tbody>\n",
 612 |        "</table>\n",
 613 |        "<p>5 rows × 26 columns</p>\n",
 614 |        "</div>"
 615 |       ],
 616 |       "text/plain": [
 617 |        "                    id      conversation_id     created_at        date  \\\n",
 618 |        "0  1151315262748205057  1151313086525116421  1563329923000  2019-07-16   \n",
 619 |        "1  1151315254615400448  1151314716091985920  1563329921000  2019-07-16   \n",
 620 |        "2  1151315222692429825  1151315222692429825  1563329914000  2019-07-16   \n",
 621 |        "3  1151315218011549696  1151315218011549696  1563329913000  2019-07-16   \n",
 622 |        "4  1151315209413386240  1151315209413386240  1563329910000  2019-07-16   \n",
 623 |        "\n",
 624 |        "       time timezone              user_id        username  \\\n",
 625 |        "0  19:18:43      PDT   930813312786366464    keytodepress   \n",
 626 |        "1  19:18:41      PDT   771371705063370752        _ron_247   \n",
 627 |        "2  19:18:34      PDT  1020503873369194496         jan550n   \n",
 628 |        "3  19:18:33      PDT           2812237658      ran_engbot   \n",
 629 |        "4  19:18:30      PDT           4833251469  sasstelligence   \n",
 630 |        "\n",
 631 |        "                            name place  ... likes_count hashtags cashtags  \\\n",
 632 |        "0                          Cupid   NaN  ...           0       []       []   \n",
 633 |        "1       MCKAY SEASON SZN (52-39)   NaN  ...           0       []       []   \n",
 634 |        "2                      elizabeth   NaN  ...           0       []       []   \n",
 635 |        "3                     Ran Yakumo   NaN  ...           0       []       []   \n",
 636 |        "4  Stressed, Depressed Espressos   NaN  ...           1       []       []   \n",
 637 |        "\n",
 638 |        "                                                link  retweet  quote_url  \\\n",
 639 |        "0  https://twitter.com/KeytoDepress/status/115131...      NaN        NaN   \n",
 640 |        "1  https://twitter.com/_ron_247/status/1151315254...      NaN        NaN   \n",
 641 |        "2  https://twitter.com/jan550n/status/11513152226...      NaN        NaN   \n",
 642 |        "3  https://twitter.com/ran_engbot/status/11513152...      NaN        NaN   \n",
 643 |        "4  https://twitter.com/Sasstelligence/status/1151...      NaN        NaN   \n",
 644 |        "\n",
 645 |        "   video user_rt_id near geo  \n",
 646 |        "0      0        NaN  NaN NaN  \n",
 647 |        "1      0        NaN  NaN NaN  \n",
 648 |        "2      0        NaN  NaN NaN  \n",
 649 |        "3      0        NaN  NaN NaN  \n",
 650 |        "4      0        NaN  NaN NaN  \n",
 651 |        "\n",
 652 |        "[5 rows x 26 columns]"
 653 |       ]
 654 |      },
 655 |      "execution_count": 9,
 656 |      "metadata": {},
 657 |      "output_type": "execute_result"
 658 |     }
 659 |    ],
 660 |    "source": [
 661 |     "#depressed_tweets_df.head()"
 662 |    ]
 663 |   },
 664 |   {
 665 |    "cell_type": "code",
 666 |    "execution_count": 10,
 667 |    "metadata": {},
 668 |    "outputs": [],
 669 |    "source": [
 670 |     "#depressed_tweets_df.drop(['date', 'timezone', 'username', 'name', 'conversation_id', 'created_at', 'user_id', 'place', 'likes_count', 'link', 'retweet', 'quote_url', 'video', 'user_rt_id', 'near', 'geo', 'mentions', 'urls', 'photos', 'replies_count', 'retweets_count'], axis = 1, inplace = True)"
 671 |    ]
 672 |   },
 673 |   {
 674 |    "cell_type": "code",
 675 |    "execution_count": 11,
 676 |    "metadata": {},
 677 |    "outputs": [
 678 |     {
 679 |      "data": {
 680 |       "text/html": [
 681 |        "<div>\n",
 682 |        "<style scoped>\n",
 683 |        "    .dataframe tbody tr th:only-of-type {\n",
 684 |        "        vertical-align: middle;\n",
 685 |        "    }\n",
 686 |        "\n",
 687 |        "    .dataframe tbody tr th {\n",
 688 |        "        vertical-align: top;\n",
 689 |        "    }\n",
 690 |        "\n",
 691 |        "    .dataframe thead th {\n",
 692 |        "        text-align: right;\n",
 693 |        "    }\n",
 694 |        "</style>\n",
 695 |        "<table border=\"1\" class=\"dataframe\">\n",
 696 |        "  <thead>\n",
 697 |        "    <tr style=\"text-align: right;\">\n",
 698 |        "      <th></th>\n",
 699 |        "      <th>id</th>\n",
 700 |        "      <th>time</th>\n",
 701 |        "      <th>tweet</th>\n",
 702 |        "      <th>hashtags</th>\n",
 703 |        "      <th>cashtags</th>\n",
 704 |        "    </tr>\n",
 705 |        "  </thead>\n",
 706 |        "  <tbody>\n",
 707 |        "    <tr>\n",
 708 |        "      <th>0</th>\n",
 709 |        "      <td>1151315262748205057</td>\n",
 710 |        "      <td>19:18:43</td>\n",
 711 |        "      <td>Listen!! IM SORRY!!   With her elder spirits g...</td>\n",
 712 |        "      <td>[]</td>\n",
 713 |        "      <td>[]</td>\n",
 714 |        "    </tr>\n",
 715 |        "    <tr>\n",
 716 |        "      <th>1</th>\n",
 717 |        "      <td>1151315254615400448</td>\n",
 718 |        "      <td>19:18:41</td>\n",
 719 |        "      <td>Im so pissed and depressed at the same time</td>\n",
 720 |        "      <td>[]</td>\n",
 721 |        "      <td>[]</td>\n",
 722 |        "    </tr>\n",
 723 |        "    <tr>\n",
 724 |        "      <th>2</th>\n",
 725 |        "      <td>1151315222692429825</td>\n",
 726 |        "      <td>19:18:34</td>\n",
 727 |        "      <td>I’m just a hot mess that’s stressed, depressed...</td>\n",
 728 |        "      <td>[]</td>\n",
 729 |        "      <td>[]</td>\n",
 730 |        "    </tr>\n",
 731 |        "    <tr>\n",
 732 |        "      <th>3</th>\n",
 733 |        "      <td>1151315218011549696</td>\n",
 734 |        "      <td>19:18:33</td>\n",
 735 |        "      <td>Chen's probably depressed too since she's no l...</td>\n",
 736 |        "      <td>[]</td>\n",
 737 |        "      <td>[]</td>\n",
 738 |        "    </tr>\n",
 739 |        "    <tr>\n",
 740 |        "      <th>4</th>\n",
 741 |        "      <td>1151315209413386240</td>\n",
 742 |        "      <td>19:18:30</td>\n",
 743 |        "      <td>Do you like it when I shake it for ya, daddy? ...</td>\n",
 744 |        "      <td>[]</td>\n",
 745 |        "      <td>[]</td>\n",
 746 |        "    </tr>\n",
 747 |        "  </tbody>\n",
 748 |        "</table>\n",
 749 |        "</div>"
 750 |       ],
 751 |       "text/plain": [
 752 |        "                    id      time  \\\n",
 753 |        "0  1151315262748205057  19:18:43   \n",
 754 |        "1  1151315254615400448  19:18:41   \n",
 755 |        "2  1151315222692429825  19:18:34   \n",
 756 |        "3  1151315218011549696  19:18:33   \n",
 757 |        "4  1151315209413386240  19:18:30   \n",
 758 |        "\n",
 759 |        "                                               tweet hashtags cashtags  \n",
 760 |        "0  Listen!! IM SORRY!!   With her elder spirits g...       []       []  \n",
 761 |        "1        Im so pissed and depressed at the same time       []       []  \n",
 762 |        "2  I’m just a hot mess that’s stressed, depressed...       []       []  \n",
 763 |        "3  Chen's probably depressed too since she's no l...       []       []  \n",
 764 |        "4  Do you like it when I shake it for ya, daddy? ...       []       []  "
 765 |       ]
 766 |      },
 767 |      "execution_count": 11,
 768 |      "metadata": {},
 769 |      "output_type": "execute_result"
 770 |     }
 771 |    ],
 772 |    "source": [
 773 |     "#depressed_tweets_df.head()"
 774 |    ]
 775 |   },
 776 |   {
 777 |    "cell_type": "code",
 778 |    "execution_count": null,
 779 |    "metadata": {},
 780 |    "outputs": [],
 781 |    "source": []
 782 |   },
 783 |   {
 784 |    "cell_type": "code",
 785 |    "execution_count": 9,
 786 |    "metadata": {},
 787 |    "outputs": [],
 788 |    "source": [
 789 |     "hopeless_tweets_df = pd.read_csv('hopeless/tweets.csv')"
 790 |    ]
 791 |   },
 792 |   {
 793 |    "cell_type": "code",
 794 |    "execution_count": 10,
 795 |    "metadata": {},
 796 |    "outputs": [
 797 |     {
 798 |      "data": {
 799 |       "text/html": [
 800 |        "<div>\n",
 801 |        "<style scoped>\n",
 802 |        "    .dataframe tbody tr th:only-of-type {\n",
 803 |        "        vertical-align: middle;\n",
 804 |        "    }\n",
 805 |        "\n",
 806 |        "    .dataframe tbody tr th {\n",
 807 |        "        vertical-align: top;\n",
 808 |        "    }\n",
 809 |        "\n",
 810 |        "    .dataframe thead th {\n",
 811 |        "        text-align: right;\n",
 812 |        "    }\n",
 813 |        "</style>\n",
 814 |        "<table border=\"1\" class=\"dataframe\">\n",
 815 |        "  <thead>\n",
 816 |        "    <tr style=\"text-align: right;\">\n",
 817 |        "      <th></th>\n",
 818 |        "      <th>id</th>\n",
 819 |        "      <th>conversation_id</th>\n",
 820 |        "      <th>created_at</th>\n",
 821 |        "      <th>date</th>\n",
 822 |        "      <th>time</th>\n",
 823 |        "      <th>timezone</th>\n",
 824 |        "      <th>user_id</th>\n",
 825 |        "      <th>username</th>\n",
 826 |        "      <th>name</th>\n",
 827 |        "      <th>place</th>\n",
 828 |        "      <th>...</th>\n",
 829 |        "      <th>likes_count</th>\n",
 830 |        "      <th>hashtags</th>\n",
 831 |        "      <th>cashtags</th>\n",
 832 |        "      <th>link</th>\n",
 833 |        "      <th>retweet</th>\n",
 834 |        "      <th>quote_url</th>\n",
 835 |        "      <th>video</th>\n",
 836 |        "      <th>user_rt_id</th>\n",
 837 |        "      <th>near</th>\n",
 838 |        "      <th>geo</th>\n",
 839 |        "    </tr>\n",
 840 |        "  </thead>\n",
 841 |        "  <tbody>\n",
 842 |        "    <tr>\n",
 843 |        "      <th>0</th>\n",
 844 |        "      <td>1151526536471728134</td>\n",
 845 |        "      <td>1151526536471728134</td>\n",
 846 |        "      <td>1563380295000</td>\n",
 847 |        "      <td>2019-07-17</td>\n",
 848 |        "      <td>09:18:15</td>\n",
 849 |        "      <td>PDT</td>\n",
 850 |        "      <td>1070085811650117633</td>\n",
 851 |        "      <td>greesybot</td>\n",
 852 |        "      <td>greesybot</td>\n",
 853 |        "      <td>NaN</td>\n",
 854 |        "      <td>...</td>\n",
 855 |        "      <td>0</td>\n",
 856 |        "      <td>[]</td>\n",
 857 |        "      <td>[]</td>\n",
 858 |        "      <td>https://twitter.com/greesybot/status/115152653...</td>\n",
 859 |        "      <td>NaN</td>\n",
 860 |        "      <td>NaN</td>\n",
 861 |        "      <td>0</td>\n",
 862 |        "      <td>NaN</td>\n",
 863 |        "      <td>NaN</td>\n",
 864 |        "      <td>NaN</td>\n",
 865 |        "    </tr>\n",
 866 |        "    <tr>\n",
 867 |        "      <th>1</th>\n",
 868 |        "      <td>1151526442922139649</td>\n",
 869 |        "      <td>1151524002457882624</td>\n",
 870 |        "      <td>1563380272000</td>\n",
 871 |        "      <td>2019-07-17</td>\n",
 872 |        "      <td>09:17:52</td>\n",
 873 |        "      <td>PDT</td>\n",
 874 |        "      <td>853583752483807232</td>\n",
 875 |        "      <td>umutsuz_vakayim</td>\n",
 876 |        "      <td>Hopeless</td>\n",
 877 |        "      <td>NaN</td>\n",
 878 |        "      <td>...</td>\n",
 879 |        "      <td>0</td>\n",
 880 |        "      <td>[]</td>\n",
 881 |        "      <td>[]</td>\n",
 882 |        "      <td>https://twitter.com/umutsuz_vakayim/status/115...</td>\n",
 883 |        "      <td>NaN</td>\n",
 884 |        "      <td>NaN</td>\n",
 885 |        "      <td>0</td>\n",
 886 |        "      <td>NaN</td>\n",
 887 |        "      <td>NaN</td>\n",
 888 |        "      <td>NaN</td>\n",
 889 |        "    </tr>\n",
 890 |        "    <tr>\n",
 891 |        "      <th>2</th>\n",
 892 |        "      <td>1151526396210110464</td>\n",
 893 |        "      <td>1151526396210110464</td>\n",
 894 |        "      <td>1563380261000</td>\n",
 895 |        "      <td>2019-07-17</td>\n",
 896 |        "      <td>09:17:41</td>\n",
 897 |        "      <td>PDT</td>\n",
 898 |        "      <td>1120246244075626496</td>\n",
 899 |        "      <td>hopeless95</td>\n",
 900 |        "      <td>𐂂</td>\n",
 901 |        "      <td>NaN</td>\n",
 902 |        "      <td>...</td>\n",
 903 |        "      <td>1</td>\n",
 904 |        "      <td>[]</td>\n",
 905 |        "      <td>[]</td>\n",
 906 |        "      <td>https://twitter.com/hopeless95/status/11515263...</td>\n",
 907 |        "      <td>NaN</td>\n",
 908 |        "      <td>NaN</td>\n",
 909 |        "      <td>0</td>\n",
 910 |        "      <td>NaN</td>\n",
 911 |        "      <td>NaN</td>\n",
 912 |        "      <td>NaN</td>\n",
 913 |        "    </tr>\n",
 914 |        "    <tr>\n",
 915 |        "      <th>3</th>\n",
 916 |        "      <td>1151526283890683904</td>\n",
 917 |        "      <td>1151525753990725632</td>\n",
 918 |        "      <td>1563380235000</td>\n",
 919 |        "      <td>2019-07-17</td>\n",
 920 |        "      <td>09:17:15</td>\n",
 921 |        "      <td>PDT</td>\n",
 922 |        "      <td>1147135129489301505</td>\n",
 923 |        "      <td>hopehopexx</td>\n",
 924 |        "      <td>Hopeless</td>\n",
 925 |        "      <td>NaN</td>\n",
 926 |        "      <td>...</td>\n",
 927 |        "      <td>0</td>\n",
 928 |        "      <td>[]</td>\n",
 929 |        "      <td>[]</td>\n",
 930 |        "      <td>https://twitter.com/Hopehopexx/status/11515262...</td>\n",
 931 |        "      <td>NaN</td>\n",
 932 |        "      <td>NaN</td>\n",
 933 |        "      <td>0</td>\n",
 934 |        "      <td>NaN</td>\n",
 935 |        "      <td>NaN</td>\n",
 936 |        "      <td>NaN</td>\n",
 937 |        "    </tr>\n",
 938 |        "    <tr>\n",
 939 |        "      <th>4</th>\n",
 940 |        "      <td>1151526267738628097</td>\n",
 941 |        "      <td>1151526267738628097</td>\n",
 942 |        "      <td>1563380231000</td>\n",
 943 |        "      <td>2019-07-17</td>\n",
 944 |        "      <td>09:17:11</td>\n",
 945 |        "      <td>PDT</td>\n",
 946 |        "      <td>1120246244075626496</td>\n",
 947 |        "      <td>hopeless95</td>\n",
 948 |        "      <td>𐂂</td>\n",
 949 |        "      <td>NaN</td>\n",
 950 |        "      <td>...</td>\n",
 951 |        "      <td>1</td>\n",
 952 |        "      <td>[]</td>\n",
 953 |        "      <td>[]</td>\n",
 954 |        "      <td>https://twitter.com/hopeless95/status/11515262...</td>\n",
 955 |        "      <td>NaN</td>\n",
 956 |        "      <td>NaN</td>\n",
 957 |        "      <td>0</td>\n",
 958 |        "      <td>NaN</td>\n",
 959 |        "      <td>NaN</td>\n",
 960 |        "      <td>NaN</td>\n",
 961 |        "    </tr>\n",
 962 |        "  </tbody>\n",
 963 |        "</table>\n",
 964 |        "<p>5 rows × 26 columns</p>\n",
 965 |        "</div>"
 966 |       ],
 967 |       "text/plain": [
 968 |        "                    id      conversation_id     created_at        date  \\\n",
 969 |        "0  1151526536471728134  1151526536471728134  1563380295000  2019-07-17   \n",
 970 |        "1  1151526442922139649  1151524002457882624  1563380272000  2019-07-17   \n",
 971 |        "2  1151526396210110464  1151526396210110464  1563380261000  2019-07-17   \n",
 972 |        "3  1151526283890683904  1151525753990725632  1563380235000  2019-07-17   \n",
 973 |        "4  1151526267738628097  1151526267738628097  1563380231000  2019-07-17   \n",
 974 |        "\n",
 975 |        "       time timezone              user_id         username       name place  \\\n",
 976 |        "0  09:18:15      PDT  1070085811650117633        greesybot  greesybot   NaN   \n",
 977 |        "1  09:17:52      PDT   853583752483807232  umutsuz_vakayim   Hopeless   NaN   \n",
 978 |        "2  09:17:41      PDT  1120246244075626496       hopeless95          𐂂   NaN   \n",
 979 |        "3  09:17:15      PDT  1147135129489301505       hopehopexx   Hopeless   NaN   \n",
 980 |        "4  09:17:11      PDT  1120246244075626496       hopeless95          𐂂   NaN   \n",
 981 |        "\n",
 982 |        "   ... likes_count hashtags cashtags  \\\n",
 983 |        "0  ...           0       []       []   \n",
 984 |        "1  ...           0       []       []   \n",
 985 |        "2  ...           1       []       []   \n",
 986 |        "3  ...           0       []       []   \n",
 987 |        "4  ...           1       []       []   \n",
 988 |        "\n",
 989 |        "                                                link  retweet  quote_url  \\\n",
 990 |        "0  https://twitter.com/greesybot/status/115152653...      NaN        NaN   \n",
 991 |        "1  https://twitter.com/umutsuz_vakayim/status/115...      NaN        NaN   \n",
 992 |        "2  https://twitter.com/hopeless95/status/11515263...      NaN        NaN   \n",
 993 |        "3  https://twitter.com/Hopehopexx/status/11515262...      NaN        NaN   \n",
 994 |        "4  https://twitter.com/hopeless95/status/11515262...      NaN        NaN   \n",
 995 |        "\n",
 996 |        "   video user_rt_id near geo  \n",
 997 |        "0      0        NaN  NaN NaN  \n",
 998 |        "1      0        NaN  NaN NaN  \n",
 999 |        "2      0        NaN  NaN NaN  \n",
1000 |        "3      0        NaN  NaN NaN  \n",
1001 |        "4      0        NaN  NaN NaN  \n",
1002 |        "\n",
1003 |        "[5 rows x 26 columns]"
1004 |       ]
1005 |      },
1006 |      "execution_count": 10,
1007 |      "metadata": {},
1008 |      "output_type": "execute_result"
1009 |     }
1010 |    ],
1011 |    "source": [
1012 |     "hopeless_tweets_df.head()"
1013 |    ]
1014 |   },
1015 |   {
1016 |    "cell_type": "code",
1017 |    "execution_count": 11,
1018 |    "metadata": {},
1019 |    "outputs": [],
1020 |    "source": [
1021 |     "hopeless_tweets_df.drop(['date', 'timezone', 'username', 'name', 'conversation_id', 'created_at', 'user_id', 'place', 'likes_count', 'link', 'retweet', 'quote_url', 'video', 'user_rt_id', 'near', 'geo', 'mentions', 'urls', 'photos', 'replies_count', 'retweets_count'], axis = 1, inplace = True)"
1022 |    ]
1023 |   },
1024 |   {
1025 |    "cell_type": "code",
1026 |    "execution_count": 12,
1027 |    "metadata": {},
1028 |    "outputs": [
1029 |     {
1030 |      "data": {
1031 |       "text/html": [
1032 |        "<div>\n",
1033 |        "<style scoped>\n",
1034 |        "    .dataframe tbody tr th:only-of-type {\n",
1035 |        "        vertical-align: middle;\n",
1036 |        "    }\n",
1037 |        "\n",
1038 |        "    .dataframe tbody tr th {\n",
1039 |        "        vertical-align: top;\n",
1040 |        "    }\n",
1041 |        "\n",
1042 |        "    .dataframe thead th {\n",
1043 |        "        text-align: right;\n",
1044 |        "    }\n",
1045 |        "</style>\n",
1046 |        "<table border=\"1\" class=\"dataframe\">\n",
1047 |        "  <thead>\n",
1048 |        "    <tr style=\"text-align: right;\">\n",
1049 |        "      <th></th>\n",
1050 |        "      <th>id</th>\n",
1051 |        "      <th>time</th>\n",
1052 |        "      <th>tweet</th>\n",
1053 |        "      <th>hashtags</th>\n",
1054 |        "      <th>cashtags</th>\n",
1055 |        "    </tr>\n",
1056 |        "  </thead>\n",
1057 |        "  <tbody>\n",
1058 |        "    <tr>\n",
1059 |        "      <th>0</th>\n",
1060 |        "      <td>1151526536471728134</td>\n",
1061 |        "      <td>09:18:15</td>\n",
1062 |        "      <td>Hopeless, crazed, and dispossessed, I walked o...</td>\n",
1063 |        "      <td>[]</td>\n",
1064 |        "      <td>[]</td>\n",
1065 |        "    </tr>\n",
1066 |        "    <tr>\n",
1067 |        "      <th>1</th>\n",
1068 |        "      <td>1151526442922139649</td>\n",
1069 |        "      <td>09:17:52</td>\n",
1070 |        "      <td>KAP haberini beklerken serSERİn olmuştuk</td>\n",
1071 |        "      <td>[]</td>\n",
1072 |        "      <td>[]</td>\n",
1073 |        "    </tr>\n",
1074 |        "    <tr>\n",
1075 |        "      <th>2</th>\n",
1076 |        "      <td>1151526396210110464</td>\n",
1077 |        "      <td>09:17:41</td>\n",
1078 |        "      <td>17-july-2019. 🦉💛.</td>\n",
1079 |        "      <td>[]</td>\n",
1080 |        "      <td>[]</td>\n",
1081 |        "    </tr>\n",
1082 |        "    <tr>\n",
1083 |        "      <th>3</th>\n",
1084 |        "      <td>1151526283890683904</td>\n",
1085 |        "      <td>09:17:15</td>\n",
1086 |        "      <td>เป็นไรสาวน้อย</td>\n",
1087 |        "      <td>[]</td>\n",
1088 |        "      <td>[]</td>\n",
1089 |        "    </tr>\n",
1090 |        "    <tr>\n",
1091 |        "      <th>4</th>\n",
1092 |        "      <td>1151526267738628097</td>\n",
1093 |        "      <td>09:17:11</td>\n",
1094 |        "      <td>انا قاعده اعيش اسعد ايام حياتي💛.</td>\n",
1095 |        "      <td>[]</td>\n",
1096 |        "      <td>[]</td>\n",
1097 |        "    </tr>\n",
1098 |        "  </tbody>\n",
1099 |        "</table>\n",
1100 |        "</div>"
1101 |       ],
1102 |       "text/plain": [
1103 |        "                    id      time  \\\n",
1104 |        "0  1151526536471728134  09:18:15   \n",
1105 |        "1  1151526442922139649  09:17:52   \n",
1106 |        "2  1151526396210110464  09:17:41   \n",
1107 |        "3  1151526283890683904  09:17:15   \n",
1108 |        "4  1151526267738628097  09:17:11   \n",
1109 |        "\n",
1110 |        "                                               tweet hashtags cashtags  \n",
1111 |        "0  Hopeless, crazed, and dispossessed, I walked o...       []       []  \n",
1112 |        "1           KAP haberini beklerken serSERİn olmuştuk       []       []  \n",
1113 |        "2                                  17-july-2019. 🦉💛.       []       []  \n",
1114 |        "3                                      เป็นไรสาวน้อย       []       []  \n",
1115 |        "4                   انا قاعده اعيش اسعد ايام حياتي💛.       []       []  "
1116 |       ]
1117 |      },
1118 |      "execution_count": 12,
1119 |      "metadata": {},
1120 |      "output_type": "execute_result"
1121 |     }
1122 |    ],
1123 |    "source": [
1124 |     "hopeless_tweets_df.head()"
1125 |    ]
1126 |   },
1127 |   {
1128 |    "cell_type": "code",
1129 |    "execution_count": null,
1130 |    "metadata": {},
1131 |    "outputs": [],
1132 |    "source": []
1133 |   },
1134 |   {
1135 |    "cell_type": "code",
1136 |    "execution_count": 13,
1137 |    "metadata": {},
1138 |    "outputs": [],
1139 |    "source": [
1140 |     "lonely_tweets_df = pd.read_csv('lonely/tweets.csv')"
1141 |    ]
1142 |   },
1143 |   {
1144 |    "cell_type": "code",
1145 |    "execution_count": 14,
1146 |    "metadata": {},
1147 |    "outputs": [
1148 |     {
1149 |      "data": {
1150 |       "text/html": [
1151 |        "<div>\n",
1152 |        "<style scoped>\n",
1153 |        "    .dataframe tbody tr th:only-of-type {\n",
1154 |        "        vertical-align: middle;\n",
1155 |        "    }\n",
1156 |        "\n",
1157 |        "    .dataframe tbody tr th {\n",
1158 |        "        vertical-align: top;\n",
1159 |        "    }\n",
1160 |        "\n",
1161 |        "    .dataframe thead th {\n",
1162 |        "        text-align: right;\n",
1163 |        "    }\n",
1164 |        "</style>\n",
1165 |        "<table border=\"1\" class=\"dataframe\">\n",
1166 |        "  <thead>\n",
1167 |        "    <tr style=\"text-align: right;\">\n",
1168 |        "      <th></th>\n",
1169 |        "      <th>id</th>\n",
1170 |        "      <th>conversation_id</th>\n",
1171 |        "      <th>created_at</th>\n",
1172 |        "      <th>date</th>\n",
1173 |        "      <th>time</th>\n",
1174 |        "      <th>timezone</th>\n",
1175 |        "      <th>user_id</th>\n",
1176 |        "      <th>username</th>\n",
1177 |        "      <th>name</th>\n",
1178 |        "      <th>place</th>\n",
1179 |        "      <th>...</th>\n",
1180 |        "      <th>likes_count</th>\n",
1181 |        "      <th>hashtags</th>\n",
1182 |        "      <th>cashtags</th>\n",
1183 |        "      <th>link</th>\n",
1184 |        "      <th>retweet</th>\n",
1185 |        "      <th>quote_url</th>\n",
1186 |        "      <th>video</th>\n",
1187 |        "      <th>user_rt_id</th>\n",
1188 |        "      <th>near</th>\n",
1189 |        "      <th>geo</th>\n",
1190 |        "    </tr>\n",
1191 |        "  </thead>\n",
1192 |        "  <tbody>\n",
1193 |        "    <tr>\n",
1194 |        "      <th>0</th>\n",
1195 |        "      <td>1152982582843326466</td>\n",
1196 |        "      <td>1152982582843326466</td>\n",
1197 |        "      <td>1563727443000</td>\n",
1198 |        "      <td>2019-07-21</td>\n",
1199 |        "      <td>09:44:03</td>\n",
1200 |        "      <td>PDT</td>\n",
1201 |        "      <td>1151002890573701120</td>\n",
1202 |        "      <td>monbebe93</td>\n",
1203 |        "      <td>제시카</td>\n",
1204 |        "      <td>NaN</td>\n",
1205 |        "      <td>...</td>\n",
1206 |        "      <td>0</td>\n",
1207 |        "      <td>[]</td>\n",
1208 |        "      <td>[]</td>\n",
1209 |        "      <td>https://twitter.com/monbebe93/status/115298258...</td>\n",
1210 |        "      <td>NaN</td>\n",
1211 |        "      <td>https://twitter.com/OI_IO999/status/1152978766...</td>\n",
1212 |        "      <td>0</td>\n",
1213 |        "      <td>NaN</td>\n",
1214 |        "      <td>NaN</td>\n",
1215 |        "      <td>NaN</td>\n",
1216 |        "    </tr>\n",
1217 |        "    <tr>\n",
1218 |        "      <th>1</th>\n",
1219 |        "      <td>1152982578741284865</td>\n",
1220 |        "      <td>1152916420587675648</td>\n",
1221 |        "      <td>1563727442000</td>\n",
1222 |        "      <td>2019-07-21</td>\n",
1223 |        "      <td>09:44:02</td>\n",
1224 |        "      <td>PDT</td>\n",
1225 |        "      <td>1065697539259854849</td>\n",
1226 |        "      <td>sugarplum_skz</td>\n",
1227 |        "      <td>lonely wolf</td>\n",
1228 |        "      <td>NaN</td>\n",
1229 |        "      <td>...</td>\n",
1230 |        "      <td>0</td>\n",
1231 |        "      <td>[]</td>\n",
1232 |        "      <td>[]</td>\n",
1233 |        "      <td>https://twitter.com/sugarplum_skz/status/11529...</td>\n",
1234 |        "      <td>NaN</td>\n",
1235 |        "      <td>NaN</td>\n",
1236 |        "      <td>0</td>\n",
1237 |        "      <td>NaN</td>\n",
1238 |        "      <td>NaN</td>\n",
1239 |        "      <td>NaN</td>\n",
1240 |        "    </tr>\n",
1241 |        "    <tr>\n",
1242 |        "      <th>2</th>\n",
1243 |        "      <td>1152982577181024259</td>\n",
1244 |        "      <td>1152976191781048322</td>\n",
1245 |        "      <td>1563727442000</td>\n",
1246 |        "      <td>2019-07-21</td>\n",
1247 |        "      <td>09:44:02</td>\n",
1248 |        "      <td>PDT</td>\n",
1249 |        "      <td>704212959950667776</td>\n",
1250 |        "      <td>lonely_walsh</td>\n",
1251 |        "      <td>Elizabeth</td>\n",
1252 |        "      <td>NaN</td>\n",
1253 |        "      <td>...</td>\n",
1254 |        "      <td>0</td>\n",
1255 |        "      <td>[]</td>\n",
1256 |        "      <td>[]</td>\n",
1257 |        "      <td>https://twitter.com/lonely_walsh/status/115298...</td>\n",
1258 |        "      <td>NaN</td>\n",
1259 |        "      <td>NaN</td>\n",
1260 |        "      <td>0</td>\n",
1261 |        "      <td>NaN</td>\n",
1262 |        "      <td>NaN</td>\n",
1263 |        "      <td>NaN</td>\n",
1264 |        "    </tr>\n",
1265 |        "    <tr>\n",
1266 |        "      <th>3</th>\n",
1267 |        "      <td>1152982576153239552</td>\n",
1268 |        "      <td>1152982576153239552</td>\n",
1269 |        "      <td>1563727442000</td>\n",
1270 |        "      <td>2019-07-21</td>\n",
1271 |        "      <td>09:44:02</td>\n",
1272 |        "      <td>PDT</td>\n",
1273 |        "      <td>284959188</td>\n",
1274 |        "      <td>lonelyoakradio</td>\n",
1275 |        "      <td>Lonely Oak radio</td>\n",
1276 |        "      <td>NaN</td>\n",
1277 |        "      <td>...</td>\n",
1278 |        "      <td>0</td>\n",
1279 |        "      <td>['#nowplaying']</td>\n",
1280 |        "      <td>[]</td>\n",
1281 |        "      <td>https://twitter.com/LonelyOakRadio/status/1152...</td>\n",
1282 |        "      <td>NaN</td>\n",
1283 |        "      <td>NaN</td>\n",
1284 |        "      <td>0</td>\n",
1285 |        "      <td>NaN</td>\n",
1286 |        "      <td>NaN</td>\n",
1287 |        "      <td>NaN</td>\n",
1288 |        "    </tr>\n",
1289 |        "    <tr>\n",
1290 |        "      <th>4</th>\n",
1291 |        "      <td>1152982566263296000</td>\n",
1292 |        "      <td>1152982566263296000</td>\n",
1293 |        "      <td>1563727439000</td>\n",
1294 |        "      <td>2019-07-21</td>\n",
1295 |        "      <td>09:43:59</td>\n",
1296 |        "      <td>PDT</td>\n",
1297 |        "      <td>144328187</td>\n",
1298 |        "      <td>noelle_amor</td>\n",
1299 |        "      <td>YaYa🌹</td>\n",
1300 |        "      <td>NaN</td>\n",
1301 |        "      <td>...</td>\n",
1302 |        "      <td>0</td>\n",
1303 |        "      <td>[]</td>\n",
1304 |        "      <td>[]</td>\n",
1305 |        "      <td>https://twitter.com/Noelle_Amor/status/1152982...</td>\n",
1306 |        "      <td>NaN</td>\n",
1307 |        "      <td>NaN</td>\n",
1308 |        "      <td>0</td>\n",
1309 |        "      <td>NaN</td>\n",
1310 |        "      <td>NaN</td>\n",
1311 |        "      <td>NaN</td>\n",
1312 |        "    </tr>\n",
1313 |        "  </tbody>\n",
1314 |        "</table>\n",
1315 |        "<p>5 rows × 26 columns</p>\n",
1316 |        "</div>"
1317 |       ],
1318 |       "text/plain": [
1319 |        "                    id      conversation_id     created_at        date  \\\n",
1320 |        "0  1152982582843326466  1152982582843326466  1563727443000  2019-07-21   \n",
1321 |        "1  1152982578741284865  1152916420587675648  1563727442000  2019-07-21   \n",
1322 |        "2  1152982577181024259  1152976191781048322  1563727442000  2019-07-21   \n",
1323 |        "3  1152982576153239552  1152982576153239552  1563727442000  2019-07-21   \n",
1324 |        "4  1152982566263296000  1152982566263296000  1563727439000  2019-07-21   \n",
1325 |        "\n",
1326 |        "       time timezone              user_id        username              name  \\\n",
1327 |        "0  09:44:03      PDT  1151002890573701120       monbebe93               제시카   \n",
1328 |        "1  09:44:02      PDT  1065697539259854849   sugarplum_skz       lonely wolf   \n",
1329 |        "2  09:44:02      PDT   704212959950667776    lonely_walsh         Elizabeth   \n",
1330 |        "3  09:44:02      PDT            284959188  lonelyoakradio  Lonely Oak radio   \n",
1331 |        "4  09:43:59      PDT            144328187     noelle_amor             YaYa🌹   \n",
1332 |        "\n",
1333 |        "  place  ... likes_count         hashtags cashtags  \\\n",
1334 |        "0   NaN  ...           0               []       []   \n",
1335 |        "1   NaN  ...           0               []       []   \n",
1336 |        "2   NaN  ...           0               []       []   \n",
1337 |        "3   NaN  ...           0  ['#nowplaying']       []   \n",
1338 |        "4   NaN  ...           0               []       []   \n",
1339 |        "\n",
1340 |        "                                                link  retweet  \\\n",
1341 |        "0  https://twitter.com/monbebe93/status/115298258...      NaN   \n",
1342 |        "1  https://twitter.com/sugarplum_skz/status/11529...      NaN   \n",
1343 |        "2  https://twitter.com/lonely_walsh/status/115298...      NaN   \n",
1344 |        "3  https://twitter.com/LonelyOakRadio/status/1152...      NaN   \n",
1345 |        "4  https://twitter.com/Noelle_Amor/status/1152982...      NaN   \n",
1346 |        "\n",
1347 |        "                                           quote_url  video user_rt_id near  \\\n",
1348 |        "0  https://twitter.com/OI_IO999/status/1152978766...      0        NaN  NaN   \n",
1349 |        "1                                                NaN      0        NaN  NaN   \n",
1350 |        "2                                                NaN      0        NaN  NaN   \n",
1351 |        "3                                                NaN      0        NaN  NaN   \n",
1352 |        "4                                                NaN      0        NaN  NaN   \n",
1353 |        "\n",
1354 |        "  geo  \n",
1355 |        "0 NaN  \n",
1356 |        "1 NaN  \n",
1357 |        "2 NaN  \n",
1358 |        "3 NaN  \n",
1359 |        "4 NaN  \n",
1360 |        "\n",
1361 |        "[5 rows x 26 columns]"
1362 |       ]
1363 |      },
1364 |      "execution_count": 14,
1365 |      "metadata": {},
1366 |      "output_type": "execute_result"
1367 |     }
1368 |    ],
1369 |    "source": [
1370 |     "lonely_tweets_df.head()"
1371 |    ]
1372 |   },
1373 |   {
1374 |    "cell_type": "code",
1375 |    "execution_count": 15,
1376 |    "metadata": {},
1377 |    "outputs": [],
1378 |    "source": [
1379 |     "lonely_tweets_df.drop(['date', 'timezone', 'username', 'name', 'conversation_id', 'created_at', 'user_id', 'place', 'likes_count', 'link', 'retweet', 'quote_url', 'video', 'user_rt_id', 'near', 'geo', 'mentions', 'urls', 'photos', 'replies_count', 'retweets_count'], axis = 1, inplace = True)"
1380 |    ]
1381 |   },
1382 |   {
1383 |    "cell_type": "code",
1384 |    "execution_count": 16,
1385 |    "metadata": {},
1386 |    "outputs": [
1387 |     {
1388 |      "data": {
1389 |       "text/html": [
1390 |        "<div>\n",
1391 |        "<style scoped>\n",
1392 |        "    .dataframe tbody tr th:only-of-type {\n",
1393 |        "        vertical-align: middle;\n",
1394 |        "    }\n",
1395 |        "\n",
1396 |        "    .dataframe tbody tr th {\n",
1397 |        "        vertical-align: top;\n",
1398 |        "    }\n",
1399 |        "\n",
1400 |        "    .dataframe thead th {\n",
1401 |        "        text-align: right;\n",
1402 |        "    }\n",
1403 |        "</style>\n",
1404 |        "<table border=\"1\" class=\"dataframe\">\n",
1405 |        "  <thead>\n",
1406 |        "    <tr style=\"text-align: right;\">\n",
1407 |        "      <th></th>\n",
1408 |        "      <th>id</th>\n",
1409 |        "      <th>time</th>\n",
1410 |        "      <th>tweet</th>\n",
1411 |        "      <th>hashtags</th>\n",
1412 |        "      <th>cashtags</th>\n",
1413 |        "    </tr>\n",
1414 |        "  </thead>\n",
1415 |        "  <tbody>\n",
1416 |        "    <tr>\n",
1417 |        "      <th>0</th>\n",
1418 |        "      <td>1152982582843326466</td>\n",
1419 |        "      <td>09:44:03</td>\n",
1420 |        "      <td>i dont know why but he looks so lonely in this...</td>\n",
1421 |        "      <td>[]</td>\n",
1422 |        "      <td>[]</td>\n",
1423 |        "    </tr>\n",
1424 |        "    <tr>\n",
1425 |        "      <th>1</th>\n",
1426 |        "      <td>1152982578741284865</td>\n",
1427 |        "      <td>09:44:02</td>\n",
1428 |        "      <td>Я после того как увидела их начала отращивать ...</td>\n",
1429 |        "      <td>[]</td>\n",
1430 |        "      <td>[]</td>\n",
1431 |        "    </tr>\n",
1432 |        "    <tr>\n",
1433 |        "      <th>2</th>\n",
1434 |        "      <td>1152982577181024259</td>\n",
1435 |        "      <td>09:44:02</td>\n",
1436 |        "      <td>Even follow you on all social networks</td>\n",
1437 |        "      <td>[]</td>\n",
1438 |        "      <td>[]</td>\n",
1439 |        "    </tr>\n",
1440 |        "    <tr>\n",
1441 |        "      <th>3</th>\n",
1442 |        "      <td>1152982576153239552</td>\n",
1443 |        "      <td>09:44:02</td>\n",
1444 |        "      <td>#Nowplaying: Garmonsway, Gibbon and Harrington...</td>\n",
1445 |        "      <td>['#nowplaying']</td>\n",
1446 |        "      <td>[]</td>\n",
1447 |        "    </tr>\n",
1448 |        "    <tr>\n",
1449 |        "      <th>4</th>\n",
1450 |        "      <td>1152982566263296000</td>\n",
1451 |        "      <td>09:43:59</td>\n",
1452 |        "      <td>Laying in this hammock every Sunday alone is g...</td>\n",
1453 |        "      <td>[]</td>\n",
1454 |        "      <td>[]</td>\n",
1455 |        "    </tr>\n",
1456 |        "  </tbody>\n",
1457 |        "</table>\n",
1458 |        "</div>"
1459 |       ],
1460 |       "text/plain": [
1461 |        "                    id      time  \\\n",
1462 |        "0  1152982582843326466  09:44:03   \n",
1463 |        "1  1152982578741284865  09:44:02   \n",
1464 |        "2  1152982577181024259  09:44:02   \n",
1465 |        "3  1152982576153239552  09:44:02   \n",
1466 |        "4  1152982566263296000  09:43:59   \n",
1467 |        "\n",
1468 |        "                                               tweet         hashtags cashtags  \n",
1469 |        "0  i dont know why but he looks so lonely in this...               []       []  \n",
1470 |        "1  Я после того как увидела их начала отращивать ...               []       []  \n",
1471 |        "2             Even follow you on all social networks               []       []  \n",
1472 |        "3  #Nowplaying: Garmonsway, Gibbon and Harrington...  ['#nowplaying']       []  \n",
1473 |        "4  Laying in this hammock every Sunday alone is g...               []       []  "
1474 |       ]
1475 |      },
1476 |      "execution_count": 16,
1477 |      "metadata": {},
1478 |      "output_type": "execute_result"
1479 |     }
1480 |    ],
1481 |    "source": [
1482 |     "lonely_tweets_df.head()"
1483 |    ]
1484 |   },
1485 |   {
1486 |    "cell_type": "code",
1487 |    "execution_count": null,
1488 |    "metadata": {},
1489 |    "outputs": [],
1490 |    "source": []
1491 |   },
1492 |   {
1493 |    "cell_type": "code",
1494 |    "execution_count": 17,
1495 |    "metadata": {},
1496 |    "outputs": [],
1497 |    "source": [
1498 |     "antidepressant_tweets_df = pd.read_csv('antidepressant/tweets.csv')"
1499 |    ]
1500 |   },
1501 |   {
1502 |    "cell_type": "code",
1503 |    "execution_count": 18,
1504 |    "metadata": {},
1505 |    "outputs": [
1506 |     {
1507 |      "data": {
1508 |       "text/html": [
1509 |        "<div>\n",
1510 |        "<style scoped>\n",
1511 |        "    .dataframe tbody tr th:only-of-type {\n",
1512 |        "        vertical-align: middle;\n",
1513 |        "    }\n",
1514 |        "\n",
1515 |        "    .dataframe tbody tr th {\n",
1516 |        "        vertical-align: top;\n",
1517 |        "    }\n",
1518 |        "\n",
1519 |        "    .dataframe thead th {\n",
1520 |        "        text-align: right;\n",
1521 |        "    }\n",
1522 |        "</style>\n",
1523 |        "<table border=\"1\" class=\"dataframe\">\n",
1524 |        "  <thead>\n",
1525 |        "    <tr style=\"text-align: right;\">\n",
1526 |        "      <th></th>\n",
1527 |        "      <th>id</th>\n",
1528 |        "      <th>conversation_id</th>\n",
1529 |        "      <th>created_at</th>\n",
1530 |        "      <th>date</th>\n",
1531 |        "      <th>time</th>\n",
1532 |        "      <th>timezone</th>\n",
1533 |        "      <th>user_id</th>\n",
1534 |        "      <th>username</th>\n",
1535 |        "      <th>name</th>\n",
1536 |        "      <th>place</th>\n",
1537 |        "      <th>...</th>\n",
1538 |        "      <th>likes_count</th>\n",
1539 |        "      <th>hashtags</th>\n",
1540 |        "      <th>cashtags</th>\n",
1541 |        "      <th>link</th>\n",
1542 |        "      <th>retweet</th>\n",
1543 |        "      <th>quote_url</th>\n",
1544 |        "      <th>video</th>\n",
1545 |        "      <th>user_rt_id</th>\n",
1546 |        "      <th>near</th>\n",
1547 |        "      <th>geo</th>\n",
1548 |        "    </tr>\n",
1549 |        "  </thead>\n",
1550 |        "  <tbody>\n",
1551 |        "    <tr>\n",
1552 |        "      <th>0</th>\n",
1553 |        "      <td>1152991919137538048</td>\n",
1554 |        "      <td>1152991908391739392</td>\n",
1555 |        "      <td>1563729669000</td>\n",
1556 |        "      <td>2019-07-21</td>\n",
1557 |        "      <td>10:21:09</td>\n",
1558 |        "      <td>PDT</td>\n",
1559 |        "      <td>794617098106441728</td>\n",
1560 |        "      <td>harlequimsy</td>\n",
1561 |        "      <td>Darnielle 🤦🏻‍♀️</td>\n",
1562 |        "      <td>NaN</td>\n",
1563 |        "      <td>...</td>\n",
1564 |        "      <td>0</td>\n",
1565 |        "      <td>[]</td>\n",
1566 |        "      <td>[]</td>\n",
1567 |        "      <td>https://twitter.com/harlequimsy/status/1152991...</td>\n",
1568 |        "      <td>NaN</td>\n",
1569 |        "      <td>NaN</td>\n",
1570 |        "      <td>0</td>\n",
1571 |        "      <td>NaN</td>\n",
1572 |        "      <td>NaN</td>\n",
1573 |        "      <td>NaN</td>\n",
1574 |        "    </tr>\n",
1575 |        "    <tr>\n",
1576 |        "      <th>1</th>\n",
1577 |        "      <td>1152991631722913793</td>\n",
1578 |        "      <td>1152991631722913793</td>\n",
1579 |        "      <td>1563729601000</td>\n",
1580 |        "      <td>2019-07-21</td>\n",
1581 |        "      <td>10:20:01</td>\n",
1582 |        "      <td>PDT</td>\n",
1583 |        "      <td>959487925992947714</td>\n",
1584 |        "      <td>aspiringapollo</td>\n",
1585 |        "      <td>Anthony</td>\n",
1586 |        "      <td>NaN</td>\n",
1587 |        "      <td>...</td>\n",
1588 |        "      <td>0</td>\n",
1589 |        "      <td>[]</td>\n",
1590 |        "      <td>[]</td>\n",
1591 |        "      <td>https://twitter.com/AspiringApollo/status/1152...</td>\n",
1592 |        "      <td>NaN</td>\n",
1593 |        "      <td>NaN</td>\n",
1594 |        "      <td>0</td>\n",
1595 |        "      <td>NaN</td>\n",
1596 |        "      <td>NaN</td>\n",
1597 |        "      <td>NaN</td>\n",
1598 |        "    </tr>\n",
1599 |        "    <tr>\n",
1600 |        "      <th>2</th>\n",
1601 |        "      <td>1152991531789406209</td>\n",
1602 |        "      <td>1152986023447732224</td>\n",
1603 |        "      <td>1563729577000</td>\n",
1604 |        "      <td>2019-07-21</td>\n",
1605 |        "      <td>10:19:37</td>\n",
1606 |        "      <td>PDT</td>\n",
1607 |        "      <td>2391838146</td>\n",
1608 |        "      <td>al_pal_22</td>\n",
1609 |        "      <td>brogram</td>\n",
1610 |        "      <td>NaN</td>\n",
1611 |        "      <td>...</td>\n",
1612 |        "      <td>0</td>\n",
1613 |        "      <td>[]</td>\n",
1614 |        "      <td>[]</td>\n",
1615 |        "      <td>https://twitter.com/al_pal_22/status/115299153...</td>\n",
1616 |        "      <td>NaN</td>\n",
1617 |        "      <td>NaN</td>\n",
1618 |        "      <td>0</td>\n",
1619 |        "      <td>NaN</td>\n",
1620 |        "      <td>NaN</td>\n",
1621 |        "      <td>NaN</td>\n",
1622 |        "    </tr>\n",
1623 |        "    <tr>\n",
1624 |        "      <th>3</th>\n",
1625 |        "      <td>1152991116733628416</td>\n",
1626 |        "      <td>1152991116733628416</td>\n",
1627 |        "      <td>1563729478000</td>\n",
1628 |        "      <td>2019-07-21</td>\n",
1629 |        "      <td>10:17:58</td>\n",
1630 |        "      <td>PDT</td>\n",
1631 |        "      <td>510205955</td>\n",
1632 |        "      <td>iceberged</td>\n",
1633 |        "      <td>Iceberg SelfHelp</td>\n",
1634 |        "      <td>NaN</td>\n",
1635 |        "      <td>...</td>\n",
1636 |        "      <td>0</td>\n",
1637 |        "      <td>['#medication', '#antidepressants', '#eatingdi...</td>\n",
1638 |        "      <td>[]</td>\n",
1639 |        "      <td>https://twitter.com/IcebergED/status/115299111...</td>\n",
1640 |        "      <td>NaN</td>\n",
1641 |        "      <td>NaN</td>\n",
1642 |        "      <td>0</td>\n",
1643 |        "      <td>NaN</td>\n",
1644 |        "      <td>NaN</td>\n",
1645 |        "      <td>NaN</td>\n",
1646 |        "    </tr>\n",
1647 |        "    <tr>\n",
1648 |        "      <th>4</th>\n",
1649 |        "      <td>1152990783420751872</td>\n",
1650 |        "      <td>1152862679452790785</td>\n",
1651 |        "      <td>1563729398000</td>\n",
1652 |        "      <td>2019-07-21</td>\n",
1653 |        "      <td>10:16:38</td>\n",
1654 |        "      <td>PDT</td>\n",
1655 |        "      <td>34530161</td>\n",
1656 |        "      <td>matchlessmarie</td>\n",
1657 |        "      <td>Amanda [matchless] Marie</td>\n",
1658 |        "      <td>NaN</td>\n",
1659 |        "      <td>...</td>\n",
1660 |        "      <td>1</td>\n",
1661 |        "      <td>[]</td>\n",
1662 |        "      <td>[]</td>\n",
1663 |        "      <td>https://twitter.com/MatchlessMarie/status/1152...</td>\n",
1664 |        "      <td>NaN</td>\n",
1665 |        "      <td>NaN</td>\n",
1666 |        "      <td>0</td>\n",
1667 |        "      <td>NaN</td>\n",
1668 |        "      <td>NaN</td>\n",
1669 |        "      <td>NaN</td>\n",
1670 |        "    </tr>\n",
1671 |        "  </tbody>\n",
1672 |        "</table>\n",
1673 |        "<p>5 rows × 26 columns</p>\n",
1674 |        "</div>"
1675 |       ],
1676 |       "text/plain": [
1677 |        "                    id      conversation_id     created_at        date  \\\n",
1678 |        "0  1152991919137538048  1152991908391739392  1563729669000  2019-07-21   \n",
1679 |        "1  1152991631722913793  1152991631722913793  1563729601000  2019-07-21   \n",
1680 |        "2  1152991531789406209  1152986023447732224  1563729577000  2019-07-21   \n",
1681 |        "3  1152991116733628416  1152991116733628416  1563729478000  2019-07-21   \n",
1682 |        "4  1152990783420751872  1152862679452790785  1563729398000  2019-07-21   \n",
1683 |        "\n",
1684 |        "       time timezone             user_id        username  \\\n",
1685 |        "0  10:21:09      PDT  794617098106441728     harlequimsy   \n",
1686 |        "1  10:20:01      PDT  959487925992947714  aspiringapollo   \n",
1687 |        "2  10:19:37      PDT          2391838146       al_pal_22   \n",
1688 |        "3  10:17:58      PDT           510205955       iceberged   \n",
1689 |        "4  10:16:38      PDT            34530161  matchlessmarie   \n",
1690 |        "\n",
1691 |        "                       name place  ... likes_count  \\\n",
1692 |        "0           Darnielle 🤦🏻‍♀️   NaN  ...           0   \n",
1693 |        "1                   Anthony   NaN  ...           0   \n",
1694 |        "2                   brogram   NaN  ...           0   \n",
1695 |        "3          Iceberg SelfHelp   NaN  ...           0   \n",
1696 |        "4  Amanda [matchless] Marie   NaN  ...           1   \n",
1697 |        "\n",
1698 |        "                                            hashtags cashtags  \\\n",
1699 |        "0                                                 []       []   \n",
1700 |        "1                                                 []       []   \n",
1701 |        "2                                                 []       []   \n",
1702 |        "3  ['#medication', '#antidepressants', '#eatingdi...       []   \n",
1703 |        "4                                                 []       []   \n",
1704 |        "\n",
1705 |        "                                                link  retweet  quote_url  \\\n",
1706 |        "0  https://twitter.com/harlequimsy/status/1152991...      NaN        NaN   \n",
1707 |        "1  https://twitter.com/AspiringApollo/status/1152...      NaN        NaN   \n",
1708 |        "2  https://twitter.com/al_pal_22/status/115299153...      NaN        NaN   \n",
1709 |        "3  https://twitter.com/IcebergED/status/115299111...      NaN        NaN   \n",
1710 |        "4  https://twitter.com/MatchlessMarie/status/1152...      NaN        NaN   \n",
1711 |        "\n",
1712 |        "   video user_rt_id near geo  \n",
1713 |        "0      0        NaN  NaN NaN  \n",
1714 |        "1      0        NaN  NaN NaN  \n",
1715 |        "2      0        NaN  NaN NaN  \n",
1716 |        "3      0        NaN  NaN NaN  \n",
1717 |        "4      0        NaN  NaN NaN  \n",
1718 |        "\n",
1719 |        "[5 rows x 26 columns]"
1720 |       ]
1721 |      },
1722 |      "execution_count": 18,
1723 |      "metadata": {},
1724 |      "output_type": "execute_result"
1725 |     }
1726 |    ],
1727 |    "source": [
1728 |     "antidepressant_tweets_df.head()"
1729 |    ]
1730 |   },
1731 |   {
1732 |    "cell_type": "code",
1733 |    "execution_count": 19,
1734 |    "metadata": {},
1735 |    "outputs": [],
1736 |    "source": [
1737 |     "antidepressant_tweets_df.drop(['date', 'timezone', 'username', 'name', 'conversation_id', 'created_at', 'user_id', 'place', 'likes_count', 'link', 'retweet', 'quote_url', 'video', 'user_rt_id', 'near', 'geo', 'mentions', 'urls', 'photos', 'replies_count', 'retweets_count'], axis = 1, inplace = True)"
1738 |    ]
1739 |   },
1740 |   {
1741 |    "cell_type": "code",
1742 |    "execution_count": 20,
1743 |    "metadata": {},
1744 |    "outputs": [
1745 |     {
1746 |      "data": {
1747 |       "text/html": [
1748 |        "<div>\n",
1749 |        "<style scoped>\n",
1750 |        "    .dataframe tbody tr th:only-of-type {\n",
1751 |        "        vertical-align: middle;\n",
1752 |        "    }\n",
1753 |        "\n",
1754 |        "    .dataframe tbody tr th {\n",
1755 |        "        vertical-align: top;\n",
1756 |        "    }\n",
1757 |        "\n",
1758 |        "    .dataframe thead th {\n",
1759 |        "        text-align: right;\n",
1760 |        "    }\n",
1761 |        "</style>\n",
1762 |        "<table border=\"1\" class=\"dataframe\">\n",
1763 |        "  <thead>\n",
1764 |        "    <tr style=\"text-align: right;\">\n",
1765 |        "      <th></th>\n",
1766 |        "      <th>id</th>\n",
1767 |        "      <th>time</th>\n",
1768 |        "      <th>tweet</th>\n",
1769 |        "      <th>hashtags</th>\n",
1770 |        "      <th>cashtags</th>\n",
1771 |        "    </tr>\n",
1772 |        "  </thead>\n",
1773 |        "  <tbody>\n",
1774 |        "    <tr>\n",
1775 |        "      <th>0</th>\n",
1776 |        "      <td>1152991919137538048</td>\n",
1777 |        "      <td>10:21:09</td>\n",
1778 |        "      <td>I hate that the antidepressants made me feel w...</td>\n",
1779 |        "      <td>[]</td>\n",
1780 |        "      <td>[]</td>\n",
1781 |        "    </tr>\n",
1782 |        "    <tr>\n",
1783 |        "      <th>1</th>\n",
1784 |        "      <td>1152991631722913793</td>\n",
1785 |        "      <td>10:20:01</td>\n",
1786 |        "      <td>Your beliefs ultimately are manifested in your...</td>\n",
1787 |        "      <td>[]</td>\n",
1788 |        "      <td>[]</td>\n",
1789 |        "    </tr>\n",
1790 |        "    <tr>\n",
1791 |        "      <th>2</th>\n",
1792 |        "      <td>1152991531789406209</td>\n",
1793 |        "      <td>10:19:37</td>\n",
1794 |        "      <td>I think current trends lead to a world where e...</td>\n",
1795 |        "      <td>[]</td>\n",
1796 |        "      <td>[]</td>\n",
1797 |        "    </tr>\n",
1798 |        "    <tr>\n",
1799 |        "      <th>3</th>\n",
1800 |        "      <td>1152991116733628416</td>\n",
1801 |        "      <td>10:17:58</td>\n",
1802 |        "      <td>Anti-Depressants and Recovery  https://www.mar...</td>\n",
1803 |        "      <td>['#medication', '#antidepressants', '#eatingdi...</td>\n",
1804 |        "      <td>[]</td>\n",
1805 |        "    </tr>\n",
1806 |        "    <tr>\n",
1807 |        "      <th>4</th>\n",
1808 |        "      <td>1152990783420751872</td>\n",
1809 |        "      <td>10:16:38</td>\n",
1810 |        "      <td>Have you thought about getting a sleep study d...</td>\n",
1811 |        "      <td>[]</td>\n",
1812 |        "      <td>[]</td>\n",
1813 |        "    </tr>\n",
1814 |        "  </tbody>\n",
1815 |        "</table>\n",
1816 |        "</div>"
1817 |       ],
1818 |       "text/plain": [
1819 |        "                    id      time  \\\n",
1820 |        "0  1152991919137538048  10:21:09   \n",
1821 |        "1  1152991631722913793  10:20:01   \n",
1822 |        "2  1152991531789406209  10:19:37   \n",
1823 |        "3  1152991116733628416  10:17:58   \n",
1824 |        "4  1152990783420751872  10:16:38   \n",
1825 |        "\n",
1826 |        "                                               tweet  \\\n",
1827 |        "0  I hate that the antidepressants made me feel w...   \n",
1828 |        "1  Your beliefs ultimately are manifested in your...   \n",
1829 |        "2  I think current trends lead to a world where e...   \n",
1830 |        "3  Anti-Depressants and Recovery  https://www.mar...   \n",
1831 |        "4  Have you thought about getting a sleep study d...   \n",
1832 |        "\n",
1833 |        "                                            hashtags cashtags  \n",
1834 |        "0                                                 []       []  \n",
1835 |        "1                                                 []       []  \n",
1836 |        "2                                                 []       []  \n",
1837 |        "3  ['#medication', '#antidepressants', '#eatingdi...       []  \n",
1838 |        "4                                                 []       []  "
1839 |       ]
1840 |      },
1841 |      "execution_count": 20,
1842 |      "metadata": {},
1843 |      "output_type": "execute_result"
1844 |     }
1845 |    ],
1846 |    "source": [
1847 |     "antidepressant_tweets_df.head()"
1848 |    ]
1849 |   },
1850 |   {
1851 |    "cell_type": "code",
1852 |    "execution_count": null,
1853 |    "metadata": {},
1854 |    "outputs": [],
1855 |    "source": []
1856 |   },
1857 |   {
1858 |    "cell_type": "code",
1859 |    "execution_count": 21,
1860 |    "metadata": {},
1861 |    "outputs": [],
1862 |    "source": [
1863 |     "antidepressants_tweets_df = pd.read_csv('antidepressants/tweets.csv')"
1864 |    ]
1865 |   },
1866 |   {
1867 |    "cell_type": "code",
1868 |    "execution_count": 22,
1869 |    "metadata": {},
1870 |    "outputs": [
1871 |     {
1872 |      "data": {
1873 |       "text/html": [
1874 |        "<div>\n",
1875 |        "<style scoped>\n",
1876 |        "    .dataframe tbody tr th:only-of-type {\n",
1877 |        "        vertical-align: middle;\n",
1878 |        "    }\n",
1879 |        "\n",
1880 |        "    .dataframe tbody tr th {\n",
1881 |        "        vertical-align: top;\n",
1882 |        "    }\n",
1883 |        "\n",
1884 |        "    .dataframe thead th {\n",
1885 |        "        text-align: right;\n",
1886 |        "    }\n",
1887 |        "</style>\n",
1888 |        "<table border=\"1\" class=\"dataframe\">\n",
1889 |        "  <thead>\n",
1890 |        "    <tr style=\"text-align: right;\">\n",
1891 |        "      <th></th>\n",
1892 |        "      <th>id</th>\n",
1893 |        "      <th>conversation_id</th>\n",
1894 |        "      <th>created_at</th>\n",
1895 |        "      <th>date</th>\n",
1896 |        "      <th>time</th>\n",
1897 |        "      <th>timezone</th>\n",
1898 |        "      <th>user_id</th>\n",
1899 |        "      <th>username</th>\n",
1900 |        "      <th>name</th>\n",
1901 |        "      <th>place</th>\n",
1902 |        "      <th>...</th>\n",
1903 |        "      <th>likes_count</th>\n",
1904 |        "      <th>hashtags</th>\n",
1905 |        "      <th>cashtags</th>\n",
1906 |        "      <th>link</th>\n",
1907 |        "      <th>retweet</th>\n",
1908 |        "      <th>quote_url</th>\n",
1909 |        "      <th>video</th>\n",
1910 |        "      <th>user_rt_id</th>\n",
1911 |        "      <th>near</th>\n",
1912 |        "      <th>geo</th>\n",
1913 |        "    </tr>\n",
1914 |        "  </thead>\n",
1915 |        "  <tbody>\n",
1916 |        "    <tr>\n",
1917 |        "      <th>0</th>\n",
1918 |        "      <td>1152995178359218176</td>\n",
1919 |        "      <td>1152995178359218176</td>\n",
1920 |        "      <td>1563730446000</td>\n",
1921 |        "      <td>2019-07-21</td>\n",
1922 |        "      <td>10:34:06</td>\n",
1923 |        "      <td>PDT</td>\n",
1924 |        "      <td>1134809541818929152</td>\n",
1925 |        "      <td>neumnelo</td>\n",
1926 |        "      <td>🍓⚢</td>\n",
1927 |        "      <td>NaN</td>\n",
1928 |        "      <td>...</td>\n",
1929 |        "      <td>0</td>\n",
1930 |        "      <td>[]</td>\n",
1931 |        "      <td>[]</td>\n",
1932 |        "      <td>https://twitter.com/neumnelo/status/1152995178...</td>\n",
1933 |        "      <td>NaN</td>\n",
1934 |        "      <td>NaN</td>\n",
1935 |        "      <td>0</td>\n",
1936 |        "      <td>NaN</td>\n",
1937 |        "      <td>NaN</td>\n",
1938 |        "      <td>NaN</td>\n",
1939 |        "    </tr>\n",
1940 |        "    <tr>\n",
1941 |        "      <th>1</th>\n",
1942 |        "      <td>1152994945537576960</td>\n",
1943 |        "      <td>1152994945537576960</td>\n",
1944 |        "      <td>1563730391000</td>\n",
1945 |        "      <td>2019-07-21</td>\n",
1946 |        "      <td>10:33:11</td>\n",
1947 |        "      <td>PDT</td>\n",
1948 |        "      <td>709759485162598400</td>\n",
1949 |        "      <td>csevern5</td>\n",
1950 |        "      <td>C Severn</td>\n",
1951 |        "      <td>NaN</td>\n",
1952 |        "      <td>...</td>\n",
1953 |        "      <td>0</td>\n",
1954 |        "      <td>[]</td>\n",
1955 |        "      <td>[]</td>\n",
1956 |        "      <td>https://twitter.com/csevern5/status/1152994945...</td>\n",
1957 |        "      <td>NaN</td>\n",
1958 |        "      <td>NaN</td>\n",
1959 |        "      <td>0</td>\n",
1960 |        "      <td>NaN</td>\n",
1961 |        "      <td>NaN</td>\n",
1962 |        "      <td>NaN</td>\n",
1963 |        "    </tr>\n",
1964 |        "    <tr>\n",
1965 |        "      <th>2</th>\n",
1966 |        "      <td>1152994834359209985</td>\n",
1967 |        "      <td>1152994145700634625</td>\n",
1968 |        "      <td>1563730364000</td>\n",
1969 |        "      <td>2019-07-21</td>\n",
1970 |        "      <td>10:32:44</td>\n",
1971 |        "      <td>PDT</td>\n",
1972 |        "      <td>969718541703368704</td>\n",
1973 |        "      <td>healingapriori</td>\n",
1974 |        "      <td>A Kid That Knows Nothing</td>\n",
1975 |        "      <td>NaN</td>\n",
1976 |        "      <td>...</td>\n",
1977 |        "      <td>0</td>\n",
1978 |        "      <td>[]</td>\n",
1979 |        "      <td>[]</td>\n",
1980 |        "      <td>https://twitter.com/healingapriori/status/1152...</td>\n",
1981 |        "      <td>NaN</td>\n",
1982 |        "      <td>NaN</td>\n",
1983 |        "      <td>0</td>\n",
1984 |        "      <td>NaN</td>\n",
1985 |        "      <td>NaN</td>\n",
1986 |        "      <td>NaN</td>\n",
1987 |        "    </tr>\n",
1988 |        "    <tr>\n",
1989 |        "      <th>3</th>\n",
1990 |        "      <td>1152994452606033920</td>\n",
1991 |        "      <td>1152994452606033920</td>\n",
1992 |        "      <td>1563730273000</td>\n",
1993 |        "      <td>2019-07-21</td>\n",
1994 |        "      <td>10:31:13</td>\n",
1995 |        "      <td>PDT</td>\n",
1996 |        "      <td>864470942159953920</td>\n",
1997 |        "      <td>liferenewedjax</td>\n",
1998 |        "      <td>Life Renewed Counseling</td>\n",
1999 |        "      <td>NaN</td>\n",
2000 |        "      <td>...</td>\n",
2001 |        "      <td>0</td>\n",
2002 |        "      <td>[]</td>\n",
2003 |        "      <td>[]</td>\n",
2004 |        "      <td>https://twitter.com/liferenewedjax/status/1152...</td>\n",
2005 |        "      <td>NaN</td>\n",
2006 |        "      <td>NaN</td>\n",
2007 |        "      <td>0</td>\n",
2008 |        "      <td>NaN</td>\n",
2009 |        "      <td>NaN</td>\n",
2010 |        "      <td>NaN</td>\n",
2011 |        "    </tr>\n",
2012 |        "    <tr>\n",
2013 |        "      <th>4</th>\n",
2014 |        "      <td>1152994432188370949</td>\n",
2015 |        "      <td>1152994432188370949</td>\n",
2016 |        "      <td>1563730268000</td>\n",
2017 |        "      <td>2019-07-21</td>\n",
2018 |        "      <td>10:31:08</td>\n",
2019 |        "      <td>PDT</td>\n",
2020 |        "      <td>1029517541608108033</td>\n",
2021 |        "      <td>glitterfairy420</td>\n",
2022 |        "      <td>𝕵𝖊𝖓𝖓𝖎𝖋𝖊𝖗★</td>\n",
2023 |        "      <td>NaN</td>\n",
2024 |        "      <td>...</td>\n",
2025 |        "      <td>0</td>\n",
2026 |        "      <td>[]</td>\n",
2027 |        "      <td>[]</td>\n",
2028 |        "      <td>https://twitter.com/Glitterfairy420/status/115...</td>\n",
2029 |        "      <td>NaN</td>\n",
2030 |        "      <td>NaN</td>\n",
2031 |        "      <td>0</td>\n",
2032 |        "      <td>NaN</td>\n",
2033 |        "      <td>NaN</td>\n",
2034 |        "      <td>NaN</td>\n",
2035 |        "    </tr>\n",
2036 |        "  </tbody>\n",
2037 |        "</table>\n",
2038 |        "<p>5 rows × 26 columns</p>\n",
2039 |        "</div>"
2040 |       ],
2041 |       "text/plain": [
2042 |        "                    id      conversation_id     created_at        date  \\\n",
2043 |        "0  1152995178359218176  1152995178359218176  1563730446000  2019-07-21   \n",
2044 |        "1  1152994945537576960  1152994945537576960  1563730391000  2019-07-21   \n",
2045 |        "2  1152994834359209985  1152994145700634625  1563730364000  2019-07-21   \n",
2046 |        "3  1152994452606033920  1152994452606033920  1563730273000  2019-07-21   \n",
2047 |        "4  1152994432188370949  1152994432188370949  1563730268000  2019-07-21   \n",
2048 |        "\n",
2049 |        "       time timezone              user_id         username  \\\n",
2050 |        "0  10:34:06      PDT  1134809541818929152         neumnelo   \n",
2051 |        "1  10:33:11      PDT   709759485162598400         csevern5   \n",
2052 |        "2  10:32:44      PDT   969718541703368704   healingapriori   \n",
2053 |        "3  10:31:13      PDT   864470942159953920   liferenewedjax   \n",
2054 |        "4  10:31:08      PDT  1029517541608108033  glitterfairy420   \n",
2055 |        "\n",
2056 |        "                       name place  ... likes_count hashtags cashtags  \\\n",
2057 |        "0                        🍓⚢   NaN  ...           0       []       []   \n",
2058 |        "1                  C Severn   NaN  ...           0       []       []   \n",
2059 |        "2  A Kid That Knows Nothing   NaN  ...           0       []       []   \n",
2060 |        "3   Life Renewed Counseling   NaN  ...           0       []       []   \n",
2061 |        "4                 𝕵𝖊𝖓𝖓𝖎𝖋𝖊𝖗★   NaN  ...           0       []       []   \n",
2062 |        "\n",
2063 |        "                                                link  retweet  quote_url  \\\n",
2064 |        "0  https://twitter.com/neumnelo/status/1152995178...      NaN        NaN   \n",
2065 |        "1  https://twitter.com/csevern5/status/1152994945...      NaN        NaN   \n",
2066 |        "2  https://twitter.com/healingapriori/status/1152...      NaN        NaN   \n",
2067 |        "3  https://twitter.com/liferenewedjax/status/1152...      NaN        NaN   \n",
2068 |        "4  https://twitter.com/Glitterfairy420/status/115...      NaN        NaN   \n",
2069 |        "\n",
2070 |        "   video user_rt_id near geo  \n",
2071 |        "0      0        NaN  NaN NaN  \n",
2072 |        "1      0        NaN  NaN NaN  \n",
2073 |        "2      0        NaN  NaN NaN  \n",
2074 |        "3      0        NaN  NaN NaN  \n",
2075 |        "4      0        NaN  NaN NaN  \n",
2076 |        "\n",
2077 |        "[5 rows x 26 columns]"
2078 |       ]
2079 |      },
2080 |      "execution_count": 22,
2081 |      "metadata": {},
2082 |      "output_type": "execute_result"
2083 |     }
2084 |    ],
2085 |    "source": [
2086 |     "antidepressants_tweets_df.head()"
2087 |    ]
2088 |   },
2089 |   {
2090 |    "cell_type": "code",
2091 |    "execution_count": 23,
2092 |    "metadata": {},
2093 |    "outputs": [],
2094 |    "source": [
2095 |     "antidepressants_tweets_df.drop(['date', 'timezone', 'username', 'name', 'conversation_id', 'created_at', 'user_id', 'place', 'likes_count', 'link', 'retweet', 'quote_url', 'video', 'user_rt_id', 'near', 'geo', 'mentions', 'urls', 'photos', 'replies_count', 'retweets_count'], axis = 1, inplace = True)"
2096 |    ]
2097 |   },
2098 |   {
2099 |    "cell_type": "code",
2100 |    "execution_count": 24,
2101 |    "metadata": {},
2102 |    "outputs": [
2103 |     {
2104 |      "data": {
2105 |       "text/html": [
2106 |        "<div>\n",
2107 |        "<style scoped>\n",
2108 |        "    .dataframe tbody tr th:only-of-type {\n",
2109 |        "        vertical-align: middle;\n",
2110 |        "    }\n",
2111 |        "\n",
2112 |        "    .dataframe tbody tr th {\n",
2113 |        "        vertical-align: top;\n",
2114 |        "    }\n",
2115 |        "\n",
2116 |        "    .dataframe thead th {\n",
2117 |        "        text-align: right;\n",
2118 |        "    }\n",
2119 |        "</style>\n",
2120 |        "<table border=\"1\" class=\"dataframe\">\n",
2121 |        "  <thead>\n",
2122 |        "    <tr style=\"text-align: right;\">\n",
2123 |        "      <th></th>\n",
2124 |        "      <th>id</th>\n",
2125 |        "      <th>time</th>\n",
2126 |        "      <th>tweet</th>\n",
2127 |        "      <th>hashtags</th>\n",
2128 |        "      <th>cashtags</th>\n",
2129 |        "    </tr>\n",
2130 |        "  </thead>\n",
2131 |        "  <tbody>\n",
2132 |        "    <tr>\n",
2133 |        "      <th>0</th>\n",
2134 |        "      <td>1152995178359218176</td>\n",
2135 |        "      <td>10:34:06</td>\n",
2136 |        "      <td>i can't think logically and all of shit i say ...</td>\n",
2137 |        "      <td>[]</td>\n",
2138 |        "      <td>[]</td>\n",
2139 |        "    </tr>\n",
2140 |        "    <tr>\n",
2141 |        "      <th>1</th>\n",
2142 |        "      <td>1152994945537576960</td>\n",
2143 |        "      <td>10:33:11</td>\n",
2144 |        "      <td>Recently moved to Australia and was ASTOUNDED ...</td>\n",
2145 |        "      <td>[]</td>\n",
2146 |        "      <td>[]</td>\n",
2147 |        "    </tr>\n",
2148 |        "    <tr>\n",
2149 |        "      <th>2</th>\n",
2150 |        "      <td>1152994834359209985</td>\n",
2151 |        "      <td>10:32:44</td>\n",
2152 |        "      <td>Maybe I should go back on my antidepressants. ...</td>\n",
2153 |        "      <td>[]</td>\n",
2154 |        "      <td>[]</td>\n",
2155 |        "    </tr>\n",
2156 |        "    <tr>\n",
2157 |        "      <th>3</th>\n",
2158 |        "      <td>1152994452606033920</td>\n",
2159 |        "      <td>10:31:13</td>\n",
2160 |        "      <td>What It’s Like to Know You’ll Be on Antidepres...</td>\n",
2161 |        "      <td>[]</td>\n",
2162 |        "      <td>[]</td>\n",
2163 |        "    </tr>\n",
2164 |        "    <tr>\n",
2165 |        "      <th>4</th>\n",
2166 |        "      <td>1152994432188370949</td>\n",
2167 |        "      <td>10:31:08</td>\n",
2168 |        "      <td>Do antidepressants work? :/</td>\n",
2169 |        "      <td>[]</td>\n",
2170 |        "      <td>[]</td>\n",
2171 |        "    </tr>\n",
2172 |        "  </tbody>\n",
2173 |        "</table>\n",
2174 |        "</div>"
2175 |       ],
2176 |       "text/plain": [
2177 |        "                    id      time  \\\n",
2178 |        "0  1152995178359218176  10:34:06   \n",
2179 |        "1  1152994945537576960  10:33:11   \n",
2180 |        "2  1152994834359209985  10:32:44   \n",
2181 |        "3  1152994452606033920  10:31:13   \n",
2182 |        "4  1152994432188370949  10:31:08   \n",
2183 |        "\n",
2184 |        "                                               tweet hashtags cashtags  \n",
2185 |        "0  i can't think logically and all of shit i say ...       []       []  \n",
2186 |        "1  Recently moved to Australia and was ASTOUNDED ...       []       []  \n",
2187 |        "2  Maybe I should go back on my antidepressants. ...       []       []  \n",
2188 |        "3  What It’s Like to Know You’ll Be on Antidepres...       []       []  \n",
2189 |        "4                        Do antidepressants work? :/       []       []  "
2190 |       ]
2191 |      },
2192 |      "execution_count": 24,
2193 |      "metadata": {},
2194 |      "output_type": "execute_result"
2195 |     }
2196 |    ],
2197 |    "source": [
2198 |     "antidepressants_tweets_df.head()"
2199 |    ]
2200 |   },
2201 |   {
2202 |    "cell_type": "code",
2203 |    "execution_count": null,
2204 |    "metadata": {},
2205 |    "outputs": [],
2206 |    "source": []
2207 |   },
2208 |   {
2209 |    "cell_type": "code",
2210 |    "execution_count": 25,
2211 |    "metadata": {},
2212 |    "outputs": [],
2213 |    "source": [
2214 |     "suicide_tweets_df = pd.read_csv('suicide/tweets.csv')"
2215 |    ]
2216 |   },
2217 |   {
2218 |    "cell_type": "code",
2219 |    "execution_count": 26,
2220 |    "metadata": {},
2221 |    "outputs": [
2222 |     {
2223 |      "data": {
2224 |       "text/html": [
2225 |        "<div>\n",
2226 |        "<style scoped>\n",
2227 |        "    .dataframe tbody tr th:only-of-type {\n",
2228 |        "        vertical-align: middle;\n",
2229 |        "    }\n",
2230 |        "\n",
2231 |        "    .dataframe tbody tr th {\n",
2232 |        "        vertical-align: top;\n",
2233 |        "    }\n",
2234 |        "\n",
2235 |        "    .dataframe thead th {\n",
2236 |        "        text-align: right;\n",
2237 |        "    }\n",
2238 |        "</style>\n",
2239 |        "<table border=\"1\" class=\"dataframe\">\n",
2240 |        "  <thead>\n",
2241 |        "    <tr style=\"text-align: right;\">\n",
2242 |        "      <th></th>\n",
2243 |        "      <th>id</th>\n",
2244 |        "      <th>conversation_id</th>\n",
2245 |        "      <th>created_at</th>\n",
2246 |        "      <th>date</th>\n",
2247 |        "      <th>time</th>\n",
2248 |        "      <th>timezone</th>\n",
2249 |        "      <th>user_id</th>\n",
2250 |        "      <th>username</th>\n",
2251 |        "      <th>name</th>\n",
2252 |        "      <th>place</th>\n",
2253 |        "      <th>...</th>\n",
2254 |        "      <th>likes_count</th>\n",
2255 |        "      <th>hashtags</th>\n",
2256 |        "      <th>cashtags</th>\n",
2257 |        "      <th>link</th>\n",
2258 |        "      <th>retweet</th>\n",
2259 |        "      <th>quote_url</th>\n",
2260 |        "      <th>video</th>\n",
2261 |        "      <th>user_rt_id</th>\n",
2262 |        "      <th>near</th>\n",
2263 |        "      <th>geo</th>\n",
2264 |        "    </tr>\n",
2265 |        "  </thead>\n",
2266 |        "  <tbody>\n",
2267 |        "    <tr>\n",
2268 |        "      <th>0</th>\n",
2269 |        "      <td>1152996044604682241</td>\n",
2270 |        "      <td>1152996044604682241</td>\n",
2271 |        "      <td>1563730653000</td>\n",
2272 |        "      <td>2019-07-21</td>\n",
2273 |        "      <td>10:37:33</td>\n",
2274 |        "      <td>PDT</td>\n",
2275 |        "      <td>2958699552</td>\n",
2276 |        "      <td>imonlylj</td>\n",
2277 |        "      <td>Misunderśtøød x Mìdaś ㊗️️</td>\n",
2278 |        "      <td>NaN</td>\n",
2279 |        "      <td>...</td>\n",
2280 |        "      <td>0</td>\n",
2281 |        "      <td>[]</td>\n",
2282 |        "      <td>[]</td>\n",
2283 |        "      <td>https://twitter.com/ImonlyLj/status/1152996044...</td>\n",
2284 |        "      <td>NaN</td>\n",
2285 |        "      <td>NaN</td>\n",
2286 |        "      <td>0</td>\n",
2287 |        "      <td>NaN</td>\n",
2288 |        "      <td>NaN</td>\n",
2289 |        "      <td>NaN</td>\n",
2290 |        "    </tr>\n",
2291 |        "    <tr>\n",
2292 |        "      <th>1</th>\n",
2293 |        "      <td>1152995993148899329</td>\n",
2294 |        "      <td>1152995993148899329</td>\n",
2295 |        "      <td>1563730641000</td>\n",
2296 |        "      <td>2019-07-21</td>\n",
2297 |        "      <td>10:37:21</td>\n",
2298 |        "      <td>PDT</td>\n",
2299 |        "      <td>29907109</td>\n",
2300 |        "      <td>_kingneal</td>\n",
2301 |        "      <td>King.</td>\n",
2302 |        "      <td>NaN</td>\n",
2303 |        "      <td>...</td>\n",
2304 |        "      <td>0</td>\n",
2305 |        "      <td>[]</td>\n",
2306 |        "      <td>[]</td>\n",
2307 |        "      <td>https://twitter.com/_kingneal/status/115299599...</td>\n",
2308 |        "      <td>NaN</td>\n",
2309 |        "      <td>NaN</td>\n",
2310 |        "      <td>0</td>\n",
2311 |        "      <td>NaN</td>\n",
2312 |        "      <td>NaN</td>\n",
2313 |        "      <td>NaN</td>\n",
2314 |        "    </tr>\n",
2315 |        "    <tr>\n",
2316 |        "      <th>2</th>\n",
2317 |        "      <td>1152995985053900800</td>\n",
2318 |        "      <td>1152995985053900800</td>\n",
2319 |        "      <td>1563730639000</td>\n",
2320 |        "      <td>2019-07-21</td>\n",
2321 |        "      <td>10:37:19</td>\n",
2322 |        "      <td>PDT</td>\n",
2323 |        "      <td>1152971452846694401</td>\n",
2324 |        "      <td>ventingbroken</td>\n",
2325 |        "      <td>Venting (More people are broken than it seems)</td>\n",
2326 |        "      <td>NaN</td>\n",
2327 |        "      <td>...</td>\n",
2328 |        "      <td>0</td>\n",
2329 |        "      <td>[]</td>\n",
2330 |        "      <td>[]</td>\n",
2331 |        "      <td>https://twitter.com/VentingBroken/status/11529...</td>\n",
2332 |        "      <td>NaN</td>\n",
2333 |        "      <td>NaN</td>\n",
2334 |        "      <td>0</td>\n",
2335 |        "      <td>NaN</td>\n",
2336 |        "      <td>NaN</td>\n",
2337 |        "      <td>NaN</td>\n",
2338 |        "    </tr>\n",
2339 |        "    <tr>\n",
2340 |        "      <th>3</th>\n",
2341 |        "      <td>1152995984642887683</td>\n",
2342 |        "      <td>1152995984642887683</td>\n",
2343 |        "      <td>1563730639000</td>\n",
2344 |        "      <td>2019-07-21</td>\n",
2345 |        "      <td>10:37:19</td>\n",
2346 |        "      <td>PDT</td>\n",
2347 |        "      <td>2561945708</td>\n",
2348 |        "      <td>awesome_thebest</td>\n",
2349 |        "      <td>Just me</td>\n",
2350 |        "      <td>NaN</td>\n",
2351 |        "      <td>...</td>\n",
2352 |        "      <td>0</td>\n",
2353 |        "      <td>[]</td>\n",
2354 |        "      <td>[]</td>\n",
2355 |        "      <td>https://twitter.com/awesome_thebest/status/115...</td>\n",
2356 |        "      <td>NaN</td>\n",
2357 |        "      <td>NaN</td>\n",
2358 |        "      <td>0</td>\n",
2359 |        "      <td>NaN</td>\n",
2360 |        "      <td>NaN</td>\n",
2361 |        "      <td>NaN</td>\n",
2362 |        "    </tr>\n",
2363 |        "    <tr>\n",
2364 |        "      <th>4</th>\n",
2365 |        "      <td>1152995955559620608</td>\n",
2366 |        "      <td>1152995955559620608</td>\n",
2367 |        "      <td>1563730632000</td>\n",
2368 |        "      <td>2019-07-21</td>\n",
2369 |        "      <td>10:37:12</td>\n",
2370 |        "      <td>PDT</td>\n",
2371 |        "      <td>891371293563596800</td>\n",
2372 |        "      <td>drmo7og</td>\n",
2373 |        "      <td>Dr.mo7og</td>\n",
2374 |        "      <td>NaN</td>\n",
2375 |        "      <td>...</td>\n",
2376 |        "      <td>0</td>\n",
2377 |        "      <td>['#sam', '#suicide']</td>\n",
2378 |        "      <td>[]</td>\n",
2379 |        "      <td>https://twitter.com/DrMo7oG/status/11529959555...</td>\n",
2380 |        "      <td>NaN</td>\n",
2381 |        "      <td>NaN</td>\n",
2382 |        "      <td>0</td>\n",
2383 |        "      <td>NaN</td>\n",
2384 |        "      <td>NaN</td>\n",
2385 |        "      <td>NaN</td>\n",
2386 |        "    </tr>\n",
2387 |        "  </tbody>\n",
2388 |        "</table>\n",
2389 |        "<p>5 rows × 26 columns</p>\n",
2390 |        "</div>"
2391 |       ],
2392 |       "text/plain": [
2393 |        "                    id      conversation_id     created_at        date  \\\n",
2394 |        "0  1152996044604682241  1152996044604682241  1563730653000  2019-07-21   \n",
2395 |        "1  1152995993148899329  1152995993148899329  1563730641000  2019-07-21   \n",
2396 |        "2  1152995985053900800  1152995985053900800  1563730639000  2019-07-21   \n",
2397 |        "3  1152995984642887683  1152995984642887683  1563730639000  2019-07-21   \n",
2398 |        "4  1152995955559620608  1152995955559620608  1563730632000  2019-07-21   \n",
2399 |        "\n",
2400 |        "       time timezone              user_id         username  \\\n",
2401 |        "0  10:37:33      PDT           2958699552         imonlylj   \n",
2402 |        "1  10:37:21      PDT             29907109        _kingneal   \n",
2403 |        "2  10:37:19      PDT  1152971452846694401    ventingbroken   \n",
2404 |        "3  10:37:19      PDT           2561945708  awesome_thebest   \n",
2405 |        "4  10:37:12      PDT   891371293563596800          drmo7og   \n",
2406 |        "\n",
2407 |        "                                             name place  ... likes_count  \\\n",
2408 |        "0                       Misunderśtøød x Mìdaś ㊗️️   NaN  ...           0   \n",
2409 |        "1                                           King.   NaN  ...           0   \n",
2410 |        "2  Venting (More people are broken than it seems)   NaN  ...           0   \n",
2411 |        "3                                         Just me   NaN  ...           0   \n",
2412 |        "4                                        Dr.mo7og   NaN  ...           0   \n",
2413 |        "\n",
2414 |        "               hashtags cashtags  \\\n",
2415 |        "0                    []       []   \n",
2416 |        "1                    []       []   \n",
2417 |        "2                    []       []   \n",
2418 |        "3                    []       []   \n",
2419 |        "4  ['#sam', '#suicide']       []   \n",
2420 |        "\n",
2421 |        "                                                link  retweet  quote_url  \\\n",
2422 |        "0  https://twitter.com/ImonlyLj/status/1152996044...      NaN        NaN   \n",
2423 |        "1  https://twitter.com/_kingneal/status/115299599...      NaN        NaN   \n",
2424 |        "2  https://twitter.com/VentingBroken/status/11529...      NaN        NaN   \n",
2425 |        "3  https://twitter.com/awesome_thebest/status/115...      NaN        NaN   \n",
2426 |        "4  https://twitter.com/DrMo7oG/status/11529959555...      NaN        NaN   \n",
2427 |        "\n",
2428 |        "   video user_rt_id near geo  \n",
2429 |        "0      0        NaN  NaN NaN  \n",
2430 |        "1      0        NaN  NaN NaN  \n",
2431 |        "2      0        NaN  NaN NaN  \n",
2432 |        "3      0        NaN  NaN NaN  \n",
2433 |        "4      0        NaN  NaN NaN  \n",
2434 |        "\n",
2435 |        "[5 rows x 26 columns]"
2436 |       ]
2437 |      },
2438 |      "execution_count": 26,
2439 |      "metadata": {},
2440 |      "output_type": "execute_result"
2441 |     }
2442 |    ],
2443 |    "source": [
2444 |     "suicide_tweets_df.head()"
2445 |    ]
2446 |   },
2447 |   {
2448 |    "cell_type": "code",
2449 |    "execution_count": 27,
2450 |    "metadata": {},
2451 |    "outputs": [],
2452 |    "source": [
2453 |     "suicide_tweets_df.drop(['date', 'timezone', 'username', 'name', 'conversation_id', 'created_at', 'user_id', 'place', 'likes_count', 'link', 'retweet', 'quote_url', 'video', 'user_rt_id', 'near', 'geo', 'mentions', 'urls', 'photos', 'replies_count', 'retweets_count'], axis = 1, inplace = True)"
2454 |    ]
2455 |   },
2456 |   {
2457 |    "cell_type": "code",
2458 |    "execution_count": 28,
2459 |    "metadata": {},
2460 |    "outputs": [
2461 |     {
2462 |      "data": {
2463 |       "text/html": [
2464 |        "<div>\n",
2465 |        "<style scoped>\n",
2466 |        "    .dataframe tbody tr th:only-of-type {\n",
2467 |        "        vertical-align: middle;\n",
2468 |        "    }\n",
2469 |        "\n",
2470 |        "    .dataframe tbody tr th {\n",
2471 |        "        vertical-align: top;\n",
2472 |        "    }\n",
2473 |        "\n",
2474 |        "    .dataframe thead th {\n",
2475 |        "        text-align: right;\n",
2476 |        "    }\n",
2477 |        "</style>\n",
2478 |        "<table border=\"1\" class=\"dataframe\">\n",
2479 |        "  <thead>\n",
2480 |        "    <tr style=\"text-align: right;\">\n",
2481 |        "      <th></th>\n",
2482 |        "      <th>id</th>\n",
2483 |        "      <th>time</th>\n",
2484 |        "      <th>tweet</th>\n",
2485 |        "      <th>hashtags</th>\n",
2486 |        "      <th>cashtags</th>\n",
2487 |        "    </tr>\n",
2488 |        "  </thead>\n",
2489 |        "  <tbody>\n",
2490 |        "    <tr>\n",
2491 |        "      <th>0</th>\n",
2492 |        "      <td>1152996044604682241</td>\n",
2493 |        "      <td>10:37:33</td>\n",
2494 |        "      <td>Suicide Thoughts ....</td>\n",
2495 |        "      <td>[]</td>\n",
2496 |        "      <td>[]</td>\n",
2497 |        "    </tr>\n",
2498 |        "    <tr>\n",
2499 |        "      <th>1</th>\n",
2500 |        "      <td>1152995993148899329</td>\n",
2501 |        "      <td>10:37:21</td>\n",
2502 |        "      <td>If I wake up as a white person in my next life...</td>\n",
2503 |        "      <td>[]</td>\n",
2504 |        "      <td>[]</td>\n",
2505 |        "    </tr>\n",
2506 |        "    <tr>\n",
2507 |        "      <th>2</th>\n",
2508 |        "      <td>1152995985053900800</td>\n",
2509 |        "      <td>10:37:19</td>\n",
2510 |        "      <td>I fixed my bio (Cant add a banner because Twit...</td>\n",
2511 |        "      <td>[]</td>\n",
2512 |        "      <td>[]</td>\n",
2513 |        "    </tr>\n",
2514 |        "    <tr>\n",
2515 |        "      <th>3</th>\n",
2516 |        "      <td>1152995984642887683</td>\n",
2517 |        "      <td>10:37:19</td>\n",
2518 |        "      <td>Weaponizign Suicide disturbs me a lot Cardi B ...</td>\n",
2519 |        "      <td>[]</td>\n",
2520 |        "      <td>[]</td>\n",
2521 |        "    </tr>\n",
2522 |        "    <tr>\n",
2523 |        "      <th>4</th>\n",
2524 |        "      <td>1152995955559620608</td>\n",
2525 |        "      <td>10:37:12</td>\n",
2526 |        "      <td>#sam harcelé par ses camarades de classe se #s...</td>\n",
2527 |        "      <td>['#sam', '#suicide']</td>\n",
2528 |        "      <td>[]</td>\n",
2529 |        "    </tr>\n",
2530 |        "  </tbody>\n",
2531 |        "</table>\n",
2532 |        "</div>"
2533 |       ],
2534 |       "text/plain": [
2535 |        "                    id      time  \\\n",
2536 |        "0  1152996044604682241  10:37:33   \n",
2537 |        "1  1152995993148899329  10:37:21   \n",
2538 |        "2  1152995985053900800  10:37:19   \n",
2539 |        "3  1152995984642887683  10:37:19   \n",
2540 |        "4  1152995955559620608  10:37:12   \n",
2541 |        "\n",
2542 |        "                                               tweet              hashtags  \\\n",
2543 |        "0                              Suicide Thoughts ....                    []   \n",
2544 |        "1  If I wake up as a white person in my next life...                    []   \n",
2545 |        "2  I fixed my bio (Cant add a banner because Twit...                    []   \n",
2546 |        "3  Weaponizign Suicide disturbs me a lot Cardi B ...                    []   \n",
2547 |        "4  #sam harcelé par ses camarades de classe se #s...  ['#sam', '#suicide']   \n",
2548 |        "\n",
2549 |        "  cashtags  \n",
2550 |        "0       []  \n",
2551 |        "1       []  \n",
2552 |        "2       []  \n",
2553 |        "3       []  \n",
2554 |        "4       []  "
2555 |       ]
2556 |      },
2557 |      "execution_count": 28,
2558 |      "metadata": {},
2559 |      "output_type": "execute_result"
2560 |     }
2561 |    ],
2562 |    "source": [
2563 |     "suicide_tweets_df.head()"
2564 |    ]
2565 |   },
2566 |   {
2567 |    "cell_type": "code",
2568 |    "execution_count": null,
2569 |    "metadata": {},
2570 |    "outputs": [],
2571 |    "source": []
2572 |   },
2573 |   {
2574 |    "cell_type": "code",
2575 |    "execution_count": 30,
2576 |    "metadata": {
2577 |     "scrolled": true
2578 |    },
2579 |    "outputs": [
2580 |     {
2581 |      "name": "stderr",
2582 |      "output_type": "stream",
2583 |      "text": [
2584 |       "/Users/anneb/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:1: FutureWarning: Sorting because non-concatenation axis is not aligned. A future version\n",
2585 |       "of pandas will change to not sort by default.\n",
2586 |       "\n",
2587 |       "To accept the future behavior, pass 'sort=False'.\n",
2588 |       "\n",
2589 |       "To retain the current behavior and silence the warning, pass 'sort=True'.\n",
2590 |       "\n",
2591 |       "  \"\"\"Entry point for launching an IPython kernel.\n"
2592 |      ]
2593 |     },
2594 |     {
2595 |      "data": {
2596 |       "text/html": [
2597 |        "<div>\n",
2598 |        "<style scoped>\n",
2599 |        "    .dataframe tbody tr th:only-of-type {\n",
2600 |        "        vertical-align: middle;\n",
2601 |        "    }\n",
2602 |        "\n",
2603 |        "    .dataframe tbody tr th {\n",
2604 |        "        vertical-align: top;\n",
2605 |        "    }\n",
2606 |        "\n",
2607 |        "    .dataframe thead th {\n",
2608 |        "        text-align: right;\n",
2609 |        "    }\n",
2610 |        "</style>\n",
2611 |        "<table border=\"1\" class=\"dataframe\">\n",
2612 |        "  <thead>\n",
2613 |        "    <tr style=\"text-align: right;\">\n",
2614 |        "      <th></th>\n",
2615 |        "      <th>Unnamed: 0</th>\n",
2616 |        "      <th>cashtags</th>\n",
2617 |        "      <th>hashtags</th>\n",
2618 |        "      <th>id</th>\n",
2619 |        "      <th>time</th>\n",
2620 |        "      <th>tweet</th>\n",
2621 |        "    </tr>\n",
2622 |        "  </thead>\n",
2623 |        "  <tbody>\n",
2624 |        "    <tr>\n",
2625 |        "      <th>0</th>\n",
2626 |        "      <td>0</td>\n",
2627 |        "      <td>[]</td>\n",
2628 |        "      <td>[]</td>\n",
2629 |        "      <td>1.15135E+18</td>\n",
2630 |        "      <td>21:25:13</td>\n",
2631 |        "      <td>Wow, my dad yday: “you don’t take those stupid...</td>\n",
2632 |        "    </tr>\n",
2633 |        "    <tr>\n",
2634 |        "      <th>1</th>\n",
2635 |        "      <td>1</td>\n",
2636 |        "      <td>[]</td>\n",
2637 |        "      <td>[]</td>\n",
2638 |        "      <td>1.15135E+18</td>\n",
2639 |        "      <td>21:25:07</td>\n",
2640 |        "      <td>what part of this was really harmfult of a lot...</td>\n",
2641 |        "    </tr>\n",
2642 |        "    <tr>\n",
2643 |        "      <th>2</th>\n",
2644 |        "      <td>2</td>\n",
2645 |        "      <td>[]</td>\n",
2646 |        "      <td>['#depression', '#uncoveringthenewu', '#change...</td>\n",
2647 |        "      <td>1.15135E+18</td>\n",
2648 |        "      <td>21:25:06</td>\n",
2649 |        "      <td>one of the ways I got through my #depression i...</td>\n",
2650 |        "    </tr>\n",
2651 |        "    <tr>\n",
2652 |        "      <th>3</th>\n",
2653 |        "      <td>3</td>\n",
2654 |        "      <td>[]</td>\n",
2655 |        "      <td>[]</td>\n",
2656 |        "      <td>1.15135E+18</td>\n",
2657 |        "      <td>21:24:55</td>\n",
2658 |        "      <td>see i wanna do one of them but they all say th...</td>\n",
2659 |        "    </tr>\n",
2660 |        "    <tr>\n",
2661 |        "      <th>4</th>\n",
2662 |        "      <td>4</td>\n",
2663 |        "      <td>[]</td>\n",
2664 |        "      <td>[]</td>\n",
2665 |        "      <td>1.15135E+18</td>\n",
2666 |        "      <td>21:24:51</td>\n",
2667 |        "      <td>IS IT clinical depression or is it the palpabl...</td>\n",
2668 |        "    </tr>\n",
2669 |        "    <tr>\n",
2670 |        "      <th>5</th>\n",
2671 |        "      <td>5</td>\n",
2672 |        "      <td>[]</td>\n",
2673 |        "      <td>[]</td>\n",
2674 |        "      <td>1.15135E+18</td>\n",
2675 |        "      <td>21:24:46</td>\n",
2676 |        "      <td>My new mantra for dealing with my anxiety/depr...</td>\n",
2677 |        "    </tr>\n",
2678 |        "    <tr>\n",
2679 |        "      <th>6</th>\n",
2680 |        "      <td>6</td>\n",
2681 |        "      <td>[]</td>\n",
2682 |        "      <td>[]</td>\n",
2683 |        "      <td>1.15135E+18</td>\n",
2684 |        "      <td>21:24:41</td>\n",
2685 |        "      <td>Can I get a woot woot for 3 months depression ...</td>\n",
2686 |        "    </tr>\n",
2687 |        "    <tr>\n",
2688 |        "      <th>7</th>\n",
2689 |        "      <td>7</td>\n",
2690 |        "      <td>[]</td>\n",
2691 |        "      <td>[]</td>\n",
2692 |        "      <td>1.15135E+18</td>\n",
2693 |        "      <td>21:24:37</td>\n",
2694 |        "      <td>Hope it's working for you.  I was on sertralin...</td>\n",
2695 |        "    </tr>\n",
2696 |        "    <tr>\n",
2697 |        "      <th>8</th>\n",
2698 |        "      <td>8</td>\n",
2699 |        "      <td>[]</td>\n",
2700 |        "      <td>[]</td>\n",
2701 |        "      <td>1.15135E+18</td>\n",
2702 |        "      <td>21:24:22</td>\n",
2703 |        "      <td>When my depression and anxiety strike at the s...</td>\n",
2704 |        "    </tr>\n",
2705 |        "    <tr>\n",
2706 |        "      <th>9</th>\n",
2707 |        "      <td>9</td>\n",
2708 |        "      <td>[]</td>\n",
2709 |        "      <td>[]</td>\n",
2710 |        "      <td>1.15135E+18</td>\n",
2711 |        "      <td>21:24:20</td>\n",
2712 |        "      <td>I want to leave, but I'm still waiting for you...</td>\n",
2713 |        "    </tr>\n",
2714 |        "    <tr>\n",
2715 |        "      <th>10</th>\n",
2716 |        "      <td>10</td>\n",
2717 |        "      <td>[]</td>\n",
2718 |        "      <td>[]</td>\n",
2719 |        "      <td>1.15135E+18</td>\n",
2720 |        "      <td>21:24:07</td>\n",
2721 |        "      <td>lrt i have FUCKING DEPRESSION</td>\n",
2722 |        "    </tr>\n",
2723 |        "    <tr>\n",
2724 |        "      <th>11</th>\n",
2725 |        "      <td>11</td>\n",
2726 |        "      <td>[]</td>\n",
2727 |        "      <td>[]</td>\n",
2728 |        "      <td>1.15135E+18</td>\n",
2729 |        "      <td>21:24:07</td>\n",
2730 |        "      <td>If you’re a new mother who is tired from postp...</td>\n",
2731 |        "    </tr>\n",
2732 |        "    <tr>\n",
2733 |        "      <th>12</th>\n",
2734 |        "      <td>12</td>\n",
2735 |        "      <td>[]</td>\n",
2736 |        "      <td>[]</td>\n",
2737 |        "      <td>1.15135E+18</td>\n",
2738 |        "      <td>21:24:04</td>\n",
2739 |        "      <td>Currently 5:23 and I’ve got depression  Ranger...</td>\n",
2740 |        "    </tr>\n",
2741 |        "    <tr>\n",
2742 |        "      <th>13</th>\n",
2743 |        "      <td>13</td>\n",
2744 |        "      <td>[]</td>\n",
2745 |        "      <td>[]</td>\n",
2746 |        "      <td>1.15135E+18</td>\n",
2747 |        "      <td>21:24:01</td>\n",
2748 |        "      <td>omg wish I could swim cause I'm gonna drown in...</td>\n",
2749 |        "    </tr>\n",
2750 |        "    <tr>\n",
2751 |        "      <th>14</th>\n",
2752 |        "      <td>14</td>\n",
2753 |        "      <td>[]</td>\n",
2754 |        "      <td>[]</td>\n",
2755 |        "      <td>1.15135E+18</td>\n",
2756 |        "      <td>21:24:00</td>\n",
2757 |        "      <td>I don’t talk about it much at all unless you’r...</td>\n",
2758 |        "    </tr>\n",
2759 |        "    <tr>\n",
2760 |        "      <th>15</th>\n",
2761 |        "      <td>15</td>\n",
2762 |        "      <td>[]</td>\n",
2763 |        "      <td>[]</td>\n",
2764 |        "      <td>1.15135E+18</td>\n",
2765 |        "      <td>21:23:55</td>\n",
2766 |        "      <td>🚨🚨🚨 If someone can help me by suggesting me ho...</td>\n",
2767 |        "    </tr>\n",
2768 |        "    <tr>\n",
2769 |        "      <th>16</th>\n",
2770 |        "      <td>16</td>\n",
2771 |        "      <td>[]</td>\n",
2772 |        "      <td>[]</td>\n",
2773 |        "      <td>1.15135E+18</td>\n",
2774 |        "      <td>21:23:39</td>\n",
2775 |        "      <td>luv 2 just start crying bc you're thinking of ...</td>\n",
2776 |        "    </tr>\n",
2777 |        "    <tr>\n",
2778 |        "      <th>17</th>\n",
2779 |        "      <td>17</td>\n",
2780 |        "      <td>[]</td>\n",
2781 |        "      <td>[]</td>\n",
2782 |        "      <td>1.15135E+18</td>\n",
2783 |        "      <td>21:23:33</td>\n",
2784 |        "      <td>yOu cAnT hUrT mE DePrEsSiOn GoT mE AlReAdY</td>\n",
2785 |        "    </tr>\n",
2786 |        "    <tr>\n",
2787 |        "      <th>18</th>\n",
2788 |        "      <td>18</td>\n",
2789 |        "      <td>[]</td>\n",
2790 |        "      <td>[]</td>\n",
2791 |        "      <td>1.15135E+18</td>\n",
2792 |        "      <td>21:23:32</td>\n",
2793 |        "      <td>The free market cab cure your depression, just...</td>\n",
2794 |        "    </tr>\n",
2795 |        "    <tr>\n",
2796 |        "      <th>19</th>\n",
2797 |        "      <td>19</td>\n",
2798 |        "      <td>[]</td>\n",
2799 |        "      <td>[]</td>\n",
2800 |        "      <td>1.15135E+18</td>\n",
2801 |        "      <td>21:23:31</td>\n",
2802 |        "      <td>I’m not steeped enough in the research to have...</td>\n",
2803 |        "    </tr>\n",
2804 |        "    <tr>\n",
2805 |        "      <th>20</th>\n",
2806 |        "      <td>20</td>\n",
2807 |        "      <td>[]</td>\n",
2808 |        "      <td>['#triggerwarning']</td>\n",
2809 |        "      <td>1.15135E+18</td>\n",
2810 |        "      <td>21:23:28</td>\n",
2811 |        "      <td>I feel like I can’t work for more than two to ...</td>\n",
2812 |        "    </tr>\n",
2813 |        "    <tr>\n",
2814 |        "      <th>21</th>\n",
2815 |        "      <td>21</td>\n",
2816 |        "      <td>[]</td>\n",
2817 |        "      <td>[]</td>\n",
2818 |        "      <td>1.15135E+18</td>\n",
2819 |        "      <td>21:23:28</td>\n",
2820 |        "      <td>dvdRadio 102 Still looking for a title.  (That...</td>\n",
2821 |        "    </tr>\n",
2822 |        "    <tr>\n",
2823 |        "      <th>22</th>\n",
2824 |        "      <td>22</td>\n",
2825 |        "      <td>[]</td>\n",
2826 |        "      <td>[]</td>\n",
2827 |        "      <td>1.15135E+18</td>\n",
2828 |        "      <td>21:23:27</td>\n",
2829 |        "      <td>Do you recommend this for every kind of depres...</td>\n",
2830 |        "    </tr>\n",
2831 |        "    <tr>\n",
2832 |        "      <th>23</th>\n",
2833 |        "      <td>23</td>\n",
2834 |        "      <td>[]</td>\n",
2835 |        "      <td>[]</td>\n",
2836 |        "      <td>1.15135E+18</td>\n",
2837 |        "      <td>21:23:26</td>\n",
2838 |        "      <td>I was having a bad day and was all depressed. ...</td>\n",
2839 |        "    </tr>\n",
2840 |        "    <tr>\n",
2841 |        "      <th>24</th>\n",
2842 |        "      <td>24</td>\n",
2843 |        "      <td>[]</td>\n",
2844 |        "      <td>[]</td>\n",
2845 |        "      <td>1.15135E+18</td>\n",
2846 |        "      <td>21:23:25</td>\n",
2847 |        "      <td>but it completely makes sense tho it a surviva...</td>\n",
2848 |        "    </tr>\n",
2849 |        "    <tr>\n",
2850 |        "      <th>25</th>\n",
2851 |        "      <td>25</td>\n",
2852 |        "      <td>[]</td>\n",
2853 |        "      <td>[]</td>\n",
2854 |        "      <td>1.15135E+18</td>\n",
2855 |        "      <td>21:23:23</td>\n",
2856 |        "      <td>For example a top has to know how to deal with...</td>\n",
2857 |        "    </tr>\n",
2858 |        "    <tr>\n",
2859 |        "      <th>26</th>\n",
2860 |        "      <td>26</td>\n",
2861 |        "      <td>[]</td>\n",
2862 |        "      <td>[]</td>\n",
2863 |        "      <td>1.15135E+18</td>\n",
2864 |        "      <td>21:23:17</td>\n",
2865 |        "      <td>So. Here is the short and skinny about me here...</td>\n",
2866 |        "    </tr>\n",
2867 |        "    <tr>\n",
2868 |        "      <th>27</th>\n",
2869 |        "      <td>27</td>\n",
2870 |        "      <td>[]</td>\n",
2871 |        "      <td>[]</td>\n",
2872 |        "      <td>1.15135E+18</td>\n",
2873 |        "      <td>21:23:12</td>\n",
2874 |        "      <td>me when someone points out my crippling anxiet...</td>\n",
2875 |        "    </tr>\n",
2876 |        "    <tr>\n",
2877 |        "      <th>28</th>\n",
2878 |        "      <td>28</td>\n",
2879 |        "      <td>[]</td>\n",
2880 |        "      <td>[]</td>\n",
2881 |        "      <td>1.15135E+18</td>\n",
2882 |        "      <td>21:23:05</td>\n",
2883 |        "      <td>No one:  Literally no one:  Clair Boucher/ム尺ﾉﾶ...</td>\n",
2884 |        "    </tr>\n",
2885 |        "    <tr>\n",
2886 |        "      <th>29</th>\n",
2887 |        "      <td>29</td>\n",
2888 |        "      <td>[]</td>\n",
2889 |        "      <td>[]</td>\n",
2890 |        "      <td>1.15135E+18</td>\n",
2891 |        "      <td>21:22:52</td>\n",
2892 |        "      <td>As a platoon leader I have to deal with that m...</td>\n",
2893 |        "    </tr>\n",
2894 |        "    <tr>\n",
2895 |        "      <th>...</th>\n",
2896 |        "      <td>...</td>\n",
2897 |        "      <td>...</td>\n",
2898 |        "      <td>...</td>\n",
2899 |        "      <td>...</td>\n",
2900 |        "      <td>...</td>\n",
2901 |        "      <td>...</td>\n",
2902 |        "    </tr>\n",
2903 |        "    <tr>\n",
2904 |        "      <th>225147</th>\n",
2905 |        "      <td>NaN</td>\n",
2906 |        "      <td>[]</td>\n",
2907 |        "      <td>[]</td>\n",
2908 |        "      <td>1152368125251338242</td>\n",
2909 |        "      <td>17:02:25</td>\n",
2910 |        "      <td>Suicide by oyster is a noble way to go  https:...</td>\n",
2911 |        "    </tr>\n",
2912 |        "    <tr>\n",
2913 |        "      <th>225148</th>\n",
2914 |        "      <td>NaN</td>\n",
2915 |        "      <td>[]</td>\n",
2916 |        "      <td>[]</td>\n",
2917 |        "      <td>1152368121723965440</td>\n",
2918 |        "      <td>17:02:24</td>\n",
2919 |        "      <td>floors are covered in water, so obviously a cl...</td>\n",
2920 |        "    </tr>\n",
2921 |        "    <tr>\n",
2922 |        "      <th>225149</th>\n",
2923 |        "      <td>NaN</td>\n",
2924 |        "      <td>[]</td>\n",
2925 |        "      <td>[]</td>\n",
2926 |        "      <td>1152368089264205825</td>\n",
2927 |        "      <td>17:02:17</td>\n",
2928 |        "      <td>That's a depressingly relatable perspective.  ...</td>\n",
2929 |        "    </tr>\n",
2930 |        "    <tr>\n",
2931 |        "      <th>225150</th>\n",
2932 |        "      <td>NaN</td>\n",
2933 |        "      <td>[]</td>\n",
2934 |        "      <td>[]</td>\n",
2935 |        "      <td>1152368083346120705</td>\n",
2936 |        "      <td>17:02:15</td>\n",
2937 |        "      <td>@glitterndior https://twitter.com/DankNeme/sta...</td>\n",
2938 |        "    </tr>\n",
2939 |        "    <tr>\n",
2940 |        "      <th>225151</th>\n",
2941 |        "      <td>NaN</td>\n",
2942 |        "      <td>[]</td>\n",
2943 |        "      <td>[]</td>\n",
2944 |        "      <td>1152368075833872384</td>\n",
2945 |        "      <td>17:02:13</td>\n",
2946 |        "      <td>TW for suicide and fatphobia.  My mom has seve...</td>\n",
2947 |        "    </tr>\n",
2948 |        "    <tr>\n",
2949 |        "      <th>225152</th>\n",
2950 |        "      <td>NaN</td>\n",
2951 |        "      <td>[]</td>\n",
2952 |        "      <td>[]</td>\n",
2953 |        "      <td>1152368031642869762</td>\n",
2954 |        "      <td>17:02:03</td>\n",
2955 |        "      <td>« Le professeur meurt et Tokyo se suicide » jl...</td>\n",
2956 |        "    </tr>\n",
2957 |        "    <tr>\n",
2958 |        "      <th>225153</th>\n",
2959 |        "      <td>NaN</td>\n",
2960 |        "      <td>[]</td>\n",
2961 |        "      <td>[]</td>\n",
2962 |        "      <td>1152368026013982720</td>\n",
2963 |        "      <td>17:02:02</td>\n",
2964 |        "      <td>Telling a gay youth is choices are suicide, ex...</td>\n",
2965 |        "    </tr>\n",
2966 |        "    <tr>\n",
2967 |        "      <th>225154</th>\n",
2968 |        "      <td>NaN</td>\n",
2969 |        "      <td>[]</td>\n",
2970 |        "      <td>[]</td>\n",
2971 |        "      <td>1152368025192058880</td>\n",
2972 |        "      <td>17:02:01</td>\n",
2973 |        "      <td>Tokyo tue professor et se suicide</td>\n",
2974 |        "    </tr>\n",
2975 |        "    <tr>\n",
2976 |        "      <th>225155</th>\n",
2977 |        "      <td>NaN</td>\n",
2978 |        "      <td>[]</td>\n",
2979 |        "      <td>[]</td>\n",
2980 |        "      <td>1152368018585980928</td>\n",
2981 |        "      <td>17:02:00</td>\n",
2982 |        "      <td>suicide's time :))</td>\n",
2983 |        "    </tr>\n",
2984 |        "    <tr>\n",
2985 |        "      <th>225156</th>\n",
2986 |        "      <td>NaN</td>\n",
2987 |        "      <td>[]</td>\n",
2988 |        "      <td>[]</td>\n",
2989 |        "      <td>1152368009643798528</td>\n",
2990 |        "      <td>17:01:58</td>\n",
2991 |        "      <td>For Those Considering Suicide  https://youtu.b...</td>\n",
2992 |        "    </tr>\n",
2993 |        "    <tr>\n",
2994 |        "      <th>225157</th>\n",
2995 |        "      <td>NaN</td>\n",
2996 |        "      <td>[]</td>\n",
2997 |        "      <td>[]</td>\n",
2998 |        "      <td>1152367994976309248</td>\n",
2999 |        "      <td>17:01:54</td>\n",
3000 |        "      <td>Tf suicide isn’t no joke  https://twitter.com/...</td>\n",
3001 |        "    </tr>\n",
3002 |        "    <tr>\n",
3003 |        "      <th>225158</th>\n",
3004 |        "      <td>NaN</td>\n",
3005 |        "      <td>[]</td>\n",
3006 |        "      <td>[]</td>\n",
3007 |        "      <td>1152367988194123776</td>\n",
3008 |        "      <td>17:01:53</td>\n",
3009 |        "      <td>It always brings to mind the “body in the bag ...</td>\n",
3010 |        "    </tr>\n",
3011 |        "    <tr>\n",
3012 |        "      <th>225159</th>\n",
3013 |        "      <td>NaN</td>\n",
3014 |        "      <td>[]</td>\n",
3015 |        "      <td>['#suicidesilence', '#youonlyliveonce', '#lege...</td>\n",
3016 |        "      <td>1152367958796062721</td>\n",
3017 |        "      <td>17:01:45</td>\n",
3018 |        "      <td>You only live once so just go fucking nuts!Go!...</td>\n",
3019 |        "    </tr>\n",
3020 |        "    <tr>\n",
3021 |        "      <th>225160</th>\n",
3022 |        "      <td>NaN</td>\n",
3023 |        "      <td>[]</td>\n",
3024 |        "      <td>[]</td>\n",
3025 |        "      <td>1152367936046346241</td>\n",
3026 |        "      <td>17:01:40</td>\n",
3027 |        "      <td>i cant wait to entrap a woman into a web of vi...</td>\n",
3028 |        "    </tr>\n",
3029 |        "    <tr>\n",
3030 |        "      <th>225161</th>\n",
3031 |        "      <td>NaN</td>\n",
3032 |        "      <td>[]</td>\n",
3033 |        "      <td>[]</td>\n",
3034 |        "      <td>1152367856283029506</td>\n",
3035 |        "      <td>17:01:21</td>\n",
3036 |        "      <td>고마웠었어 #€</td>\n",
3037 |        "    </tr>\n",
3038 |        "    <tr>\n",
3039 |        "      <th>225162</th>\n",
3040 |        "      <td>NaN</td>\n",
3041 |        "      <td>[]</td>\n",
3042 |        "      <td>[]</td>\n",
3043 |        "      <td>1152367827321544707</td>\n",
3044 |        "      <td>17:01:14</td>\n",
3045 |        "      <td>The “Clinton Suicide Squad “ is gearing up as ...</td>\n",
3046 |        "    </tr>\n",
3047 |        "    <tr>\n",
3048 |        "      <th>225163</th>\n",
3049 |        "      <td>NaN</td>\n",
3050 |        "      <td>[]</td>\n",
3051 |        "      <td>[]</td>\n",
3052 |        "      <td>1152367826348531712</td>\n",
3053 |        "      <td>17:01:14</td>\n",
3054 |        "      <td>Last Monday a I had to tell a client his benef...</td>\n",
3055 |        "    </tr>\n",
3056 |        "    <tr>\n",
3057 |        "      <th>225164</th>\n",
3058 |        "      <td>NaN</td>\n",
3059 |        "      <td>[]</td>\n",
3060 |        "      <td>[]</td>\n",
3061 |        "      <td>1152367802705174528</td>\n",
3062 |        "      <td>17:01:08</td>\n",
3063 |        "      <td>http://bit.ly/MurderOfTalent  Why is the publ...</td>\n",
3064 |        "    </tr>\n",
3065 |        "    <tr>\n",
3066 |        "      <th>225165</th>\n",
3067 |        "      <td>NaN</td>\n",
3068 |        "      <td>[]</td>\n",
3069 |        "      <td>[]</td>\n",
3070 |        "      <td>1152367775291019264</td>\n",
3071 |        "      <td>17:01:02</td>\n",
3072 |        "      <td>戸塚：電車の車内でケータイが鳴った一八木さんが「いま電話の中だから電車切るぞ」って言ってケー...</td>\n",
3073 |        "    </tr>\n",
3074 |        "    <tr>\n",
3075 |        "      <th>225166</th>\n",
3076 |        "      <td>NaN</td>\n",
3077 |        "      <td>[]</td>\n",
3078 |        "      <td>[]</td>\n",
3079 |        "      <td>1152367743833923584</td>\n",
3080 |        "      <td>17:00:54</td>\n",
3081 |        "      <td>y'a pas d'incruste ti é la famille</td>\n",
3082 |        "    </tr>\n",
3083 |        "    <tr>\n",
3084 |        "      <th>225167</th>\n",
3085 |        "      <td>NaN</td>\n",
3086 |        "      <td>[]</td>\n",
3087 |        "      <td>['#mentalhealth', '#suicideprevention']</td>\n",
3088 |        "      <td>1152367735445131264</td>\n",
3089 |        "      <td>17:00:52</td>\n",
3090 |        "      <td>A study will use CCTV from certain locations t...</td>\n",
3091 |        "    </tr>\n",
3092 |        "    <tr>\n",
3093 |        "      <th>225168</th>\n",
3094 |        "      <td>NaN</td>\n",
3095 |        "      <td>[]</td>\n",
3096 |        "      <td>[]</td>\n",
3097 |        "      <td>1152367689433636866</td>\n",
3098 |        "      <td>17:00:41</td>\n",
3099 |        "      <td>Since I was reminded of her today, everyone pl...</td>\n",
3100 |        "    </tr>\n",
3101 |        "    <tr>\n",
3102 |        "      <th>225169</th>\n",
3103 |        "      <td>NaN</td>\n",
3104 |        "      <td>[]</td>\n",
3105 |        "      <td>[]</td>\n",
3106 |        "      <td>1152367664192471040</td>\n",
3107 |        "      <td>17:00:35</td>\n",
3108 |        "      <td>Mariko was a quick favorite for me. I'm glad s...</td>\n",
3109 |        "    </tr>\n",
3110 |        "    <tr>\n",
3111 |        "      <th>225170</th>\n",
3112 |        "      <td>NaN</td>\n",
3113 |        "      <td>[]</td>\n",
3114 |        "      <td>[]</td>\n",
3115 |        "      <td>1152367606919237635</td>\n",
3116 |        "      <td>17:00:22</td>\n",
3117 |        "      <td>pic.twitter.com/sm9tNmrEQJ</td>\n",
3118 |        "    </tr>\n",
3119 |        "    <tr>\n",
3120 |        "      <th>225171</th>\n",
3121 |        "      <td>NaN</td>\n",
3122 |        "      <td>[]</td>\n",
3123 |        "      <td>[]</td>\n",
3124 |        "      <td>1152367589961732096</td>\n",
3125 |        "      <td>17:00:18</td>\n",
3126 |        "      <td>https://youtu.be/WJ0OkkIDZug   Deathnote is r...</td>\n",
3127 |        "    </tr>\n",
3128 |        "    <tr>\n",
3129 |        "      <th>225172</th>\n",
3130 |        "      <td>NaN</td>\n",
3131 |        "      <td>[]</td>\n",
3132 |        "      <td>[]</td>\n",
3133 |        "      <td>1152367589030391809</td>\n",
3134 |        "      <td>17:00:17</td>\n",
3135 |        "      <td>えっ？！オニィ結構なお歳……（今知った） 変な声でちゃった(笑)</td>\n",
3136 |        "    </tr>\n",
3137 |        "    <tr>\n",
3138 |        "      <th>225173</th>\n",
3139 |        "      <td>NaN</td>\n",
3140 |        "      <td>[]</td>\n",
3141 |        "      <td>['#physicianfriday', '#suicide', '#physicians'...</td>\n",
3142 |        "      <td>1152367565483761664</td>\n",
3143 |        "      <td>17:00:12</td>\n",
3144 |        "      <td>#PhysicianFriday \"Let's empower doctors to tak...</td>\n",
3145 |        "    </tr>\n",
3146 |        "    <tr>\n",
3147 |        "      <th>225174</th>\n",
3148 |        "      <td>NaN</td>\n",
3149 |        "      <td>[]</td>\n",
3150 |        "      <td>['#aztrauma', '#traumatraining', '#suicide', '...</td>\n",
3151 |        "      <td>1152367519283367936</td>\n",
3152 |        "      <td>17:00:01</td>\n",
3153 |        "      <td>A spike in suicides among teenage boys in the ...</td>\n",
3154 |        "    </tr>\n",
3155 |        "    <tr>\n",
3156 |        "      <th>225175</th>\n",
3157 |        "      <td>NaN</td>\n",
3158 |        "      <td>[]</td>\n",
3159 |        "      <td>[]</td>\n",
3160 |        "      <td>1152367516083204096</td>\n",
3161 |        "      <td>17:00:00</td>\n",
3162 |        "      <td>Need some support? Check out the following res...</td>\n",
3163 |        "    </tr>\n",
3164 |        "    <tr>\n",
3165 |        "      <th>225176</th>\n",
3166 |        "      <td>NaN</td>\n",
3167 |        "      <td>[]</td>\n",
3168 |        "      <td>[]</td>\n",
3169 |        "      <td>1152367515978424321</td>\n",
3170 |        "      <td>17:00:00</td>\n",
3171 |        "      <td>You can improve the quality of life for a frie...</td>\n",
3172 |        "    </tr>\n",
3173 |        "  </tbody>\n",
3174 |        "</table>\n",
3175 |        "<p>225177 rows × 6 columns</p>\n",
3176 |        "</div>"
3177 |       ],
3178 |       "text/plain": [
3179 |        "       Unnamed: 0 cashtags                                           hashtags  \\\n",
3180 |        "0               0       []                                                 []   \n",
3181 |        "1               1       []                                                 []   \n",
3182 |        "2               2       []  ['#depression', '#uncoveringthenewu', '#change...   \n",
3183 |        "3               3       []                                                 []   \n",
3184 |        "4               4       []                                                 []   \n",
3185 |        "5               5       []                                                 []   \n",
3186 |        "6               6       []                                                 []   \n",
3187 |        "7               7       []                                                 []   \n",
3188 |        "8               8       []                                                 []   \n",
3189 |        "9               9       []                                                 []   \n",
3190 |        "10             10       []                                                 []   \n",
3191 |        "11             11       []                                                 []   \n",
3192 |        "12             12       []                                                 []   \n",
3193 |        "13             13       []                                                 []   \n",
3194 |        "14             14       []                                                 []   \n",
3195 |        "15             15       []                                                 []   \n",
3196 |        "16             16       []                                                 []   \n",
3197 |        "17             17       []                                                 []   \n",
3198 |        "18             18       []                                                 []   \n",
3199 |        "19             19       []                                                 []   \n",
3200 |        "20             20       []                                ['#triggerwarning']   \n",
3201 |        "21             21       []                                                 []   \n",
3202 |        "22             22       []                                                 []   \n",
3203 |        "23             23       []                                                 []   \n",
3204 |        "24             24       []                                                 []   \n",
3205 |        "25             25       []                                                 []   \n",
3206 |        "26             26       []                                                 []   \n",
3207 |        "27             27       []                                                 []   \n",
3208 |        "28             28       []                                                 []   \n",
3209 |        "29             29       []                                                 []   \n",
3210 |        "...           ...      ...                                                ...   \n",
3211 |        "225147        NaN       []                                                 []   \n",
3212 |        "225148        NaN       []                                                 []   \n",
3213 |        "225149        NaN       []                                                 []   \n",
3214 |        "225150        NaN       []                                                 []   \n",
3215 |        "225151        NaN       []                                                 []   \n",
3216 |        "225152        NaN       []                                                 []   \n",
3217 |        "225153        NaN       []                                                 []   \n",
3218 |        "225154        NaN       []                                                 []   \n",
3219 |        "225155        NaN       []                                                 []   \n",
3220 |        "225156        NaN       []                                                 []   \n",
3221 |        "225157        NaN       []                                                 []   \n",
3222 |        "225158        NaN       []                                                 []   \n",
3223 |        "225159        NaN       []  ['#suicidesilence', '#youonlyliveonce', '#lege...   \n",
3224 |        "225160        NaN       []                                                 []   \n",
3225 |        "225161        NaN       []                                                 []   \n",
3226 |        "225162        NaN       []                                                 []   \n",
3227 |        "225163        NaN       []                                                 []   \n",
3228 |        "225164        NaN       []                                                 []   \n",
3229 |        "225165        NaN       []                                                 []   \n",
3230 |        "225166        NaN       []                                                 []   \n",
3231 |        "225167        NaN       []            ['#mentalhealth', '#suicideprevention']   \n",
3232 |        "225168        NaN       []                                                 []   \n",
3233 |        "225169        NaN       []                                                 []   \n",
3234 |        "225170        NaN       []                                                 []   \n",
3235 |        "225171        NaN       []                                                 []   \n",
3236 |        "225172        NaN       []                                                 []   \n",
3237 |        "225173        NaN       []  ['#physicianfriday', '#suicide', '#physicians'...   \n",
3238 |        "225174        NaN       []  ['#aztrauma', '#traumatraining', '#suicide', '...   \n",
3239 |        "225175        NaN       []                                                 []   \n",
3240 |        "225176        NaN       []                                                 []   \n",
3241 |        "\n",
3242 |        "                         id      time  \\\n",
3243 |        "0               1.15135E+18  21:25:13   \n",
3244 |        "1               1.15135E+18  21:25:07   \n",
3245 |        "2               1.15135E+18  21:25:06   \n",
3246 |        "3               1.15135E+18  21:24:55   \n",
3247 |        "4               1.15135E+18  21:24:51   \n",
3248 |        "5               1.15135E+18  21:24:46   \n",
3249 |        "6               1.15135E+18  21:24:41   \n",
3250 |        "7               1.15135E+18  21:24:37   \n",
3251 |        "8               1.15135E+18  21:24:22   \n",
3252 |        "9               1.15135E+18  21:24:20   \n",
3253 |        "10              1.15135E+18  21:24:07   \n",
3254 |        "11              1.15135E+18  21:24:07   \n",
3255 |        "12              1.15135E+18  21:24:04   \n",
3256 |        "13              1.15135E+18  21:24:01   \n",
3257 |        "14              1.15135E+18  21:24:00   \n",
3258 |        "15              1.15135E+18  21:23:55   \n",
3259 |        "16              1.15135E+18  21:23:39   \n",
3260 |        "17              1.15135E+18  21:23:33   \n",
3261 |        "18              1.15135E+18  21:23:32   \n",
3262 |        "19              1.15135E+18  21:23:31   \n",
3263 |        "20              1.15135E+18  21:23:28   \n",
3264 |        "21              1.15135E+18  21:23:28   \n",
3265 |        "22              1.15135E+18  21:23:27   \n",
3266 |        "23              1.15135E+18  21:23:26   \n",
3267 |        "24              1.15135E+18  21:23:25   \n",
3268 |        "25              1.15135E+18  21:23:23   \n",
3269 |        "26              1.15135E+18  21:23:17   \n",
3270 |        "27              1.15135E+18  21:23:12   \n",
3271 |        "28              1.15135E+18  21:23:05   \n",
3272 |        "29              1.15135E+18  21:22:52   \n",
3273 |        "...                     ...       ...   \n",
3274 |        "225147  1152368125251338242  17:02:25   \n",
3275 |        "225148  1152368121723965440  17:02:24   \n",
3276 |        "225149  1152368089264205825  17:02:17   \n",
3277 |        "225150  1152368083346120705  17:02:15   \n",
3278 |        "225151  1152368075833872384  17:02:13   \n",
3279 |        "225152  1152368031642869762  17:02:03   \n",
3280 |        "225153  1152368026013982720  17:02:02   \n",
3281 |        "225154  1152368025192058880  17:02:01   \n",
3282 |        "225155  1152368018585980928  17:02:00   \n",
3283 |        "225156  1152368009643798528  17:01:58   \n",
3284 |        "225157  1152367994976309248  17:01:54   \n",
3285 |        "225158  1152367988194123776  17:01:53   \n",
3286 |        "225159  1152367958796062721  17:01:45   \n",
3287 |        "225160  1152367936046346241  17:01:40   \n",
3288 |        "225161  1152367856283029506  17:01:21   \n",
3289 |        "225162  1152367827321544707  17:01:14   \n",
3290 |        "225163  1152367826348531712  17:01:14   \n",
3291 |        "225164  1152367802705174528  17:01:08   \n",
3292 |        "225165  1152367775291019264  17:01:02   \n",
3293 |        "225166  1152367743833923584  17:00:54   \n",
3294 |        "225167  1152367735445131264  17:00:52   \n",
3295 |        "225168  1152367689433636866  17:00:41   \n",
3296 |        "225169  1152367664192471040  17:00:35   \n",
3297 |        "225170  1152367606919237635  17:00:22   \n",
3298 |        "225171  1152367589961732096  17:00:18   \n",
3299 |        "225172  1152367589030391809  17:00:17   \n",
3300 |        "225173  1152367565483761664  17:00:12   \n",
3301 |        "225174  1152367519283367936  17:00:01   \n",
3302 |        "225175  1152367516083204096  17:00:00   \n",
3303 |        "225176  1152367515978424321  17:00:00   \n",
3304 |        "\n",
3305 |        "                                                    tweet  \n",
3306 |        "0       Wow, my dad yday: “you don’t take those stupid...  \n",
3307 |        "1       what part of this was really harmfult of a lot...  \n",
3308 |        "2       one of the ways I got through my #depression i...  \n",
3309 |        "3       see i wanna do one of them but they all say th...  \n",
3310 |        "4       IS IT clinical depression or is it the palpabl...  \n",
3311 |        "5       My new mantra for dealing with my anxiety/depr...  \n",
3312 |        "6       Can I get a woot woot for 3 months depression ...  \n",
3313 |        "7       Hope it's working for you.  I was on sertralin...  \n",
3314 |        "8       When my depression and anxiety strike at the s...  \n",
3315 |        "9       I want to leave, but I'm still waiting for you...  \n",
3316 |        "10                          lrt i have FUCKING DEPRESSION  \n",
3317 |        "11      If you’re a new mother who is tired from postp...  \n",
3318 |        "12      Currently 5:23 and I’ve got depression  Ranger...  \n",
3319 |        "13      omg wish I could swim cause I'm gonna drown in...  \n",
3320 |        "14      I don’t talk about it much at all unless you’r...  \n",
3321 |        "15      🚨🚨🚨 If someone can help me by suggesting me ho...  \n",
3322 |        "16      luv 2 just start crying bc you're thinking of ...  \n",
3323 |        "17             yOu cAnT hUrT mE DePrEsSiOn GoT mE AlReAdY  \n",
3324 |        "18      The free market cab cure your depression, just...  \n",
3325 |        "19      I’m not steeped enough in the research to have...  \n",
3326 |        "20      I feel like I can’t work for more than two to ...  \n",
3327 |        "21      dvdRadio 102 Still looking for a title.  (That...  \n",
3328 |        "22      Do you recommend this for every kind of depres...  \n",
3329 |        "23      I was having a bad day and was all depressed. ...  \n",
3330 |        "24      but it completely makes sense tho it a surviva...  \n",
3331 |        "25      For example a top has to know how to deal with...  \n",
3332 |        "26      So. Here is the short and skinny about me here...  \n",
3333 |        "27      me when someone points out my crippling anxiet...  \n",
3334 |        "28      No one:  Literally no one:  Clair Boucher/ム尺ﾉﾶ...  \n",
3335 |        "29      As a platoon leader I have to deal with that m...  \n",
3336 |        "...                                                   ...  \n",
3337 |        "225147  Suicide by oyster is a noble way to go  https:...  \n",
3338 |        "225148  floors are covered in water, so obviously a cl...  \n",
3339 |        "225149  That's a depressingly relatable perspective.  ...  \n",
3340 |        "225150  @glitterndior https://twitter.com/DankNeme/sta...  \n",
3341 |        "225151  TW for suicide and fatphobia.  My mom has seve...  \n",
3342 |        "225152  « Le professeur meurt et Tokyo se suicide » jl...  \n",
3343 |        "225153  Telling a gay youth is choices are suicide, ex...  \n",
3344 |        "225154                  Tokyo tue professor et se suicide  \n",
3345 |        "225155                                 suicide's time :))  \n",
3346 |        "225156  For Those Considering Suicide  https://youtu.b...  \n",
3347 |        "225157  Tf suicide isn’t no joke  https://twitter.com/...  \n",
3348 |        "225158  It always brings to mind the “body in the bag ...  \n",
3349 |        "225159  You only live once so just go fucking nuts!Go!...  \n",
3350 |        "225160  i cant wait to entrap a woman into a web of vi...  \n",
3351 |        "225161                                           고마웠었어 #€  \n",
3352 |        "225162  The “Clinton Suicide Squad “ is gearing up as ...  \n",
3353 |        "225163  Last Monday a I had to tell a client his benef...  \n",
3354 |        "225164   http://bit.ly/MurderOfTalent  Why is the publ...  \n",
3355 |        "225165  戸塚：電車の車内でケータイが鳴った一八木さんが「いま電話の中だから電車切るぞ」って言ってケー...  \n",
3356 |        "225166                 y'a pas d'incruste ti é la famille  \n",
3357 |        "225167  A study will use CCTV from certain locations t...  \n",
3358 |        "225168  Since I was reminded of her today, everyone pl...  \n",
3359 |        "225169  Mariko was a quick favorite for me. I'm glad s...  \n",
3360 |        "225170                         pic.twitter.com/sm9tNmrEQJ  \n",
3361 |        "225171   https://youtu.be/WJ0OkkIDZug   Deathnote is r...  \n",
3362 |        "225172                   えっ？！オニィ結構なお歳……（今知った） 変な声でちゃった(笑)  \n",
3363 |        "225173  #PhysicianFriday \"Let's empower doctors to tak...  \n",
3364 |        "225174  A spike in suicides among teenage boys in the ...  \n",
3365 |        "225175  Need some support? Check out the following res...  \n",
3366 |        "225176  You can improve the quality of life for a frie...  \n",
3367 |        "\n",
3368 |        "[225177 rows x 6 columns]"
3369 |       ]
3370 |      },
3371 |      "execution_count": 30,
3372 |      "metadata": {},
3373 |      "output_type": "execute_result"
3374 |     }
3375 |    ],
3376 |    "source": [
3377 |     "df_row_reindex = pd.concat([depression_tweets_df, hopeless_tweets_df, lonely_tweets_df, antidepressant_tweets_df, antidepressants_tweets_df, suicide_tweets_df], ignore_index=True)\n",
3378 |     "\n",
3379 |     "df_row_reindex"
3380 |    ]
3381 |   },
3382 |   {
3383 |    "cell_type": "code",
3384 |    "execution_count": 36,
3385 |    "metadata": {},
3386 |    "outputs": [],
3387 |    "source": [
3388 |     "df = df_row_reindex"
3389 |    ]
3390 |   },
3391 |   {
3392 |    "cell_type": "code",
3393 |    "execution_count": 42,
3394 |    "metadata": {},
3395 |    "outputs": [
3396 |     {
3397 |      "data": {
3398 |       "text/html": [
3399 |        "<div>\n",
3400 |        "<style scoped>\n",
3401 |        "    .dataframe tbody tr th:only-of-type {\n",
3402 |        "        vertical-align: middle;\n",
3403 |        "    }\n",
3404 |        "\n",
3405 |        "    .dataframe tbody tr th {\n",
3406 |        "        vertical-align: top;\n",
3407 |        "    }\n",
3408 |        "\n",
3409 |        "    .dataframe thead th {\n",
3410 |        "        text-align: right;\n",
3411 |        "    }\n",
3412 |        "</style>\n",
3413 |        "<table border=\"1\" class=\"dataframe\">\n",
3414 |        "  <thead>\n",
3415 |        "    <tr style=\"text-align: right;\">\n",
3416 |        "      <th></th>\n",
3417 |        "      <th>Unnamed: 0</th>\n",
3418 |        "      <th>cashtags</th>\n",
3419 |        "      <th>hashtags</th>\n",
3420 |        "      <th>id</th>\n",
3421 |        "      <th>time</th>\n",
3422 |        "      <th>tweet</th>\n",
3423 |        "    </tr>\n",
3424 |        "  </thead>\n",
3425 |        "  <tbody>\n",
3426 |        "    <tr>\n",
3427 |        "      <th>0</th>\n",
3428 |        "      <td>0</td>\n",
3429 |        "      <td>[]</td>\n",
3430 |        "      <td>[]</td>\n",
3431 |        "      <td>1.15135E+18</td>\n",
3432 |        "      <td>21:25:13</td>\n",
3433 |        "      <td>Wow, my dad yday: “you don’t take those stupid...</td>\n",
3434 |        "    </tr>\n",
3435 |        "    <tr>\n",
3436 |        "      <th>1</th>\n",
3437 |        "      <td>1</td>\n",
3438 |        "      <td>[]</td>\n",
3439 |        "      <td>[]</td>\n",
3440 |        "      <td>1.15135E+18</td>\n",
3441 |        "      <td>21:25:07</td>\n",
3442 |        "      <td>what part of this was really harmfult of a lot...</td>\n",
3443 |        "    </tr>\n",
3444 |        "    <tr>\n",
3445 |        "      <th>2</th>\n",
3446 |        "      <td>2</td>\n",
3447 |        "      <td>[]</td>\n",
3448 |        "      <td>['#depression', '#uncoveringthenewu', '#change...</td>\n",
3449 |        "      <td>1.15135E+18</td>\n",
3450 |        "      <td>21:25:06</td>\n",
3451 |        "      <td>one of the ways I got through my #depression i...</td>\n",
3452 |        "    </tr>\n",
3453 |        "    <tr>\n",
3454 |        "      <th>3</th>\n",
3455 |        "      <td>3</td>\n",
3456 |        "      <td>[]</td>\n",
3457 |        "      <td>[]</td>\n",
3458 |        "      <td>1.15135E+18</td>\n",
3459 |        "      <td>21:24:55</td>\n",
3460 |        "      <td>see i wanna do one of them but they all say th...</td>\n",
3461 |        "    </tr>\n",
3462 |        "    <tr>\n",
3463 |        "      <th>4</th>\n",
3464 |        "      <td>4</td>\n",
3465 |        "      <td>[]</td>\n",
3466 |        "      <td>[]</td>\n",
3467 |        "      <td>1.15135E+18</td>\n",
3468 |        "      <td>21:24:51</td>\n",
3469 |        "      <td>IS IT clinical depression or is it the palpabl...</td>\n",
3470 |        "    </tr>\n",
3471 |        "  </tbody>\n",
3472 |        "</table>\n",
3473 |        "</div>"
3474 |       ],
3475 |       "text/plain": [
3476 |        "  Unnamed: 0 cashtags                                           hashtags  \\\n",
3477 |        "0          0       []                                                 []   \n",
3478 |        "1          1       []                                                 []   \n",
3479 |        "2          2       []  ['#depression', '#uncoveringthenewu', '#change...   \n",
3480 |        "3          3       []                                                 []   \n",
3481 |        "4          4       []                                                 []   \n",
3482 |        "\n",
3483 |        "            id      time                                              tweet  \n",
3484 |        "0  1.15135E+18  21:25:13  Wow, my dad yday: “you don’t take those stupid...  \n",
3485 |        "1  1.15135E+18  21:25:07  what part of this was really harmfult of a lot...  \n",
3486 |        "2  1.15135E+18  21:25:06  one of the ways I got through my #depression i...  \n",
3487 |        "3  1.15135E+18  21:24:55  see i wanna do one of them but they all say th...  \n",
3488 |        "4  1.15135E+18  21:24:51  IS IT clinical depression or is it the palpabl...  "
3489 |       ]
3490 |      },
3491 |      "execution_count": 42,
3492 |      "metadata": {},
3493 |      "output_type": "execute_result"
3494 |     }
3495 |    ],
3496 |    "source": [
3497 |     "depressive_twint_tweets_df = df_row_reindex\n",
3498 |     "depressive_twint_tweets_df.head()"
3499 |    ]
3500 |   },
3501 |   {
3502 |    "cell_type": "code",
3503 |    "execution_count": 44,
3504 |    "metadata": {},
3505 |    "outputs": [],
3506 |    "source": [
3507 |     "depressive_twint_tweets_df = df.drop_duplicates()\n"
3508 |    ]
3509 |   },
3510 |   {
3511 |    "cell_type": "code",
3512 |    "execution_count": 48,
3513 |    "metadata": {},
3514 |    "outputs": [
3515 |     {
3516 |      "data": {
3517 |       "text/html": [
3518 |        "<div>\n",
3519 |        "<style scoped>\n",
3520 |        "    .dataframe tbody tr th:only-of-type {\n",
3521 |        "        vertical-align: middle;\n",
3522 |        "    }\n",
3523 |        "\n",
3524 |        "    .dataframe tbody tr th {\n",
3525 |        "        vertical-align: top;\n",
3526 |        "    }\n",
3527 |        "\n",
3528 |        "    .dataframe thead th {\n",
3529 |        "        text-align: right;\n",
3530 |        "    }\n",
3531 |        "</style>\n",
3532 |        "<table border=\"1\" class=\"dataframe\">\n",
3533 |        "  <thead>\n",
3534 |        "    <tr style=\"text-align: right;\">\n",
3535 |        "      <th></th>\n",
3536 |        "      <th>Unnamed: 0</th>\n",
3537 |        "      <th>cashtags</th>\n",
3538 |        "      <th>hashtags</th>\n",
3539 |        "      <th>id</th>\n",
3540 |        "      <th>time</th>\n",
3541 |        "      <th>tweet</th>\n",
3542 |        "    </tr>\n",
3543 |        "  </thead>\n",
3544 |        "  <tbody>\n",
3545 |        "    <tr>\n",
3546 |        "      <th>0</th>\n",
3547 |        "      <td>0</td>\n",
3548 |        "      <td>[]</td>\n",
3549 |        "      <td>[]</td>\n",
3550 |        "      <td>1.15135E+18</td>\n",
3551 |        "      <td>21:25:13</td>\n",
3552 |        "      <td>Wow, my dad yday: “you don’t take those stupid...</td>\n",
3553 |        "    </tr>\n",
3554 |        "    <tr>\n",
3555 |        "      <th>1</th>\n",
3556 |        "      <td>1</td>\n",
3557 |        "      <td>[]</td>\n",
3558 |        "      <td>[]</td>\n",
3559 |        "      <td>1.15135E+18</td>\n",
3560 |        "      <td>21:25:07</td>\n",
3561 |        "      <td>what part of this was really harmfult of a lot...</td>\n",
3562 |        "    </tr>\n",
3563 |        "    <tr>\n",
3564 |        "      <th>2</th>\n",
3565 |        "      <td>2</td>\n",
3566 |        "      <td>[]</td>\n",
3567 |        "      <td>['#depression', '#uncoveringthenewu', '#change...</td>\n",
3568 |        "      <td>1.15135E+18</td>\n",
3569 |        "      <td>21:25:06</td>\n",
3570 |        "      <td>one of the ways I got through my #depression i...</td>\n",
3571 |        "    </tr>\n",
3572 |        "    <tr>\n",
3573 |        "      <th>3</th>\n",
3574 |        "      <td>3</td>\n",
3575 |        "      <td>[]</td>\n",
3576 |        "      <td>[]</td>\n",
3577 |        "      <td>1.15135E+18</td>\n",
3578 |        "      <td>21:24:55</td>\n",
3579 |        "      <td>see i wanna do one of them but they all say th...</td>\n",
3580 |        "    </tr>\n",
3581 |        "    <tr>\n",
3582 |        "      <th>4</th>\n",
3583 |        "      <td>4</td>\n",
3584 |        "      <td>[]</td>\n",
3585 |        "      <td>[]</td>\n",
3586 |        "      <td>1.15135E+18</td>\n",
3587 |        "      <td>21:24:51</td>\n",
3588 |        "      <td>IS IT clinical depression or is it the palpabl...</td>\n",
3589 |        "    </tr>\n",
3590 |        "    <tr>\n",
3591 |        "      <th>5</th>\n",
3592 |        "      <td>5</td>\n",
3593 |        "      <td>[]</td>\n",
3594 |        "      <td>[]</td>\n",
3595 |        "      <td>1.15135E+18</td>\n",
3596 |        "      <td>21:24:46</td>\n",
3597 |        "      <td>My new mantra for dealing with my anxiety/depr...</td>\n",
3598 |        "    </tr>\n",
3599 |        "    <tr>\n",
3600 |        "      <th>6</th>\n",
3601 |        "      <td>6</td>\n",
3602 |        "      <td>[]</td>\n",
3603 |        "      <td>[]</td>\n",
3604 |        "      <td>1.15135E+18</td>\n",
3605 |        "      <td>21:24:41</td>\n",
3606 |        "      <td>Can I get a woot woot for 3 months depression ...</td>\n",
3607 |        "    </tr>\n",
3608 |        "    <tr>\n",
3609 |        "      <th>7</th>\n",
3610 |        "      <td>7</td>\n",
3611 |        "      <td>[]</td>\n",
3612 |        "      <td>[]</td>\n",
3613 |        "      <td>1.15135E+18</td>\n",
3614 |        "      <td>21:24:37</td>\n",
3615 |        "      <td>Hope it's working for you.  I was on sertralin...</td>\n",
3616 |        "    </tr>\n",
3617 |        "    <tr>\n",
3618 |        "      <th>8</th>\n",
3619 |        "      <td>8</td>\n",
3620 |        "      <td>[]</td>\n",
3621 |        "      <td>[]</td>\n",
3622 |        "      <td>1.15135E+18</td>\n",
3623 |        "      <td>21:24:22</td>\n",
3624 |        "      <td>When my depression and anxiety strike at the s...</td>\n",
3625 |        "    </tr>\n",
3626 |        "    <tr>\n",
3627 |        "      <th>9</th>\n",
3628 |        "      <td>9</td>\n",
3629 |        "      <td>[]</td>\n",
3630 |        "      <td>[]</td>\n",
3631 |        "      <td>1.15135E+18</td>\n",
3632 |        "      <td>21:24:20</td>\n",
3633 |        "      <td>I want to leave, but I'm still waiting for you...</td>\n",
3634 |        "    </tr>\n",
3635 |        "    <tr>\n",
3636 |        "      <th>10</th>\n",
3637 |        "      <td>10</td>\n",
3638 |        "      <td>[]</td>\n",
3639 |        "      <td>[]</td>\n",
3640 |        "      <td>1.15135E+18</td>\n",
3641 |        "      <td>21:24:07</td>\n",
3642 |        "      <td>lrt i have FUCKING DEPRESSION</td>\n",
3643 |        "    </tr>\n",
3644 |        "    <tr>\n",
3645 |        "      <th>11</th>\n",
3646 |        "      <td>11</td>\n",
3647 |        "      <td>[]</td>\n",
3648 |        "      <td>[]</td>\n",
3649 |        "      <td>1.15135E+18</td>\n",
3650 |        "      <td>21:24:07</td>\n",
3651 |        "      <td>If you’re a new mother who is tired from postp...</td>\n",
3652 |        "    </tr>\n",
3653 |        "    <tr>\n",
3654 |        "      <th>12</th>\n",
3655 |        "      <td>12</td>\n",
3656 |        "      <td>[]</td>\n",
3657 |        "      <td>[]</td>\n",
3658 |        "      <td>1.15135E+18</td>\n",
3659 |        "      <td>21:24:04</td>\n",
3660 |        "      <td>Currently 5:23 and I’ve got depression  Ranger...</td>\n",
3661 |        "    </tr>\n",
3662 |        "    <tr>\n",
3663 |        "      <th>13</th>\n",
3664 |        "      <td>13</td>\n",
3665 |        "      <td>[]</td>\n",
3666 |        "      <td>[]</td>\n",
3667 |        "      <td>1.15135E+18</td>\n",
3668 |        "      <td>21:24:01</td>\n",
3669 |        "      <td>omg wish I could swim cause I'm gonna drown in...</td>\n",
3670 |        "    </tr>\n",
3671 |        "    <tr>\n",
3672 |        "      <th>14</th>\n",
3673 |        "      <td>14</td>\n",
3674 |        "      <td>[]</td>\n",
3675 |        "      <td>[]</td>\n",
3676 |        "      <td>1.15135E+18</td>\n",
3677 |        "      <td>21:24:00</td>\n",
3678 |        "      <td>I don’t talk about it much at all unless you’r...</td>\n",
3679 |        "    </tr>\n",
3680 |        "    <tr>\n",
3681 |        "      <th>15</th>\n",
3682 |        "      <td>15</td>\n",
3683 |        "      <td>[]</td>\n",
3684 |        "      <td>[]</td>\n",
3685 |        "      <td>1.15135E+18</td>\n",
3686 |        "      <td>21:23:55</td>\n",
3687 |        "      <td>🚨🚨🚨 If someone can help me by suggesting me ho...</td>\n",
3688 |        "    </tr>\n",
3689 |        "    <tr>\n",
3690 |        "      <th>16</th>\n",
3691 |        "      <td>16</td>\n",
3692 |        "      <td>[]</td>\n",
3693 |        "      <td>[]</td>\n",
3694 |        "      <td>1.15135E+18</td>\n",
3695 |        "      <td>21:23:39</td>\n",
3696 |        "      <td>luv 2 just start crying bc you're thinking of ...</td>\n",
3697 |        "    </tr>\n",
3698 |        "    <tr>\n",
3699 |        "      <th>17</th>\n",
3700 |        "      <td>17</td>\n",
3701 |        "      <td>[]</td>\n",
3702 |        "      <td>[]</td>\n",
3703 |        "      <td>1.15135E+18</td>\n",
3704 |        "      <td>21:23:33</td>\n",
3705 |        "      <td>yOu cAnT hUrT mE DePrEsSiOn GoT mE AlReAdY</td>\n",
3706 |        "    </tr>\n",
3707 |        "    <tr>\n",
3708 |        "      <th>18</th>\n",
3709 |        "      <td>18</td>\n",
3710 |        "      <td>[]</td>\n",
3711 |        "      <td>[]</td>\n",
3712 |        "      <td>1.15135E+18</td>\n",
3713 |        "      <td>21:23:32</td>\n",
3714 |        "      <td>The free market cab cure your depression, just...</td>\n",
3715 |        "    </tr>\n",
3716 |        "    <tr>\n",
3717 |        "      <th>19</th>\n",
3718 |        "      <td>19</td>\n",
3719 |        "      <td>[]</td>\n",
3720 |        "      <td>[]</td>\n",
3721 |        "      <td>1.15135E+18</td>\n",
3722 |        "      <td>21:23:31</td>\n",
3723 |        "      <td>I’m not steeped enough in the research to have...</td>\n",
3724 |        "    </tr>\n",
3725 |        "    <tr>\n",
3726 |        "      <th>20</th>\n",
3727 |        "      <td>20</td>\n",
3728 |        "      <td>[]</td>\n",
3729 |        "      <td>['#triggerwarning']</td>\n",
3730 |        "      <td>1.15135E+18</td>\n",
3731 |        "      <td>21:23:28</td>\n",
3732 |        "      <td>I feel like I can’t work for more than two to ...</td>\n",
3733 |        "    </tr>\n",
3734 |        "    <tr>\n",
3735 |        "      <th>21</th>\n",
3736 |        "      <td>21</td>\n",
3737 |        "      <td>[]</td>\n",
3738 |        "      <td>[]</td>\n",
3739 |        "      <td>1.15135E+18</td>\n",
3740 |        "      <td>21:23:28</td>\n",
3741 |        "      <td>dvdRadio 102 Still looking for a title.  (That...</td>\n",
3742 |        "    </tr>\n",
3743 |        "    <tr>\n",
3744 |        "      <th>22</th>\n",
3745 |        "      <td>22</td>\n",
3746 |        "      <td>[]</td>\n",
3747 |        "      <td>[]</td>\n",
3748 |        "      <td>1.15135E+18</td>\n",
3749 |        "      <td>21:23:27</td>\n",
3750 |        "      <td>Do you recommend this for every kind of depres...</td>\n",
3751 |        "    </tr>\n",
3752 |        "    <tr>\n",
3753 |        "      <th>23</th>\n",
3754 |        "      <td>23</td>\n",
3755 |        "      <td>[]</td>\n",
3756 |        "      <td>[]</td>\n",
3757 |        "      <td>1.15135E+18</td>\n",
3758 |        "      <td>21:23:26</td>\n",
3759 |        "      <td>I was having a bad day and was all depressed. ...</td>\n",
3760 |        "    </tr>\n",
3761 |        "    <tr>\n",
3762 |        "      <th>24</th>\n",
3763 |        "      <td>24</td>\n",
3764 |        "      <td>[]</td>\n",
3765 |        "      <td>[]</td>\n",
3766 |        "      <td>1.15135E+18</td>\n",
3767 |        "      <td>21:23:25</td>\n",
3768 |        "      <td>but it completely makes sense tho it a surviva...</td>\n",
3769 |        "    </tr>\n",
3770 |        "    <tr>\n",
3771 |        "      <th>25</th>\n",
3772 |        "      <td>25</td>\n",
3773 |        "      <td>[]</td>\n",
3774 |        "      <td>[]</td>\n",
3775 |        "      <td>1.15135E+18</td>\n",
3776 |        "      <td>21:23:23</td>\n",
3777 |        "      <td>For example a top has to know how to deal with...</td>\n",
3778 |        "    </tr>\n",
3779 |        "    <tr>\n",
3780 |        "      <th>26</th>\n",
3781 |        "      <td>26</td>\n",
3782 |        "      <td>[]</td>\n",
3783 |        "      <td>[]</td>\n",
3784 |        "      <td>1.15135E+18</td>\n",
3785 |        "      <td>21:23:17</td>\n",
3786 |        "      <td>So. Here is the short and skinny about me here...</td>\n",
3787 |        "    </tr>\n",
3788 |        "    <tr>\n",
3789 |        "      <th>27</th>\n",
3790 |        "      <td>27</td>\n",
3791 |        "      <td>[]</td>\n",
3792 |        "      <td>[]</td>\n",
3793 |        "      <td>1.15135E+18</td>\n",
3794 |        "      <td>21:23:12</td>\n",
3795 |        "      <td>me when someone points out my crippling anxiet...</td>\n",
3796 |        "    </tr>\n",
3797 |        "    <tr>\n",
3798 |        "      <th>28</th>\n",
3799 |        "      <td>28</td>\n",
3800 |        "      <td>[]</td>\n",
3801 |        "      <td>[]</td>\n",
3802 |        "      <td>1.15135E+18</td>\n",
3803 |        "      <td>21:23:05</td>\n",
3804 |        "      <td>No one:  Literally no one:  Clair Boucher/ム尺ﾉﾶ...</td>\n",
3805 |        "    </tr>\n",
3806 |        "    <tr>\n",
3807 |        "      <th>29</th>\n",
3808 |        "      <td>29</td>\n",
3809 |        "      <td>[]</td>\n",
3810 |        "      <td>[]</td>\n",
3811 |        "      <td>1.15135E+18</td>\n",
3812 |        "      <td>21:22:52</td>\n",
3813 |        "      <td>As a platoon leader I have to deal with that m...</td>\n",
3814 |        "    </tr>\n",
3815 |        "    <tr>\n",
3816 |        "      <th>...</th>\n",
3817 |        "      <td>...</td>\n",
3818 |        "      <td>...</td>\n",
3819 |        "      <td>...</td>\n",
3820 |        "      <td>...</td>\n",
3821 |        "      <td>...</td>\n",
3822 |        "      <td>...</td>\n",
3823 |        "    </tr>\n",
3824 |        "    <tr>\n",
3825 |        "      <th>225147</th>\n",
3826 |        "      <td>NaN</td>\n",
3827 |        "      <td>[]</td>\n",
3828 |        "      <td>[]</td>\n",
3829 |        "      <td>1152368125251338242</td>\n",
3830 |        "      <td>17:02:25</td>\n",
3831 |        "      <td>Suicide by oyster is a noble way to go  https:...</td>\n",
3832 |        "    </tr>\n",
3833 |        "    <tr>\n",
3834 |        "      <th>225148</th>\n",
3835 |        "      <td>NaN</td>\n",
3836 |        "      <td>[]</td>\n",
3837 |        "      <td>[]</td>\n",
3838 |        "      <td>1152368121723965440</td>\n",
3839 |        "      <td>17:02:24</td>\n",
3840 |        "      <td>floors are covered in water, so obviously a cl...</td>\n",
3841 |        "    </tr>\n",
3842 |        "    <tr>\n",
3843 |        "      <th>225149</th>\n",
3844 |        "      <td>NaN</td>\n",
3845 |        "      <td>[]</td>\n",
3846 |        "      <td>[]</td>\n",
3847 |        "      <td>1152368089264205825</td>\n",
3848 |        "      <td>17:02:17</td>\n",
3849 |        "      <td>That's a depressingly relatable perspective.  ...</td>\n",
3850 |        "    </tr>\n",
3851 |        "    <tr>\n",
3852 |        "      <th>225150</th>\n",
3853 |        "      <td>NaN</td>\n",
3854 |        "      <td>[]</td>\n",
3855 |        "      <td>[]</td>\n",
3856 |        "      <td>1152368083346120705</td>\n",
3857 |        "      <td>17:02:15</td>\n",
3858 |        "      <td>@glitterndior https://twitter.com/DankNeme/sta...</td>\n",
3859 |        "    </tr>\n",
3860 |        "    <tr>\n",
3861 |        "      <th>225151</th>\n",
3862 |        "      <td>NaN</td>\n",
3863 |        "      <td>[]</td>\n",
3864 |        "      <td>[]</td>\n",
3865 |        "      <td>1152368075833872384</td>\n",
3866 |        "      <td>17:02:13</td>\n",
3867 |        "      <td>TW for suicide and fatphobia.  My mom has seve...</td>\n",
3868 |        "    </tr>\n",
3869 |        "    <tr>\n",
3870 |        "      <th>225152</th>\n",
3871 |        "      <td>NaN</td>\n",
3872 |        "      <td>[]</td>\n",
3873 |        "      <td>[]</td>\n",
3874 |        "      <td>1152368031642869762</td>\n",
3875 |        "      <td>17:02:03</td>\n",
3876 |        "      <td>« Le professeur meurt et Tokyo se suicide » jl...</td>\n",
3877 |        "    </tr>\n",
3878 |        "    <tr>\n",
3879 |        "      <th>225153</th>\n",
3880 |        "      <td>NaN</td>\n",
3881 |        "      <td>[]</td>\n",
3882 |        "      <td>[]</td>\n",
3883 |        "      <td>1152368026013982720</td>\n",
3884 |        "      <td>17:02:02</td>\n",
3885 |        "      <td>Telling a gay youth is choices are suicide, ex...</td>\n",
3886 |        "    </tr>\n",
3887 |        "    <tr>\n",
3888 |        "      <th>225154</th>\n",
3889 |        "      <td>NaN</td>\n",
3890 |        "      <td>[]</td>\n",
3891 |        "      <td>[]</td>\n",
3892 |        "      <td>1152368025192058880</td>\n",
3893 |        "      <td>17:02:01</td>\n",
3894 |        "      <td>Tokyo tue professor et se suicide</td>\n",
3895 |        "    </tr>\n",
3896 |        "    <tr>\n",
3897 |        "      <th>225155</th>\n",
3898 |        "      <td>NaN</td>\n",
3899 |        "      <td>[]</td>\n",
3900 |        "      <td>[]</td>\n",
3901 |        "      <td>1152368018585980928</td>\n",
3902 |        "      <td>17:02:00</td>\n",
3903 |        "      <td>suicide's time :))</td>\n",
3904 |        "    </tr>\n",
3905 |        "    <tr>\n",
3906 |        "      <th>225156</th>\n",
3907 |        "      <td>NaN</td>\n",
3908 |        "      <td>[]</td>\n",
3909 |        "      <td>[]</td>\n",
3910 |        "      <td>1152368009643798528</td>\n",
3911 |        "      <td>17:01:58</td>\n",
3912 |        "      <td>For Those Considering Suicide  https://youtu.b...</td>\n",
3913 |        "    </tr>\n",
3914 |        "    <tr>\n",
3915 |        "      <th>225157</th>\n",
3916 |        "      <td>NaN</td>\n",
3917 |        "      <td>[]</td>\n",
3918 |        "      <td>[]</td>\n",
3919 |        "      <td>1152367994976309248</td>\n",
3920 |        "      <td>17:01:54</td>\n",
3921 |        "      <td>Tf suicide isn’t no joke  https://twitter.com/...</td>\n",
3922 |        "    </tr>\n",
3923 |        "    <tr>\n",
3924 |        "      <th>225158</th>\n",
3925 |        "      <td>NaN</td>\n",
3926 |        "      <td>[]</td>\n",
3927 |        "      <td>[]</td>\n",
3928 |        "      <td>1152367988194123776</td>\n",
3929 |        "      <td>17:01:53</td>\n",
3930 |        "      <td>It always brings to mind the “body in the bag ...</td>\n",
3931 |        "    </tr>\n",
3932 |        "    <tr>\n",
3933 |        "      <th>225159</th>\n",
3934 |        "      <td>NaN</td>\n",
3935 |        "      <td>[]</td>\n",
3936 |        "      <td>['#suicidesilence', '#youonlyliveonce', '#lege...</td>\n",
3937 |        "      <td>1152367958796062721</td>\n",
3938 |        "      <td>17:01:45</td>\n",
3939 |        "      <td>You only live once so just go fucking nuts!Go!...</td>\n",
3940 |        "    </tr>\n",
3941 |        "    <tr>\n",
3942 |        "      <th>225160</th>\n",
3943 |        "      <td>NaN</td>\n",
3944 |        "      <td>[]</td>\n",
3945 |        "      <td>[]</td>\n",
3946 |        "      <td>1152367936046346241</td>\n",
3947 |        "      <td>17:01:40</td>\n",
3948 |        "      <td>i cant wait to entrap a woman into a web of vi...</td>\n",
3949 |        "    </tr>\n",
3950 |        "    <tr>\n",
3951 |        "      <th>225161</th>\n",
3952 |        "      <td>NaN</td>\n",
3953 |        "      <td>[]</td>\n",
3954 |        "      <td>[]</td>\n",
3955 |        "      <td>1152367856283029506</td>\n",
3956 |        "      <td>17:01:21</td>\n",
3957 |        "      <td>고마웠었어 #€</td>\n",
3958 |        "    </tr>\n",
3959 |        "    <tr>\n",
3960 |        "      <th>225162</th>\n",
3961 |        "      <td>NaN</td>\n",
3962 |        "      <td>[]</td>\n",
3963 |        "      <td>[]</td>\n",
3964 |        "      <td>1152367827321544707</td>\n",
3965 |        "      <td>17:01:14</td>\n",
3966 |        "      <td>The “Clinton Suicide Squad “ is gearing up as ...</td>\n",
3967 |        "    </tr>\n",
3968 |        "    <tr>\n",
3969 |        "      <th>225163</th>\n",
3970 |        "      <td>NaN</td>\n",
3971 |        "      <td>[]</td>\n",
3972 |        "      <td>[]</td>\n",
3973 |        "      <td>1152367826348531712</td>\n",
3974 |        "      <td>17:01:14</td>\n",
3975 |        "      <td>Last Monday a I had to tell a client his benef...</td>\n",
3976 |        "    </tr>\n",
3977 |        "    <tr>\n",
3978 |        "      <th>225164</th>\n",
3979 |        "      <td>NaN</td>\n",
3980 |        "      <td>[]</td>\n",
3981 |        "      <td>[]</td>\n",
3982 |        "      <td>1152367802705174528</td>\n",
3983 |        "      <td>17:01:08</td>\n",
3984 |        "      <td>http://bit.ly/MurderOfTalent  Why is the publ...</td>\n",
3985 |        "    </tr>\n",
3986 |        "    <tr>\n",
3987 |        "      <th>225165</th>\n",
3988 |        "      <td>NaN</td>\n",
3989 |        "      <td>[]</td>\n",
3990 |        "      <td>[]</td>\n",
3991 |        "      <td>1152367775291019264</td>\n",
3992 |        "      <td>17:01:02</td>\n",
3993 |        "      <td>戸塚：電車の車内でケータイが鳴った一八木さんが「いま電話の中だから電車切るぞ」って言ってケー...</td>\n",
3994 |        "    </tr>\n",
3995 |        "    <tr>\n",
3996 |        "      <th>225166</th>\n",
3997 |        "      <td>NaN</td>\n",
3998 |        "      <td>[]</td>\n",
3999 |        "      <td>[]</td>\n",
4000 |        "      <td>1152367743833923584</td>\n",
4001 |        "      <td>17:00:54</td>\n",
4002 |        "      <td>y'a pas d'incruste ti é la famille</td>\n",
4003 |        "    </tr>\n",
4004 |        "    <tr>\n",
4005 |        "      <th>225167</th>\n",
4006 |        "      <td>NaN</td>\n",
4007 |        "      <td>[]</td>\n",
4008 |        "      <td>['#mentalhealth', '#suicideprevention']</td>\n",
4009 |        "      <td>1152367735445131264</td>\n",
4010 |        "      <td>17:00:52</td>\n",
4011 |        "      <td>A study will use CCTV from certain locations t...</td>\n",
4012 |        "    </tr>\n",
4013 |        "    <tr>\n",
4014 |        "      <th>225168</th>\n",
4015 |        "      <td>NaN</td>\n",
4016 |        "      <td>[]</td>\n",
4017 |        "      <td>[]</td>\n",
4018 |        "      <td>1152367689433636866</td>\n",
4019 |        "      <td>17:00:41</td>\n",
4020 |        "      <td>Since I was reminded of her today, everyone pl...</td>\n",
4021 |        "    </tr>\n",
4022 |        "    <tr>\n",
4023 |        "      <th>225169</th>\n",
4024 |        "      <td>NaN</td>\n",
4025 |        "      <td>[]</td>\n",
4026 |        "      <td>[]</td>\n",
4027 |        "      <td>1152367664192471040</td>\n",
4028 |        "      <td>17:00:35</td>\n",
4029 |        "      <td>Mariko was a quick favorite for me. I'm glad s...</td>\n",
4030 |        "    </tr>\n",
4031 |        "    <tr>\n",
4032 |        "      <th>225170</th>\n",
4033 |        "      <td>NaN</td>\n",
4034 |        "      <td>[]</td>\n",
4035 |        "      <td>[]</td>\n",
4036 |        "      <td>1152367606919237635</td>\n",
4037 |        "      <td>17:00:22</td>\n",
4038 |        "      <td>pic.twitter.com/sm9tNmrEQJ</td>\n",
4039 |        "    </tr>\n",
4040 |        "    <tr>\n",
4041 |        "      <th>225171</th>\n",
4042 |        "      <td>NaN</td>\n",
4043 |        "      <td>[]</td>\n",
4044 |        "      <td>[]</td>\n",
4045 |        "      <td>1152367589961732096</td>\n",
4046 |        "      <td>17:00:18</td>\n",
4047 |        "      <td>https://youtu.be/WJ0OkkIDZug   Deathnote is r...</td>\n",
4048 |        "    </tr>\n",
4049 |        "    <tr>\n",
4050 |        "      <th>225172</th>\n",
4051 |        "      <td>NaN</td>\n",
4052 |        "      <td>[]</td>\n",
4053 |        "      <td>[]</td>\n",
4054 |        "      <td>1152367589030391809</td>\n",
4055 |        "      <td>17:00:17</td>\n",
4056 |        "      <td>えっ？！オニィ結構なお歳……（今知った） 変な声でちゃった(笑)</td>\n",
4057 |        "    </tr>\n",
4058 |        "    <tr>\n",
4059 |        "      <th>225173</th>\n",
4060 |        "      <td>NaN</td>\n",
4061 |        "      <td>[]</td>\n",
4062 |        "      <td>['#physicianfriday', '#suicide', '#physicians'...</td>\n",
4063 |        "      <td>1152367565483761664</td>\n",
4064 |        "      <td>17:00:12</td>\n",
4065 |        "      <td>#PhysicianFriday \"Let's empower doctors to tak...</td>\n",
4066 |        "    </tr>\n",
4067 |        "    <tr>\n",
4068 |        "      <th>225174</th>\n",
4069 |        "      <td>NaN</td>\n",
4070 |        "      <td>[]</td>\n",
4071 |        "      <td>['#aztrauma', '#traumatraining', '#suicide', '...</td>\n",
4072 |        "      <td>1152367519283367936</td>\n",
4073 |        "      <td>17:00:01</td>\n",
4074 |        "      <td>A spike in suicides among teenage boys in the ...</td>\n",
4075 |        "    </tr>\n",
4076 |        "    <tr>\n",
4077 |        "      <th>225175</th>\n",
4078 |        "      <td>NaN</td>\n",
4079 |        "      <td>[]</td>\n",
4080 |        "      <td>[]</td>\n",
4081 |        "      <td>1152367516083204096</td>\n",
4082 |        "      <td>17:00:00</td>\n",
4083 |        "      <td>Need some support? Check out the following res...</td>\n",
4084 |        "    </tr>\n",
4085 |        "    <tr>\n",
4086 |        "      <th>225176</th>\n",
4087 |        "      <td>NaN</td>\n",
4088 |        "      <td>[]</td>\n",
4089 |        "      <td>[]</td>\n",
4090 |        "      <td>1152367515978424321</td>\n",
4091 |        "      <td>17:00:00</td>\n",
4092 |        "      <td>You can improve the quality of life for a frie...</td>\n",
4093 |        "    </tr>\n",
4094 |        "  </tbody>\n",
4095 |        "</table>\n",
4096 |        "<p>224273 rows × 6 columns</p>\n",
4097 |        "</div>"
4098 |       ],
4099 |       "text/plain": [
4100 |        "       Unnamed: 0 cashtags                                           hashtags  \\\n",
4101 |        "0               0       []                                                 []   \n",
4102 |        "1               1       []                                                 []   \n",
4103 |        "2               2       []  ['#depression', '#uncoveringthenewu', '#change...   \n",
4104 |        "3               3       []                                                 []   \n",
4105 |        "4               4       []                                                 []   \n",
4106 |        "5               5       []                                                 []   \n",
4107 |        "6               6       []                                                 []   \n",
4108 |        "7               7       []                                                 []   \n",
4109 |        "8               8       []                                                 []   \n",
4110 |        "9               9       []                                                 []   \n",
4111 |        "10             10       []                                                 []   \n",
4112 |        "11             11       []                                                 []   \n",
4113 |        "12             12       []                                                 []   \n",
4114 |        "13             13       []                                                 []   \n",
4115 |        "14             14       []                                                 []   \n",
4116 |        "15             15       []                                                 []   \n",
4117 |        "16             16       []                                                 []   \n",
4118 |        "17             17       []                                                 []   \n",
4119 |        "18             18       []                                                 []   \n",
4120 |        "19             19       []                                                 []   \n",
4121 |        "20             20       []                                ['#triggerwarning']   \n",
4122 |        "21             21       []                                                 []   \n",
4123 |        "22             22       []                                                 []   \n",
4124 |        "23             23       []                                                 []   \n",
4125 |        "24             24       []                                                 []   \n",
4126 |        "25             25       []                                                 []   \n",
4127 |        "26             26       []                                                 []   \n",
4128 |        "27             27       []                                                 []   \n",
4129 |        "28             28       []                                                 []   \n",
4130 |        "29             29       []                                                 []   \n",
4131 |        "...           ...      ...                                                ...   \n",
4132 |        "225147        NaN       []                                                 []   \n",
4133 |        "225148        NaN       []                                                 []   \n",
4134 |        "225149        NaN       []                                                 []   \n",
4135 |        "225150        NaN       []                                                 []   \n",
4136 |        "225151        NaN       []                                                 []   \n",
4137 |        "225152        NaN       []                                                 []   \n",
4138 |        "225153        NaN       []                                                 []   \n",
4139 |        "225154        NaN       []                                                 []   \n",
4140 |        "225155        NaN       []                                                 []   \n",
4141 |        "225156        NaN       []                                                 []   \n",
4142 |        "225157        NaN       []                                                 []   \n",
4143 |        "225158        NaN       []                                                 []   \n",
4144 |        "225159        NaN       []  ['#suicidesilence', '#youonlyliveonce', '#lege...   \n",
4145 |        "225160        NaN       []                                                 []   \n",
4146 |        "225161        NaN       []                                                 []   \n",
4147 |        "225162        NaN       []                                                 []   \n",
4148 |        "225163        NaN       []                                                 []   \n",
4149 |        "225164        NaN       []                                                 []   \n",
4150 |        "225165        NaN       []                                                 []   \n",
4151 |        "225166        NaN       []                                                 []   \n",
4152 |        "225167        NaN       []            ['#mentalhealth', '#suicideprevention']   \n",
4153 |        "225168        NaN       []                                                 []   \n",
4154 |        "225169        NaN       []                                                 []   \n",
4155 |        "225170        NaN       []                                                 []   \n",
4156 |        "225171        NaN       []                                                 []   \n",
4157 |        "225172        NaN       []                                                 []   \n",
4158 |        "225173        NaN       []  ['#physicianfriday', '#suicide', '#physicians'...   \n",
4159 |        "225174        NaN       []  ['#aztrauma', '#traumatraining', '#suicide', '...   \n",
4160 |        "225175        NaN       []                                                 []   \n",
4161 |        "225176        NaN       []                                                 []   \n",
4162 |        "\n",
4163 |        "                         id      time  \\\n",
4164 |        "0               1.15135E+18  21:25:13   \n",
4165 |        "1               1.15135E+18  21:25:07   \n",
4166 |        "2               1.15135E+18  21:25:06   \n",
4167 |        "3               1.15135E+18  21:24:55   \n",
4168 |        "4               1.15135E+18  21:24:51   \n",
4169 |        "5               1.15135E+18  21:24:46   \n",
4170 |        "6               1.15135E+18  21:24:41   \n",
4171 |        "7               1.15135E+18  21:24:37   \n",
4172 |        "8               1.15135E+18  21:24:22   \n",
4173 |        "9               1.15135E+18  21:24:20   \n",
4174 |        "10              1.15135E+18  21:24:07   \n",
4175 |        "11              1.15135E+18  21:24:07   \n",
4176 |        "12              1.15135E+18  21:24:04   \n",
4177 |        "13              1.15135E+18  21:24:01   \n",
4178 |        "14              1.15135E+18  21:24:00   \n",
4179 |        "15              1.15135E+18  21:23:55   \n",
4180 |        "16              1.15135E+18  21:23:39   \n",
4181 |        "17              1.15135E+18  21:23:33   \n",
4182 |        "18              1.15135E+18  21:23:32   \n",
4183 |        "19              1.15135E+18  21:23:31   \n",
4184 |        "20              1.15135E+18  21:23:28   \n",
4185 |        "21              1.15135E+18  21:23:28   \n",
4186 |        "22              1.15135E+18  21:23:27   \n",
4187 |        "23              1.15135E+18  21:23:26   \n",
4188 |        "24              1.15135E+18  21:23:25   \n",
4189 |        "25              1.15135E+18  21:23:23   \n",
4190 |        "26              1.15135E+18  21:23:17   \n",
4191 |        "27              1.15135E+18  21:23:12   \n",
4192 |        "28              1.15135E+18  21:23:05   \n",
4193 |        "29              1.15135E+18  21:22:52   \n",
4194 |        "...                     ...       ...   \n",
4195 |        "225147  1152368125251338242  17:02:25   \n",
4196 |        "225148  1152368121723965440  17:02:24   \n",
4197 |        "225149  1152368089264205825  17:02:17   \n",
4198 |        "225150  1152368083346120705  17:02:15   \n",
4199 |        "225151  1152368075833872384  17:02:13   \n",
4200 |        "225152  1152368031642869762  17:02:03   \n",
4201 |        "225153  1152368026013982720  17:02:02   \n",
4202 |        "225154  1152368025192058880  17:02:01   \n",
4203 |        "225155  1152368018585980928  17:02:00   \n",
4204 |        "225156  1152368009643798528  17:01:58   \n",
4205 |        "225157  1152367994976309248  17:01:54   \n",
4206 |        "225158  1152367988194123776  17:01:53   \n",
4207 |        "225159  1152367958796062721  17:01:45   \n",
4208 |        "225160  1152367936046346241  17:01:40   \n",
4209 |        "225161  1152367856283029506  17:01:21   \n",
4210 |        "225162  1152367827321544707  17:01:14   \n",
4211 |        "225163  1152367826348531712  17:01:14   \n",
4212 |        "225164  1152367802705174528  17:01:08   \n",
4213 |        "225165  1152367775291019264  17:01:02   \n",
4214 |        "225166  1152367743833923584  17:00:54   \n",
4215 |        "225167  1152367735445131264  17:00:52   \n",
4216 |        "225168  1152367689433636866  17:00:41   \n",
4217 |        "225169  1152367664192471040  17:00:35   \n",
4218 |        "225170  1152367606919237635  17:00:22   \n",
4219 |        "225171  1152367589961732096  17:00:18   \n",
4220 |        "225172  1152367589030391809  17:00:17   \n",
4221 |        "225173  1152367565483761664  17:00:12   \n",
4222 |        "225174  1152367519283367936  17:00:01   \n",
4223 |        "225175  1152367516083204096  17:00:00   \n",
4224 |        "225176  1152367515978424321  17:00:00   \n",
4225 |        "\n",
4226 |        "                                                    tweet  \n",
4227 |        "0       Wow, my dad yday: “you don’t take those stupid...  \n",
4228 |        "1       what part of this was really harmfult of a lot...  \n",
4229 |        "2       one of the ways I got through my #depression i...  \n",
4230 |        "3       see i wanna do one of them but they all say th...  \n",
4231 |        "4       IS IT clinical depression or is it the palpabl...  \n",
4232 |        "5       My new mantra for dealing with my anxiety/depr...  \n",
4233 |        "6       Can I get a woot woot for 3 months depression ...  \n",
4234 |        "7       Hope it's working for you.  I was on sertralin...  \n",
4235 |        "8       When my depression and anxiety strike at the s...  \n",
4236 |        "9       I want to leave, but I'm still waiting for you...  \n",
4237 |        "10                          lrt i have FUCKING DEPRESSION  \n",
4238 |        "11      If you’re a new mother who is tired from postp...  \n",
4239 |        "12      Currently 5:23 and I’ve got depression  Ranger...  \n",
4240 |        "13      omg wish I could swim cause I'm gonna drown in...  \n",
4241 |        "14      I don’t talk about it much at all unless you’r...  \n",
4242 |        "15      🚨🚨🚨 If someone can help me by suggesting me ho...  \n",
4243 |        "16      luv 2 just start crying bc you're thinking of ...  \n",
4244 |        "17             yOu cAnT hUrT mE DePrEsSiOn GoT mE AlReAdY  \n",
4245 |        "18      The free market cab cure your depression, just...  \n",
4246 |        "19      I’m not steeped enough in the research to have...  \n",
4247 |        "20      I feel like I can’t work for more than two to ...  \n",
4248 |        "21      dvdRadio 102 Still looking for a title.  (That...  \n",
4249 |        "22      Do you recommend this for every kind of depres...  \n",
4250 |        "23      I was having a bad day and was all depressed. ...  \n",
4251 |        "24      but it completely makes sense tho it a surviva...  \n",
4252 |        "25      For example a top has to know how to deal with...  \n",
4253 |        "26      So. Here is the short and skinny about me here...  \n",
4254 |        "27      me when someone points out my crippling anxiet...  \n",
4255 |        "28      No one:  Literally no one:  Clair Boucher/ム尺ﾉﾶ...  \n",
4256 |        "29      As a platoon leader I have to deal with that m...  \n",
4257 |        "...                                                   ...  \n",
4258 |        "225147  Suicide by oyster is a noble way to go  https:...  \n",
4259 |        "225148  floors are covered in water, so obviously a cl...  \n",
4260 |        "225149  That's a depressingly relatable perspective.  ...  \n",
4261 |        "225150  @glitterndior https://twitter.com/DankNeme/sta...  \n",
4262 |        "225151  TW for suicide and fatphobia.  My mom has seve...  \n",
4263 |        "225152  « Le professeur meurt et Tokyo se suicide » jl...  \n",
4264 |        "225153  Telling a gay youth is choices are suicide, ex...  \n",
4265 |        "225154                  Tokyo tue professor et se suicide  \n",
4266 |        "225155                                 suicide's time :))  \n",
4267 |        "225156  For Those Considering Suicide  https://youtu.b...  \n",
4268 |        "225157  Tf suicide isn’t no joke  https://twitter.com/...  \n",
4269 |        "225158  It always brings to mind the “body in the bag ...  \n",
4270 |        "225159  You only live once so just go fucking nuts!Go!...  \n",
4271 |        "225160  i cant wait to entrap a woman into a web of vi...  \n",
4272 |        "225161                                           고마웠었어 #€  \n",
4273 |        "225162  The “Clinton Suicide Squad “ is gearing up as ...  \n",
4274 |        "225163  Last Monday a I had to tell a client his benef...  \n",
4275 |        "225164   http://bit.ly/MurderOfTalent  Why is the publ...  \n",
4276 |        "225165  戸塚：電車の車内でケータイが鳴った一八木さんが「いま電話の中だから電車切るぞ」って言ってケー...  \n",
4277 |        "225166                 y'a pas d'incruste ti é la famille  \n",
4278 |        "225167  A study will use CCTV from certain locations t...  \n",
4279 |        "225168  Since I was reminded of her today, everyone pl...  \n",
4280 |        "225169  Mariko was a quick favorite for me. I'm glad s...  \n",
4281 |        "225170                         pic.twitter.com/sm9tNmrEQJ  \n",
4282 |        "225171   https://youtu.be/WJ0OkkIDZug   Deathnote is r...  \n",
4283 |        "225172                   えっ？！オニィ結構なお歳……（今知った） 変な声でちゃった(笑)  \n",
4284 |        "225173  #PhysicianFriday \"Let's empower doctors to tak...  \n",
4285 |        "225174  A spike in suicides among teenage boys in the ...  \n",
4286 |        "225175  Need some support? Check out the following res...  \n",
4287 |        "225176  You can improve the quality of life for a frie...  \n",
4288 |        "\n",
4289 |        "[224273 rows x 6 columns]"
4290 |       ]
4291 |      },
4292 |      "execution_count": 48,
4293 |      "metadata": {},
4294 |      "output_type": "execute_result"
4295 |     }
4296 |    ],
4297 |    "source": [
4298 |     "depressive_twint_tweets_df"
4299 |    ]
4300 |   },
4301 |   {
4302 |    "cell_type": "code",
4303 |    "execution_count": 49,
4304 |    "metadata": {},
4305 |    "outputs": [],
4306 |    "source": [
4307 |     "export_csv = depressive_twint_tweets_df.to_csv(r'depressive_unigram_tweets_final.csv')"
4308 |    ]
4309 |   },
4310 |   {
4311 |    "cell_type": "code",
4312 |    "execution_count": null,
4313 |    "metadata": {},
4314 |    "outputs": [],
4315 |    "source": []
4316 |   }
4317 |  ],
4318 |  "metadata": {
4319 |   "kernelspec": {
4320 |    "name": "Python 3.8.3 64-bit ('base': conda)",
4321 |    "display_name": "Python 3.8.3 64-bit ('base': conda)",
4322 |    "metadata": {
4323 |     "interpreter": {
4324 |      "hash": "49e8b44c8c86fbe7b3f3589e64730502565b20435433ce44148baa614a6d2e5f"
4325 |     }
4326 |    }
4327 |   },
4328 |   "language_info": {
4329 |    "codemirror_mode": {
4330 |     "name": "ipython",
4331 |     "version": 3
4332 |    },
4333 |    "file_extension": ".py",
4334 |    "mimetype": "text/x-python",
4335 |    "name": "python",
4336 |    "nbconvert_exporter": "python",
4337 |    "pygments_lexer": "ipython3",
4338 |    "version": "3.8.3-final"
4339 |   }
4340 |  },
4341 |  "nbformat": 4,
4342 |  "nbformat_minor": 2
4343 | }


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Welcome !
 2 | 
 3 | ### Hi there, I'm tulasi ram - Data Scientist [codeLOVEr] 
 4 | 
 5 | * Know more about me [** Portfolio **](https://tulasiram-portfolio.netlify.app) 👋
 6 | 
 7 | 
 8 | ## I'm a Data Science, Machine Learning, NLP, Deep Learning, Artificial Intelligence Enthusiast!!
 9 | 
10 | - 🔭 I am a recent Graduate : [Want to Become A Data Scientist!]
11 | - 🌱 I’m currently learning everything 🤣
12 | - 👯 I’m looking to collaborate with other developers
13 | - 🥅 2020 Goals: Improve and gain Knowledge on ML techniques
14 | - ⚡ Fun fact: I love to travel, play video games, reading and writing articles
15 | 
16 | ### Connect with me:
17 | 
18 | * Let's stay connected [linkedin](https://www.linkedin.com/in/tulasiram574)
19 | * Read my articles [Medium](https://www.tulasiram574.medium.com)
20 | * For Introducing [Skype](https://join.skype.com/invite/m73hqlTWoETf)
21 | * Let's get Connect [Instagram](https://www.instagram.com/ram_lucky574/)
22 | 
23 | 
24 | # Bussiness Objective
25 | 
26 | ### Twitter has become a large platform to extract data and can be used to solve different kinds of bussiness objectives.
27 | 
28 | * Customer behaviour analysis
29 | * sentiment analysis
30 | * AI chatbots
31 | * Recommendation system, etc
32 | 
33 | In our case, we collect different kinds of tweets with these keywords Depressed, Depression, Hopeless, Lonely, Suicide, Antidepressant
34 | Antidepressants from twitter and analyse to depression prediction and it appears that this solution is significant enough to have solved the difficulty.
35 | 
36 | 
37 | ## Data Collection:
38 | 
39 | Tweets collected on Linux system commands using Twint tool. This tool is a magical for developers to collect data for thier desired use cases.
40 | 
41 | * Random tweets that do not necessarily indicate depression and tweets that demonstrate that the user may have depression and/or depressive
42 |   symptoms.
43 | * A dataset of random tweets can be sourced from the Sentiment140 dataset available on Kaggle
44 | 
45 | 
46 | https://drive.google.com/drive/folders/1z-PrTTT6u3xciSUc0eZQRfQa4qn09urc?usp=sharing
47 | 
48 | 
49 | ## Data Exploration & Data visualisation
50 | 
51 | * Words Frequency
52 | * Characters Frequency
53 | * Most common words
54 | * word cloud  
55 | 
56 | ## Model Evaluation and Validation
57 | 
58 | Hence it is a binary classification model, Accuracy and loss are recorded and visualized and compared to a benchmark logistic regression model.
59 | 
60 | <img width="210" alt="Screen Shot 2021-09-29 at 17 41 43" src="https://user-images.githubusercontent.com/38869311/135302870-5a1c27b6-1494-40f0-9ef1-c9f49077e4f3.png">
61 | 
62 | ## conclusion
63 | 
64 | The final model proves to be far more accurate than the benchmark model. The benchmark model, run on the same data for the same number of epochs, shows an accuracy of approximately 64%, while the final model has an accuracy of approximately 97%. This proves to be a much more robust and effective model for depression prediction and it appears that this solution is significant enough to have solved the difficulty of effectively analyzing Tweets for depression.
65 | 
66 | ### For more information get into my article on medium
67 | 
68 | https://medium.com/swlh/detecting-depression-in-social-media-via-twitter-usage-2d8f3df9b313
69 | 
70 | 


--------------------------------------------------------------------------------
/config.yml:
--------------------------------------------------------------------------------
 1 | # Use the latest 2.1 version of CircleCI pipeline process engine. See: https://circleci.com/docs/2.0/configuration-reference
 2 | version: 2.1
 3 | # Use a package of configuration called an orb.
 4 | orbs:
 5 |   # Declare a dependency on the welcome-orb
 6 |   welcome: circleci/welcome-orb@0.4.1
 7 | # Orchestrate or schedule a set of jobs
 8 | workflows:
 9 |   # Name the workflow "welcome"
10 |   welcome:
11 |     # Run the welcome/run job in its own container
12 |     jobs:
13 |       - welcome/run
14 | 


--------------------------------------------------------------------------------