diff --git a/Fake-News-Classification/Dataset/README.md b/Fake-News-Classification/Dataset/README.md
new file mode 100644
index 000000000..d22ba02d2
--- /dev/null
+++ b/Fake-News-Classification/Dataset/README.md
@@ -0,0 +1,97 @@
+# Fake News Classification using DL 
+
+## PROJECT TITLE
+
+Fake News Detection using Deep Learning 
+
+## GOAL
+
+To identify whether the given news is fake or not. 
+
+## DATASET
+
+The link for the dataset used in this project:  https://www.kaggle.com/competitions/fake-news/data?select=train.csv 
+
+
+## DESCRIPTION
+
+This project aims to identify whether the given news is fake or not by extracting meaning and semantics of the given news.
+
+## WHAT I HAD DONE
+
+1. Data collection: From the link of the dataset given above. 
+2. Data preprocessing: Preprocessed the news by combining title and text to create a new feature and did some augementation like tokeinizing and vectorising before passing them to model training
+3. Model selection: Self Designed model having a Embedding Layer followed by Global Pooling Layer and then 2 Dense layers and then output layer.Second model had a Embedding layer followed by a RNN layer and a Dense output layer.
+4. Comparative analysis: Compared the accuracy score of all the models.
+
+## MODELS SUMMARY
+
+Model-1: "sequential"
+_________________________________________________________________
+ Layer (type)                Output Shape              Param #   
+=================================================================
+ embedding (Embedding)       (None, 12140, 182)        30222010  
+                                                                 
+ global_average_pooling1d (  (None, 182)               0         
+ GlobalAveragePooling1D)                                         
+                                                                 
+ dense (Dense)               (None, 96)                17568     
+                                                                 
+ dense_1 (Dense)             (None, 24)                2328      
+                                                                 
+ dense_2 (Dense)             (None, 1)                 25        
+                                                                 
+=================================================================
+Total params: 30241931 (115.36 MB)
+Trainable params: 30241931 (115.36 MB)
+Non-trainable params: 0 (0.00 Byte)
+
+Model-2: "sequential_3"
+_________________________________________________________________
+ Layer (type)                Output Shape              Param #   
+=================================================================
+ embedding_3 (Embedding)     (None, 12140, 100)        16605500  
+                                                                 
+ simple_rnn (SimpleRNN)      (None, 10)                1110      
+                                                                 
+ dense_5 (Dense)             (None, 1)                 11        
+                                                                 
+=================================================================
+Total params: 16606621 (63.35 MB)
+Trainable params: 16606621 (63.35 MB)
+Non-trainable params: 0 (0.00 Byte)
+
+## LIBRARIES NEEDED
+
+The following libraries are required to run this project:
+
+- nltk
+- pandas
+- matplotlib
+- tensorflow
+- keras
+- sklearn
+
+## EVALUATION METRICS
+
+The evaluation metrics I used to assess the models:
+
+- Accuracy 
+- Loss
+
+It is shown using Confusion Matrix in the Images folder
+
+## RESULTS
+Results on Val dataset:
+For Model-1:
+Accuracy:96.11%
+loss: 0.1350
+
+For Model-2:
+Accuracy:85.03%
+loss: 0.1439
+
+## CONCLUSION
+Based on results we can draw following conclusions:
+
+1.The model-1 showed high validation accuracy of 96.11% and loss of 0.1350.Thus the model-1 worked fairly well identifying 2874 fake articles from a total of 3044.The first model performed better.The second model had good training accuracy but less test accuracy hinting towards overfitting.Maybe the key reason being in fake news it is important to capture overall sentiment better than individual word sentiment.
diff --git a/Fake-News-Classification/Images/Dataset.png b/Fake-News-Classification/Images/Dataset.png
new file mode 100644
index 000000000..1e317542d
Binary files /dev/null and b/Fake-News-Classification/Images/Dataset.png differ
diff --git a/Fake-News-Classification/Images/EDA.png b/Fake-News-Classification/Images/EDA.png
new file mode 100644
index 000000000..17401792b
Binary files /dev/null and b/Fake-News-Classification/Images/EDA.png differ
diff --git a/Fake-News-Classification/Images/EDA1.png b/Fake-News-Classification/Images/EDA1.png
new file mode 100644
index 000000000..ddf9bc5f0
Binary files /dev/null and b/Fake-News-Classification/Images/EDA1.png differ
diff --git a/Fake-News-Classification/Images/metrics.png b/Fake-News-Classification/Images/metrics.png
new file mode 100644
index 000000000..1dc7d3150
Binary files /dev/null and b/Fake-News-Classification/Images/metrics.png differ
diff --git a/Fake-News-Classification/Images/model.png b/Fake-News-Classification/Images/model.png
new file mode 100644
index 000000000..a8cd84df6
Binary files /dev/null and b/Fake-News-Classification/Images/model.png differ
diff --git a/Fake-News-Classification/Images/model2.png b/Fake-News-Classification/Images/model2.png
new file mode 100644
index 000000000..b95d80c07
Binary files /dev/null and b/Fake-News-Classification/Images/model2.png differ
diff --git a/Fake-News-Classification/Images/model2metrics.png b/Fake-News-Classification/Images/model2metrics.png
new file mode 100644
index 000000000..e7631795b
Binary files /dev/null and b/Fake-News-Classification/Images/model2metrics.png differ
diff --git a/Fake-News-Classification/Model/PridictionModel.ipynb b/Fake-News-Classification/Model/PridictionModel.ipynb
new file mode 100644
index 000000000..6b37ebbe1
--- /dev/null
+++ b/Fake-News-Classification/Model/PridictionModel.ipynb
@@ -0,0 +1,2513 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T06:50:29.636394Z",
+     "iopub.status.busy": "2021-05-25T06:50:29.636041Z",
+     "iopub.status.idle": "2021-05-25T06:50:29.643277Z",
+     "shell.execute_reply": "2021-05-25T06:50:29.642127Z",
+     "shell.execute_reply.started": "2021-05-25T06:50:29.636365Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import sklearn\n",
+    "import itertools\n",
+    "import numpy as np\n",
+    "import seaborn as sb\n",
+    "import re\n",
+    "import nltk\n",
+    "import pickle\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "from sklearn.metrics import accuracy_score\n",
+    "from sklearn.metrics import confusion_matrix\n",
+    "from matplotlib import pyplot as plt\n",
+    "from sklearn.linear_model import PassiveAggressiveClassifier,LogisticRegression\n",
+    "from nltk.stem import WordNetLemmatizer\n",
+    "from nltk.corpus import stopwords"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T06:50:29.656569Z",
+     "iopub.status.busy": "2021-05-25T06:50:29.656203Z",
+     "iopub.status.idle": "2021-05-25T06:50:32.048864Z",
+     "shell.execute_reply": "2021-05-25T06:50:32.047882Z",
+     "shell.execute_reply.started": "2021-05-25T06:50:29.65654Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "train_df = pd.read_csv('train.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T06:50:32.05136Z",
+     "iopub.status.busy": "2021-05-25T06:50:32.051032Z",
+     "iopub.status.idle": "2021-05-25T06:50:32.089516Z",
+     "shell.execute_reply": "2021-05-25T06:50:32.088399Z",
+     "shell.execute_reply.started": "2021-05-25T06:50:32.051329Z"
+    }
+   },
+   "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>id</th>\n",
+       "      <th>title</th>\n",
+       "      <th>author</th>\n",
+       "      <th>text</th>\n",
+       "      <th>label</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>House Dem Aide: We Didn’t Even See Comey’s Let...</td>\n",
+       "      <td>Darrell Lucus</td>\n",
+       "      <td>House Dem Aide: We Didn’t Even See Comey’s Let...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>FLYNN: Hillary Clinton, Big Woman on Campus - ...</td>\n",
+       "      <td>Daniel J. Flynn</td>\n",
+       "      <td>Ever get the feeling your life circles the rou...</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Why the Truth Might Get You Fired</td>\n",
+       "      <td>Consortiumnews.com</td>\n",
+       "      <td>Why the Truth Might Get You Fired October 29, ...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3</td>\n",
+       "      <td>15 Civilians Killed In Single US Airstrike Hav...</td>\n",
+       "      <td>Jessica Purkiss</td>\n",
+       "      <td>Videos 15 Civilians Killed In Single US Airstr...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>4</td>\n",
+       "      <td>Iranian woman jailed for fictional unpublished...</td>\n",
+       "      <td>Howard Portnoy</td>\n",
+       "      <td>Print \\nAn Iranian woman has been sentenced to...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Jackie Mason: Hollywood Would Love Trump if He...</td>\n",
+       "      <td>Daniel Nussbaum</td>\n",
+       "      <td>In these trying times, Jackie Mason is the Voi...</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>6</td>\n",
+       "      <td>Life: Life Of Luxury: Elton John’s 6 Favorite ...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Ever wonder how Britain’s most iconic pop pian...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>7</td>\n",
+       "      <td>Benoît Hamon Wins French Socialist Party’s Pre...</td>\n",
+       "      <td>Alissa J. Rubin</td>\n",
+       "      <td>PARIS  —   France chose an idealistic, traditi...</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>8</td>\n",
+       "      <td>Excerpts From a Draft Script for Donald Trump’...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Donald J. Trump is scheduled to make a highly ...</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>9</td>\n",
+       "      <td>A Back-Channel Plan for Ukraine and Russia, Co...</td>\n",
+       "      <td>Megan Twohey and Scott Shane</td>\n",
+       "      <td>A week before Michael T. Flynn resigned as nat...</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>10</td>\n",
+       "      <td>Obama’s Organizing for Action Partners with So...</td>\n",
+       "      <td>Aaron Klein</td>\n",
+       "      <td>Organizing for Action, the activist group that...</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>11</td>\n",
+       "      <td>BBC Comedy Sketch \"Real Housewives of ISIS\" Ca...</td>\n",
+       "      <td>Chris Tomlinson</td>\n",
+       "      <td>The BBC produced spoof on the “Real Housewives...</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>12</td>\n",
+       "      <td>Russian Researchers Discover Secret Nazi Milit...</td>\n",
+       "      <td>Amando Flavio</td>\n",
+       "      <td>The mystery surrounding The Third Reich and Na...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>13</td>\n",
+       "      <td>US Officials See No Link Between Trump and Russia</td>\n",
+       "      <td>Jason Ditz</td>\n",
+       "      <td>Clinton Campaign Demands FBI Affirm Trump's Ru...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>14</td>\n",
+       "      <td>Re: Yes, There Are Paid Government Trolls On S...</td>\n",
+       "      <td>AnotherAnnie</td>\n",
+       "      <td>Yes, There Are Paid Government Trolls On Socia...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    id                                              title  \\\n",
+       "0    0  House Dem Aide: We Didn’t Even See Comey’s Let...   \n",
+       "1    1  FLYNN: Hillary Clinton, Big Woman on Campus - ...   \n",
+       "2    2                  Why the Truth Might Get You Fired   \n",
+       "3    3  15 Civilians Killed In Single US Airstrike Hav...   \n",
+       "4    4  Iranian woman jailed for fictional unpublished...   \n",
+       "5    5  Jackie Mason: Hollywood Would Love Trump if He...   \n",
+       "6    6  Life: Life Of Luxury: Elton John’s 6 Favorite ...   \n",
+       "7    7  Benoît Hamon Wins French Socialist Party’s Pre...   \n",
+       "8    8  Excerpts From a Draft Script for Donald Trump’...   \n",
+       "9    9  A Back-Channel Plan for Ukraine and Russia, Co...   \n",
+       "10  10  Obama’s Organizing for Action Partners with So...   \n",
+       "11  11  BBC Comedy Sketch \"Real Housewives of ISIS\" Ca...   \n",
+       "12  12  Russian Researchers Discover Secret Nazi Milit...   \n",
+       "13  13  US Officials See No Link Between Trump and Russia   \n",
+       "14  14  Re: Yes, There Are Paid Government Trolls On S...   \n",
+       "\n",
+       "                          author  \\\n",
+       "0                  Darrell Lucus   \n",
+       "1                Daniel J. Flynn   \n",
+       "2             Consortiumnews.com   \n",
+       "3                Jessica Purkiss   \n",
+       "4                 Howard Portnoy   \n",
+       "5                Daniel Nussbaum   \n",
+       "6                            NaN   \n",
+       "7                Alissa J. Rubin   \n",
+       "8                            NaN   \n",
+       "9   Megan Twohey and Scott Shane   \n",
+       "10                   Aaron Klein   \n",
+       "11               Chris Tomlinson   \n",
+       "12                 Amando Flavio   \n",
+       "13                    Jason Ditz   \n",
+       "14                  AnotherAnnie   \n",
+       "\n",
+       "                                                 text  label  \n",
+       "0   House Dem Aide: We Didn’t Even See Comey’s Let...      1  \n",
+       "1   Ever get the feeling your life circles the rou...      0  \n",
+       "2   Why the Truth Might Get You Fired October 29, ...      1  \n",
+       "3   Videos 15 Civilians Killed In Single US Airstr...      1  \n",
+       "4   Print \\nAn Iranian woman has been sentenced to...      1  \n",
+       "5   In these trying times, Jackie Mason is the Voi...      0  \n",
+       "6   Ever wonder how Britain’s most iconic pop pian...      1  \n",
+       "7   PARIS  —   France chose an idealistic, traditi...      0  \n",
+       "8   Donald J. Trump is scheduled to make a highly ...      0  \n",
+       "9   A week before Michael T. Flynn resigned as nat...      0  \n",
+       "10  Organizing for Action, the activist group that...      0  \n",
+       "11  The BBC produced spoof on the “Real Housewives...      0  \n",
+       "12  The mystery surrounding The Third Reich and Na...      1  \n",
+       "13  Clinton Campaign Demands FBI Affirm Trump's Ru...      1  \n",
+       "14  Yes, There Are Paid Government Trolls On Socia...      1  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_df.head(15)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T06:50:32.10674Z",
+     "iopub.status.busy": "2021-05-25T06:50:32.106434Z",
+     "iopub.status.idle": "2021-05-25T06:50:32.120541Z",
+     "shell.execute_reply": "2021-05-25T06:50:32.119386Z",
+     "shell.execute_reply.started": "2021-05-25T06:50:32.106712Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(20800, 5)"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_df.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T06:50:32.124489Z",
+     "iopub.status.busy": "2021-05-25T06:50:32.12414Z",
+     "iopub.status.idle": "2021-05-25T06:50:32.140229Z",
+     "shell.execute_reply": "2021-05-25T06:50:32.139288Z",
+     "shell.execute_reply.started": "2021-05-25T06:50:32.124461Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 20800 entries, 0 to 20799\n",
+      "Data columns (total 5 columns):\n",
+      " #   Column  Non-Null Count  Dtype \n",
+      "---  ------  --------------  ----- \n",
+      " 0   id      20800 non-null  int64 \n",
+      " 1   title   20242 non-null  object\n",
+      " 2   author  18843 non-null  object\n",
+      " 3   text    20761 non-null  object\n",
+      " 4   label   20800 non-null  int64 \n",
+      "dtypes: int64(2), object(3)\n",
+      "memory usage: 812.6+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "train_df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([10413, 10387], dtype=int64)"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# def create_distribution(dataFile):\n",
+    "#     return sb.countplot(x='label', data=dataFile, palette='hls')\n",
+    "\n",
+    "# #by calling below we can see that training, test and valid data seems to be failry evenly distributed between the classes\n",
+    "# create_distribution(train_df)\n",
+    "train_df['label'].value_counts().values"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "bars= plt.bar(['True','False'],train_df['label'].value_counts().values)\n",
+    "for bar in bars:\n",
+    "    yval = bar.get_height()\n",
+    "    plt.text(bar.get_x() + bar.get_width() / 2, yval, round(yval, 2), ha='center', va='bottom')\n",
+    "\n",
+    "plt.show()\n",
+    "#Hence data has nearly equal cases of True and False News."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T06:50:32.306146Z",
+     "iopub.status.busy": "2021-05-25T06:50:32.305826Z",
+     "iopub.status.idle": "2021-05-25T06:50:32.335357Z",
+     "shell.execute_reply": "2021-05-25T06:50:32.33417Z",
+     "shell.execute_reply.started": "2021-05-25T06:50:32.306118Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[1mCOLUMN\u001b[0m                        \u001b[1mNULL VALUES COUNT\u001b[0m\n",
+      "id                                0\n",
+      "title                             558\n",
+      "author                            1957\n",
+      "text                              39\n",
+      "label                             0\n"
+     ]
+    }
+   ],
+   "source": [
+    "def data_qualityCheck():\n",
+    "    print(\"{:{}}\".format(\"\\033[1mCOLUMN\\033[0m\",38),end='')\n",
+    "    print(\"{:{}}\".format(\"\\033[1mNULL VALUES COUNT\\033[0m\",18))\n",
+    "    for x in train_df.columns:\n",
+    "        print(\"{:{}}\".format(x,34),end='')\n",
+    "        print(train_df[x].isnull().sum())\n",
+    "\n",
+    "    \n",
+    "data_qualityCheck()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T06:50:32.337061Z",
+     "iopub.status.busy": "2021-05-25T06:50:32.336735Z",
+     "iopub.status.idle": "2021-05-25T06:50:32.367948Z",
+     "shell.execute_reply": "2021-05-25T06:50:32.366933Z",
+     "shell.execute_reply.started": "2021-05-25T06:50:32.33703Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "train_df=train_df.drop([\"id\", \"author\"], axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T06:50:32.401314Z",
+     "iopub.status.busy": "2021-05-25T06:50:32.400868Z",
+     "iopub.status.idle": "2021-05-25T06:50:32.407806Z",
+     "shell.execute_reply": "2021-05-25T06:50:32.406589Z",
+     "shell.execute_reply.started": "2021-05-25T06:50:32.401272Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(20800, 3)"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_df.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T06:50:32.409912Z",
+     "iopub.status.busy": "2021-05-25T06:50:32.409162Z",
+     "iopub.status.idle": "2021-05-25T06:50:32.426843Z",
+     "shell.execute_reply": "2021-05-25T06:50:32.425727Z",
+     "shell.execute_reply.started": "2021-05-25T06:50:32.409868Z"
+    }
+   },
+   "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>title</th>\n",
+       "      <th>text</th>\n",
+       "      <th>label</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>House Dem Aide: We Didn’t Even See Comey’s Let...</td>\n",
+       "      <td>House Dem Aide: We Didn’t Even See Comey’s Let...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>FLYNN: Hillary Clinton, Big Woman on Campus - ...</td>\n",
+       "      <td>Ever get the feeling your life circles the rou...</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Why the Truth Might Get You Fired</td>\n",
+       "      <td>Why the Truth Might Get You Fired October 29, ...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>15 Civilians Killed In Single US Airstrike Hav...</td>\n",
+       "      <td>Videos 15 Civilians Killed In Single US Airstr...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Iranian woman jailed for fictional unpublished...</td>\n",
+       "      <td>Print \\nAn Iranian woman has been sentenced to...</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                               title  \\\n",
+       "0  House Dem Aide: We Didn’t Even See Comey’s Let...   \n",
+       "1  FLYNN: Hillary Clinton, Big Woman on Campus - ...   \n",
+       "2                  Why the Truth Might Get You Fired   \n",
+       "3  15 Civilians Killed In Single US Airstrike Hav...   \n",
+       "4  Iranian woman jailed for fictional unpublished...   \n",
+       "\n",
+       "                                                text  label  \n",
+       "0  House Dem Aide: We Didn’t Even See Comey’s Let...      1  \n",
+       "1  Ever get the feeling your life circles the rou...      0  \n",
+       "2  Why the Truth Might Get You Fired October 29, ...      1  \n",
+       "3  Videos 15 Civilians Killed In Single US Airstr...      1  \n",
+       "4  Print \\nAn Iranian woman has been sentenced to...      1  "
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T06:50:32.457112Z",
+     "iopub.status.busy": "2021-05-25T06:50:32.45653Z",
+     "iopub.status.idle": "2021-05-25T06:50:32.46346Z",
+     "shell.execute_reply": "2021-05-25T06:50:32.461467Z",
+     "shell.execute_reply.started": "2021-05-25T06:50:32.457067Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0        1\n",
+       "1        0\n",
+       "2        1\n",
+       "3        1\n",
+       "4        1\n",
+       "        ..\n",
+       "20795    0\n",
+       "20796    0\n",
+       "20797    0\n",
+       "20798    1\n",
+       "20799    1\n",
+       "Name: label, Length: 20800, dtype: int64"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "label_train = train_df['label']\n",
+    "label_train"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T06:50:32.46513Z",
+     "iopub.status.busy": "2021-05-25T06:50:32.46484Z",
+     "iopub.status.idle": "2021-05-25T06:50:32.479833Z",
+     "shell.execute_reply": "2021-05-25T06:50:32.478601Z",
+     "shell.execute_reply.started": "2021-05-25T06:50:32.465102Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0    1\n",
+       "1    0\n",
+       "2    1\n",
+       "3    1\n",
+       "4    1\n",
+       "5    0\n",
+       "6    1\n",
+       "7    0\n",
+       "8    0\n",
+       "9    0\n",
+       "Name: label, dtype: int64"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "label_train.head(10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T06:50:32.481757Z",
+     "iopub.status.busy": "2021-05-25T06:50:32.481439Z",
+     "iopub.status.idle": "2021-05-25T06:50:32.493571Z",
+     "shell.execute_reply": "2021-05-25T06:50:32.492736Z",
+     "shell.execute_reply.started": "2021-05-25T06:50:32.481728Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "train_df = train_df.drop(\"label\", axis = 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T06:50:32.495566Z",
+     "iopub.status.busy": "2021-05-25T06:50:32.495116Z",
+     "iopub.status.idle": "2021-05-25T06:50:32.513957Z",
+     "shell.execute_reply": "2021-05-25T06:50:32.51265Z",
+     "shell.execute_reply.started": "2021-05-25T06:50:32.495526Z"
+    }
+   },
+   "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>title</th>\n",
+       "      <th>text</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>House Dem Aide: We Didn’t Even See Comey’s Let...</td>\n",
+       "      <td>House Dem Aide: We Didn’t Even See Comey’s Let...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>FLYNN: Hillary Clinton, Big Woman on Campus - ...</td>\n",
+       "      <td>Ever get the feeling your life circles the rou...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Why the Truth Might Get You Fired</td>\n",
+       "      <td>Why the Truth Might Get You Fired October 29, ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>15 Civilians Killed In Single US Airstrike Hav...</td>\n",
+       "      <td>Videos 15 Civilians Killed In Single US Airstr...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Iranian woman jailed for fictional unpublished...</td>\n",
+       "      <td>Print \\nAn Iranian woman has been sentenced to...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>Jackie Mason: Hollywood Would Love Trump if He...</td>\n",
+       "      <td>In these trying times, Jackie Mason is the Voi...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>Life: Life Of Luxury: Elton John’s 6 Favorite ...</td>\n",
+       "      <td>Ever wonder how Britain’s most iconic pop pian...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>Benoît Hamon Wins French Socialist Party’s Pre...</td>\n",
+       "      <td>PARIS  —   France chose an idealistic, traditi...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>Excerpts From a Draft Script for Donald Trump’...</td>\n",
+       "      <td>Donald J. Trump is scheduled to make a highly ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>A Back-Channel Plan for Ukraine and Russia, Co...</td>\n",
+       "      <td>A week before Michael T. Flynn resigned as nat...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                               title  \\\n",
+       "0  House Dem Aide: We Didn’t Even See Comey’s Let...   \n",
+       "1  FLYNN: Hillary Clinton, Big Woman on Campus - ...   \n",
+       "2                  Why the Truth Might Get You Fired   \n",
+       "3  15 Civilians Killed In Single US Airstrike Hav...   \n",
+       "4  Iranian woman jailed for fictional unpublished...   \n",
+       "5  Jackie Mason: Hollywood Would Love Trump if He...   \n",
+       "6  Life: Life Of Luxury: Elton John’s 6 Favorite ...   \n",
+       "7  Benoît Hamon Wins French Socialist Party’s Pre...   \n",
+       "8  Excerpts From a Draft Script for Donald Trump’...   \n",
+       "9  A Back-Channel Plan for Ukraine and Russia, Co...   \n",
+       "\n",
+       "                                                text  \n",
+       "0  House Dem Aide: We Didn’t Even See Comey’s Let...  \n",
+       "1  Ever get the feeling your life circles the rou...  \n",
+       "2  Why the Truth Might Get You Fired October 29, ...  \n",
+       "3  Videos 15 Civilians Killed In Single US Airstr...  \n",
+       "4  Print \\nAn Iranian woman has been sentenced to...  \n",
+       "5  In these trying times, Jackie Mason is the Voi...  \n",
+       "6  Ever wonder how Britain’s most iconic pop pian...  \n",
+       "7  PARIS  —   France chose an idealistic, traditi...  \n",
+       "8  Donald J. Trump is scheduled to make a highly ...  \n",
+       "9  A week before Michael T. Flynn resigned as nat...  "
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_df.head(10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def fill_data(data):\n",
+    "    data[\"title\"] = data[\"title\"].fillna(\"Has No Title\")\n",
+    "    data[\"text\"] = data[\"text\"].fillna(\"Has No text\")\n",
+    "    return data\n",
+    "\n",
+    "train_df= fill_data(train_df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[1mCOLUMN\u001b[0m                        \u001b[1mNULL VALUES COUNT\u001b[0m\n",
+      "title                             0\n",
+      "text                              0\n"
+     ]
+    }
+   ],
+   "source": [
+    "data_qualityCheck()"
+   ]
+  },
+  {
+   "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>title</th>\n",
+       "      <th>text</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>House Dem Aide: We Didn’t Even See Comey’s Let...</td>\n",
+       "      <td>House Dem Aide: We Didn’t Even See Comey’s Let...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>FLYNN: Hillary Clinton, Big Woman on Campus - ...</td>\n",
+       "      <td>Ever get the feeling your life circles the rou...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Why the Truth Might Get You Fired</td>\n",
+       "      <td>Why the Truth Might Get You Fired October 29, ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>15 Civilians Killed In Single US Airstrike Hav...</td>\n",
+       "      <td>Videos 15 Civilians Killed In Single US Airstr...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Iranian woman jailed for fictional unpublished...</td>\n",
+       "      <td>Print \\nAn Iranian woman has been sentenced to...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>Jackie Mason: Hollywood Would Love Trump if He...</td>\n",
+       "      <td>In these trying times, Jackie Mason is the Voi...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>Life: Life Of Luxury: Elton John’s 6 Favorite ...</td>\n",
+       "      <td>Ever wonder how Britain’s most iconic pop pian...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>Benoît Hamon Wins French Socialist Party’s Pre...</td>\n",
+       "      <td>PARIS  —   France chose an idealistic, traditi...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>Excerpts From a Draft Script for Donald Trump’...</td>\n",
+       "      <td>Donald J. Trump is scheduled to make a highly ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>A Back-Channel Plan for Ukraine and Russia, Co...</td>\n",
+       "      <td>A week before Michael T. Flynn resigned as nat...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>Obama’s Organizing for Action Partners with So...</td>\n",
+       "      <td>Organizing for Action, the activist group that...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>BBC Comedy Sketch \"Real Housewives of ISIS\" Ca...</td>\n",
+       "      <td>The BBC produced spoof on the “Real Housewives...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>Russian Researchers Discover Secret Nazi Milit...</td>\n",
+       "      <td>The mystery surrounding The Third Reich and Na...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>US Officials See No Link Between Trump and Russia</td>\n",
+       "      <td>Clinton Campaign Demands FBI Affirm Trump's Ru...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>Re: Yes, There Are Paid Government Trolls On S...</td>\n",
+       "      <td>Yes, There Are Paid Government Trolls On Socia...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>In Major League Soccer, Argentines Find a Home...</td>\n",
+       "      <td>Guillermo Barros Schelotto was not the first A...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16</th>\n",
+       "      <td>Wells Fargo Chief Abruptly Steps Down - The Ne...</td>\n",
+       "      <td>The scandal engulfing Wells Fargo toppled its ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17</th>\n",
+       "      <td>Anonymous Donor Pays $2.5 Million To Release E...</td>\n",
+       "      <td>A Caddo Nation tribal leader has just been fre...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>18</th>\n",
+       "      <td>FBI Closes In On Hillary!</td>\n",
+       "      <td>FBI Closes In On Hillary! Posted on Home » Hea...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>19</th>\n",
+       "      <td>Chuck Todd: ’BuzzFeed Did Donald Trump a Polit...</td>\n",
+       "      <td>Wednesday after   Donald Trump’s press confere...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                                title  \\\n",
+       "0   House Dem Aide: We Didn’t Even See Comey’s Let...   \n",
+       "1   FLYNN: Hillary Clinton, Big Woman on Campus - ...   \n",
+       "2                   Why the Truth Might Get You Fired   \n",
+       "3   15 Civilians Killed In Single US Airstrike Hav...   \n",
+       "4   Iranian woman jailed for fictional unpublished...   \n",
+       "5   Jackie Mason: Hollywood Would Love Trump if He...   \n",
+       "6   Life: Life Of Luxury: Elton John’s 6 Favorite ...   \n",
+       "7   Benoît Hamon Wins French Socialist Party’s Pre...   \n",
+       "8   Excerpts From a Draft Script for Donald Trump’...   \n",
+       "9   A Back-Channel Plan for Ukraine and Russia, Co...   \n",
+       "10  Obama’s Organizing for Action Partners with So...   \n",
+       "11  BBC Comedy Sketch \"Real Housewives of ISIS\" Ca...   \n",
+       "12  Russian Researchers Discover Secret Nazi Milit...   \n",
+       "13  US Officials See No Link Between Trump and Russia   \n",
+       "14  Re: Yes, There Are Paid Government Trolls On S...   \n",
+       "15  In Major League Soccer, Argentines Find a Home...   \n",
+       "16  Wells Fargo Chief Abruptly Steps Down - The Ne...   \n",
+       "17  Anonymous Donor Pays $2.5 Million To Release E...   \n",
+       "18                          FBI Closes In On Hillary!   \n",
+       "19  Chuck Todd: ’BuzzFeed Did Donald Trump a Polit...   \n",
+       "\n",
+       "                                                 text  \n",
+       "0   House Dem Aide: We Didn’t Even See Comey’s Let...  \n",
+       "1   Ever get the feeling your life circles the rou...  \n",
+       "2   Why the Truth Might Get You Fired October 29, ...  \n",
+       "3   Videos 15 Civilians Killed In Single US Airstr...  \n",
+       "4   Print \\nAn Iranian woman has been sentenced to...  \n",
+       "5   In these trying times, Jackie Mason is the Voi...  \n",
+       "6   Ever wonder how Britain’s most iconic pop pian...  \n",
+       "7   PARIS  —   France chose an idealistic, traditi...  \n",
+       "8   Donald J. Trump is scheduled to make a highly ...  \n",
+       "9   A week before Michael T. Flynn resigned as nat...  \n",
+       "10  Organizing for Action, the activist group that...  \n",
+       "11  The BBC produced spoof on the “Real Housewives...  \n",
+       "12  The mystery surrounding The Third Reich and Na...  \n",
+       "13  Clinton Campaign Demands FBI Affirm Trump's Ru...  \n",
+       "14  Yes, There Are Paid Government Trolls On Socia...  \n",
+       "15  Guillermo Barros Schelotto was not the first A...  \n",
+       "16  The scandal engulfing Wells Fargo toppled its ...  \n",
+       "17  A Caddo Nation tribal leader has just been fre...  \n",
+       "18  FBI Closes In On Hillary! Posted on Home » Hea...  \n",
+       "19  Wednesday after   Donald Trump’s press confere...  "
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_df.head(20)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_df[\"new_text\"] = train_df[\"title\"] + \" \" + train_df[\"text\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "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>title</th>\n",
+       "      <th>text</th>\n",
+       "      <th>new_text</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>House Dem Aide: We Didn’t Even See Comey’s Let...</td>\n",
+       "      <td>House Dem Aide: We Didn’t Even See Comey’s Let...</td>\n",
+       "      <td>House Dem Aide: We Didn’t Even See Comey’s Let...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>FLYNN: Hillary Clinton, Big Woman on Campus - ...</td>\n",
+       "      <td>Ever get the feeling your life circles the rou...</td>\n",
+       "      <td>FLYNN: Hillary Clinton, Big Woman on Campus - ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Why the Truth Might Get You Fired</td>\n",
+       "      <td>Why the Truth Might Get You Fired October 29, ...</td>\n",
+       "      <td>Why the Truth Might Get You Fired Why the Trut...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>15 Civilians Killed In Single US Airstrike Hav...</td>\n",
+       "      <td>Videos 15 Civilians Killed In Single US Airstr...</td>\n",
+       "      <td>15 Civilians Killed In Single US Airstrike Hav...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Iranian woman jailed for fictional unpublished...</td>\n",
+       "      <td>Print \\nAn Iranian woman has been sentenced to...</td>\n",
+       "      <td>Iranian woman jailed for fictional unpublished...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>Jackie Mason: Hollywood Would Love Trump if He...</td>\n",
+       "      <td>In these trying times, Jackie Mason is the Voi...</td>\n",
+       "      <td>Jackie Mason: Hollywood Would Love Trump if He...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>Life: Life Of Luxury: Elton John’s 6 Favorite ...</td>\n",
+       "      <td>Ever wonder how Britain’s most iconic pop pian...</td>\n",
+       "      <td>Life: Life Of Luxury: Elton John’s 6 Favorite ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>Benoît Hamon Wins French Socialist Party’s Pre...</td>\n",
+       "      <td>PARIS  —   France chose an idealistic, traditi...</td>\n",
+       "      <td>Benoît Hamon Wins French Socialist Party’s Pre...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>Excerpts From a Draft Script for Donald Trump’...</td>\n",
+       "      <td>Donald J. Trump is scheduled to make a highly ...</td>\n",
+       "      <td>Excerpts From a Draft Script for Donald Trump’...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>A Back-Channel Plan for Ukraine and Russia, Co...</td>\n",
+       "      <td>A week before Michael T. Flynn resigned as nat...</td>\n",
+       "      <td>A Back-Channel Plan for Ukraine and Russia, Co...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>Obama’s Organizing for Action Partners with So...</td>\n",
+       "      <td>Organizing for Action, the activist group that...</td>\n",
+       "      <td>Obama’s Organizing for Action Partners with So...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>BBC Comedy Sketch \"Real Housewives of ISIS\" Ca...</td>\n",
+       "      <td>The BBC produced spoof on the “Real Housewives...</td>\n",
+       "      <td>BBC Comedy Sketch \"Real Housewives of ISIS\" Ca...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>Russian Researchers Discover Secret Nazi Milit...</td>\n",
+       "      <td>The mystery surrounding The Third Reich and Na...</td>\n",
+       "      <td>Russian Researchers Discover Secret Nazi Milit...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>US Officials See No Link Between Trump and Russia</td>\n",
+       "      <td>Clinton Campaign Demands FBI Affirm Trump's Ru...</td>\n",
+       "      <td>US Officials See No Link Between Trump and Rus...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>Re: Yes, There Are Paid Government Trolls On S...</td>\n",
+       "      <td>Yes, There Are Paid Government Trolls On Socia...</td>\n",
+       "      <td>Re: Yes, There Are Paid Government Trolls On S...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>In Major League Soccer, Argentines Find a Home...</td>\n",
+       "      <td>Guillermo Barros Schelotto was not the first A...</td>\n",
+       "      <td>In Major League Soccer, Argentines Find a Home...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16</th>\n",
+       "      <td>Wells Fargo Chief Abruptly Steps Down - The Ne...</td>\n",
+       "      <td>The scandal engulfing Wells Fargo toppled its ...</td>\n",
+       "      <td>Wells Fargo Chief Abruptly Steps Down - The Ne...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17</th>\n",
+       "      <td>Anonymous Donor Pays $2.5 Million To Release E...</td>\n",
+       "      <td>A Caddo Nation tribal leader has just been fre...</td>\n",
+       "      <td>Anonymous Donor Pays $2.5 Million To Release E...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>18</th>\n",
+       "      <td>FBI Closes In On Hillary!</td>\n",
+       "      <td>FBI Closes In On Hillary! Posted on Home » Hea...</td>\n",
+       "      <td>FBI Closes In On Hillary! FBI Closes In On Hil...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>19</th>\n",
+       "      <td>Chuck Todd: ’BuzzFeed Did Donald Trump a Polit...</td>\n",
+       "      <td>Wednesday after   Donald Trump’s press confere...</td>\n",
+       "      <td>Chuck Todd: ’BuzzFeed Did Donald Trump a Polit...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                                title  \\\n",
+       "0   House Dem Aide: We Didn’t Even See Comey’s Let...   \n",
+       "1   FLYNN: Hillary Clinton, Big Woman on Campus - ...   \n",
+       "2                   Why the Truth Might Get You Fired   \n",
+       "3   15 Civilians Killed In Single US Airstrike Hav...   \n",
+       "4   Iranian woman jailed for fictional unpublished...   \n",
+       "5   Jackie Mason: Hollywood Would Love Trump if He...   \n",
+       "6   Life: Life Of Luxury: Elton John’s 6 Favorite ...   \n",
+       "7   Benoît Hamon Wins French Socialist Party’s Pre...   \n",
+       "8   Excerpts From a Draft Script for Donald Trump’...   \n",
+       "9   A Back-Channel Plan for Ukraine and Russia, Co...   \n",
+       "10  Obama’s Organizing for Action Partners with So...   \n",
+       "11  BBC Comedy Sketch \"Real Housewives of ISIS\" Ca...   \n",
+       "12  Russian Researchers Discover Secret Nazi Milit...   \n",
+       "13  US Officials See No Link Between Trump and Russia   \n",
+       "14  Re: Yes, There Are Paid Government Trolls On S...   \n",
+       "15  In Major League Soccer, Argentines Find a Home...   \n",
+       "16  Wells Fargo Chief Abruptly Steps Down - The Ne...   \n",
+       "17  Anonymous Donor Pays $2.5 Million To Release E...   \n",
+       "18                          FBI Closes In On Hillary!   \n",
+       "19  Chuck Todd: ’BuzzFeed Did Donald Trump a Polit...   \n",
+       "\n",
+       "                                                 text  \\\n",
+       "0   House Dem Aide: We Didn’t Even See Comey’s Let...   \n",
+       "1   Ever get the feeling your life circles the rou...   \n",
+       "2   Why the Truth Might Get You Fired October 29, ...   \n",
+       "3   Videos 15 Civilians Killed In Single US Airstr...   \n",
+       "4   Print \\nAn Iranian woman has been sentenced to...   \n",
+       "5   In these trying times, Jackie Mason is the Voi...   \n",
+       "6   Ever wonder how Britain’s most iconic pop pian...   \n",
+       "7   PARIS  —   France chose an idealistic, traditi...   \n",
+       "8   Donald J. Trump is scheduled to make a highly ...   \n",
+       "9   A week before Michael T. Flynn resigned as nat...   \n",
+       "10  Organizing for Action, the activist group that...   \n",
+       "11  The BBC produced spoof on the “Real Housewives...   \n",
+       "12  The mystery surrounding The Third Reich and Na...   \n",
+       "13  Clinton Campaign Demands FBI Affirm Trump's Ru...   \n",
+       "14  Yes, There Are Paid Government Trolls On Socia...   \n",
+       "15  Guillermo Barros Schelotto was not the first A...   \n",
+       "16  The scandal engulfing Wells Fargo toppled its ...   \n",
+       "17  A Caddo Nation tribal leader has just been fre...   \n",
+       "18  FBI Closes In On Hillary! Posted on Home » Hea...   \n",
+       "19  Wednesday after   Donald Trump’s press confere...   \n",
+       "\n",
+       "                                             new_text  \n",
+       "0   House Dem Aide: We Didn’t Even See Comey’s Let...  \n",
+       "1   FLYNN: Hillary Clinton, Big Woman on Campus - ...  \n",
+       "2   Why the Truth Might Get You Fired Why the Trut...  \n",
+       "3   15 Civilians Killed In Single US Airstrike Hav...  \n",
+       "4   Iranian woman jailed for fictional unpublished...  \n",
+       "5   Jackie Mason: Hollywood Would Love Trump if He...  \n",
+       "6   Life: Life Of Luxury: Elton John’s 6 Favorite ...  \n",
+       "7   Benoît Hamon Wins French Socialist Party’s Pre...  \n",
+       "8   Excerpts From a Draft Script for Donald Trump’...  \n",
+       "9   A Back-Channel Plan for Ukraine and Russia, Co...  \n",
+       "10  Obama’s Organizing for Action Partners with So...  \n",
+       "11  BBC Comedy Sketch \"Real Housewives of ISIS\" Ca...  \n",
+       "12  Russian Researchers Discover Secret Nazi Milit...  \n",
+       "13  US Officials See No Link Between Trump and Rus...  \n",
+       "14  Re: Yes, There Are Paid Government Trolls On S...  \n",
+       "15  In Major League Soccer, Argentines Find a Home...  \n",
+       "16  Wells Fargo Chief Abruptly Steps Down - The Ne...  \n",
+       "17  Anonymous Donor Pays $2.5 Million To Release E...  \n",
+       "18  FBI Closes In On Hillary! FBI Closes In On Hil...  \n",
+       "19  Chuck Todd: ’BuzzFeed Did Donald Trump a Polit...  "
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_df.head(20)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_df=train_df.drop(['title','text'],axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "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>new_text</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>House Dem Aide: We Didn’t Even See Comey’s Let...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>FLYNN: Hillary Clinton, Big Woman on Campus - ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Why the Truth Might Get You Fired Why the Trut...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>15 Civilians Killed In Single US Airstrike Hav...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Iranian woman jailed for fictional unpublished...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                            new_text\n",
+       "0  House Dem Aide: We Didn’t Even See Comey’s Let...\n",
+       "1  FLYNN: Hillary Clinton, Big Woman on Campus - ...\n",
+       "2  Why the Truth Might Get You Fired Why the Trut...\n",
+       "3  15 Civilians Killed In Single US Airstrike Hav...\n",
+       "4  Iranian woman jailed for fictional unpublished..."
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "custom_download_dir = \"C:\\\\Users\\\\ysach/nltk\"\n",
+    "nltk.data.path.append(custom_download_dir)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[nltk_data] Downloading package stopwords to C:\\Users\\ysach/nltk...\n",
+      "[nltk_data]   Package stopwords is already up-to-date!\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "nltk.download('stopwords',download_dir=custom_download_dir)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T06:50:32.51602Z",
+     "iopub.status.busy": "2021-05-25T06:50:32.515411Z",
+     "iopub.status.idle": "2021-05-25T06:50:32.531829Z",
+     "shell.execute_reply": "2021-05-25T06:50:32.530895Z",
+     "shell.execute_reply.started": "2021-05-25T06:50:32.515972Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "lemmatizer = WordNetLemmatizer()\n",
+    "stpwrds = list(stopwords.words('english'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['i',\n",
+       " 'me',\n",
+       " 'my',\n",
+       " 'myself',\n",
+       " 'we',\n",
+       " 'our',\n",
+       " 'ours',\n",
+       " 'ourselves',\n",
+       " 'you',\n",
+       " \"you're\",\n",
+       " \"you've\",\n",
+       " \"you'll\",\n",
+       " \"you'd\",\n",
+       " 'your',\n",
+       " 'yours',\n",
+       " 'yourself',\n",
+       " 'yourselves',\n",
+       " 'he',\n",
+       " 'him',\n",
+       " 'his',\n",
+       " 'himself',\n",
+       " 'she',\n",
+       " \"she's\",\n",
+       " 'her',\n",
+       " 'hers',\n",
+       " 'herself',\n",
+       " 'it',\n",
+       " \"it's\",\n",
+       " 'its',\n",
+       " 'itself',\n",
+       " 'they',\n",
+       " 'them',\n",
+       " 'their',\n",
+       " 'theirs',\n",
+       " 'themselves',\n",
+       " 'what',\n",
+       " 'which',\n",
+       " 'who',\n",
+       " 'whom',\n",
+       " 'this',\n",
+       " 'that',\n",
+       " \"that'll\",\n",
+       " 'these',\n",
+       " 'those',\n",
+       " 'am',\n",
+       " 'is',\n",
+       " 'are',\n",
+       " 'was',\n",
+       " 'were',\n",
+       " 'be',\n",
+       " 'been',\n",
+       " 'being',\n",
+       " 'have',\n",
+       " 'has',\n",
+       " 'had',\n",
+       " 'having',\n",
+       " 'do',\n",
+       " 'does',\n",
+       " 'did',\n",
+       " 'doing',\n",
+       " 'a',\n",
+       " 'an',\n",
+       " 'the',\n",
+       " 'and',\n",
+       " 'but',\n",
+       " 'if',\n",
+       " 'or',\n",
+       " 'because',\n",
+       " 'as',\n",
+       " 'until',\n",
+       " 'while',\n",
+       " 'of',\n",
+       " 'at',\n",
+       " 'by',\n",
+       " 'for',\n",
+       " 'with',\n",
+       " 'about',\n",
+       " 'against',\n",
+       " 'between',\n",
+       " 'into',\n",
+       " 'through',\n",
+       " 'during',\n",
+       " 'before',\n",
+       " 'after',\n",
+       " 'above',\n",
+       " 'below',\n",
+       " 'to',\n",
+       " 'from',\n",
+       " 'up',\n",
+       " 'down',\n",
+       " 'in',\n",
+       " 'out',\n",
+       " 'on',\n",
+       " 'off',\n",
+       " 'over',\n",
+       " 'under',\n",
+       " 'again',\n",
+       " 'further',\n",
+       " 'then',\n",
+       " 'once',\n",
+       " 'here',\n",
+       " 'there',\n",
+       " 'when',\n",
+       " 'where',\n",
+       " 'why',\n",
+       " 'how',\n",
+       " 'all',\n",
+       " 'any',\n",
+       " 'both',\n",
+       " 'each',\n",
+       " 'few',\n",
+       " 'more',\n",
+       " 'most',\n",
+       " 'other',\n",
+       " 'some',\n",
+       " 'such',\n",
+       " 'no',\n",
+       " 'nor',\n",
+       " 'not',\n",
+       " 'only',\n",
+       " 'own',\n",
+       " 'same',\n",
+       " 'so',\n",
+       " 'than',\n",
+       " 'too',\n",
+       " 'very',\n",
+       " 's',\n",
+       " 't',\n",
+       " 'can',\n",
+       " 'will',\n",
+       " 'just',\n",
+       " 'don',\n",
+       " \"don't\",\n",
+       " 'should',\n",
+       " \"should've\",\n",
+       " 'now',\n",
+       " 'd',\n",
+       " 'll',\n",
+       " 'm',\n",
+       " 'o',\n",
+       " 're',\n",
+       " 've',\n",
+       " 'y',\n",
+       " 'ain',\n",
+       " 'aren',\n",
+       " \"aren't\",\n",
+       " 'couldn',\n",
+       " \"couldn't\",\n",
+       " 'didn',\n",
+       " \"didn't\",\n",
+       " 'doesn',\n",
+       " \"doesn't\",\n",
+       " 'hadn',\n",
+       " \"hadn't\",\n",
+       " 'hasn',\n",
+       " \"hasn't\",\n",
+       " 'haven',\n",
+       " \"haven't\",\n",
+       " 'isn',\n",
+       " \"isn't\",\n",
+       " 'ma',\n",
+       " 'mightn',\n",
+       " \"mightn't\",\n",
+       " 'mustn',\n",
+       " \"mustn't\",\n",
+       " 'needn',\n",
+       " \"needn't\",\n",
+       " 'shan',\n",
+       " \"shan't\",\n",
+       " 'shouldn',\n",
+       " \"shouldn't\",\n",
+       " 'wasn',\n",
+       " \"wasn't\",\n",
+       " 'weren',\n",
+       " \"weren't\",\n",
+       " 'won',\n",
+       " \"won't\",\n",
+       " 'wouldn',\n",
+       " \"wouldn't\"]"
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "stpwrds"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[nltk_data] Downloading package punkt to C:\\Users\\ysach/nltk...\n",
+      "[nltk_data]   Package punkt is already up-to-date!\n",
+      "[nltk_data] Downloading package wordnet to C:\\Users\\ysach/nltk...\n",
+      "[nltk_data]   Package wordnet is already up-to-date!\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 34,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "nltk.download('punkt',download_dir=custom_download_dir)\n",
+    "nltk.download('wordnet',download_dir=custom_download_dir)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[nltk_data] Downloading package omw-1.4 to C:\\Users\\ysach/nltk...\n",
+      "[nltk_data]   Package omw-1.4 is already up-to-date!\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "nltk.download('omw-1.4',download_dir=custom_download_dir)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T06:50:32.54905Z",
+     "iopub.status.busy": "2021-05-25T06:50:32.548517Z",
+     "iopub.status.idle": "2021-05-25T06:53:51.648153Z",
+     "shell.execute_reply": "2021-05-25T06:53:51.647283Z",
+     "shell.execute_reply.started": "2021-05-25T06:50:32.549015Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "for x in range(len(train_df)) :\n",
+    "    corpus = []\n",
+    "    review = train_df['new_text'][x]\n",
+    "    review = re.sub(r'[^a-zA-Z\\s]', '', review)\n",
+    "    review = review.lower()\n",
+    "    review = nltk.word_tokenize(review)\n",
+    "    for y in review :\n",
+    "        if y not in stpwrds :\n",
+    "            corpus.append(lemmatizer.lemmatize(y))\n",
+    "    review = ' '.join(corpus)\n",
+    "    train_df['new_text'][x] = review"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T07:14:51.798724Z",
+     "iopub.status.busy": "2021-05-25T07:14:51.798361Z",
+     "iopub.status.idle": "2021-05-25T07:14:51.805617Z",
+     "shell.execute_reply": "2021-05-25T07:14:51.804946Z",
+     "shell.execute_reply.started": "2021-05-25T07:14:51.798694Z"
+    },
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'actor steven seagal live tv erupts hillary obama intense comment actor steven seagal stood america rest hollywood remains silent week rough country first democratic nominee hillary clinton collapsed memorial called million hardworking american deplorable werent enough nfl player throughout country blatantly disrespecting american flag needle say seagal enough think important job secretary state ensuring people dont get killed seagal tweeted cant email protected pneumonia going disastrous american people notohillary continued course seagal quickly became target liberal fire comment refused break particularly lost one twitter user tried argued hillary capable presidency capable capable leaving american die capable disregarding law capable disrespecting rape survivor argued went address race relation united state true role president barack obama played social evolution country obama abysmal race relation usa truth need start honest dialog wrote seagal concluded pointing irony attack receiving liberal everywhere best thing worldmaking one statement freedom getting attacked every demo hypocritical tweeted america without democrat white house safer america think seagals comment'"
+      ]
+     },
+     "execution_count": 37,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_df['new_text'][2188]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 75,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "1"
+      ]
+     },
+     "execution_count": 75,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "label_train[2188]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T07:16:37.152728Z",
+     "iopub.status.busy": "2021-05-25T07:16:37.152216Z",
+     "iopub.status.idle": "2021-05-25T07:16:37.163059Z",
+     "shell.execute_reply": "2021-05-25T07:16:37.161884Z",
+     "shell.execute_reply.started": "2021-05-25T07:16:37.152696Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "X_train= train_df['new_text']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0        house dem aide didnt even see comeys letter ja...\n",
+       "1        flynn hillary clinton big woman campus breitba...\n",
+       "2        truth might get fired truth might get fired oc...\n",
+       "3        civilian killed single u airstrike identified ...\n",
+       "4        iranian woman jailed fictional unpublished sto...\n",
+       "                               ...                        \n",
+       "20795    rapper ti trump poster child white supremacy r...\n",
+       "20796    nfl playoff schedule matchup odds new york tim...\n",
+       "20797    macys said receive takeover approach hudson ba...\n",
+       "20798    nato russia hold parallel exercise balkan nato...\n",
+       "20799    keep f alive david swanson author activist jou...\n",
+       "Name: new_text, Length: 20800, dtype: object"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X_train"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T07:17:50.592597Z",
+     "iopub.status.busy": "2021-05-25T07:17:50.592095Z",
+     "iopub.status.idle": "2021-05-25T07:17:50.598862Z",
+     "shell.execute_reply": "2021-05-25T07:17:50.597641Z",
+     "shell.execute_reply.started": "2021-05-25T07:17:50.592566Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(20800,)"
+      ]
+     },
+     "execution_count": 40,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X_train.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T07:18:05.89317Z",
+     "iopub.status.busy": "2021-05-25T07:18:05.892651Z",
+     "iopub.status.idle": "2021-05-25T07:18:05.902743Z",
+     "shell.execute_reply": "2021-05-25T07:18:05.901523Z",
+     "shell.execute_reply.started": "2021-05-25T07:18:05.893127Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(20800,)"
+      ]
+     },
+     "execution_count": 41,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "label_train.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:tensorflow:From c:\\Users\\ysach\\anaconda3\\lib\\site-packages\\keras\\src\\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead.\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from keras.preprocessing.text import Tokenizer\n",
+    "from keras.preprocessing.sequence import pad_sequences"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The Padding Sequance Shape is  -->  (20800, 12140)\n"
+     ]
+    }
+   ],
+   "source": [
+    "tokenize = Tokenizer(oov_token=\"<OOV>\")\n",
+    "tokenize.fit_on_texts(X_train)\n",
+    "word_idx = tokenize.word_index\n",
+    "\n",
+    "text2seq = tokenize.texts_to_sequences(X_train)\n",
+    "\n",
+    "# pad_seq = pad_sequences(text2seq, maxlen=150, padding=\"pre\", truncating=\"pre\")\n",
+    "\n",
+    "pad_seq = pad_sequences(text2seq, padding=\"pre\", truncating=\"pre\")\n",
+    "\n",
+    "\n",
+    "print(\"The Padding Sequance Shape is  --> \", pad_seq.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "input_length = max(len(seq) for seq in text2seq)\n",
+    "\n",
+    "vocabulary_size = len(word_idx) + 1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The maximum Sequance Length is  -->  12140\n",
+      "The vocabulary size of dataset is  -->  166055\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"The maximum Sequance Length is  --> \", input_length)\n",
+    "print(\"The vocabulary size of dataset is  --> \", vocabulary_size)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "from sklearn.feature_extraction.text import CountVectorizer\n",
+    "vectorizer = CountVectorizer(\n",
+    "    ngram_range=(1,1),\n",
+    "    max_features=250\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 118,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T07:18:10.901469Z",
+     "iopub.status.busy": "2021-05-25T07:18:10.901136Z",
+     "iopub.status.idle": "2021-05-25T07:18:22.003384Z",
+     "shell.execute_reply": "2021-05-25T07:18:22.002314Z",
+     "shell.execute_reply.started": "2021-05-25T07:18:10.90144Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "#tfidf_v = TfidfVectorizer()\n",
+    "#tfidf_X_train = vectorizer.fit_transform(X_train)\n",
+    "#tfidf_X_test = vectorizer.transform(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 119,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T07:18:24.321674Z",
+     "iopub.status.busy": "2021-05-25T07:18:24.321329Z",
+     "iopub.status.idle": "2021-05-25T07:18:24.327063Z",
+     "shell.execute_reply": "2021-05-25T07:18:24.325975Z",
+     "shell.execute_reply.started": "2021-05-25T07:18:24.321644Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(7168, 250)"
+      ]
+     },
+     "execution_count": 119,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#tfidf_X_train.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T07:18:31.418929Z",
+     "iopub.status.busy": "2021-05-25T07:18:31.418573Z",
+     "iopub.status.idle": "2021-05-25T07:18:31.427535Z",
+     "shell.execute_reply": "2021-05-25T07:18:31.426865Z",
+     "shell.execute_reply.started": "2021-05-25T07:18:31.418889Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "def plot_confusion_matrix(cm, classes,\n",
+    "                          normalize=False,\n",
+    "                          title='Confusion matrix',\n",
+    "                          cmap=plt.cm.GnBu):\n",
+    "    \n",
+    "    plt.imshow(cm, interpolation='nearest', cmap=cmap)\n",
+    "    plt.title(title)\n",
+    "    plt.colorbar()\n",
+    "    tick_marks = np.arange(len(classes))\n",
+    "    plt.xticks(tick_marks, classes, rotation=45)\n",
+    "    plt.yticks(tick_marks, classes)\n",
+    "\n",
+    "    if normalize:\n",
+    "        cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]\n",
+    "        print(\"Normalized confusion matrix\")\n",
+    "    else:\n",
+    "        print('Confusion matrix, without normalization')\n",
+    "\n",
+    "    thresh = cm.max() / 2.\n",
+    "    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):\n",
+    "        plt.text(j, i, cm[i, j],\n",
+    "                 horizontalalignment=\"center\",\n",
+    "                 color=\"white\" if cm[i, j] > thresh else \"black\")\n",
+    "\n",
+    "    plt.tight_layout()\n",
+    "    plt.ylabel('True label')\n",
+    "    plt.xlabel('Predicted label')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: tensorflow in c:\\users\\ysach\\anaconda3\\lib\\site-packages (2.15.0)\n",
+      "Requirement already satisfied: tensorflow-intel==2.15.0 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow) (2.15.0)\n",
+      "Requirement already satisfied: opt-einsum>=2.3.2 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (3.3.0)\n",
+      "Requirement already satisfied: six>=1.12.0 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (1.16.0)\n",
+      "Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (0.31.0)\n",
+      "Requirement already satisfied: setuptools in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (65.6.3)\n",
+      "Requirement already satisfied: keras<2.16,>=2.15.0 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (2.15.0)\n",
+      "Requirement already satisfied: wrapt<1.15,>=1.11.0 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (1.14.1)\n",
+      "Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (0.5.4)\n",
+      "Requirement already satisfied: libclang>=13.0.0 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (16.0.6)\n",
+      "Requirement already satisfied: packaging in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (22.0)\n",
+      "Requirement already satisfied: grpcio<2.0,>=1.24.3 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (1.60.0)\n",
+      "Requirement already satisfied: astunparse>=1.6.0 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (1.6.3)\n",
+      "Requirement already satisfied: typing-extensions>=3.6.6 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (4.4.0)\n",
+      "Requirement already satisfied: tensorflow-estimator<2.16,>=2.15.0 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (2.15.0)\n",
+      "Requirement already satisfied: google-pasta>=0.1.1 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (0.2.0)\n",
+      "Requirement already satisfied: absl-py>=1.0.0 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (2.0.0)\n",
+      "Requirement already satisfied: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.20.3 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (4.23.4)\n",
+      "Requirement already satisfied: flatbuffers>=23.5.26 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (23.5.26)\n",
+      "Requirement already satisfied: ml-dtypes~=0.2.0 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (0.2.0)\n",
+      "Requirement already satisfied: tensorboard<2.16,>=2.15 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (2.15.1)\n",
+      "Requirement already satisfied: termcolor>=1.1.0 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (2.4.0)\n",
+      "Requirement already satisfied: numpy<2.0.0,>=1.23.5 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (1.23.5)\n",
+      "Requirement already satisfied: h5py>=2.9.0 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorflow-intel==2.15.0->tensorflow) (3.7.0)\n",
+      "Requirement already satisfied: wheel<1.0,>=0.23.0 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from astunparse>=1.6.0->tensorflow-intel==2.15.0->tensorflow) (0.38.4)\n",
+      "Requirement already satisfied: google-auth<3,>=1.6.3 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorboard<2.16,>=2.15->tensorflow-intel==2.15.0->tensorflow) (2.25.2)\n",
+      "Requirement already satisfied: markdown>=2.6.8 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorboard<2.16,>=2.15->tensorflow-intel==2.15.0->tensorflow) (3.4.1)\n",
+      "Requirement already satisfied: google-auth-oauthlib<2,>=0.5 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorboard<2.16,>=2.15->tensorflow-intel==2.15.0->tensorflow) (1.2.0)\n",
+      "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorboard<2.16,>=2.15->tensorflow-intel==2.15.0->tensorflow) (0.7.2)\n",
+      "Requirement already satisfied: requests<3,>=2.21.0 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorboard<2.16,>=2.15->tensorflow-intel==2.15.0->tensorflow) (2.28.1)\n",
+      "Requirement already satisfied: werkzeug>=1.0.1 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from tensorboard<2.16,>=2.15->tensorflow-intel==2.15.0->tensorflow) (2.2.2)\n",
+      "Requirement already satisfied: rsa<5,>=3.1.4 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow-intel==2.15.0->tensorflow) (4.9)\n",
+      "Requirement already satisfied: pyasn1-modules>=0.2.1 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow-intel==2.15.0->tensorflow) (0.2.8)\n",
+      "Requirement already satisfied: cachetools<6.0,>=2.0.0 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow-intel==2.15.0->tensorflow) (5.3.2)\n",
+      "Requirement already satisfied: requests-oauthlib>=0.7.0 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from google-auth-oauthlib<2,>=0.5->tensorboard<2.16,>=2.15->tensorflow-intel==2.15.0->tensorflow) (1.3.1)\n",
+      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.16,>=2.15->tensorflow-intel==2.15.0->tensorflow) (1.26.14)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.16,>=2.15->tensorflow-intel==2.15.0->tensorflow) (3.4)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.16,>=2.15->tensorflow-intel==2.15.0->tensorflow) (2023.11.17)\n",
+      "Requirement already satisfied: charset-normalizer<3,>=2 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from requests<3,>=2.21.0->tensorboard<2.16,>=2.15->tensorflow-intel==2.15.0->tensorflow) (2.0.4)\n",
+      "Requirement already satisfied: MarkupSafe>=2.1.1 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from werkzeug>=1.0.1->tensorboard<2.16,>=2.15->tensorflow-intel==2.15.0->tensorflow) (2.1.1)\n",
+      "Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard<2.16,>=2.15->tensorflow-intel==2.15.0->tensorflow) (0.4.8)\n",
+      "Requirement already satisfied: oauthlib>=3.0.0 in c:\\users\\ysach\\anaconda3\\lib\\site-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<2,>=0.5->tensorboard<2.16,>=2.15->tensorflow-intel==2.15.0->tensorflow) (3.2.2)\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install tensorflow"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import tensorflow as tf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import keras\n",
+    "from keras.models import Sequential\n",
+    "from keras.utils import to_categorical\n",
+    "from keras import metrics as metrics1\n",
+    "from keras.layers import LeakyReLU\n",
+    "from keras.layers import Dense, Embedding, GlobalAveragePooling1D, LSTM, Bidirectional"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x_train1, x_test, y_train1, y_test = train_test_split(pad_seq, label_train, train_size=0.7)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:tensorflow:From c:\\Users\\ysach\\anaconda3\\lib\\site-packages\\keras\\src\\backend.py:873: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.\n",
+      "\n",
+      "WARNING:tensorflow:From c:\\Users\\ysach\\anaconda3\\lib\\site-packages\\keras\\src\\optimizers\\__init__.py:309: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "classifier = Sequential()\n",
+    "classifier.add(Embedding(vocabulary_size, 182, input_length=input_length))\n",
+    "classifier.add(GlobalAveragePooling1D())\n",
+    "classifier.add(Dense(96, activation='relu'))\n",
+    "classifier.add(Dense(24, activation='relu'))\n",
+    "classifier.add(Dense(1, activation='sigmoid'))\n",
+    "\n",
+    "# Compile the model\n",
+    "classifier.compile(optimizer='adam',\n",
+    "              loss='binary_crossentropy',\n",
+    "              metrics=['accuracy'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model: \"sequential\"\n",
+      "_________________________________________________________________\n",
+      " Layer (type)                Output Shape              Param #   \n",
+      "=================================================================\n",
+      " embedding (Embedding)       (None, 12140, 182)        30222010  \n",
+      "                                                                 \n",
+      " global_average_pooling1d (  (None, 182)               0         \n",
+      " GlobalAveragePooling1D)                                         \n",
+      "                                                                 \n",
+      " dense (Dense)               (None, 96)                17568     \n",
+      "                                                                 \n",
+      " dense_1 (Dense)             (None, 24)                2328      \n",
+      "                                                                 \n",
+      " dense_2 (Dense)             (None, 1)                 25        \n",
+      "                                                                 \n",
+      "=================================================================\n",
+      "Total params: 30241931 (115.36 MB)\n",
+      "Trainable params: 30241931 (115.36 MB)\n",
+      "Non-trainable params: 0 (0.00 Byte)\n",
+      "_________________________________________________________________\n"
+     ]
+    }
+   ],
+   "source": [
+    "classifier.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/10\n",
+      "WARNING:tensorflow:From c:\\Users\\ysach\\anaconda3\\lib\\site-packages\\keras\\src\\utils\\tf_utils.py:492: The name tf.ragged.RaggedTensorValue is deprecated. Please use tf.compat.v1.ragged.RaggedTensorValue instead.\n",
+      "\n",
+      "WARNING:tensorflow:From c:\\Users\\ysach\\anaconda3\\lib\\site-packages\\keras\\src\\engine\\base_layer_utils.py:384: The name tf.executing_eagerly_outside_functions is deprecated. Please use tf.compat.v1.executing_eagerly_outside_functions instead.\n",
+      "\n",
+      "455/455 [==============================] - 422s 923ms/step - loss: 0.6866 - accuracy: 0.5386 - val_loss: 0.6534 - val_accuracy: 0.5832\n",
+      "Epoch 2/10\n",
+      "455/455 [==============================] - 433s 952ms/step - loss: 0.4281 - accuracy: 0.8095 - val_loss: 0.3156 - val_accuracy: 0.8345\n",
+      "Epoch 3/10\n",
+      "455/455 [==============================] - 422s 927ms/step - loss: 0.2246 - accuracy: 0.9132 - val_loss: 0.2006 - val_accuracy: 0.9226\n",
+      "Epoch 4/10\n",
+      "455/455 [==============================] - 418s 919ms/step - loss: 0.1441 - accuracy: 0.9494 - val_loss: 0.1607 - val_accuracy: 0.9502\n",
+      "Epoch 5/10\n",
+      "455/455 [==============================] - 414s 910ms/step - loss: 0.1020 - accuracy: 0.9671 - val_loss: 0.1505 - val_accuracy: 0.9535\n",
+      "Epoch 6/10\n",
+      "455/455 [==============================] - 413s 909ms/step - loss: 0.0765 - accuracy: 0.9750 - val_loss: 0.1286 - val_accuracy: 0.9564\n",
+      "Epoch 7/10\n",
+      "455/455 [==============================] - 428s 942ms/step - loss: 0.0586 - accuracy: 0.9812 - val_loss: 0.1270 - val_accuracy: 0.9583\n",
+      "Epoch 8/10\n",
+      "455/455 [==============================] - 423s 930ms/step - loss: 0.0476 - accuracy: 0.9840 - val_loss: 0.1698 - val_accuracy: 0.9441\n",
+      "Epoch 9/10\n",
+      "455/455 [==============================] - 414s 911ms/step - loss: 0.0311 - accuracy: 0.9912 - val_loss: 0.1222 - val_accuracy: 0.9617\n",
+      "Epoch 10/10\n",
+      "455/455 [==============================] - 411s 904ms/step - loss: 0.0303 - accuracy: 0.9908 - val_loss: 0.1265 - val_accuracy: 0.9627\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.src.callbacks.History at 0x174deb95ab0>"
+      ]
+     },
+     "execution_count": 56,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "classifier.fit(x_train1,y_train1,epochs=10,validation_data=(x_test, y_test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "196/196 [==============================] - 29s 148ms/step\n"
+     ]
+    }
+   ],
+   "source": [
+    "Y_pred = classifier.predict(x_test)\n",
+    "a=[]\n",
+    "for x in Y_pred:\n",
+    "    if x>=0.5:\n",
+    "        a.append(1)\n",
+    "    else:\n",
+    "        a.append(0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2021-05-25T07:18:41.422338Z",
+     "iopub.status.busy": "2021-05-25T07:18:41.421887Z",
+     "iopub.status.idle": "2021-05-25T07:18:41.673492Z",
+     "shell.execute_reply": "2021-05-25T07:18:41.672498Z",
+     "shell.execute_reply.started": "2021-05-25T07:18:41.422308Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 96.27%\n",
+      "Confusion matrix, without normalization\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "score = accuracy_score(y_test, a)\n",
+    "print(f'Accuracy: {round(score*100,2)}%')\n",
+    "cm = confusion_matrix(y_test, a)\n",
+    "plot_confusion_matrix(cm, classes=['FAKE Data', 'REAL Data'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from keras.layers import SimpleRNN,LSTM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 69,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = Sequential()\n",
+    "model.add(Embedding(vocabulary_size, 100, input_length=input_length))\n",
+    "model.add(SimpleRNN(units=10, return_sequences=False))\n",
+    "model.add(Dense(units=1))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 70,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model.compile(optimizer='adam',\n",
+    "              loss='binary_crossentropy',\n",
+    "              metrics=['accuracy'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 71,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model: \"sequential_3\"\n",
+      "_________________________________________________________________\n",
+      " Layer (type)                Output Shape              Param #   \n",
+      "=================================================================\n",
+      " embedding_3 (Embedding)     (None, 12140, 100)        16605500  \n",
+      "                                                                 \n",
+      " simple_rnn (SimpleRNN)      (None, 10)                1110      \n",
+      "                                                                 \n",
+      " dense_5 (Dense)             (None, 1)                 11        \n",
+      "                                                                 \n",
+      "=================================================================\n",
+      "Total params: 16606621 (63.35 MB)\n",
+      "Trainable params: 16606621 (63.35 MB)\n",
+      "Non-trainable params: 0 (0.00 Byte)\n",
+      "_________________________________________________________________\n"
+     ]
+    }
+   ],
+   "source": [
+    "model.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/3\n",
+      "455/455 [==============================] - 2882s 6s/step - loss: 0.7130 - accuracy: 0.8058 - val_loss: 0.6941 - val_accuracy: 0.8763\n",
+      "Epoch 2/3\n",
+      "455/455 [==============================] - 3135s 7s/step - loss: 0.2564 - accuracy: 0.9559 - val_loss: 0.8114 - val_accuracy: 0.7906\n",
+      "Epoch 3/3\n",
+      "455/455 [==============================] - 3928s 9s/step - loss: 0.1439 - accuracy: 0.9792 - val_loss: 0.7665 - val_accuracy: 0.8503\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.src.callbacks.History at 0x1760ee6eec0>"
+      ]
+     },
+     "execution_count": 72,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model.fit(x_train1,y_train1,epochs=3,validation_data=(x_test, y_test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 73,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "196/196 [==============================] - 65s 328ms/step\n"
+     ]
+    }
+   ],
+   "source": [
+    "Y_pred = model.predict(x_test)\n",
+    "a=[]\n",
+    "for x in Y_pred:\n",
+    "    if x>=0.5:\n",
+    "        a.append(1)\n",
+    "    else:\n",
+    "        a.append(0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 85.03%\n",
+      "Confusion matrix, without normalization\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#For second model\n",
+    "score = accuracy_score(y_test, a)\n",
+    "print(f'Accuracy: {round(score*100,2)}%')\n",
+    "cm = confusion_matrix(y_test, a)\n",
+    "plot_confusion_matrix(cm, classes=['FAKE Data', 'REAL Data'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#The first model performed better.The second model had good training accuracy but less test accuracy hinting towards overfitting.Maybe the key reason being in fake news it is important to capture overall sentiment better than individual word sentiment."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 76,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def fake_news_det(news):\n",
+    "    review = news\n",
+    "    review = re.sub(r'[^a-zA-Z\\s]', '', review)\n",
+    "    review = review.lower()\n",
+    "    review = nltk.word_tokenize(review)\n",
+    "    for y in review :\n",
+    "        if y not in stpwrds :\n",
+    "            corpus.append(lemmatizer.lemmatize(y))     \n",
+    "    input_data = [' '.join(corpus)]\n",
+    "    vectorized_input_data_pre = tokenize.texts_to_sequences(input_data)\n",
+    "    vectorized_input_data=pad_sequences(vectorized_input_data_pre, padding=\"pre\", truncating=\"pre\")\n",
+    "    prediction = classifier.predict(vectorized_input_data)\n",
+    "    if prediction[0] == 1:\n",
+    "        print(\"Prediction of the News :  Looking Fake⚠ News📰 \")\n",
+    "    else:\n",
+    "        print(\"Prediction of the News : Looking Real News📰 \")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 77,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1/1 [==============================] - 0s 86ms/step\n",
+      "Prediction of the News :  Looking Fake⚠ News📰 \n"
+     ]
+    }
+   ],
+   "source": [
+    "fake_news_det(\"actor steven seagal live tv erupts hillary obama intense comment actor steven seagal stood america rest hollywood remains silent week rough country first democratic nominee hillary clinton collapsed memorial called million hardworking american deplorable werent enough nfl player throughout country blatantly disrespecting american flag needle say seagal enough think important job secretary state ensuring people dont get killed seagal tweeted cant email protected pneumonia going disastrous american people notohillary continued course seagal quickly became target liberal fire comment refused break particularly lost one twitter user tried argued hillary capable presidency capable capable leaving american die capable disregarding law capable disrespecting rape survivor argued went address race relation united state true role president barack obama played social evolution country obama abysmal race relation usa truth need start honest dialog wrote seagal concluded pointing irony attack receiving liberal everywhere best thing worldmaking one statement freedom getting attacked every demo hypocritical tweeted america without democrat white house safer america think seagals comment\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.10.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/Fake-News-Classification/README.md b/Fake-News-Classification/README.md
new file mode 100644
index 000000000..d22ba02d2
--- /dev/null
+++ b/Fake-News-Classification/README.md
@@ -0,0 +1,97 @@
+# Fake News Classification using DL 
+
+## PROJECT TITLE
+
+Fake News Detection using Deep Learning 
+
+## GOAL
+
+To identify whether the given news is fake or not. 
+
+## DATASET
+
+The link for the dataset used in this project:  https://www.kaggle.com/competitions/fake-news/data?select=train.csv 
+
+
+## DESCRIPTION
+
+This project aims to identify whether the given news is fake or not by extracting meaning and semantics of the given news.
+
+## WHAT I HAD DONE
+
+1. Data collection: From the link of the dataset given above. 
+2. Data preprocessing: Preprocessed the news by combining title and text to create a new feature and did some augementation like tokeinizing and vectorising before passing them to model training
+3. Model selection: Self Designed model having a Embedding Layer followed by Global Pooling Layer and then 2 Dense layers and then output layer.Second model had a Embedding layer followed by a RNN layer and a Dense output layer.
+4. Comparative analysis: Compared the accuracy score of all the models.
+
+## MODELS SUMMARY
+
+Model-1: "sequential"
+_________________________________________________________________
+ Layer (type)                Output Shape              Param #   
+=================================================================
+ embedding (Embedding)       (None, 12140, 182)        30222010  
+                                                                 
+ global_average_pooling1d (  (None, 182)               0         
+ GlobalAveragePooling1D)                                         
+                                                                 
+ dense (Dense)               (None, 96)                17568     
+                                                                 
+ dense_1 (Dense)             (None, 24)                2328      
+                                                                 
+ dense_2 (Dense)             (None, 1)                 25        
+                                                                 
+=================================================================
+Total params: 30241931 (115.36 MB)
+Trainable params: 30241931 (115.36 MB)
+Non-trainable params: 0 (0.00 Byte)
+
+Model-2: "sequential_3"
+_________________________________________________________________
+ Layer (type)                Output Shape              Param #   
+=================================================================
+ embedding_3 (Embedding)     (None, 12140, 100)        16605500  
+                                                                 
+ simple_rnn (SimpleRNN)      (None, 10)                1110      
+                                                                 
+ dense_5 (Dense)             (None, 1)                 11        
+                                                                 
+=================================================================
+Total params: 16606621 (63.35 MB)
+Trainable params: 16606621 (63.35 MB)
+Non-trainable params: 0 (0.00 Byte)
+
+## LIBRARIES NEEDED
+
+The following libraries are required to run this project:
+
+- nltk
+- pandas
+- matplotlib
+- tensorflow
+- keras
+- sklearn
+
+## EVALUATION METRICS
+
+The evaluation metrics I used to assess the models:
+
+- Accuracy 
+- Loss
+
+It is shown using Confusion Matrix in the Images folder
+
+## RESULTS
+Results on Val dataset:
+For Model-1:
+Accuracy:96.11%
+loss: 0.1350
+
+For Model-2:
+Accuracy:85.03%
+loss: 0.1439
+
+## CONCLUSION
+Based on results we can draw following conclusions:
+
+1.The model-1 showed high validation accuracy of 96.11% and loss of 0.1350.Thus the model-1 worked fairly well identifying 2874 fake articles from a total of 3044.The first model performed better.The second model had good training accuracy but less test accuracy hinting towards overfitting.Maybe the key reason being in fake news it is important to capture overall sentiment better than individual word sentiment.