Initial Flask app deployment

Dockerfile.txt

@@ -0,0 +1,7 @@
+FROM python:3.9
+WORKDIR /code
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+COPY . .
+EXPOSE 7860
+CMD ["gunicorn", "app:app", "--bind", "0.0.0.0:7860"]

app.py

@@ -0,0 +1,57 @@
+from flask import Flask, render_template, url_for, request
+from flask_bootstrap import Bootstrap
+import pickle
+import pandas as pd
+import numpy as np
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.feature_extraction.text import TfidfVectorizer
+import joblib
+
+app = Flask(__name__)
+Bootstrap(app)
+
+
+@app.route('/')
+def home():
+	return render_template("home.html")
+
+@app.route('/predict', methods = ['POST'])
+def predict():
+	#return render_template("result.html")
+	
+
+	df= pd.read_csv("data2.csv")
+
+	df_data = df[["class", "comments"]]
+	df_x = df_data["comments"]
+	df_y = df_data["class"]
+
+	corpus = df_x
+	cv = CountVectorizer()
+	X = cv.fit_transform(corpus)
+
+	from sklearn.model_selection import train_test_split
+	X_train, X_test, y_train, y_test = train_test_split(X, df_y, test_size=0.3, random_state=42)
+
+	from sklearn.linear_model import LogisticRegression
+	clf = LogisticRegression()
+	clf.fit(X_train, y_train)
+	clf.score(X_test, y_test)
+
+	# # #load the vectorizer
+	# my_vectorizer = open("comment_vectorizer.pkl", "rb")
+	# vector = joblib.load(my_vectorizer)
+	# #load the model
+	# my_model = open("myFinalModel.pkl","rb")
+	# model_clf = joblib.load(my_model)
+
+
+	if request.method == 'POST':
+		comment = request.form['comment']
+		data = [comment]
+		vect = cv.transform(data).toarray()
+		my_prediction = clf.predict(vect)
+	return render_template('home.html', name = data, prediction = my_prediction, user_comment = comment)
+
+if __name__ == '__main__':
+	app.run(debug = True)

classifier.ipynb

@@ -0,0 +1,1609 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.feature_extraction.text import CountVectorizer\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df= pd.read_csv(\"data.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>class</th>\n",
+       "      <th>comments</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>you are sick upstairs</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0</td>\n",
+       "      <td>i really dont understand your pointxa0 it seem...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0</td>\n",
+       "      <td>axcxa0majority of canadians can and has been w...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0</td>\n",
+       "      <td>sdl ok but i would hope theyd sign him to a on...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0</td>\n",
+       "      <td>yeah and where are you now</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   class                                           comments\n",
+       "0      1                              you are sick upstairs\n",
+       "1      0  i really dont understand your pointxa0 it seem...\n",
+       "2      0  axcxa0majority of canadians can and has been w...\n",
+       "3      0  sdl ok but i would hope theyd sign him to a on...\n",
+       "4      0                         yeah and where are you now"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "8744"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.size"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['class', 'comments'], dtype='object')"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "class        int64\n",
+       "comments    object\n",
+       "dtype: object"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#checking for datatypes\n",
+    "df.dtypes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "class       0\n",
+       "comments    0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#checking for missing nan\n",
+    "df.isnull().isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_data = df[[\"class\", \"comments\"]]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['class', 'comments'], dtype='object')"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_data.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_x = df_data[\"comments\"]\n",
+    "df_y = df_data[\"class\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Feature Extraction from Text\n",
+    "\n",
+    "cv = CountVectorizer()\n",
+    "ex = cv.fit_transform([\"Hello baby gitl\", \"My Nigga wetin dey\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[1, 0, 1, 1, 0, 0, 0],\n",
+       "       [0, 1, 0, 0, 1, 1, 1]], dtype=int64)"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "ex.toarray()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['baby', 'dey', 'gitl', 'hello', 'my', 'nigga', 'wetin']"
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "cv.get_feature_names()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "corpus = df_x\n",
+    "cv = CountVectorizer()\n",
+    "X = cv.fit_transform(corpus)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[0, 0, 0, ..., 0, 0, 0],\n",
+       "       [0, 0, 0, ..., 0, 0, 0],\n",
+       "       [0, 0, 0, ..., 0, 0, 0],\n",
+       "       ...,\n",
+       "       [0, 0, 0, ..., 0, 0, 0],\n",
+       "       [0, 0, 0, ..., 0, 0, 0],\n",
+       "       [0, 0, 0, ..., 0, 0, 0]], dtype=int64)"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X.toarray()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['00',\n",
+       " '000',\n",
+       " '0000',\n",
+       " '00000',\n",
+       " '000000',\n",
+       " '0000harrison',\n",
+       " '0001nobama',\n",
+       " '000nnjfeigelsondebevoisecomnnnnnnall',\n",
+       " '000sxcxa0',\n",
+       " '001',\n",
+       " '0011',\n",
+       " '00gallonxcxa0',\n",
+       " '00nnemmanueltouheythehillcomnnnnand',\n",
+       " '00nnthis',\n",
+       " '00xa0',\n",
+       " '00xa0islam',\n",
+       " '01',\n",
+       " '010',\n",
+       " '010nndid',\n",
+       " '010nnthe',\n",
+       " '010xcxa0maxine',\n",
+       " '011',\n",
+       " '011nnthe',\n",
+       " '01it',\n",
+       " '01nnnndear',\n",
+       " '01nthe',\n",
+       " '01skeeter',\n",
+       " '0bama',\n",
+       " '0bstructionism',\n",
+       " '0f',\n",
+       " '0fps',\n",
+       " '0k',\n",
+       " '0kg',\n",
+       " '0ld',\n",
+       " '0nndallas',\n",
+       " '0nokc',\n",
+       " '0nsee',\n",
+       " '0px',\n",
+       " '0pxparam',\n",
+       " '0s',\n",
+       " '0th',\n",
+       " '0thcentury',\n",
+       " '0you',\n",
+       " '10',\n",
+       " '100',\n",
+       " '1000',\n",
+       " '10000',\n",
+       " '100000',\n",
+       " '100k',\n",
+       " '100nthey',\n",
+       " '100st',\n",
+       " '100sxa0',\n",
+       " '101',\n",
+       " '1011',\n",
+       " '10110',\n",
+       " '10k',\n",
+       " '10lbs',\n",
+       " '10mp',\n",
+       " '10nceltics',\n",
+       " '10nnwhat',\n",
+       " '10pm',\n",
+       " '10s',\n",
+       " '10snnn',\n",
+       " '10th',\n",
+       " '10x',\n",
+       " '10xa0',\n",
+       " '10xa0ncountries',\n",
+       " '11',\n",
+       " '11010',\n",
+       " '110111',\n",
+       " '11despite',\n",
+       " '11nspurs',\n",
+       " '11th',\n",
+       " '1500',\n",
+       " '16',\n",
+       " '17',\n",
+       " '18',\n",
+       " '1976',\n",
+       " '19800',\n",
+       " '1am',\n",
+       " '1bpblogspotcomyvszmvvirwtmokfaugmiaaaaaaaaa0knllaahknniss100kill',\n",
+       " '1cm',\n",
+       " '1htmlxcxa0nnfor',\n",
+       " '1kmonth',\n",
+       " '1m',\n",
+       " '1mgdl',\n",
+       " '1mm',\n",
+       " '1nbarney',\n",
+       " '1nbobcats',\n",
+       " '1nncorporations',\n",
+       " '1nnndeniece',\n",
+       " '1nnpar',\n",
+       " '1nnso',\n",
+       " '1paterno',\n",
+       " '1st',\n",
+       " '1th',\n",
+       " '1when',\n",
+       " '1xa0thought',\n",
+       " '1xa0xa0',\n",
+       " '1xcxa0frederick',\n",
+       " '1yearold',\n",
+       " '1yo',\n",
+       " '1yr',\n",
+       " '2017',\n",
+       " '2m',\n",
+       " '30',\n",
+       " '30k',\n",
+       " '30th',\n",
+       " '4th',\n",
+       " '504',\n",
+       " '50k',\n",
+       " '59',\n",
+       " '5k',\n",
+       " '70',\n",
+       " '86',\n",
+       " '900pm',\n",
+       " '9ice',\n",
+       " '9ja',\n",
+       " 'a1',\n",
+       " 'aaaaaaand',\n",
+       " 'aaaah',\n",
+       " 'aaahhh',\n",
+       " 'aac',\n",
+       " 'aamir',\n",
+       " 'aap',\n",
+       " 'aarongmyers',\n",
+       " 'ab',\n",
+       " 'abacha',\n",
+       " 'abandon',\n",
+       " 'abandoned',\n",
+       " 'abandonment',\n",
+       " 'abc',\n",
+       " 'abe',\n",
+       " 'abeds',\n",
+       " 'abeg',\n",
+       " 'abel',\n",
+       " 'aberdeen',\n",
+       " 'abetted',\n",
+       " 'abey',\n",
+       " 'abi',\n",
+       " 'abide',\n",
+       " 'abiding',\n",
+       " 'abigail',\n",
+       " 'abilities',\n",
+       " 'ability',\n",
+       " 'abilitya',\n",
+       " 'abilityn',\n",
+       " 'abit',\n",
+       " 'able',\n",
+       " 'abnormal',\n",
+       " 'abolish',\n",
+       " 'abomination',\n",
+       " 'abominations',\n",
+       " 'abort',\n",
+       " 'aborted',\n",
+       " 'abortifacients',\n",
+       " 'abortion',\n",
+       " 'abortionneven',\n",
+       " 'abortions',\n",
+       " 'abortionsnnalso',\n",
+       " 'about',\n",
+       " 'aboutn',\n",
+       " 'aboutnot',\n",
+       " 'aboutxa0u0u0u0au0u0a',\n",
+       " 'above',\n",
+       " 'abraham',\n",
+       " 'abroad',\n",
+       " 'abroadxcxa0nfacts',\n",
+       " 'abruptly',\n",
+       " 'abs',\n",
+       " 'abs0lutely',\n",
+       " 'abscam',\n",
+       " 'absence',\n",
+       " 'absolute',\n",
+       " 'absolutejoke',\n",
+       " 'absolutely',\n",
+       " 'abstaining',\n",
+       " 'absurd',\n",
+       " 'absurdly',\n",
+       " 'absurdumnatt',\n",
+       " 'absurt',\n",
+       " 'abundantly',\n",
+       " 'aburrido',\n",
+       " 'abuse',\n",
+       " 'abused',\n",
+       " 'abuses',\n",
+       " 'abusing',\n",
+       " 'abusive',\n",
+       " 'abxcxa0',\n",
+       " 'abxxv',\n",
+       " 'abysmal',\n",
+       " 'ac',\n",
+       " 'academic',\n",
+       " 'acc',\n",
+       " 'accentblacks',\n",
+       " 'accept',\n",
+       " 'acceptable',\n",
+       " 'accepted',\n",
+       " 'accepting',\n",
+       " 'access',\n",
+       " 'accessible',\n",
+       " 'accessories',\n",
+       " 'accident',\n",
+       " 'accidental',\n",
+       " 'accidentally',\n",
+       " 'accidents',\n",
+       " 'accolades',\n",
+       " 'accomplish',\n",
+       " 'accomplished',\n",
+       " 'accomplishednnyou',\n",
+       " 'accomplishment',\n",
+       " 'accomplishments',\n",
+       " 'accordance',\n",
+       " 'according',\n",
+       " 'account',\n",
+       " 'accountability',\n",
+       " 'accountable',\n",
+       " 'accountsnjust',\n",
+       " 'accra',\n",
+       " 'accumulate',\n",
+       " 'accurate',\n",
+       " 'accurately',\n",
+       " 'accusation',\n",
+       " 'accuse',\n",
+       " 'accused',\n",
+       " 'accuser',\n",
+       " 'accusing',\n",
+       " 'accustomed',\n",
+       " 'ace',\n",
+       " 'acha',\n",
+       " 'acheson',\n",
+       " 'achieve',\n",
+       " 'achievement',\n",
+       " 'achievements',\n",
+       " 'achievementsbut',\n",
+       " 'achieving',\n",
+       " 'acid',\n",
+       " 'aciddragonxa0xa0rourke',\n",
+       " 'ackbar',\n",
+       " 'acknowledge',\n",
+       " 'acknowledged',\n",
+       " 'acknowledging',\n",
+       " 'acl',\n",
+       " 'acordxe',\n",
+       " 'acquire',\n",
+       " 'acquired',\n",
+       " 'acquiring',\n",
+       " 'acquitted',\n",
+       " 'acres',\n",
+       " 'across',\n",
+       " 'act',\n",
+       " 'acted',\n",
+       " 'acting',\n",
+       " 'actio',\n",
+       " 'action',\n",
+       " 'actions',\n",
+       " 'actitud',\n",
+       " 'active',\n",
+       " 'actively',\n",
+       " 'activists',\n",
+       " 'activistsxcxa0xcxa0',\n",
+       " 'activities',\n",
+       " 'activity',\n",
+       " 'actor',\n",
+       " 'actorif',\n",
+       " 'actress',\n",
+       " 'acts',\n",
+       " 'actsxcxa0hasnt',\n",
+       " 'actual',\n",
+       " 'actuality',\n",
+       " 'actually',\n",
+       " 'actuallyxa0',\n",
+       " 'actxa0',\n",
+       " 'acute',\n",
+       " 'ad',\n",
+       " 'ada',\n",
+       " 'adage',\n",
+       " 'adam',\n",
+       " 'adam1',\n",
+       " 'adamant',\n",
+       " 'adamawa',\n",
+       " 'adamomarsxa0xa0dieofnvxa0the',\n",
+       " 'adapt',\n",
+       " 'adapted',\n",
+       " 'adaptible',\n",
+       " 'add',\n",
+       " 'added',\n",
+       " 'addict',\n",
+       " 'addicted',\n",
+       " 'addiction',\n",
+       " 'addicts',\n",
+       " 'adding',\n",
+       " 'addition',\n",
+       " 'additional',\n",
+       " 'additionally',\n",
+       " 'address',\n",
+       " 'addresses',\n",
+       " 'addressing',\n",
+       " 'addressstop',\n",
+       " 'adds',\n",
+       " 'addy',\n",
+       " 'adele',\n",
+       " 'adept',\n",
+       " 'adhere',\n",
+       " 'adherents',\n",
+       " 'adhocits',\n",
+       " 'adicted',\n",
+       " 'adjust',\n",
+       " 'admin',\n",
+       " 'administration',\n",
+       " 'administrationnto',\n",
+       " 'administrationnwould',\n",
+       " 'administrations',\n",
+       " 'administrative',\n",
+       " 'administratorxa0',\n",
+       " 'adminstration',\n",
+       " 'admirably',\n",
+       " 'admiral',\n",
+       " 'admire',\n",
+       " 'admiring',\n",
+       " 'admit',\n",
+       " 'admits',\n",
+       " 'admitted',\n",
+       " 'admittedly',\n",
+       " 'admitting',\n",
+       " 'adolescent',\n",
+       " 'adolf',\n",
+       " 'adopt',\n",
+       " 'adopted',\n",
+       " 'adopting',\n",
+       " 'adoption',\n",
+       " 'adoptions',\n",
+       " 'adorable',\n",
+       " 'adult',\n",
+       " 'adulterer',\n",
+       " 'adulterers',\n",
+       " 'adultery',\n",
+       " 'adults',\n",
+       " 'adultsxcxa0',\n",
+       " 'adultsxcxa0xcxa0most',\n",
+       " 'adumbas',\n",
+       " 'advancement',\n",
+       " 'advancements',\n",
+       " 'advantage',\n",
+       " 'adverise',\n",
+       " 'adversaries',\n",
+       " 'adversary',\n",
+       " 'advertising',\n",
+       " 'advice',\n",
+       " 'advicenand',\n",
+       " 'advised',\n",
+       " 'adviser',\n",
+       " 'advisers',\n",
+       " 'advisor',\n",
+       " 'advocate',\n",
+       " 'advocates',\n",
+       " 'advocating',\n",
+       " 'aes',\n",
+       " 'afar',\n",
+       " 'affair',\n",
+       " 'affairs',\n",
+       " 'affairsnnextremist',\n",
+       " 'affect',\n",
+       " 'affected',\n",
+       " 'affects',\n",
+       " 'afffects',\n",
+       " 'affiliate',\n",
+       " 'affiliation',\n",
+       " 'affirming',\n",
+       " 'affixed',\n",
+       " 'affluent',\n",
+       " 'affod',\n",
+       " 'afford',\n",
+       " 'afforded',\n",
+       " 'affraid',\n",
+       " 'affront',\n",
+       " 'afgans',\n",
+       " 'afghan',\n",
+       " 'afghanistan',\n",
+       " 'afiliados',\n",
+       " 'afixing',\n",
+       " 'afraid',\n",
+       " 'africa',\n",
+       " 'africaand',\n",
+       " 'africamore',\n",
+       " 'african',\n",
+       " 'africans',\n",
+       " 'africansnslavery',\n",
+       " 'africayou',\n",
+       " 'afrika',\n",
+       " 'afroamerican',\n",
+       " 'after',\n",
+       " 'afterall',\n",
+       " 'aftermath',\n",
+       " 'afternoonthat',\n",
+       " 'afterward',\n",
+       " 'afterwardsnn',\n",
+       " 'afterwardsnninstead',\n",
+       " 'afucking',\n",
+       " 'afvet11nnim',\n",
+       " 'ag',\n",
+       " 'again',\n",
+       " 'again1',\n",
+       " 'againever',\n",
+       " 'againhe',\n",
+       " 'againnif',\n",
+       " 'againnn',\n",
+       " 'againnn1',\n",
+       " 'againnnand',\n",
+       " 'againnnmeanwhile',\n",
+       " 'againnnunless',\n",
+       " 'againnnyou',\n",
+       " 'agains',\n",
+       " 'against',\n",
+       " 'againstnthe',\n",
+       " 'againtonyretardo',\n",
+       " 'againxa0xa0',\n",
+       " 'agbaya',\n",
+       " 'age',\n",
+       " 'aged',\n",
+       " 'agencies',\n",
+       " 'agency',\n",
+       " 'agenda',\n",
+       " 'agent',\n",
+       " 'agents',\n",
+       " 'ages',\n",
+       " 'aggie',\n",
+       " 'aggressive',\n",
+       " 'aginst',\n",
+       " 'agism',\n",
+       " 'ago',\n",
+       " 'agoxcxa0',\n",
+       " 'agree',\n",
+       " 'agreed',\n",
+       " 'agreeing',\n",
+       " 'agreement',\n",
+       " 'agrees',\n",
+       " 'agriculture',\n",
+       " 'aguycommenting',\n",
+       " 'agxcxa0',\n",
+       " 'ah',\n",
+       " 'ahahah',\n",
+       " 'ahahahahah',\n",
+       " 'ahead',\n",
+       " 'aheadnnq',\n",
+       " 'ahn',\n",
+       " 'ahole',\n",
+       " 'aholennnot',\n",
+       " 'aholexa0',\n",
+       " 'ahr1xa0xa0',\n",
+       " 'ahs',\n",
+       " 'aid',\n",
+       " 'aided',\n",
+       " 'aids',\n",
+       " 'ail',\n",
+       " 'aimed',\n",
+       " 'aimless',\n",
+       " 'aint',\n",
+       " 'aipac',\n",
+       " 'air',\n",
+       " 'airbad',\n",
+       " 'airbrush',\n",
+       " 'airchair',\n",
+       " 'aircraft',\n",
+       " 'airing',\n",
+       " 'airmix',\n",
+       " 'airplane',\n",
+       " 'airport',\n",
+       " 'airwaves',\n",
+       " 'ajumoke',\n",
+       " 'aka',\n",
+       " 'akiinwale',\n",
+       " 'akinwunmiambode',\n",
+       " 'akklaim',\n",
+       " 'akp',\n",
+       " 'aks',\n",
+       " 'aktuxe1lnu011bju011xedhokritickxehomoralizujxedcxedho',\n",
+       " 'al',\n",
+       " 'alabama',\n",
+       " 'alain',\n",
+       " 'alainironu',\n",
+       " 'alakda',\n",
+       " 'alan',\n",
+       " 'alarm',\n",
+       " 'alarming',\n",
+       " 'alasthis',\n",
+       " 'albaxf1il',\n",
+       " 'album',\n",
+       " 'albumnnfor',\n",
+       " 'albums',\n",
+       " 'alcohol',\n",
+       " 'alcoholic',\n",
+       " 'alcohols',\n",
+       " 'aldasity',\n",
+       " 'aldickweed',\n",
+       " 'aldri',\n",
+       " 'ale',\n",
+       " 'alecs',\n",
+       " 'aleging',\n",
+       " 'aleisterhyde',\n",
+       " 'alejate',\n",
+       " 'alenlemone',\n",
+       " 'alert',\n",
+       " 'alessandra',\n",
+       " 'alex',\n",
+       " 'alexander',\n",
+       " 'alexis',\n",
+       " 'ali',\n",
+       " 'aliberal',\n",
+       " 'alice',\n",
+       " 'alien',\n",
+       " 'alienated',\n",
+       " 'alienates',\n",
+       " 'alienating',\n",
+       " 'aliens',\n",
+       " 'aliensnnyou',\n",
+       " 'aliensxa0to',\n",
+       " 'alike',\n",
+       " 'alikexa0',\n",
+       " 'alinsky',\n",
+       " 'alisterdognwhat',\n",
+       " 'alive',\n",
+       " 'alivennits',\n",
+       " 'alivexa0',\n",
+       " 'alkohol',\n",
+       " 'all',\n",
+       " 'alla',\n",
+       " 'allah',\n",
+       " 'allahpunditnnvia',\n",
+       " 'allan',\n",
+       " 'allegations',\n",
+       " 'alleged',\n",
+       " 'allegedly',\n",
+       " 'allegiance',\n",
+       " 'allen',\n",
+       " 'allergic',\n",
+       " 'allergies',\n",
+       " 'allergiesxa0nni',\n",
+       " 'alley',\n",
+       " 'allgaybryan',\n",
+       " 'alliance',\n",
+       " 'alliances',\n",
+       " 'allies',\n",
+       " 'alligator',\n",
+       " 'allinit1',\n",
+       " 'allkpop',\n",
+       " 'alll',\n",
+       " 'allmxenna',\n",
+       " 'allnassessments',\n",
+       " 'allnnthis',\n",
+       " 'allnnyour',\n",
+       " 'allnthat',\n",
+       " 'allnthe',\n",
+       " 'allocated',\n",
+       " 'allot',\n",
+       " 'allow',\n",
+       " 'allowed',\n",
+       " 'allowfullscreentrue',\n",
+       " 'allowing',\n",
+       " 'allows',\n",
+       " 'allowscriptaccessalways',\n",
+       " 'allpowerful',\n",
+       " 'allpro',\n",
+       " 'allra',\n",
+       " 'alls',\n",
+       " 'allstar',\n",
+       " 'allt',\n",
+       " 'allu0i',\n",
+       " 'allways',\n",
+       " 'allxa0',\n",
+       " 'allxa0as',\n",
+       " 'allxa0passed',\n",
+       " 'allxcxa0',\n",
+       " 'allxcxa0nnthe',\n",
+       " 'ally',\n",
+       " 'allyxa0',\n",
+       " 'almajiris',\n",
+       " 'almighty',\n",
+       " 'almost',\n",
+       " 'alone',\n",
+       " 'alonebitch',\n",
+       " 'alonehell',\n",
+       " 'alonennand',\n",
+       " 'alonexa0',\n",
+       " 'along',\n",
+       " 'alongshes',\n",
+       " 'alot',\n",
+       " 'alotnkeeps',\n",
+       " 'already',\n",
+       " 'alreadynkennedy',\n",
+       " 'alreadyxa0',\n",
+       " 'alrightnwell',\n",
+       " 'also',\n",
+       " 'alsoruns',\n",
+       " 'alsoxa0',\n",
+       " 'alsum',\n",
+       " 'altar',\n",
+       " 'alter',\n",
+       " 'alterego',\n",
+       " 'alternate',\n",
+       " 'alternatives',\n",
+       " 'although',\n",
+       " 'altogether',\n",
+       " 'alumni',\n",
+       " 'always',\n",
+       " 'am',\n",
+       " 'ama',\n",
+       " 'amala',\n",
+       " 'amanda',\n",
+       " 'amateur',\n",
+       " 'amazaballs',\n",
+       " 'amazed',\n",
+       " 'amazement',\n",
+       " 'amazing',\n",
+       " 'amazzzzing',\n",
+       " 'ambassadornand',\n",
+       " 'amber',\n",
+       " 'ambition',\n",
+       " 'ambitious',\n",
+       " 'amd',\n",
+       " 'amdnnnnnyou',\n",
+       " 'amen',\n",
+       " 'amendment',\n",
+       " 'amendments',\n",
+       " 'amendmentxcxa0nnroman',\n",
+       " 'amends',\n",
+       " 'amerians',\n",
+       " 'america',\n",
+       " 'americacutting',\n",
+       " 'american',\n",
+       " 'american0',\n",
+       " 'americannvan',\n",
+       " 'americans',\n",
+       " 'americansnnif',\n",
+       " 'americansno',\n",
+       " 'americansxa0xa0nlol',\n",
+       " 'americansxcxa0',\n",
+       " 'americanyoure',\n",
+       " 'americas',\n",
+       " 'americaxa0',\n",
+       " 'americaxcxa0',\n",
+       " 'americaxex0xdnxex0xcwhat',\n",
+       " 'amerikan',\n",
+       " 'amerikans',\n",
+       " 'amid',\n",
+       " 'amir',\n",
+       " 'ammede',\n",
+       " 'ammunition',\n",
+       " 'ammunitionnas',\n",
+       " 'amnesty',\n",
+       " 'among',\n",
+       " 'amoral',\n",
+       " 'amount',\n",
+       " 'amounted',\n",
+       " 'amounts',\n",
+       " 'amous',\n",
+       " 'amp',\n",
+       " 'amso',\n",
+       " 'amused',\n",
+       " 'amusement',\n",
+       " 'amuses',\n",
+       " 'amxa0',\n",
+       " 'amy',\n",
+       " 'an',\n",
+       " 'anachronism',\n",
+       " 'anal',\n",
+       " 'analogy',\n",
+       " 'analy',\n",
+       " 'analysis',\n",
+       " 'analyst',\n",
+       " 'anaphylactic',\n",
+       " 'anathema',\n",
+       " 'anc',\n",
+       " 'ancelotti',\n",
+       " 'ancestors',\n",
+       " 'ancient',\n",
+       " 'and',\n",
+       " 'andato',\n",
+       " 'anderson',\n",
+       " 'andersons',\n",
+       " 'andf',\n",
+       " 'andfuckedup',\n",
+       " 'andi',\n",
+       " 'andignorant',\n",
+       " 'andino',\n",
+       " 'andnothers',\n",
+       " 'andntestify',\n",
+       " 'andor',\n",
+       " 'andrea',\n",
+       " 'andrew',\n",
+       " 'android',\n",
+       " 'andxa0',\n",
+       " 'andxa0surveillance',\n",
+       " 'andxcxa0a',\n",
+       " 'andxcxa0he',\n",
+       " 'andxcxa0medicare',\n",
+       " 'andxcxa0sink',\n",
+       " 'andxcxa0social',\n",
+       " 'andxcxa0that',\n",
+       " 'andy',\n",
+       " 'andyou',\n",
+       " 'andys',\n",
+       " 'anecdotal',\n",
+       " 'anelka',\n",
+       " 'anelkas',\n",
+       " 'anew',\n",
+       " 'anf',\n",
+       " 'angel',\n",
+       " 'angeles',\n",
+       " 'angelic',\n",
+       " 'angelnffs',\n",
+       " 'angelos',\n",
+       " 'angels',\n",
+       " 'anger',\n",
+       " 'angle',\n",
+       " 'anglo',\n",
+       " 'anglos',\n",
+       " 'angry',\n",
+       " 'angrys',\n",
+       " 'angsty',\n",
+       " 'anh',\n",
+       " 'ani',\n",
+       " 'animal',\n",
+       " 'animals',\n",
+       " 'animation',\n",
+       " 'anime',\n",
+       " 'animosity',\n",
+       " 'animoto',\n",
+       " 'animus',\n",
+       " 'annabelle',\n",
+       " 'annabortion',\n",
+       " 'annars',\n",
+       " 'annat',\n",
+       " 'annavaram',\n",
+       " 'annaxa0',\n",
+       " 'anndan',\n",
+       " 'announced',\n",
+       " 'announcement',\n",
+       " 'announcements',\n",
+       " 'announcers',\n",
+       " 'annoy',\n",
+       " 'annoyed',\n",
+       " 'annoying',\n",
+       " 'annoys',\n",
+       " 'annual',\n",
+       " 'annul',\n",
+       " 'ano',\n",
+       " 'anointing',\n",
+       " 'anology',\n",
+       " 'anon',\n",
+       " 'anonymous',\n",
+       " 'anonymouseorg',\n",
+       " 'anonymously',\n",
+       " 'another',\n",
+       " 'anothers',\n",
+       " 'anout',\n",
+       " 'ans',\n",
+       " 'anser',\n",
+       " 'answer',\n",
+       " 'answered',\n",
+       " 'answering',\n",
+       " 'answers',\n",
+       " 'ant',\n",
+       " 'antaga',\n",
+       " 'antagonize',\n",
+       " 'anthem',\n",
+       " 'anthems',\n",
+       " 'anthony',\n",
+       " 'anthropophagy',\n",
+       " 'anti',\n",
+       " 'antiabortion',\n",
+       " 'antiamerican',\n",
+       " 'anticipate',\n",
+       " 'anticipated',\n",
+       " 'anticsfirst',\n",
+       " 'antigay',\n",
+       " 'antiimmigrant',\n",
+       " 'antilib',\n",
+       " 'antisemit',\n",
+       " 'antisemitic',\n",
+       " 'antitolerance',\n",
+       " 'antiwar',\n",
+       " 'antlers',\n",
+       " 'ants',\n",
+       " 'antunnaru',\n",
+       " 'anuofia',\n",
+       " 'anus',\n",
+       " 'anxa0nexecutivexa0privilegenclaim',\n",
+       " 'any',\n",
+       " 'anybody',\n",
+       " 'anycockll',\n",
+       " 'anyday',\n",
+       " 'anyhow',\n",
+       " 'anymore',\n",
+       " 'anymorenncan',\n",
+       " 'anymorexcxa0',\n",
+       " 'anynbetter',\n",
+       " 'anynnational',\n",
+       " 'anyone',\n",
+       " 'anyoneits',\n",
+       " 'anyonenhad',\n",
+       " 'anyones',\n",
+       " 'anyonr',\n",
+       " 'anyplacen',\n",
+       " 'anything',\n",
+       " 'anythingnboth',\n",
+       " 'anythingnif',\n",
+       " 'anythingnn',\n",
+       " 'anytime',\n",
+       " 'anytimennget',\n",
+       " 'anyway',\n",
+       " 'anywayit',\n",
+       " 'anyways',\n",
+       " 'anywhere',\n",
+       " 'aok',\n",
+       " 'apa',\n",
+       " 'apart',\n",
+       " 'apartfrom',\n",
+       " 'apartment',\n",
+       " 'ape',\n",
+       " 'apegary',\n",
+       " 'apes',\n",
+       " 'aphrodisiacx',\n",
+       " 'apnay',\n",
+       " 'apni',\n",
+       " 'apo',\n",
+       " 'apologetic',\n",
+       " 'apologies',\n",
+       " 'apologise',\n",
+       " 'apologist',\n",
+       " 'apologists',\n",
+       " 'apologize',\n",
+       " 'apologized',\n",
+       " 'apologizing',\n",
+       " 'apology',\n",
+       " 'apoplectic',\n",
+       " 'apostasy',\n",
+       " 'app',\n",
+       " 'appalachians',\n",
+       " 'appalling',\n",
+       " 'apparent',\n",
+       " 'apparently',\n",
+       " 'appealing',\n",
+       " 'appear',\n",
+       " 'appearance',\n",
+       " 'appeared',\n",
+       " 'appearing',\n",
+       " 'appears',\n",
+       " 'appease',\n",
+       " 'appeasing',\n",
+       " 'applauseking',\n",
+       " 'apple',\n",
+       " 'applegadget',\n",
+       " 'apples',\n",
+       " 'applicable',\n",
+       " 'application',\n",
+       " 'applied',\n",
+       " 'applies',\n",
+       " 'apply',\n",
+       " 'appointed',\n",
+       " 'appoints',\n",
+       " 'appreciate',\n",
+       " 'appreciates',\n",
+       " 'appreciation',\n",
+       " 'apprentice',\n",
+       " 'approaching',\n",
+       " 'approachingxa0',\n",
+       " 'appropriate',\n",
+       " 'approvalnobama',\n",
+       " 'approve',\n",
+       " 'approved',\n",
+       " 'approvel',\n",
+       " 'approximately',\n",
+       " 'apps',\n",
+       " 'appt',\n",
+       " 'april',\n",
+       " 'aquino',\n",
+       " 'aquire',\n",
+       " 'aquiring',\n",
+       " 'ar',\n",
+       " 'arab',\n",
+       " 'arabia',\n",
+       " 'arabs',\n",
+       " 'aramis',\n",
+       " 'arar',\n",
+       " 'aratsass',\n",
+       " 'arbetas',\n",
+       " 'arbitrarynnthe',\n",
+       " 'arborist',\n",
+       " 'arborists',\n",
+       " 'arbystyle',\n",
+       " 'arc',\n",
+       " 'arcade',\n",
+       " 'archangel',\n",
+       " 'architecture',\n",
+       " 'archives',\n",
+       " 'are',\n",
+       " 'area',\n",
+       " 'arealconservatinntill',\n",
+       " 'areas',\n",
+       " 'arefunny',\n",
+       " 'arehope',\n",
+       " 'arena',\n",
+       " 'arenand',\n",
+       " 'arennnpussyblockquotennfuck',\n",
+       " 'arennso',\n",
+       " 'arennthe',\n",
+       " 'arenplease',\n",
+       " 'arent',\n",
+       " 'arenxex0xt',\n",
+       " 'areonly',\n",
+       " 'aressted',\n",
+       " 'arestupid',\n",
+       " 'areufeff',\n",
+       " 'arewere',\n",
+       " 'arexa0',\n",
+       " 'arexa0absolutelyxa0right',\n",
+       " 'arexa0always',\n",
+       " 'arexa0consequencesxa0for',\n",
+       " 'arexa0not',\n",
+       " 'arexa0puzzling',\n",
+       " 'arexa0xa0there',\n",
+       " 'arexcxa0',\n",
+       " 'argentina',\n",
+       " 'argentine',\n",
+       " 'argentinean',\n",
+       " 'argentines',\n",
+       " 'argentinians',\n",
+       " 'argie',\n",
+       " 'argies',\n",
+       " 'argo',\n",
+       " 'arguaments',\n",
+       " 'argue',\n",
+       " 'argued',\n",
+       " 'arguement',\n",
+       " 'arguements',\n",
+       " 'arguing',\n",
+       " 'argument',\n",
+       " 'arguments',\n",
+       " 'aries',\n",
+       " 'aristocracy',\n",
+       " 'aritculett',\n",
+       " 'arizona',\n",
+       " 'arkannnyou',\n",
+       " 'arlington',\n",
+       " 'arm',\n",
+       " 'armando',\n",
+       " 'armies',\n",
+       " 'armiesnnthe',\n",
+       " 'armpits',\n",
+       " 'arms',\n",
+       " 'army',\n",
+       " 'armyin',\n",
+       " 'arnt',\n",
+       " 'arod',\n",
+       " 'aroud',\n",
+       " 'around',\n",
+       " 'aroundnnso',\n",
+       " 'arrange',\n",
+       " 'arrangements',\n",
+       " 'arrangementsnntell',\n",
+       " 'arrest',\n",
+       " 'arrested',\n",
+       " 'arrestedndid',\n",
+       " 'arrests',\n",
+       " 'arrive',\n",
+       " 'arrived',\n",
+       " 'arriving',\n",
+       " 'arrnott',\n",
+       " 'arrogance',\n",
+       " 'arrogant',\n",
+       " 'arrogate',\n",
+       " 'ars',\n",
+       " 'arse',\n",
+       " 'arseanal',\n",
+       " 'arsehole',\n",
+       " 'arsenal',\n",
+       " 'arsenalnxa0ni',\n",
+       " 'arsene',\n",
+       " 'art',\n",
+       " 'article',\n",
+       " 'articlennin',\n",
+       " 'articles',\n",
+       " 'articlexa0bdonald',\n",
+       " 'articulate',\n",
+       " 'articulett',\n",
+       " 'artificial',\n",
+       " 'artist',\n",
+       " 'artists',\n",
+       " 'arufeffe',\n",
+       " 'arum',\n",
+       " 'as',\n",
+       " 'asad',\n",
+       " 'asami',\n",
+       " 'asap',\n",
+       " 'asdrubal',\n",
+       " 'ashamed',\n",
+       " 'ashewo',\n",
+       " 'ashley',\n",
+       " 'ashole',\n",
+       " ...]"
+      ]
+     },
+     "execution_count": 36,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "cv.get_feature_names()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#model Building\n",
+    "\n",
+    "from sklearn.model_selection import train_test_split"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train, X_test, y_train, y_test = train_test_split(X, df_y, test_size=0.3, random_state=42)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<3060x18923 sparse matrix of type '<class 'numpy.int64'>'\n",
+       "\twith 71327 stored elements in Compressed Sparse Row format>"
+      ]
+     },
+     "execution_count": 40,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X_train"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.8147865853658537"
+      ]
+     },
+     "execution_count": 46,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#logistic Regression 81%\n",
+    "\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "clf = LogisticRegression()\n",
+    "clf.fit(X_train, y_train)\n",
+    "clf.score(X_test, y_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# #naive bayes 77%\n",
+    "\n",
+    "# from sklearn.naive_bayes import MultinomialNB\n",
+    "# clf = MultinomialNB()\n",
+    "# clf.fit(X_train, y_train)\n",
+    "# clf.score(X_test, y_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([1, 1, 0, ..., 0, 0, 0], dtype=int64)"
+      ]
+     },
+     "execution_count": 48,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "clf.predict(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#sample prediction\n",
+    "comment = ['Hello fine boy']\n",
+    "vect = cv.transform(comment).toarray() "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([0], dtype=int64)"
+      ]
+     },
+     "execution_count": 50,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "clf.predict(vect)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Not Hate Speech\n"
+     ]
+    }
+   ],
+   "source": [
+    "if clf.predict(vect) == 1:\n",
+    "    print(\"Hate Sppech\")\n",
+    "else:\n",
+    "    print(\"Not Hate Speech\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([1], dtype=int64)"
+      ]
+     },
+     "execution_count": 53,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#sample prediction 2\n",
+    "comment2 = ['fuck you nigga']\n",
+    "vect2 = cv.transform(comment2).toarray()\n",
+    "clf.predict(vect2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pickle"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "logisticML = open(\"myFinalModel.pkl\", \"wb\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pickle.dump(clf, logisticML)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "logisticML.close()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "\n",
+    "#load the model\n",
+    "my_model = open(\"myFinalModel.pkl\", \"rb\")\n",
+    "new_model = pickle.load(my_model)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

myFinalModel.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:485ec29db4fcd16b5481338a91f9db6e0c38173f341ec7799517f852a47cc793
+size 152217

requirements.txt.txt

@@ -0,0 +1,7 @@
+flask
+flask_bootstrap
+pandas
+numpy
+scikit-learn
+joblib
+gunicorn

templates/home.html

@@ -0,0 +1,165 @@
+<!doctype html>
+<html lang="en">
+
+<head>
+  <meta charset="utf-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
+  <title>Offensive Comments Detection</title>
+
+  <link rel="stylesheet" href="https://stackpath.bootstrapcdn.com/bootstrap/4.2.1/css/bootstrap.min.css"
+    integrity="sha384-GJzZqFGwb1QTTN6wy59ffF1BuGJpLSa9DkKMp0DgiMDm4iYMj70gZWKYbI706tWS" crossorigin="anonymous">
+
+  <link href="https://fonts.googleapis.com/css2?family=Lato:wght@700&display=swap" rel="stylesheet">
+  <link href="https://fonts.googleapis.com/css2?family=Orbitron&display=swap" rel="stylesheet">
+
+  <style>
+    body {
+      background: linear-gradient(135deg, #0f2027, #203a43, #2c5364);
+      color: #fff;
+      font-family: 'Lato', sans-serif;
+      background-attachment: fixed;
+    }
+
+    h1 {
+      font-family: 'Orbitron', sans-serif;
+      font-size: 3rem;
+      color: #00ffc3;
+      text-shadow: 2px 2px 5px rgba(0, 255, 195, 0.5);
+    }
+
+    .card-3d {
+      background: linear-gradient(to right, #1f1c2c, #928dab);
+      border-radius: 30px;
+      box-shadow: 0 15px 30px rgba(0, 0, 0, 0.5);
+      padding: 2rem;
+    }
+
+    textarea::placeholder {
+      text-align: center;
+      font-size: 18px;
+    }
+
+    .submit-btn {
+      width: 250px;
+      height: 50px;
+      border-radius: 25px;
+      font-size: 22px;
+      background-color: #00ffc3;
+      border: none;
+      color: #000;
+    }
+
+    .submit-btn:hover {
+      background-color: #00b39f;
+    }
+
+    .dashboard {
+      margin-top: 3rem;
+      background-color: rgba(255, 255, 255, 0.05);
+      border-radius: 20px;
+      padding: 2rem;
+      text-align: center;
+      box-shadow: 0 0 20px rgba(0, 255, 195, 0.3);
+    }
+
+    .dashboard h2 {
+      color: #00ffc3;
+    }
+
+    .highlight {
+      background-color: rgba(0, 255, 195, 0.1);
+      padding: 1rem;
+      border-radius: 10px;
+      margin-top: 1rem;
+      font-size: 1.2rem;
+    }
+  </style>
+</head>
+
+<body>
+
+  <div class="container-fluid">
+    <div class="text-right mt-3 mr-3">
+      <a href="#" class="btn btn-outline-light">How To Use</a>
+    </div>
+
+    <div class="row justify-content-center mt-5">
+      <div class="col-lg-6 text-center">
+        <h1>Offensive Comments Detection</h1>
+        <p class="lead">An intelligent system to detect offensive or abusive language in text. Stay safe. Stay smart.</p>
+      </div>
+    </div>
+
+    <div class="row justify-content-center mt-4">
+      <div class="col-lg-6">
+        <div class="card-3d">
+          <form action="{{url_for('predict')}}" method="POST" class="needs-validation form" novalidate>
+            <textarea name="comment" class="form-control custom-control" rows="8" placeholder="Enter text for prediction"
+              required>{{user_comment}}</textarea>
+            <div class="invalid-feedback text-center">
+              Field cannot be empty, Please enter text and click predict button.
+            </div>
+            <br />
+            <div class="text-center">
+              <button type="submit" class="submit-btn">Predict</button>
+            </div>
+          </form>
+        </div>
+      </div>
+    </div>
+
+    {% if prediction is not none %}
+    <div class="row justify-content-center">
+      <div class="col-lg-8 dashboard">
+        <h2>Prediction Dashboard</h2>
+        <div class="highlight">
+          <strong>Your Comment:</strong> {{user_comment}}
+        </div>
+
+        {% if prediction == 1 %}
+        <div class="highlight text-danger">
+          <strong>Result:</strong> Offensive Comment Detected ❌
+        </div>
+        {% elif prediction == 0 %}
+        <div class="highlight text-success">
+          <strong>Result:</strong> Not Offensive ✅
+        </div>
+        {% endif %}
+      </div>
+    </div>
+    {% endif %}
+  </div>
+
+  <!-- JavaScript dependencies -->
+  <script src="https://code.jquery.com/jquery-3.3.1.slim.min.js"
+    integrity="sha384-q8i/X+965DzO0rT7abK41JStQIAqVgRVzpbzo5smXKp4YfRvH+8abtTE1Pi6jizo"
+    crossorigin="anonymous"></script>
+  <script src="https://cdnjs.cloudflare.com/ajax/libs/popper.js/1.14.6/umd/popper.min.js"
+    integrity="sha384-wHAiFfRlMFy6i5SRaxvfOCifBUQy1xHdJ/yoi7FRNXMRBu5WHdZYu1hA6ZOblgut"
+    crossorigin="anonymous"></script>
+  <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.2.1/js/bootstrap.min.js"
+    integrity="sha384-B0UglyR+jN6CkvvICOB2joaf5I4l3gm9GU6Hc1og6Ls7i6U/mkkaduKaBhlAXv9k"
+    crossorigin="anonymous"></script>
+
+  <script>
+    // Bootstrap form validation
+    (function () {
+      'use strict';
+      window.addEventListener('load', function () {
+        var forms = document.getElementsByClassName('needs-validation');
+        var validation = Array.prototype.filter.call(forms, function (form) {
+          form.addEventListener('submit', function (event) {
+            if (form.checkValidity() === false) {
+              event.preventDefault();
+              event.stopPropagation();
+            }
+            form.classList.add('was-validated');
+          }, false);
+        });
+      }, false);
+    })();
+  </script>
+
+</body>
+
+</html>