├── App
    ├── app.py
    ├── data.db
    ├── models
    │   └── emotion_classifier_pipe_lr_03_june_2021.pkl
    └── track_utils.py
├── README.md
├── data
    ├── EmotionClf-End2End.png
    ├── EmotionDetectionNLP-End2End.pdf
    └── emotion_dataset_2.csv
├── models
    └── emotion_classifier_pipe_lr_03_june_2021.pkl
└── notebooks
    ├── .ipynb_checkpoints
        └── End2End-NLP-Project-checkpoint.ipynb
    ├── End2End-NLP-Project.ipynb
    ├── data
        ├── emotion_dataset_2.csv
        └── emotion_dataset_raw.csv
    └── emotion_classifier_pipe_lr_03_june_2021.pkl


/App/app.py:
--------------------------------------------------------------------------------
  1 | # Core Pkgs
  2 | import streamlit as st 
  3 | import altair as alt
  4 | import plotly.express as px 
  5 | 
  6 | # EDA Pkgs
  7 | import pandas as pd 
  8 | import numpy as np 
  9 | from datetime import datetime
 10 | 
 11 | # Utils
 12 | import joblib 
 13 | pipe_lr = joblib.load(open("models/emotion_classifier_pipe_lr_03_june_2021.pkl","rb"))
 14 | 
 15 | 
 16 | # Track Utils
 17 | from track_utils import create_page_visited_table,add_page_visited_details,view_all_page_visited_details,add_prediction_details,view_all_prediction_details,create_emotionclf_table
 18 | 
 19 | # Fxn
 20 | def predict_emotions(docx):
 21 | 	results = pipe_lr.predict([docx])
 22 | 	return results[0]
 23 | 
 24 | def get_prediction_proba(docx):
 25 | 	results = pipe_lr.predict_proba([docx])
 26 | 	return results
 27 | 
 28 | emotions_emoji_dict = {"anger":"😠","disgust":"🤮", "fear":"😨😱", "happy":"🤗", "joy":"😂", "neutral":"😐", "sad":"😔", "sadness":"😔", "shame":"😳", "surprise":"😮"}
 29 | 
 30 | 
 31 | # Main Application
 32 | def main():
 33 | 	st.title("Emotion Classifier App")
 34 | 	menu = ["Home","Monitor","About"]
 35 | 	choice = st.sidebar.selectbox("Menu",menu)
 36 | 	create_page_visited_table()
 37 | 	create_emotionclf_table()
 38 | 	if choice == "Home":
 39 | 		add_page_visited_details("Home",datetime.now())
 40 | 		st.subheader("Home-Emotion In Text")
 41 | 
 42 | 		with st.form(key='emotion_clf_form'):
 43 | 			raw_text = st.text_area("Type Here")
 44 | 			submit_text = st.form_submit_button(label='Submit')
 45 | 
 46 | 		if submit_text:
 47 | 			col1,col2  = st.beta_columns(2)
 48 | 
 49 | 			# Apply Fxn Here
 50 | 			prediction = predict_emotions(raw_text)
 51 | 			probability = get_prediction_proba(raw_text)
 52 | 			
 53 | 			add_prediction_details(raw_text,prediction,np.max(probability),datetime.now())
 54 | 
 55 | 			with col1:
 56 | 				st.success("Original Text")
 57 | 				st.write(raw_text)
 58 | 
 59 | 				st.success("Prediction")
 60 | 				emoji_icon = emotions_emoji_dict[prediction]
 61 | 				st.write("{}:{}".format(prediction,emoji_icon))
 62 | 				st.write("Confidence:{}".format(np.max(probability)))
 63 | 
 64 | 
 65 | 
 66 | 			with col2:
 67 | 				st.success("Prediction Probability")
 68 | 				# st.write(probability)
 69 | 				proba_df = pd.DataFrame(probability,columns=pipe_lr.classes_)
 70 | 				# st.write(proba_df.T)
 71 | 				proba_df_clean = proba_df.T.reset_index()
 72 | 				proba_df_clean.columns = ["emotions","probability"]
 73 | 
 74 | 				fig = alt.Chart(proba_df_clean).mark_bar().encode(x='emotions',y='probability',color='emotions')
 75 | 				st.altair_chart(fig,use_container_width=True)
 76 | 
 77 | 
 78 | 
 79 | 	elif choice == "Monitor":
 80 | 		add_page_visited_details("Monitor",datetime.now())
 81 | 		st.subheader("Monitor App")
 82 | 
 83 | 		with st.beta_expander("Page Metrics"):
 84 | 			page_visited_details = pd.DataFrame(view_all_page_visited_details(),columns=['Pagename','Time_of_Visit'])
 85 | 			st.dataframe(page_visited_details)	
 86 | 
 87 | 			pg_count = page_visited_details['Pagename'].value_counts().rename_axis('Pagename').reset_index(name='Counts')
 88 | 			c = alt.Chart(pg_count).mark_bar().encode(x='Pagename',y='Counts',color='Pagename')
 89 | 			st.altair_chart(c,use_container_width=True)	
 90 | 
 91 | 			p = px.pie(pg_count,values='Counts',names='Pagename')
 92 | 			st.plotly_chart(p,use_container_width=True)
 93 | 
 94 | 		with st.beta_expander('Emotion Classifier Metrics'):
 95 | 			df_emotions = pd.DataFrame(view_all_prediction_details(),columns=['Rawtext','Prediction','Probability','Time_of_Visit'])
 96 | 			st.dataframe(df_emotions)
 97 | 
 98 | 			prediction_count = df_emotions['Prediction'].value_counts().rename_axis('Prediction').reset_index(name='Counts')
 99 | 			pc = alt.Chart(prediction_count).mark_bar().encode(x='Prediction',y='Counts',color='Prediction')
100 | 			st.altair_chart(pc,use_container_width=True)	
101 | 
102 | 
103 | 
104 | 	else:
105 | 		st.subheader("About")
106 | 		add_page_visited_details("About",datetime.now())
107 | 
108 | 
109 | 
110 | 
111 | 
112 | if __name__ == '__main__':
113 | 	main()


--------------------------------------------------------------------------------
/App/data.db:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Jcharis/end2end-nlp-project/f82d87ed6d2608ad2c9b43e29e06da53429c1915/App/data.db


--------------------------------------------------------------------------------
/App/models/emotion_classifier_pipe_lr_03_june_2021.pkl:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Jcharis/end2end-nlp-project/f82d87ed6d2608ad2c9b43e29e06da53429c1915/App/models/emotion_classifier_pipe_lr_03_june_2021.pkl


--------------------------------------------------------------------------------
/App/track_utils.py:
--------------------------------------------------------------------------------
 1 | # Load Database Pkg
 2 | import sqlite3
 3 | conn = sqlite3.connect('data.db')
 4 | c = conn.cursor()
 5 | 
 6 | 
 7 | # Fxn
 8 | def create_page_visited_table():
 9 | 	c.execute('CREATE TABLE IF NOT EXISTS pageTrackTable(pagename TEXT,timeOfvisit TIMESTAMP)')
10 | 
11 | def add_page_visited_details(pagename,timeOfvisit):
12 | 	c.execute('INSERT INTO pageTrackTable(pagename,timeOfvisit) VALUES(?,?)',(pagename,timeOfvisit))
13 | 	conn.commit()
14 | 
15 | def view_all_page_visited_details():
16 | 	c.execute('SELECT * FROM pageTrackTable')
17 | 	data = c.fetchall()
18 | 	return data
19 | 
20 | 
21 | # Fxn To Track Input & Prediction
22 | def create_emotionclf_table():
23 | 	c.execute('CREATE TABLE IF NOT EXISTS emotionclfTable(rawtext TEXT,prediction TEXT,probability NUMBER,timeOfvisit TIMESTAMP)')
24 | 
25 | def add_prediction_details(rawtext,prediction,probability,timeOfvisit):
26 | 	c.execute('INSERT INTO emotionclfTable(rawtext,prediction,probability,timeOfvisit) VALUES(?,?,?,?)',(rawtext,prediction,probability,timeOfvisit))
27 | 	conn.commit()
28 | 
29 | def view_all_prediction_details():
30 | 	c.execute('SELECT * FROM emotionclfTable')
31 | 	data = c.fetchall()
32 | 	return data


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # end2end-nlp-project
2 | End 2 End NLP Project with Python
3 | 


--------------------------------------------------------------------------------
/data/EmotionClf-End2End.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Jcharis/end2end-nlp-project/f82d87ed6d2608ad2c9b43e29e06da53429c1915/data/EmotionClf-End2End.png


--------------------------------------------------------------------------------
/data/EmotionDetectionNLP-End2End.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Jcharis/end2end-nlp-project/f82d87ed6d2608ad2c9b43e29e06da53429c1915/data/EmotionDetectionNLP-End2End.pdf


--------------------------------------------------------------------------------
/models/emotion_classifier_pipe_lr_03_june_2021.pkl:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Jcharis/end2end-nlp-project/f82d87ed6d2608ad2c9b43e29e06da53429c1915/models/emotion_classifier_pipe_lr_03_june_2021.pkl


--------------------------------------------------------------------------------
/notebooks/.ipynb_checkpoints/End2End-NLP-Project-checkpoint.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "id": "36f38e2a-9998-4c73-bfc3-21b74d64a5ee",
  6 |    "metadata": {},
  7 |    "source": [
  8 |     "### End 2 End NLP Project\n",
  9 |     "+ Emotion Detection In Text \n",
 10 |     "+ Text Classifier"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 1,
 16 |    "id": "f0814628-3d83-4fd6-a511-2eccf79f9f1e",
 17 |    "metadata": {},
 18 |    "outputs": [],
 19 |    "source": [
 20 |     "# Load EDA Pkgs\n",
 21 |     "import pandas as pd\n",
 22 |     "import numpy as np"
 23 |    ]
 24 |   },
 25 |   {
 26 |    "cell_type": "code",
 27 |    "execution_count": 2,
 28 |    "id": "ea0d580d-c31c-44b7-b09b-10225857eebe",
 29 |    "metadata": {},
 30 |    "outputs": [],
 31 |    "source": [
 32 |     "# Load Data Viz Pkgs\n",
 33 |     "import seaborn as sns"
 34 |    ]
 35 |   },
 36 |   {
 37 |    "cell_type": "code",
 38 |    "execution_count": 3,
 39 |    "id": "91eccfbf-d4d0-4e16-b0f7-2d7941efddb0",
 40 |    "metadata": {},
 41 |    "outputs": [],
 42 |    "source": [
 43 |     "# Load Text Cleaning Pkgs\n",
 44 |     "import neattext.functions as nfx"
 45 |    ]
 46 |   },
 47 |   {
 48 |    "cell_type": "code",
 49 |    "execution_count": 5,
 50 |    "id": "21e7e868-35fb-483f-82b6-842a29ef1342",
 51 |    "metadata": {},
 52 |    "outputs": [],
 53 |    "source": [
 54 |     "# Load ML Pkgs\n",
 55 |     "# Estimators\n",
 56 |     "from sklearn.linear_model import LogisticRegression\n",
 57 |     "from sklearn.naive_bayes import MultinomialNB\n",
 58 |     "\n",
 59 |     "# Transformers\n",
 60 |     "from sklearn.feature_extraction.text import CountVectorizer\n",
 61 |     "from sklearn.model_selection import train_test_split\n",
 62 |     "from sklearn.metrics import accuracy_score,classification_report,confusion_matrix"
 63 |    ]
 64 |   },
 65 |   {
 66 |    "cell_type": "code",
 67 |    "execution_count": 10,
 68 |    "id": "b209e004-ab77-4407-8689-b4318944d47f",
 69 |    "metadata": {},
 70 |    "outputs": [],
 71 |    "source": [
 72 |     "# Load Dataset\n",
 73 |     "df = pd.read_csv(\"data/emotion_dataset_raw.csv\")"
 74 |    ]
 75 |   },
 76 |   {
 77 |    "cell_type": "code",
 78 |    "execution_count": 11,
 79 |    "id": "fea2d4c0-3bdd-405e-ab69-507ceaac36cb",
 80 |    "metadata": {},
 81 |    "outputs": [
 82 |     {
 83 |      "data": {
 84 |       "text/html": [
 85 |        "<div>\n",
 86 |        "<style scoped>\n",
 87 |        "    .dataframe tbody tr th:only-of-type {\n",
 88 |        "        vertical-align: middle;\n",
 89 |        "    }\n",
 90 |        "\n",
 91 |        "    .dataframe tbody tr th {\n",
 92 |        "        vertical-align: top;\n",
 93 |        "    }\n",
 94 |        "\n",
 95 |        "    .dataframe thead th {\n",
 96 |        "        text-align: right;\n",
 97 |        "    }\n",
 98 |        "</style>\n",
 99 |        "<table border=\"1\" class=\"dataframe\">\n",
100 |        "  <thead>\n",
101 |        "    <tr style=\"text-align: right;\">\n",
102 |        "      <th></th>\n",
103 |        "      <th>Emotion</th>\n",
104 |        "      <th>Text</th>\n",
105 |        "    </tr>\n",
106 |        "  </thead>\n",
107 |        "  <tbody>\n",
108 |        "    <tr>\n",
109 |        "      <th>0</th>\n",
110 |        "      <td>neutral</td>\n",
111 |        "      <td>Why ?</td>\n",
112 |        "    </tr>\n",
113 |        "    <tr>\n",
114 |        "      <th>1</th>\n",
115 |        "      <td>joy</td>\n",
116 |        "      <td>Sage Act upgrade on my to do list for tommorow.</td>\n",
117 |        "    </tr>\n",
118 |        "    <tr>\n",
119 |        "      <th>2</th>\n",
120 |        "      <td>sadness</td>\n",
121 |        "      <td>ON THE WAY TO MY HOMEGIRL BABY FUNERAL!!! MAN ...</td>\n",
122 |        "    </tr>\n",
123 |        "    <tr>\n",
124 |        "      <th>3</th>\n",
125 |        "      <td>joy</td>\n",
126 |        "      <td>Such an eye ! The true hazel eye-and so brill...</td>\n",
127 |        "    </tr>\n",
128 |        "    <tr>\n",
129 |        "      <th>4</th>\n",
130 |        "      <td>joy</td>\n",
131 |        "      <td>@Iluvmiasantos ugh babe.. hugggzzz for u .!  b...</td>\n",
132 |        "    </tr>\n",
133 |        "  </tbody>\n",
134 |        "</table>\n",
135 |        "</div>"
136 |       ],
137 |       "text/plain": [
138 |        "   Emotion                                               Text\n",
139 |        "0  neutral                                             Why ? \n",
140 |        "1      joy    Sage Act upgrade on my to do list for tommorow.\n",
141 |        "2  sadness  ON THE WAY TO MY HOMEGIRL BABY FUNERAL!!! MAN ...\n",
142 |        "3      joy   Such an eye ! The true hazel eye-and so brill...\n",
143 |        "4      joy  @Iluvmiasantos ugh babe.. hugggzzz for u .!  b..."
144 |       ]
145 |      },
146 |      "execution_count": 11,
147 |      "metadata": {},
148 |      "output_type": "execute_result"
149 |     }
150 |    ],
151 |    "source": [
152 |     "df.head()"
153 |    ]
154 |   },
155 |   {
156 |    "cell_type": "code",
157 |    "execution_count": 12,
158 |    "id": "430565a3-cf3b-4c6f-afa5-bafd084f5676",
159 |    "metadata": {},
160 |    "outputs": [
161 |     {
162 |      "data": {
163 |       "text/plain": [
164 |        "joy         11045\n",
165 |        "sadness      6722\n",
166 |        "fear         5410\n",
167 |        "anger        4297\n",
168 |        "surprise     4062\n",
169 |        "neutral      2254\n",
170 |        "disgust       856\n",
171 |        "shame         146\n",
172 |        "Name: Emotion, dtype: int64"
173 |       ]
174 |      },
175 |      "execution_count": 12,
176 |      "metadata": {},
177 |      "output_type": "execute_result"
178 |     }
179 |    ],
180 |    "source": [
181 |     "# Value Counts\n",
182 |     "df['Emotion'].value_counts()"
183 |    ]
184 |   },
185 |   {
186 |    "cell_type": "code",
187 |    "execution_count": 13,
188 |    "id": "531d3449-a959-4a19-bff0-3ffed551e619",
189 |    "metadata": {},
190 |    "outputs": [
191 |     {
192 |      "data": {
193 |       "text/plain": [
194 |        "<AxesSubplot:xlabel='Emotion', ylabel='count'>"
195 |       ]
196 |      },
197 |      "execution_count": 13,
198 |      "metadata": {},
199 |      "output_type": "execute_result"
200 |     },
201 |     {
202 |      "data": {
203 |       "image/png": "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\n",
204 |       "text/plain": [
205 |        "<Figure size 432x288 with 1 Axes>"
206 |       ]
207 |      },
208 |      "metadata": {
209 |       "needs_background": "light"
210 |      },
211 |      "output_type": "display_data"
212 |     }
213 |    ],
214 |    "source": [
215 |     "# Plot\n",
216 |     "sns.countplot(x='Emotion',data=df)"
217 |    ]
218 |   },
219 |   {
220 |    "cell_type": "code",
221 |    "execution_count": 14,
222 |    "id": "40f991d0-952f-40c1-bf00-f3476ce0436d",
223 |    "metadata": {
224 |     "collapsed": true,
225 |     "jupyter": {
226 |      "outputs_hidden": true
227 |     },
228 |     "tags": []
229 |    },
230 |    "outputs": [
231 |     {
232 |      "data": {
233 |       "text/plain": [
234 |        "['BTC_ADDRESS_REGEX',\n",
235 |        " 'CURRENCY_REGEX',\n",
236 |        " 'CURRENCY_SYMB_REGEX',\n",
237 |        " 'Counter',\n",
238 |        " 'DATE_REGEX',\n",
239 |        " 'EMAIL_REGEX',\n",
240 |        " 'EMOJI_REGEX',\n",
241 |        " 'HASTAG_REGEX',\n",
242 |        " 'MASTERCard_REGEX',\n",
243 |        " 'MD5_SHA_REGEX',\n",
244 |        " 'MOST_COMMON_PUNCT_REGEX',\n",
245 |        " 'NUMBERS_REGEX',\n",
246 |        " 'PHONE_REGEX',\n",
247 |        " 'PoBOX_REGEX',\n",
248 |        " 'SPECIAL_CHARACTERS_REGEX',\n",
249 |        " 'STOPWORDS',\n",
250 |        " 'STOPWORDS_de',\n",
251 |        " 'STOPWORDS_en',\n",
252 |        " 'STOPWORDS_es',\n",
253 |        " 'STOPWORDS_fr',\n",
254 |        " 'STOPWORDS_ru',\n",
255 |        " 'STOPWORDS_yo',\n",
256 |        " 'STREET_ADDRESS_REGEX',\n",
257 |        " 'TextFrame',\n",
258 |        " 'URL_PATTERN',\n",
259 |        " 'USER_HANDLES_REGEX',\n",
260 |        " 'VISACard_REGEX',\n",
261 |        " '__builtins__',\n",
262 |        " '__cached__',\n",
263 |        " '__doc__',\n",
264 |        " '__file__',\n",
265 |        " '__generate_text',\n",
266 |        " '__loader__',\n",
267 |        " '__name__',\n",
268 |        " '__numbers_dict',\n",
269 |        " '__package__',\n",
270 |        " '__spec__',\n",
271 |        " '_lex_richness_herdan',\n",
272 |        " '_lex_richness_maas_ttr',\n",
273 |        " 'clean_text',\n",
274 |        " 'defaultdict',\n",
275 |        " 'digit2words',\n",
276 |        " 'extract_btc_address',\n",
277 |        " 'extract_currencies',\n",
278 |        " 'extract_currency_symbols',\n",
279 |        " 'extract_dates',\n",
280 |        " 'extract_emails',\n",
281 |        " 'extract_emojis',\n",
282 |        " 'extract_hashtags',\n",
283 |        " 'extract_html_tags',\n",
284 |        " 'extract_mastercard_addr',\n",
285 |        " 'extract_md5sha',\n",
286 |        " 'extract_numbers',\n",
287 |        " 'extract_pattern',\n",
288 |        " 'extract_phone_numbers',\n",
289 |        " 'extract_postoffice_box',\n",
290 |        " 'extract_shortwords',\n",
291 |        " 'extract_special_characters',\n",
292 |        " 'extract_stopwords',\n",
293 |        " 'extract_street_address',\n",
294 |        " 'extract_urls',\n",
295 |        " 'extract_userhandles',\n",
296 |        " 'extract_visacard_addr',\n",
297 |        " 'fix_contractions',\n",
298 |        " 'generate_sentence',\n",
299 |        " 'hamming_distance',\n",
300 |        " 'inverse_df',\n",
301 |        " 'lexical_richness',\n",
302 |        " 'markov_chain',\n",
303 |        " 'math',\n",
304 |        " 'nlargest',\n",
305 |        " 'normalize',\n",
306 |        " 'num2words',\n",
307 |        " 'random',\n",
308 |        " 're',\n",
309 |        " 'read_txt',\n",
310 |        " 'remove_bad_quotes',\n",
311 |        " 'remove_btc_address',\n",
312 |        " 'remove_currencies',\n",
313 |        " 'remove_currency_symbols',\n",
314 |        " 'remove_custom_pattern',\n",
315 |        " 'remove_custom_words',\n",
316 |        " 'remove_dates',\n",
317 |        " 'remove_emails',\n",
318 |        " 'remove_emojis',\n",
319 |        " 'remove_hashtags',\n",
320 |        " 'remove_html_tags',\n",
321 |        " 'remove_mastercard_addr',\n",
322 |        " 'remove_md5sha',\n",
323 |        " 'remove_multiple_spaces',\n",
324 |        " 'remove_non_ascii',\n",
325 |        " 'remove_numbers',\n",
326 |        " 'remove_phone_numbers',\n",
327 |        " 'remove_postoffice_box',\n",
328 |        " 'remove_puncts',\n",
329 |        " 'remove_punctuations',\n",
330 |        " 'remove_shortwords',\n",
331 |        " 'remove_special_characters',\n",
332 |        " 'remove_stopwords',\n",
333 |        " 'remove_street_address',\n",
334 |        " 'remove_urls',\n",
335 |        " 'remove_userhandles',\n",
336 |        " 'remove_visacard_addr',\n",
337 |        " 'replace_bad_quotes',\n",
338 |        " 'replace_currencies',\n",
339 |        " 'replace_currency_symbols',\n",
340 |        " 'replace_dates',\n",
341 |        " 'replace_emails',\n",
342 |        " 'replace_emojis',\n",
343 |        " 'replace_numbers',\n",
344 |        " 'replace_phone_numbers',\n",
345 |        " 'replace_special_characters',\n",
346 |        " 'replace_term',\n",
347 |        " 'replace_urls',\n",
348 |        " 'string',\n",
349 |        " 'term_freq',\n",
350 |        " 'to_txt',\n",
351 |        " 'word_freq',\n",
352 |        " 'word_length_freq']"
353 |       ]
354 |      },
355 |      "execution_count": 14,
356 |      "metadata": {},
357 |      "output_type": "execute_result"
358 |     }
359 |    ],
360 |    "source": [
361 |     "# Data Cleaning\n",
362 |     "dir(nfx)"
363 |    ]
364 |   },
365 |   {
366 |    "cell_type": "code",
367 |    "execution_count": 17,
368 |    "id": "b1f87847-a91c-4bd6-a307-d746eb5aa9a0",
369 |    "metadata": {},
370 |    "outputs": [],
371 |    "source": [
372 |     "# User handles\n",
373 |     "df['Clean_Text'] = df['Text'].apply(nfx.remove_userhandles)"
374 |    ]
375 |   },
376 |   {
377 |    "cell_type": "code",
378 |    "execution_count": 18,
379 |    "id": "03886bc3-1ac4-4f1b-842b-e5d2d770ff81",
380 |    "metadata": {},
381 |    "outputs": [],
382 |    "source": [
383 |     "# Stopwords\n",
384 |     "df['Clean_Text'] = df['Clean_Text'].apply(nfx.remove_stopwords)"
385 |    ]
386 |   },
387 |   {
388 |    "cell_type": "code",
389 |    "execution_count": 19,
390 |    "id": "0a0fcc0c-4adf-4f0b-b226-164659ad70ba",
391 |    "metadata": {
392 |     "collapsed": true,
393 |     "jupyter": {
394 |      "outputs_hidden": true
395 |     },
396 |     "tags": []
397 |    },
398 |    "outputs": [
399 |     {
400 |      "data": {
401 |       "text/html": [
402 |        "<div>\n",
403 |        "<style scoped>\n",
404 |        "    .dataframe tbody tr th:only-of-type {\n",
405 |        "        vertical-align: middle;\n",
406 |        "    }\n",
407 |        "\n",
408 |        "    .dataframe tbody tr th {\n",
409 |        "        vertical-align: top;\n",
410 |        "    }\n",
411 |        "\n",
412 |        "    .dataframe thead th {\n",
413 |        "        text-align: right;\n",
414 |        "    }\n",
415 |        "</style>\n",
416 |        "<table border=\"1\" class=\"dataframe\">\n",
417 |        "  <thead>\n",
418 |        "    <tr style=\"text-align: right;\">\n",
419 |        "      <th></th>\n",
420 |        "      <th>Emotion</th>\n",
421 |        "      <th>Text</th>\n",
422 |        "      <th>Clean_Text</th>\n",
423 |        "    </tr>\n",
424 |        "  </thead>\n",
425 |        "  <tbody>\n",
426 |        "    <tr>\n",
427 |        "      <th>0</th>\n",
428 |        "      <td>neutral</td>\n",
429 |        "      <td>Why ?</td>\n",
430 |        "      <td>?</td>\n",
431 |        "    </tr>\n",
432 |        "    <tr>\n",
433 |        "      <th>1</th>\n",
434 |        "      <td>joy</td>\n",
435 |        "      <td>Sage Act upgrade on my to do list for tommorow.</td>\n",
436 |        "      <td>Sage Act upgrade list tommorow.</td>\n",
437 |        "    </tr>\n",
438 |        "    <tr>\n",
439 |        "      <th>2</th>\n",
440 |        "      <td>sadness</td>\n",
441 |        "      <td>ON THE WAY TO MY HOMEGIRL BABY FUNERAL!!! MAN ...</td>\n",
442 |        "      <td>WAY HOMEGIRL BABY FUNERAL!!! MAN HATE FUNERALS...</td>\n",
443 |        "    </tr>\n",
444 |        "    <tr>\n",
445 |        "      <th>3</th>\n",
446 |        "      <td>joy</td>\n",
447 |        "      <td>Such an eye ! The true hazel eye-and so brill...</td>\n",
448 |        "      <td>eye ! true hazel eye-and brilliant ! Regular f...</td>\n",
449 |        "    </tr>\n",
450 |        "    <tr>\n",
451 |        "      <th>4</th>\n",
452 |        "      <td>joy</td>\n",
453 |        "      <td>@Iluvmiasantos ugh babe.. hugggzzz for u .!  b...</td>\n",
454 |        "      <td>ugh babe.. hugggzzz u .! babe naamazed nga ako...</td>\n",
455 |        "    </tr>\n",
456 |        "    <tr>\n",
457 |        "      <th>...</th>\n",
458 |        "      <td>...</td>\n",
459 |        "      <td>...</td>\n",
460 |        "      <td>...</td>\n",
461 |        "    </tr>\n",
462 |        "    <tr>\n",
463 |        "      <th>34787</th>\n",
464 |        "      <td>surprise</td>\n",
465 |        "      <td>@MichelGW have you gift! Hope you like it! It'...</td>\n",
466 |        "      <td>gift! Hope like it! hand wear ! It'll warm! Lol</td>\n",
467 |        "    </tr>\n",
468 |        "    <tr>\n",
469 |        "      <th>34788</th>\n",
470 |        "      <td>joy</td>\n",
471 |        "      <td>The world didnt give it to me..so the world MO...</td>\n",
472 |        "      <td>world didnt me..so world DEFINITELY cnt away!!!</td>\n",
473 |        "    </tr>\n",
474 |        "    <tr>\n",
475 |        "      <th>34789</th>\n",
476 |        "      <td>anger</td>\n",
477 |        "      <td>A man robbed me today .</td>\n",
478 |        "      <td>man robbed today .</td>\n",
479 |        "    </tr>\n",
480 |        "    <tr>\n",
481 |        "      <th>34790</th>\n",
482 |        "      <td>fear</td>\n",
483 |        "      <td>Youu call it JEALOUSY, I call it of #Losing YO...</td>\n",
484 |        "      <td>Youu JEALOUSY, #Losing YOU...</td>\n",
485 |        "    </tr>\n",
486 |        "    <tr>\n",
487 |        "      <th>34791</th>\n",
488 |        "      <td>sadness</td>\n",
489 |        "      <td>I think about you baby, and I dream about you ...</td>\n",
490 |        "      <td>think baby, dream time</td>\n",
491 |        "    </tr>\n",
492 |        "  </tbody>\n",
493 |        "</table>\n",
494 |        "<p>34792 rows × 3 columns</p>\n",
495 |        "</div>"
496 |       ],
497 |       "text/plain": [
498 |        "        Emotion                                               Text  \\\n",
499 |        "0       neutral                                             Why ?    \n",
500 |        "1           joy    Sage Act upgrade on my to do list for tommorow.   \n",
501 |        "2       sadness  ON THE WAY TO MY HOMEGIRL BABY FUNERAL!!! MAN ...   \n",
502 |        "3           joy   Such an eye ! The true hazel eye-and so brill...   \n",
503 |        "4           joy  @Iluvmiasantos ugh babe.. hugggzzz for u .!  b...   \n",
504 |        "...         ...                                                ...   \n",
505 |        "34787  surprise  @MichelGW have you gift! Hope you like it! It'...   \n",
506 |        "34788       joy  The world didnt give it to me..so the world MO...   \n",
507 |        "34789     anger                           A man robbed me today .    \n",
508 |        "34790      fear  Youu call it JEALOUSY, I call it of #Losing YO...   \n",
509 |        "34791   sadness  I think about you baby, and I dream about you ...   \n",
510 |        "\n",
511 |        "                                              Clean_Text  \n",
512 |        "0                                                      ?  \n",
513 |        "1                        Sage Act upgrade list tommorow.  \n",
514 |        "2      WAY HOMEGIRL BABY FUNERAL!!! MAN HATE FUNERALS...  \n",
515 |        "3      eye ! true hazel eye-and brilliant ! Regular f...  \n",
516 |        "4      ugh babe.. hugggzzz u .! babe naamazed nga ako...  \n",
517 |        "...                                                  ...  \n",
518 |        "34787    gift! Hope like it! hand wear ! It'll warm! Lol  \n",
519 |        "34788    world didnt me..so world DEFINITELY cnt away!!!  \n",
520 |        "34789                                 man robbed today .  \n",
521 |        "34790                      Youu JEALOUSY, #Losing YOU...  \n",
522 |        "34791                             think baby, dream time  \n",
523 |        "\n",
524 |        "[34792 rows x 3 columns]"
525 |       ]
526 |      },
527 |      "execution_count": 19,
528 |      "metadata": {},
529 |      "output_type": "execute_result"
530 |     }
531 |    ],
532 |    "source": [
533 |     "df"
534 |    ]
535 |   },
536 |   {
537 |    "cell_type": "code",
538 |    "execution_count": 20,
539 |    "id": "450c39c0-79dd-4eaf-85fe-57e344eb81bd",
540 |    "metadata": {},
541 |    "outputs": [],
542 |    "source": [
543 |     "# Features & Labels\n",
544 |     "Xfeatures = df['Clean_Text']\n",
545 |     "ylabels = df['Emotion']"
546 |    ]
547 |   },
548 |   {
549 |    "cell_type": "code",
550 |    "execution_count": 21,
551 |    "id": "27d7f976-c28f-449e-ae1a-53a42bbda4e8",
552 |    "metadata": {},
553 |    "outputs": [],
554 |    "source": [
555 |     "#  Split Data\n",
556 |     "x_train,x_test,y_train,y_test = train_test_split(Xfeatures,ylabels,test_size=0.3,random_state=42)"
557 |    ]
558 |   },
559 |   {
560 |    "cell_type": "code",
561 |    "execution_count": 22,
562 |    "id": "2f086f29-dba9-40d2-a9dd-f06a6cca3a4c",
563 |    "metadata": {},
564 |    "outputs": [],
565 |    "source": [
566 |     "# Build Pipeline\n",
567 |     "from sklearn.pipeline import Pipeline"
568 |    ]
569 |   },
570 |   {
571 |    "cell_type": "code",
572 |    "execution_count": 23,
573 |    "id": "6b81cc86-2bef-40c2-b9a3-668caaadaff0",
574 |    "metadata": {},
575 |    "outputs": [],
576 |    "source": [
577 |     "# LogisticRegression Pipeline\n",
578 |     "pipe_lr = Pipeline(steps=[('cv',CountVectorizer()),('lr',LogisticRegression())])"
579 |    ]
580 |   },
581 |   {
582 |    "cell_type": "code",
583 |    "execution_count": 24,
584 |    "id": "dc64b9a7-efe2-4bc4-a0e7-46dff1d52b31",
585 |    "metadata": {
586 |     "collapsed": true,
587 |     "jupyter": {
588 |      "outputs_hidden": true
589 |     },
590 |     "tags": []
591 |    },
592 |    "outputs": [
593 |     {
594 |      "name": "stderr",
595 |      "output_type": "stream",
596 |      "text": [
597 |       "/usr/local/lib/python3.9/dist-packages/sklearn/linear_model/_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
598 |       "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
599 |       "\n",
600 |       "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
601 |       "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
602 |       "Please also refer to the documentation for alternative solver options:\n",
603 |       "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
604 |       "  n_iter_i = _check_optimize_result(\n"
605 |      ]
606 |     },
607 |     {
608 |      "data": {
609 |       "text/plain": [
610 |        "Pipeline(steps=[('cv', CountVectorizer()), ('lr', LogisticRegression())])"
611 |       ]
612 |      },
613 |      "execution_count": 24,
614 |      "metadata": {},
615 |      "output_type": "execute_result"
616 |     }
617 |    ],
618 |    "source": [
619 |     "# Train and Fit Data\n",
620 |     "pipe_lr.fit(x_train,y_train)"
621 |    ]
622 |   },
623 |   {
624 |    "cell_type": "code",
625 |    "execution_count": 25,
626 |    "id": "135ed6f8-56ff-4d53-85e3-541e3a7ae2d7",
627 |    "metadata": {},
628 |    "outputs": [
629 |     {
630 |      "data": {
631 |       "text/plain": [
632 |        "Pipeline(steps=[('cv', CountVectorizer()), ('lr', LogisticRegression())])"
633 |       ]
634 |      },
635 |      "execution_count": 25,
636 |      "metadata": {},
637 |      "output_type": "execute_result"
638 |     }
639 |    ],
640 |    "source": [
641 |     "pipe_lr"
642 |    ]
643 |   },
644 |   {
645 |    "cell_type": "code",
646 |    "execution_count": 26,
647 |    "id": "28396371-5f5c-4a3b-b974-164e047764f3",
648 |    "metadata": {},
649 |    "outputs": [
650 |     {
651 |      "data": {
652 |       "text/plain": [
653 |        "0.6200421536692853"
654 |       ]
655 |      },
656 |      "execution_count": 26,
657 |      "metadata": {},
658 |      "output_type": "execute_result"
659 |     }
660 |    ],
661 |    "source": [
662 |     "# Check Accuracy\n",
663 |     "pipe_lr.score(x_test,y_test)"
664 |    ]
665 |   },
666 |   {
667 |    "cell_type": "code",
668 |    "execution_count": 27,
669 |    "id": "eb3a26b6-d09e-422f-991b-b08c48f55b75",
670 |    "metadata": {},
671 |    "outputs": [],
672 |    "source": [
673 |     "# Make A Prediction\n",
674 |     "ex1 = \"This book was so interesting it made me happy\""
675 |    ]
676 |   },
677 |   {
678 |    "cell_type": "code",
679 |    "execution_count": 28,
680 |    "id": "b08597d9-6f59-45cb-a648-95b0da1ce313",
681 |    "metadata": {},
682 |    "outputs": [
683 |     {
684 |      "data": {
685 |       "text/plain": [
686 |        "array(['joy'], dtype=object)"
687 |       ]
688 |      },
689 |      "execution_count": 28,
690 |      "metadata": {},
691 |      "output_type": "execute_result"
692 |     }
693 |    ],
694 |    "source": [
695 |     "pipe_lr.predict([ex1])"
696 |    ]
697 |   },
698 |   {
699 |    "cell_type": "code",
700 |    "execution_count": 29,
701 |    "id": "5b3822ac-17fc-43dd-9bb7-8dad07a4d32c",
702 |    "metadata": {},
703 |    "outputs": [
704 |     {
705 |      "data": {
706 |       "text/plain": [
707 |        "array([[1.60353503e-03, 7.05960421e-03, 6.95963589e-03, 9.43781635e-01,\n",
708 |        "        1.00430913e-04, 2.63557471e-02, 6.65377751e-05, 1.40728742e-02]])"
709 |       ]
710 |      },
711 |      "execution_count": 29,
712 |      "metadata": {},
713 |      "output_type": "execute_result"
714 |     }
715 |    ],
716 |    "source": [
717 |     "# Prediction Prob\n",
718 |     "pipe_lr.predict_proba([ex1])"
719 |    ]
720 |   },
721 |   {
722 |    "cell_type": "code",
723 |    "execution_count": 30,
724 |    "id": "5b7c4596-d643-48e5-a777-79a6f55c49da",
725 |    "metadata": {},
726 |    "outputs": [
727 |     {
728 |      "data": {
729 |       "text/plain": [
730 |        "array(['anger', 'disgust', 'fear', 'joy', 'neutral', 'sadness', 'shame',\n",
731 |        "       'surprise'], dtype=object)"
732 |       ]
733 |      },
734 |      "execution_count": 30,
735 |      "metadata": {},
736 |      "output_type": "execute_result"
737 |     }
738 |    ],
739 |    "source": [
740 |     "# To Know the classes\n",
741 |     "pipe_lr.classes_"
742 |    ]
743 |   },
744 |   {
745 |    "cell_type": "code",
746 |    "execution_count": 31,
747 |    "id": "c0d40f62-b1fd-4748-a279-c8f50c748f26",
748 |    "metadata": {},
749 |    "outputs": [],
750 |    "source": [
751 |     "# Save Model & Pipeline\n",
752 |     "import joblib\n",
753 |     "pipeline_file = open(\"emotion_classifier_pipe_lr_03_june_2021.pkl\",\"wb\")\n",
754 |     "joblib.dump(pipe_lr,pipeline_file)\n",
755 |     "pipeline_file.close()"
756 |    ]
757 |   },
758 |   {
759 |    "cell_type": "code",
760 |    "execution_count": null,
761 |    "id": "377c4e98-67f0-45e5-8dd5-0417585754f0",
762 |    "metadata": {},
763 |    "outputs": [],
764 |    "source": []
765 |   }
766 |  ],
767 |  "metadata": {
768 |   "kernelspec": {
769 |    "display_name": "Python 3",
770 |    "language": "python",
771 |    "name": "python3"
772 |   },
773 |   "language_info": {
774 |    "codemirror_mode": {
775 |     "name": "ipython",
776 |     "version": 3
777 |    },
778 |    "file_extension": ".py",
779 |    "mimetype": "text/x-python",
780 |    "name": "python",
781 |    "nbconvert_exporter": "python",
782 |    "pygments_lexer": "ipython3",
783 |    "version": "3.9.1+"
784 |   }
785 |  },
786 |  "nbformat": 4,
787 |  "nbformat_minor": 5
788 | }
789 | 


--------------------------------------------------------------------------------
/notebooks/End2End-NLP-Project.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "id": "36f38e2a-9998-4c73-bfc3-21b74d64a5ee",
  6 |    "metadata": {},
  7 |    "source": [
  8 |     "### End 2 End NLP Project\n",
  9 |     "+ Emotion Detection In Text \n",
 10 |     "+ Text Classifier"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 1,
 16 |    "id": "f0814628-3d83-4fd6-a511-2eccf79f9f1e",
 17 |    "metadata": {},
 18 |    "outputs": [],
 19 |    "source": [
 20 |     "# Load EDA Pkgs\n",
 21 |     "import pandas as pd\n",
 22 |     "import numpy as np"
 23 |    ]
 24 |   },
 25 |   {
 26 |    "cell_type": "code",
 27 |    "execution_count": 2,
 28 |    "id": "ea0d580d-c31c-44b7-b09b-10225857eebe",
 29 |    "metadata": {},
 30 |    "outputs": [],
 31 |    "source": [
 32 |     "# Load Data Viz Pkgs\n",
 33 |     "import seaborn as sns"
 34 |    ]
 35 |   },
 36 |   {
 37 |    "cell_type": "code",
 38 |    "execution_count": 3,
 39 |    "id": "91eccfbf-d4d0-4e16-b0f7-2d7941efddb0",
 40 |    "metadata": {},
 41 |    "outputs": [],
 42 |    "source": [
 43 |     "# Load Text Cleaning Pkgs\n",
 44 |     "import neattext.functions as nfx"
 45 |    ]
 46 |   },
 47 |   {
 48 |    "cell_type": "code",
 49 |    "execution_count": 5,
 50 |    "id": "21e7e868-35fb-483f-82b6-842a29ef1342",
 51 |    "metadata": {},
 52 |    "outputs": [],
 53 |    "source": [
 54 |     "# Load ML Pkgs\n",
 55 |     "# Estimators\n",
 56 |     "from sklearn.linear_model import LogisticRegression\n",
 57 |     "from sklearn.naive_bayes import MultinomialNB\n",
 58 |     "\n",
 59 |     "# Transformers\n",
 60 |     "from sklearn.feature_extraction.text import CountVectorizer\n",
 61 |     "from sklearn.model_selection import train_test_split\n",
 62 |     "from sklearn.metrics import accuracy_score,classification_report,confusion_matrix"
 63 |    ]
 64 |   },
 65 |   {
 66 |    "cell_type": "code",
 67 |    "execution_count": 10,
 68 |    "id": "b209e004-ab77-4407-8689-b4318944d47f",
 69 |    "metadata": {},
 70 |    "outputs": [],
 71 |    "source": [
 72 |     "# Load Dataset\n",
 73 |     "df = pd.read_csv(\"data/emotion_dataset_raw.csv\")"
 74 |    ]
 75 |   },
 76 |   {
 77 |    "cell_type": "code",
 78 |    "execution_count": 11,
 79 |    "id": "fea2d4c0-3bdd-405e-ab69-507ceaac36cb",
 80 |    "metadata": {},
 81 |    "outputs": [
 82 |     {
 83 |      "data": {
 84 |       "text/html": [
 85 |        "<div>\n",
 86 |        "<style scoped>\n",
 87 |        "    .dataframe tbody tr th:only-of-type {\n",
 88 |        "        vertical-align: middle;\n",
 89 |        "    }\n",
 90 |        "\n",
 91 |        "    .dataframe tbody tr th {\n",
 92 |        "        vertical-align: top;\n",
 93 |        "    }\n",
 94 |        "\n",
 95 |        "    .dataframe thead th {\n",
 96 |        "        text-align: right;\n",
 97 |        "    }\n",
 98 |        "</style>\n",
 99 |        "<table border=\"1\" class=\"dataframe\">\n",
100 |        "  <thead>\n",
101 |        "    <tr style=\"text-align: right;\">\n",
102 |        "      <th></th>\n",
103 |        "      <th>Emotion</th>\n",
104 |        "      <th>Text</th>\n",
105 |        "    </tr>\n",
106 |        "  </thead>\n",
107 |        "  <tbody>\n",
108 |        "    <tr>\n",
109 |        "      <th>0</th>\n",
110 |        "      <td>neutral</td>\n",
111 |        "      <td>Why ?</td>\n",
112 |        "    </tr>\n",
113 |        "    <tr>\n",
114 |        "      <th>1</th>\n",
115 |        "      <td>joy</td>\n",
116 |        "      <td>Sage Act upgrade on my to do list for tommorow.</td>\n",
117 |        "    </tr>\n",
118 |        "    <tr>\n",
119 |        "      <th>2</th>\n",
120 |        "      <td>sadness</td>\n",
121 |        "      <td>ON THE WAY TO MY HOMEGIRL BABY FUNERAL!!! MAN ...</td>\n",
122 |        "    </tr>\n",
123 |        "    <tr>\n",
124 |        "      <th>3</th>\n",
125 |        "      <td>joy</td>\n",
126 |        "      <td>Such an eye ! The true hazel eye-and so brill...</td>\n",
127 |        "    </tr>\n",
128 |        "    <tr>\n",
129 |        "      <th>4</th>\n",
130 |        "      <td>joy</td>\n",
131 |        "      <td>@Iluvmiasantos ugh babe.. hugggzzz for u .!  b...</td>\n",
132 |        "    </tr>\n",
133 |        "  </tbody>\n",
134 |        "</table>\n",
135 |        "</div>"
136 |       ],
137 |       "text/plain": [
138 |        "   Emotion                                               Text\n",
139 |        "0  neutral                                             Why ? \n",
140 |        "1      joy    Sage Act upgrade on my to do list for tommorow.\n",
141 |        "2  sadness  ON THE WAY TO MY HOMEGIRL BABY FUNERAL!!! MAN ...\n",
142 |        "3      joy   Such an eye ! The true hazel eye-and so brill...\n",
143 |        "4      joy  @Iluvmiasantos ugh babe.. hugggzzz for u .!  b..."
144 |       ]
145 |      },
146 |      "execution_count": 11,
147 |      "metadata": {},
148 |      "output_type": "execute_result"
149 |     }
150 |    ],
151 |    "source": [
152 |     "df.head()"
153 |    ]
154 |   },
155 |   {
156 |    "cell_type": "code",
157 |    "execution_count": 12,
158 |    "id": "430565a3-cf3b-4c6f-afa5-bafd084f5676",
159 |    "metadata": {},
160 |    "outputs": [
161 |     {
162 |      "data": {
163 |       "text/plain": [
164 |        "joy         11045\n",
165 |        "sadness      6722\n",
166 |        "fear         5410\n",
167 |        "anger        4297\n",
168 |        "surprise     4062\n",
169 |        "neutral      2254\n",
170 |        "disgust       856\n",
171 |        "shame         146\n",
172 |        "Name: Emotion, dtype: int64"
173 |       ]
174 |      },
175 |      "execution_count": 12,
176 |      "metadata": {},
177 |      "output_type": "execute_result"
178 |     }
179 |    ],
180 |    "source": [
181 |     "# Value Counts\n",
182 |     "df['Emotion'].value_counts()"
183 |    ]
184 |   },
185 |   {
186 |    "cell_type": "code",
187 |    "execution_count": 13,
188 |    "id": "531d3449-a959-4a19-bff0-3ffed551e619",
189 |    "metadata": {},
190 |    "outputs": [
191 |     {
192 |      "data": {
193 |       "text/plain": [
194 |        "<AxesSubplot:xlabel='Emotion', ylabel='count'>"
195 |       ]
196 |      },
197 |      "execution_count": 13,
198 |      "metadata": {},
199 |      "output_type": "execute_result"
200 |     },
201 |     {
202 |      "data": {
203 |       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAZIAAAEGCAYAAABPdROvAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8QVMy6AAAACXBIWXMAAAsTAAALEwEAmpwYAAAZ1ElEQVR4nO3debgkdX3v8fdHcAERBBm5OEMconNVIHFhRHBFMco1GohKHCMC6r1zNajBJRGjj6I+KFGjEQ3c4Aa4IeICmiiSQSRRFoclDEsIE0GYOMK4IW7g4Pf+Ub8jzZk+h2bqnNMc5v16nn66+tdVv/pVnTr16Vr616kqJEnaWPcYdwMkSfObQSJJ6sUgkST1YpBIknoxSCRJvWw+7gbMte23374WL1487mZI0rxywQUX/LCqFgx7b5MLksWLF7Ny5cpxN0OS5pUk35vqPU9tSZJ6MUgkSb0YJJKkXgwSSVIvBokkqReDRJLUi0EiSerFIJEk9WKQSJJ62eS+2T5fXfv2Pxh3EwD4vbesGncTJN3FeEQiSerFIJEk9WKQSJJ6MUgkSb0YJJKkXgwSSVIvBokkqReDRJLUi0EiSerFIJEk9WKQSJJ6MUgkSb0YJJKkXgwSSVIvBokkqZdZC5IkH0tyQ5JLB8q2S3JGkqva87YD770xyeokVyZ55kD57klWtfeOTpJWfu8kn23l5yVZPFvLIkma2mwekRwP7Dup7HBgRVUtAVa01yTZBVgG7NqmOSbJZm2aY4HlwJL2mKjzZcBPquqhwPuBv521JZEkTWnWgqSqzgZ+PKl4P+CENnwCsP9A+UlVdXNVXQ2sBvZIsiOwdVWdU1UFnDhpmom6TgH2mThakSTNnbm+RrJDVa0FaM8PbOULgesGxlvTyha24cnlt5umqtYDNwIPGDbTJMuTrEyyct26dTO0KJIkuOtcbB92JFHTlE83zYaFVcdV1dKqWrpgwYKNbKIkaZi5DpLr2+kq2vMNrXwNsNPAeIuA77fyRUPKbzdNks2BbdjwVJokaZbNdZCcBhzchg8GTh0oX9buxNqZ7qL6+e30101J9mzXPw6aNM1EXc8HzmzXUSRJc2jz2ao4yWeAvYHtk6wB3gocBZyc5GXAtcABAFV1WZKTgcuB9cChVXVrq+oVdHeAbQF8tT0APgp8IslquiORZbO1LJKkqc1akFTVC6d4a58pxj8SOHJI+UpgtyHlv6YFkSRpfO4qF9slSfOUQSJJ6sUgkST1YpBIknoxSCRJvRgkkqReDBJJUi8GiSSpF4NEktSLQSJJ6sUgkST1YpBIknoxSCRJvRgkkqReDBJJUi8GiSSpF4NEktSLQSJJ6sUgkST1YpBIknoxSCRJvRgkkqReDBJJUi8GiSSpF4NEktSLQSJJ6sUgkST1YpBIknoxSCRJvYwlSJK8JsllSS5N8pkk90myXZIzklzVnrcdGP+NSVYnuTLJMwfKd0+yqr13dJKMY3kkaVM250GSZCHwamBpVe0GbAYsAw4HVlTVEmBFe02SXdr7uwL7Asck2axVdyywHFjSHvvO4aJIkhjfqa3NgS2SbA5sCXwf2A84ob1/ArB/G94POKmqbq6qq4HVwB5JdgS2rqpzqqqAEwemkSTNkTkPkqr6b+C9wLXAWuDGqvo6sENVrW3jrAUe2CZZCFw3UMWaVrawDU8u30CS5UlWJlm5bt26mVwcSdrkjePU1rZ0Rxk7Aw8C7pvkwOkmGVJW05RvWFh1XFUtraqlCxYsuLNNliRNYxyntp4OXF1V66rqN8AXgMcD17fTVbTnG9r4a4CdBqZfRHcqbE0bnlwuSZpD4wiSa4E9k2zZ7rLaB7gCOA04uI1zMHBqGz4NWJbk3kl2pruofn47/XVTkj1bPQcNTCNJmiObz/UMq+q8JKcAFwLrgYuA44CtgJOTvIwubA5o41+W5GTg8jb+oVV1a6vuFcDxwBbAV9tDkjSH5jxIAKrqrcBbJxXfTHd0Mmz8I4Ejh5SvBHab8QZKkkbmN9slSb0YJJKkXgwSSVIvBokkqReDRJLUi0EiSerFIJEk9WKQSJJ6MUgkSb0YJJKkXgwSSVIvBokkqReDRJLUi0EiSerFIJEk9WKQSJJ6MUgkSb0YJJKkXsbyU7u6+3rCB58w7ibwrVd9a9xNkDYpHpFIknoxSCRJvRgkkqReDBJJUi8GiSSpl5GCJMmKUcokSZueaW//TXIfYEtg+yTbAmlvbQ08aJbbJkmaB+7oeyT/FziMLjQu4LYg+RnwD7PXLEnSfDFtkFTVB4APJHlVVX1wjtokSZpHRrpGUlUfTPL4JH+e5KCJx8bONMn9k5yS5D+SXJFkryTbJTkjyVXteduB8d+YZHWSK5M8c6B89ySr2ntHJ8nwOUqSZsuoF9s/AbwXeCLw2PZY2mO+HwC+VlUPBx4JXAEcDqyoqiXAivaaJLsAy4BdgX2BY5Js1uo5FlgOLGmPfXu0SZK0EUbta2spsEtVVd8ZJtkaeDJwCEBV3QLckmQ/YO822gnAWcAbgP2Ak6rqZuDqJKuBPZJcA2xdVee0ek8E9ge+2reNkqTRjfo9kkuB/zFD8/x9YB3w8SQXJflIkvsCO1TVWoD2/MA2/kLguoHp17SyhW14cvkGkixPsjLJynXr1s3QYkiSYPQg2R64PMnpSU6beGzkPDcHHgMcW1WPBn5BO401hWHXPWqa8g0Lq46rqqVVtXTBggV3tr2SpGmMemrriBmc5xpgTVWd116fQhck1yfZsarWJtkRuGFg/J0Gpl8EfL+VLxpSLkmaQyMFSVV9c6ZmWFU/SHJdkodV1ZXAPsDl7XEwcFR7PrVNchrw6STvo/s+yxLg/Kq6NclNSfYEzgMOArxFWZLm2EhBkuQmbjttdC/gnsAvqmrrjZzvq4BPJbkX8F3gJXSn2U5O8jLgWuAAgKq6LMnJdEGzHji0qm5t9bwCOB7Ygu4iuxfaJWmOjXpEcr/B10n2B/bY2JlW1cUMv314nynGPxI4ckj5SmC3jW2HJKm/jer9t6q+BDxtZpsiSZqPRj219dyBl/egO5ro/Z0SSdL8N+pdW88ZGF4PXEP3RUFJ0iZu1GskL5nthkiS5qdR+9palOSLSW5Icn2SzydZdMdTSpLu7kY9tfVx4NO0W3KBA1vZH81Go6TZ9s0nP2XcTeApZ8/Y17OksRr1rq0FVfXxqlrfHscD9jUiSRo5SH6Y5MAkm7XHgcCPZrNhkqT5YdQgeSnwZ8APgLXA8+m+jS5J2sSNeo3kHcDBVfUTgCTb0f3Q1Utnq2GSpPlh1COSP5wIEYCq+jHw6NlpkiRpPhk1SO4x6TfUt2P0oxlJ0t3YqGHwd8C3k5xC1zXKnzGkE0VJ0qZn1G+2n5hkJV1HjQGeW1WXz2rLJEnzwsinp1pwGB6SpNvZqG7kJUmaYJBIknoxSCRJvRgkkqReDBJJUi8GiSSpF4NEktSLQSJJ6sUgkST1YpBIknoxSCRJvdgVvKTejjzw+eNuAm/65CnjbsImyyMSSVIvBokkqZexBUmSzZJclOQr7fV2Sc5IclV7HvxFxjcmWZ3kyiTPHCjfPcmq9t7RSTKOZZGkTdk4j0j+Erhi4PXhwIqqWgKsaK9JsguwDNgV2Bc4JslmbZpjgeXAkvbYd26aLkmaMJaL7UkWAX9M93O9r23F+wF7t+ETgLOAN7Tyk6rqZuDqJKuBPZJcA2xdVee0Ok8E9ge+OicLIc2BD73uy+NuAq/8u+eMuwm6ixvXEcnfA38N/HagbIeqWgvQnh/YyhcC1w2Mt6aVLWzDk8s3kGR5kpVJVq5bt25GFkCS1JnzIEnybOCGqrpg1EmGlNU05RsWVh1XVUuraumCBQtGnK0kaRTjOLX1BOBPkjwLuA+wdZJPAtcn2bGq1ibZEbihjb8G2Glg+kXA91v5oiHlkqQ5NOdHJFX1xqpaVFWL6S6in1lVBwKnAQe30Q4GTm3DpwHLktw7yc50F9XPb6e/bkqyZ7tb66CBaSRJc+Su9M32o4CTk7wMuBY4AKCqLktyMnA5sB44tKpubdO8Ajge2ILuIrsX2iVpjo01SKrqLLq7s6iqHwH7TDHekXR3eE0uXwnsNnstlCTdEb/ZLknqxSCRJPVikEiSejFIJEm9GCSSpF4MEklSLwaJJKkXg0SS1ItBIknqxSCRJPVikEiSejFIJEm9GCSSpF4MEklSLwaJJKkXg0SS1ItBIknqxSCRJPVikEiSejFIJEm9GCSSpF4MEklSLwaJJKkXg0SS1ItBIknqxSCRJPVikEiSetl83A0Yt93/6sRxNwGAC95z0LibIEkbZc6PSJLslOQbSa5IclmSv2zl2yU5I8lV7XnbgWnemGR1kiuTPHOgfPckq9p7RyfJXC+PJG3qxnFqaz3wuqp6BLAncGiSXYDDgRVVtQRY0V7T3lsG7ArsCxyTZLNW17HAcmBJe+w7lwsiSRpDkFTV2qq6sA3fBFwBLAT2A05oo50A7N+G9wNOqqqbq+pqYDWwR5Idga2r6pyqKuDEgWkkSXNkrBfbkywGHg2cB+xQVWuhCxvggW20hcB1A5OtaWUL2/Dk8mHzWZ5kZZKV69atm9FlkKRN3diCJMlWwOeBw6rqZ9ONOqSspinfsLDquKpaWlVLFyxYcOcbK0ma0liCJMk96ULkU1X1hVZ8fTtdRXu+oZWvAXYamHwR8P1WvmhIuSRpDo3jrq0AHwWuqKr3Dbx1GnBwGz4YOHWgfFmSeyfZme6i+vnt9NdNSfZsdR40MI0kaY6M43skTwBeDKxKcnEr+xvgKODkJC8DrgUOAKiqy5KcDFxOd8fXoVV1a5vuFcDxwBbAV9tDkjSH5jxIqurfGH59A2CfKaY5EjhySPlKYLeZa50k6c6yixRJUi8GiSSpF4NEktSLQSJJ6sUgkST1YpBIknoxSCRJvRgkkqReDBJJUi8GiSSpF4NEktSLQSJJ6sUgkST1YpBIknoxSCRJvRgkkqRexvELiZKkKRxxxBHjbgJw59rhEYkkqReDRJLUi0EiSerFIJEk9WKQSJJ6MUgkSb0YJJKkXgwSSVIvBokkqReDRJLUi0EiSerFIJEk9TLvO21Msi/wAWAz4CNVddSYmyTpLuiKI88cdxMAeMSbnjbuJsy4eX1EkmQz4B+A/wXsArwwyS7jbZUkbVrmdZAAewCrq+q7VXULcBKw35jbJEmblFTVuNuw0ZI8H9i3qv53e/1i4HFV9cpJ4y0HlreXDwOunOGmbA/8cIbrnA22c2bNh3bOhzaC7Zxps9HOB1fVgmFvzPdrJBlStkEyVtVxwHGz1ohkZVUtna36Z4rtnFnzoZ3zoY1gO2faXLdzvp/aWgPsNPB6EfD9MbVFkjZJ8z1IvgMsSbJzknsBy4DTxtwmSdqkzOtTW1W1PskrgdPpbv/9WFVdNoamzNppsxlmO2fWfGjnfGgj2M6ZNqftnNcX2yVJ4zffT21JksbMIJEk9WKQzJAki5P8+UZO+/MZbsu3Z7K+2dLW2aXjbscwSV6d5Ioknxp3W2ZLkn9Ocv9xt2PcklyTZPtxt2OYJEckeX2Styd5+hzMb/+N6R3EIJk5i4GhQZJkTm9qqKrHz+X87qb+AnhWVb1oYytoXfjMmVG3s3TuUVXPqqqfznKzZs3Ecoy7HXOhqt5SVf8yB7Pan667qTunqjbpB10AXAF8GLgM+DqwBfAQ4GvABcC/Ag9v4x8PPH9g+p+353OBG4GLgdcAhwCfA74MnAlsBawALgRWAftNrmMGl+nndF/WfA9waZvfC9p7n5g0708Bf9JzfvcF/gn49za/FwBvobs9+1K6O0gmbuzYvY13zkT7WvkhwBfaOr8KePdA/c9o41/Y1ulWrfwo4HLgEuC9reyANs9/B87eyOX5f8Atbb29CfhYW5aLJtZd227+tbXpQuDxrXxv4BvAp4HLZ3B9XgNs395fCpzVho9o6/frbZ6HAKe29Xgl8NZJ2/kxbTkePFHnsPkN/K2+Sfc/cDqw44jt/1Kb5jJg+cA2eWSbx7nADq38Ie31d4C3M/C/APxVK78EeNtUyzFD6/Zt3Pa/OfG/vgfw7TafbwMPG9hWv0T3v3018ErgtW28c4HtBpZtg33ICG18U/vb/QvwGeD1DOx3GL7dD12PdNvjVwbq/hBwyLB6gMcDP27LdDHwkJHXa58dyN3h0TbM9cCj2uuTgQPpdvpLWtnjgDPb8O/+oBP/IFP8wQ6h+8LkxEa1ObB1G94eWM1tO9fZCJLnAWfQ3Ra9A3AtsCPwFOBLbbxt2kazec/5PQ/48MDrbSaWu73+BPCcNnwJ8JQ2PDlIvtumvQ/wPbovm24PnA3ct433BrqQ2q79s02sw/u351XAwsGyjVyma9q83wkcOFEf8J90O6Mtgfu08iXAyoHt4BfAzjO8Pq9h6iC5ANhiYD2uBR5A94Ho0jb+YuC3wJ5DlnHY/O5Jt/Nc0MpeQHd7/Sjtn9jmJ+b/ALoeJya2gXcDb27DXwFe2IZfzm3/T8+gfQChO3PyFeDJw5Zjhtbtq9rrv6DrRRxga9r/BvB04PMD63g1cD9gAd0HyJe3994PHNaGh+5D7qB9u9Ntw1u2+a9mIEiYerufaj3uzZAgmaae4xnYv4362CQOC0dwdVVd3IYvoNtYHw98LsnFwD/S7YTvrDOq6sdtOMA7k1xC90ljId0OfrY8EfhMVd1aVdfTfbJ8bFV9E3hokgcCL6T751jfc16rgKcn+dskT6qqG4GnJjkvySrgacCuSbah22C/2ab7xKR6VlTVjVX1a7pPSg8G9qQ71P5W+1sc3Mp/Bvwa+EiS5wK/bHV8Czg+yf+hC9G+ngEc3uZ9Fl3I/R7djvbDbfk+x+1PB5xfVVf3mOew9Tmd06rqVwOvz6iqH7WyL9BtCwDfq6pzR5zfw4DdgDPasr+ZrueIUbw6ycSRx050QXsL3c4ObvsfA9iLbv1Bd0Q14RntcRHdkcLDWz3TLccoplq3XxjStm3o9gGX0gXErgP1fKOqbqqqdXRB8uWB+hcn2YqN24c8CfhiVf2yqn7Ghl+wnmq7n2o9TmWqejbKvP5C4gy6eWD4Vrod/E+r6lFDxl1Pu7aUJMC9pqn3FwPDL6L79LJ7Vf0myTV0O6XZMqwfsgmfaO1ZBry074yq6j+T7A48C3hXkq8DhwJLq+q6JEfQLWsY0hfagMl/h83bNGdU1Qsnj5xkD2CfthyvBJ5WVS9P8jjgj4GLkzyqqn7UY/ECPK+qbtfRZ1um64FH0m0Pvx54e/DvfqdNsT5/t92x4XYzeX6T13FNMd508/sicFlV7XVn2p5kb7pP73tV1S+TnNXa+5tqH3m57W87bVXAu6rqHyfVv3iq5RjFFMsKt217g217B11g/Gmb71kDVQ1uq78deP3bNv09mHofcofNnKb964dt99PUNbjdQNt2NqKeaXlEMtzPgKuTHAC/u6j3yPbeNXSHn9B1WX/PNnwT3aHuVLYBbmgh8lS6T9Wz6WzgBUk2S7KA7rTA+e2944HDAGoGegJI8iDgl1X1SbpzrY9pb/2wfTJ7fpvXT4Ebk0x8Qh7lQva5wBOSPLTNa8sk/7PVu01V/XNblke19x9SVedV1Vvoej/daXi1IzsdeFX70ECSR7fybYC1VfVb4MXMzNEPbR7D1uc13LbdPe8OqvijJNsl2YLu4um3NmJ+VwILkuzVxrlnkl2nqWbCNsBPWog8nO6IcjrnctvyLBsoPx14afs7k2RhO4ruZZptdZhtgP9uw4fcmfm0o4mp9iHTORv40yRbJLkf8JxJ7R+63TP1evwesEuSe7czAvvcQT13tB8byiOSqb0IODbJm+nC4iS6C3QfBk5Ncj7dOdCJT0eXAOvbIf3xwE8m1fcp4MtJVtJdyPqPWWx70X2i3Ku1uYC/rqofAFTV9UmuoLtgOBP+AHhPkt8CvwFeQbcDW0W3A/zOwLgvAT6W5Jd0O4vpF6RqXZJDgM8kuXcrfjPdBn9qkokjnde0996TZEkrW0G3/H28A/h74JIWJtcAz6a72Pv5tqP4Bj2PQiYZtj63AD6a5G+A8+5g+n+jO+p8KPDpqlrZPlGPPL+quiXdzzQc3XZAm9Othzv64PE14OXtFO6VdDu46RwGfDLJ6+gugt8IUFVfT/II4JyW4T+nu3Z56x3Ud0eGrdtTphj33cAJSV5Ld8PMnTXVPmRKVXVhks/S7SO+R3eRftD9GL7dH8bw9XhdkpPp9k9X0Z0qnK6ek+hO2b6a7lrJf42yoHaRcjeT5AHAhVU15RFPki3pdvKPGeH8u+aRFrpLa9Jv8txVtW3xV1VVSZbRXTDeb9ztmm/GvR49IrkbaYftZ9Edsk81ztPpbmd9nyGiu4DdgQ+1o72fMgPX7DZRY12PHpFIknrxYrskqReDRJLUi0EiSerFIJF6SHJrkosHHofPQJ2360k6ydIkR/etV5otXmyXekjy86raaobr3Bt4fVU9eybrlWaLRyTSLEj3GxfvTHJOkpVJHpPk9CT/leTlbZwkeU+SS5OsSvKCNvlRwJPaEc5rkuyd5Cttmu2SfCnJJUnOTfKHrfyIJB9LclaS77YvlElzwu+RSP1ska5TvgnvqqrPtuHrqmqvJO+n6+3gCXR9HV1G11X9c+m6pngkXS+830lyNnA4A0ck7QhlwtuAi6pq/yRPA07ktu4tHg48le5by1cmObaqfjOTCysNY5BI/fxqmo75JnpuXUX3Gyo3ATcl+XW6Xyb8XQ/NwPVJvgk8lq6vt6k8kdanUlWdmeQBrQsTgH+qqpuBm5PcQNf56JoeyyaNxFNb0uwZ7BF2cm+xEz0b31nDppm40Dms92Rp1hkk0vhM1UPzdD2wnk3rNbmd8vph62lWGhs/sUj9TL5G8rWqGvUW4KE9NCf5EbfvSfqigWmOAD7eetf9Jd0PfUlj5e2/kqRePLUlSerFIJEk9WKQSJJ6MUgkSb0YJJKkXgwSSVIvBokkqZf/D8jGbTFp2Y+OAAAAAElFTkSuQmCC\n",
204 |       "text/plain": [
205 |        "<Figure size 432x288 with 1 Axes>"
206 |       ]
207 |      },
208 |      "metadata": {
209 |       "needs_background": "light"
210 |      },
211 |      "output_type": "display_data"
212 |     }
213 |    ],
214 |    "source": [
215 |     "# Plot\n",
216 |     "sns.countplot(x='Emotion',data=df)"
217 |    ]
218 |   },
219 |   {
220 |    "cell_type": "code",
221 |    "execution_count": 14,
222 |    "id": "40f991d0-952f-40c1-bf00-f3476ce0436d",
223 |    "metadata": {
224 |     "collapsed": true,
225 |     "jupyter": {
226 |      "outputs_hidden": true
227 |     },
228 |     "tags": []
229 |    },
230 |    "outputs": [
231 |     {
232 |      "data": {
233 |       "text/plain": [
234 |        "['BTC_ADDRESS_REGEX',\n",
235 |        " 'CURRENCY_REGEX',\n",
236 |        " 'CURRENCY_SYMB_REGEX',\n",
237 |        " 'Counter',\n",
238 |        " 'DATE_REGEX',\n",
239 |        " 'EMAIL_REGEX',\n",
240 |        " 'EMOJI_REGEX',\n",
241 |        " 'HASTAG_REGEX',\n",
242 |        " 'MASTERCard_REGEX',\n",
243 |        " 'MD5_SHA_REGEX',\n",
244 |        " 'MOST_COMMON_PUNCT_REGEX',\n",
245 |        " 'NUMBERS_REGEX',\n",
246 |        " 'PHONE_REGEX',\n",
247 |        " 'PoBOX_REGEX',\n",
248 |        " 'SPECIAL_CHARACTERS_REGEX',\n",
249 |        " 'STOPWORDS',\n",
250 |        " 'STOPWORDS_de',\n",
251 |        " 'STOPWORDS_en',\n",
252 |        " 'STOPWORDS_es',\n",
253 |        " 'STOPWORDS_fr',\n",
254 |        " 'STOPWORDS_ru',\n",
255 |        " 'STOPWORDS_yo',\n",
256 |        " 'STREET_ADDRESS_REGEX',\n",
257 |        " 'TextFrame',\n",
258 |        " 'URL_PATTERN',\n",
259 |        " 'USER_HANDLES_REGEX',\n",
260 |        " 'VISACard_REGEX',\n",
261 |        " '__builtins__',\n",
262 |        " '__cached__',\n",
263 |        " '__doc__',\n",
264 |        " '__file__',\n",
265 |        " '__generate_text',\n",
266 |        " '__loader__',\n",
267 |        " '__name__',\n",
268 |        " '__numbers_dict',\n",
269 |        " '__package__',\n",
270 |        " '__spec__',\n",
271 |        " '_lex_richness_herdan',\n",
272 |        " '_lex_richness_maas_ttr',\n",
273 |        " 'clean_text',\n",
274 |        " 'defaultdict',\n",
275 |        " 'digit2words',\n",
276 |        " 'extract_btc_address',\n",
277 |        " 'extract_currencies',\n",
278 |        " 'extract_currency_symbols',\n",
279 |        " 'extract_dates',\n",
280 |        " 'extract_emails',\n",
281 |        " 'extract_emojis',\n",
282 |        " 'extract_hashtags',\n",
283 |        " 'extract_html_tags',\n",
284 |        " 'extract_mastercard_addr',\n",
285 |        " 'extract_md5sha',\n",
286 |        " 'extract_numbers',\n",
287 |        " 'extract_pattern',\n",
288 |        " 'extract_phone_numbers',\n",
289 |        " 'extract_postoffice_box',\n",
290 |        " 'extract_shortwords',\n",
291 |        " 'extract_special_characters',\n",
292 |        " 'extract_stopwords',\n",
293 |        " 'extract_street_address',\n",
294 |        " 'extract_urls',\n",
295 |        " 'extract_userhandles',\n",
296 |        " 'extract_visacard_addr',\n",
297 |        " 'fix_contractions',\n",
298 |        " 'generate_sentence',\n",
299 |        " 'hamming_distance',\n",
300 |        " 'inverse_df',\n",
301 |        " 'lexical_richness',\n",
302 |        " 'markov_chain',\n",
303 |        " 'math',\n",
304 |        " 'nlargest',\n",
305 |        " 'normalize',\n",
306 |        " 'num2words',\n",
307 |        " 'random',\n",
308 |        " 're',\n",
309 |        " 'read_txt',\n",
310 |        " 'remove_bad_quotes',\n",
311 |        " 'remove_btc_address',\n",
312 |        " 'remove_currencies',\n",
313 |        " 'remove_currency_symbols',\n",
314 |        " 'remove_custom_pattern',\n",
315 |        " 'remove_custom_words',\n",
316 |        " 'remove_dates',\n",
317 |        " 'remove_emails',\n",
318 |        " 'remove_emojis',\n",
319 |        " 'remove_hashtags',\n",
320 |        " 'remove_html_tags',\n",
321 |        " 'remove_mastercard_addr',\n",
322 |        " 'remove_md5sha',\n",
323 |        " 'remove_multiple_spaces',\n",
324 |        " 'remove_non_ascii',\n",
325 |        " 'remove_numbers',\n",
326 |        " 'remove_phone_numbers',\n",
327 |        " 'remove_postoffice_box',\n",
328 |        " 'remove_puncts',\n",
329 |        " 'remove_punctuations',\n",
330 |        " 'remove_shortwords',\n",
331 |        " 'remove_special_characters',\n",
332 |        " 'remove_stopwords',\n",
333 |        " 'remove_street_address',\n",
334 |        " 'remove_urls',\n",
335 |        " 'remove_userhandles',\n",
336 |        " 'remove_visacard_addr',\n",
337 |        " 'replace_bad_quotes',\n",
338 |        " 'replace_currencies',\n",
339 |        " 'replace_currency_symbols',\n",
340 |        " 'replace_dates',\n",
341 |        " 'replace_emails',\n",
342 |        " 'replace_emojis',\n",
343 |        " 'replace_numbers',\n",
344 |        " 'replace_phone_numbers',\n",
345 |        " 'replace_special_characters',\n",
346 |        " 'replace_term',\n",
347 |        " 'replace_urls',\n",
348 |        " 'string',\n",
349 |        " 'term_freq',\n",
350 |        " 'to_txt',\n",
351 |        " 'word_freq',\n",
352 |        " 'word_length_freq']"
353 |       ]
354 |      },
355 |      "execution_count": 14,
356 |      "metadata": {},
357 |      "output_type": "execute_result"
358 |     }
359 |    ],
360 |    "source": [
361 |     "# Data Cleaning\n",
362 |     "dir(nfx)"
363 |    ]
364 |   },
365 |   {
366 |    "cell_type": "code",
367 |    "execution_count": 17,
368 |    "id": "b1f87847-a91c-4bd6-a307-d746eb5aa9a0",
369 |    "metadata": {},
370 |    "outputs": [],
371 |    "source": [
372 |     "# User handles\n",
373 |     "df['Clean_Text'] = df['Text'].apply(nfx.remove_userhandles)"
374 |    ]
375 |   },
376 |   {
377 |    "cell_type": "code",
378 |    "execution_count": 18,
379 |    "id": "03886bc3-1ac4-4f1b-842b-e5d2d770ff81",
380 |    "metadata": {},
381 |    "outputs": [],
382 |    "source": [
383 |     "# Stopwords\n",
384 |     "df['Clean_Text'] = df['Clean_Text'].apply(nfx.remove_stopwords)"
385 |    ]
386 |   },
387 |   {
388 |    "cell_type": "code",
389 |    "execution_count": 19,
390 |    "id": "0a0fcc0c-4adf-4f0b-b226-164659ad70ba",
391 |    "metadata": {
392 |     "collapsed": true,
393 |     "jupyter": {
394 |      "outputs_hidden": true
395 |     },
396 |     "tags": []
397 |    },
398 |    "outputs": [
399 |     {
400 |      "data": {
401 |       "text/html": [
402 |        "<div>\n",
403 |        "<style scoped>\n",
404 |        "    .dataframe tbody tr th:only-of-type {\n",
405 |        "        vertical-align: middle;\n",
406 |        "    }\n",
407 |        "\n",
408 |        "    .dataframe tbody tr th {\n",
409 |        "        vertical-align: top;\n",
410 |        "    }\n",
411 |        "\n",
412 |        "    .dataframe thead th {\n",
413 |        "        text-align: right;\n",
414 |        "    }\n",
415 |        "</style>\n",
416 |        "<table border=\"1\" class=\"dataframe\">\n",
417 |        "  <thead>\n",
418 |        "    <tr style=\"text-align: right;\">\n",
419 |        "      <th></th>\n",
420 |        "      <th>Emotion</th>\n",
421 |        "      <th>Text</th>\n",
422 |        "      <th>Clean_Text</th>\n",
423 |        "    </tr>\n",
424 |        "  </thead>\n",
425 |        "  <tbody>\n",
426 |        "    <tr>\n",
427 |        "      <th>0</th>\n",
428 |        "      <td>neutral</td>\n",
429 |        "      <td>Why ?</td>\n",
430 |        "      <td>?</td>\n",
431 |        "    </tr>\n",
432 |        "    <tr>\n",
433 |        "      <th>1</th>\n",
434 |        "      <td>joy</td>\n",
435 |        "      <td>Sage Act upgrade on my to do list for tommorow.</td>\n",
436 |        "      <td>Sage Act upgrade list tommorow.</td>\n",
437 |        "    </tr>\n",
438 |        "    <tr>\n",
439 |        "      <th>2</th>\n",
440 |        "      <td>sadness</td>\n",
441 |        "      <td>ON THE WAY TO MY HOMEGIRL BABY FUNERAL!!! MAN ...</td>\n",
442 |        "      <td>WAY HOMEGIRL BABY FUNERAL!!! MAN HATE FUNERALS...</td>\n",
443 |        "    </tr>\n",
444 |        "    <tr>\n",
445 |        "      <th>3</th>\n",
446 |        "      <td>joy</td>\n",
447 |        "      <td>Such an eye ! The true hazel eye-and so brill...</td>\n",
448 |        "      <td>eye ! true hazel eye-and brilliant ! Regular f...</td>\n",
449 |        "    </tr>\n",
450 |        "    <tr>\n",
451 |        "      <th>4</th>\n",
452 |        "      <td>joy</td>\n",
453 |        "      <td>@Iluvmiasantos ugh babe.. hugggzzz for u .!  b...</td>\n",
454 |        "      <td>ugh babe.. hugggzzz u .! babe naamazed nga ako...</td>\n",
455 |        "    </tr>\n",
456 |        "    <tr>\n",
457 |        "      <th>...</th>\n",
458 |        "      <td>...</td>\n",
459 |        "      <td>...</td>\n",
460 |        "      <td>...</td>\n",
461 |        "    </tr>\n",
462 |        "    <tr>\n",
463 |        "      <th>34787</th>\n",
464 |        "      <td>surprise</td>\n",
465 |        "      <td>@MichelGW have you gift! Hope you like it! It'...</td>\n",
466 |        "      <td>gift! Hope like it! hand wear ! It'll warm! Lol</td>\n",
467 |        "    </tr>\n",
468 |        "    <tr>\n",
469 |        "      <th>34788</th>\n",
470 |        "      <td>joy</td>\n",
471 |        "      <td>The world didnt give it to me..so the world MO...</td>\n",
472 |        "      <td>world didnt me..so world DEFINITELY cnt away!!!</td>\n",
473 |        "    </tr>\n",
474 |        "    <tr>\n",
475 |        "      <th>34789</th>\n",
476 |        "      <td>anger</td>\n",
477 |        "      <td>A man robbed me today .</td>\n",
478 |        "      <td>man robbed today .</td>\n",
479 |        "    </tr>\n",
480 |        "    <tr>\n",
481 |        "      <th>34790</th>\n",
482 |        "      <td>fear</td>\n",
483 |        "      <td>Youu call it JEALOUSY, I call it of #Losing YO...</td>\n",
484 |        "      <td>Youu JEALOUSY, #Losing YOU...</td>\n",
485 |        "    </tr>\n",
486 |        "    <tr>\n",
487 |        "      <th>34791</th>\n",
488 |        "      <td>sadness</td>\n",
489 |        "      <td>I think about you baby, and I dream about you ...</td>\n",
490 |        "      <td>think baby, dream time</td>\n",
491 |        "    </tr>\n",
492 |        "  </tbody>\n",
493 |        "</table>\n",
494 |        "<p>34792 rows × 3 columns</p>\n",
495 |        "</div>"
496 |       ],
497 |       "text/plain": [
498 |        "        Emotion                                               Text  \\\n",
499 |        "0       neutral                                             Why ?    \n",
500 |        "1           joy    Sage Act upgrade on my to do list for tommorow.   \n",
501 |        "2       sadness  ON THE WAY TO MY HOMEGIRL BABY FUNERAL!!! MAN ...   \n",
502 |        "3           joy   Such an eye ! The true hazel eye-and so brill...   \n",
503 |        "4           joy  @Iluvmiasantos ugh babe.. hugggzzz for u .!  b...   \n",
504 |        "...         ...                                                ...   \n",
505 |        "34787  surprise  @MichelGW have you gift! Hope you like it! It'...   \n",
506 |        "34788       joy  The world didnt give it to me..so the world MO...   \n",
507 |        "34789     anger                           A man robbed me today .    \n",
508 |        "34790      fear  Youu call it JEALOUSY, I call it of #Losing YO...   \n",
509 |        "34791   sadness  I think about you baby, and I dream about you ...   \n",
510 |        "\n",
511 |        "                                              Clean_Text  \n",
512 |        "0                                                      ?  \n",
513 |        "1                        Sage Act upgrade list tommorow.  \n",
514 |        "2      WAY HOMEGIRL BABY FUNERAL!!! MAN HATE FUNERALS...  \n",
515 |        "3      eye ! true hazel eye-and brilliant ! Regular f...  \n",
516 |        "4      ugh babe.. hugggzzz u .! babe naamazed nga ako...  \n",
517 |        "...                                                  ...  \n",
518 |        "34787    gift! Hope like it! hand wear ! It'll warm! Lol  \n",
519 |        "34788    world didnt me..so world DEFINITELY cnt away!!!  \n",
520 |        "34789                                 man robbed today .  \n",
521 |        "34790                      Youu JEALOUSY, #Losing YOU...  \n",
522 |        "34791                             think baby, dream time  \n",
523 |        "\n",
524 |        "[34792 rows x 3 columns]"
525 |       ]
526 |      },
527 |      "execution_count": 19,
528 |      "metadata": {},
529 |      "output_type": "execute_result"
530 |     }
531 |    ],
532 |    "source": [
533 |     "df"
534 |    ]
535 |   },
536 |   {
537 |    "cell_type": "code",
538 |    "execution_count": 20,
539 |    "id": "450c39c0-79dd-4eaf-85fe-57e344eb81bd",
540 |    "metadata": {},
541 |    "outputs": [],
542 |    "source": [
543 |     "# Features & Labels\n",
544 |     "Xfeatures = df['Clean_Text']\n",
545 |     "ylabels = df['Emotion']"
546 |    ]
547 |   },
548 |   {
549 |    "cell_type": "code",
550 |    "execution_count": 21,
551 |    "id": "27d7f976-c28f-449e-ae1a-53a42bbda4e8",
552 |    "metadata": {},
553 |    "outputs": [],
554 |    "source": [
555 |     "#  Split Data\n",
556 |     "x_train,x_test,y_train,y_test = train_test_split(Xfeatures,ylabels,test_size=0.3,random_state=42)"
557 |    ]
558 |   },
559 |   {
560 |    "cell_type": "code",
561 |    "execution_count": 22,
562 |    "id": "2f086f29-dba9-40d2-a9dd-f06a6cca3a4c",
563 |    "metadata": {},
564 |    "outputs": [],
565 |    "source": [
566 |     "# Build Pipeline\n",
567 |     "from sklearn.pipeline import Pipeline"
568 |    ]
569 |   },
570 |   {
571 |    "cell_type": "code",
572 |    "execution_count": 23,
573 |    "id": "6b81cc86-2bef-40c2-b9a3-668caaadaff0",
574 |    "metadata": {},
575 |    "outputs": [],
576 |    "source": [
577 |     "# LogisticRegression Pipeline\n",
578 |     "pipe_lr = Pipeline(steps=[('cv',CountVectorizer()),('lr',LogisticRegression())])"
579 |    ]
580 |   },
581 |   {
582 |    "cell_type": "code",
583 |    "execution_count": 24,
584 |    "id": "dc64b9a7-efe2-4bc4-a0e7-46dff1d52b31",
585 |    "metadata": {
586 |     "collapsed": true,
587 |     "jupyter": {
588 |      "outputs_hidden": true
589 |     },
590 |     "tags": []
591 |    },
592 |    "outputs": [
593 |     {
594 |      "name": "stderr",
595 |      "output_type": "stream",
596 |      "text": [
597 |       "/usr/local/lib/python3.9/dist-packages/sklearn/linear_model/_logistic.py:763: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
598 |       "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
599 |       "\n",
600 |       "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
601 |       "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
602 |       "Please also refer to the documentation for alternative solver options:\n",
603 |       "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
604 |       "  n_iter_i = _check_optimize_result(\n"
605 |      ]
606 |     },
607 |     {
608 |      "data": {
609 |       "text/plain": [
610 |        "Pipeline(steps=[('cv', CountVectorizer()), ('lr', LogisticRegression())])"
611 |       ]
612 |      },
613 |      "execution_count": 24,
614 |      "metadata": {},
615 |      "output_type": "execute_result"
616 |     }
617 |    ],
618 |    "source": [
619 |     "# Train and Fit Data\n",
620 |     "pipe_lr.fit(x_train,y_train)"
621 |    ]
622 |   },
623 |   {
624 |    "cell_type": "code",
625 |    "execution_count": 25,
626 |    "id": "135ed6f8-56ff-4d53-85e3-541e3a7ae2d7",
627 |    "metadata": {},
628 |    "outputs": [
629 |     {
630 |      "data": {
631 |       "text/plain": [
632 |        "Pipeline(steps=[('cv', CountVectorizer()), ('lr', LogisticRegression())])"
633 |       ]
634 |      },
635 |      "execution_count": 25,
636 |      "metadata": {},
637 |      "output_type": "execute_result"
638 |     }
639 |    ],
640 |    "source": [
641 |     "pipe_lr"
642 |    ]
643 |   },
644 |   {
645 |    "cell_type": "code",
646 |    "execution_count": 26,
647 |    "id": "28396371-5f5c-4a3b-b974-164e047764f3",
648 |    "metadata": {},
649 |    "outputs": [
650 |     {
651 |      "data": {
652 |       "text/plain": [
653 |        "0.6200421536692853"
654 |       ]
655 |      },
656 |      "execution_count": 26,
657 |      "metadata": {},
658 |      "output_type": "execute_result"
659 |     }
660 |    ],
661 |    "source": [
662 |     "# Check Accuracy\n",
663 |     "pipe_lr.score(x_test,y_test)"
664 |    ]
665 |   },
666 |   {
667 |    "cell_type": "code",
668 |    "execution_count": 27,
669 |    "id": "eb3a26b6-d09e-422f-991b-b08c48f55b75",
670 |    "metadata": {},
671 |    "outputs": [],
672 |    "source": [
673 |     "# Make A Prediction\n",
674 |     "ex1 = \"This book was so interesting it made me happy\""
675 |    ]
676 |   },
677 |   {
678 |    "cell_type": "code",
679 |    "execution_count": 28,
680 |    "id": "b08597d9-6f59-45cb-a648-95b0da1ce313",
681 |    "metadata": {},
682 |    "outputs": [
683 |     {
684 |      "data": {
685 |       "text/plain": [
686 |        "array(['joy'], dtype=object)"
687 |       ]
688 |      },
689 |      "execution_count": 28,
690 |      "metadata": {},
691 |      "output_type": "execute_result"
692 |     }
693 |    ],
694 |    "source": [
695 |     "pipe_lr.predict([ex1])"
696 |    ]
697 |   },
698 |   {
699 |    "cell_type": "code",
700 |    "execution_count": 29,
701 |    "id": "5b3822ac-17fc-43dd-9bb7-8dad07a4d32c",
702 |    "metadata": {},
703 |    "outputs": [
704 |     {
705 |      "data": {
706 |       "text/plain": [
707 |        "array([[1.60353503e-03, 7.05960421e-03, 6.95963589e-03, 9.43781635e-01,\n",
708 |        "        1.00430913e-04, 2.63557471e-02, 6.65377751e-05, 1.40728742e-02]])"
709 |       ]
710 |      },
711 |      "execution_count": 29,
712 |      "metadata": {},
713 |      "output_type": "execute_result"
714 |     }
715 |    ],
716 |    "source": [
717 |     "# Prediction Prob\n",
718 |     "pipe_lr.predict_proba([ex1])"
719 |    ]
720 |   },
721 |   {
722 |    "cell_type": "code",
723 |    "execution_count": 30,
724 |    "id": "5b7c4596-d643-48e5-a777-79a6f55c49da",
725 |    "metadata": {},
726 |    "outputs": [
727 |     {
728 |      "data": {
729 |       "text/plain": [
730 |        "array(['anger', 'disgust', 'fear', 'joy', 'neutral', 'sadness', 'shame',\n",
731 |        "       'surprise'], dtype=object)"
732 |       ]
733 |      },
734 |      "execution_count": 30,
735 |      "metadata": {},
736 |      "output_type": "execute_result"
737 |     }
738 |    ],
739 |    "source": [
740 |     "# To Know the classes\n",
741 |     "pipe_lr.classes_"
742 |    ]
743 |   },
744 |   {
745 |    "cell_type": "code",
746 |    "execution_count": 31,
747 |    "id": "c0d40f62-b1fd-4748-a279-c8f50c748f26",
748 |    "metadata": {},
749 |    "outputs": [],
750 |    "source": [
751 |     "# Save Model & Pipeline\n",
752 |     "import joblib\n",
753 |     "pipeline_file = open(\"emotion_classifier_pipe_lr_03_june_2021.pkl\",\"wb\")\n",
754 |     "joblib.dump(pipe_lr,pipeline_file)\n",
755 |     "pipeline_file.close()"
756 |    ]
757 |   },
758 |   {
759 |    "cell_type": "code",
760 |    "execution_count": null,
761 |    "id": "377c4e98-67f0-45e5-8dd5-0417585754f0",
762 |    "metadata": {},
763 |    "outputs": [],
764 |    "source": []
765 |   }
766 |  ],
767 |  "metadata": {
768 |   "kernelspec": {
769 |    "display_name": "Python 3",
770 |    "language": "python",
771 |    "name": "python3"
772 |   },
773 |   "language_info": {
774 |    "codemirror_mode": {
775 |     "name": "ipython",
776 |     "version": 3
777 |    },
778 |    "file_extension": ".py",
779 |    "mimetype": "text/x-python",
780 |    "name": "python",
781 |    "nbconvert_exporter": "python",
782 |    "pygments_lexer": "ipython3",
783 |    "version": "3.9.1+"
784 |   }
785 |  },
786 |  "nbformat": 4,
787 |  "nbformat_minor": 5
788 | }
789 | 


--------------------------------------------------------------------------------
/notebooks/emotion_classifier_pipe_lr_03_june_2021.pkl:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Jcharis/end2end-nlp-project/f82d87ed6d2608ad2c9b43e29e06da53429c1915/notebooks/emotion_classifier_pipe_lr_03_june_2021.pkl


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