diff --git a/.ipynb_checkpoints/Main-checkpoint.ipynb b/.ipynb_checkpoints/Main-checkpoint.ipynb
new file mode 100644
index 0000000..363fcab
--- /dev/null
+++ b/.ipynb_checkpoints/Main-checkpoint.ipynb
@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/NLP_main.ipynb b/NLP_main.ipynb
new file mode 100644
index 0000000..30e184a
--- /dev/null
+++ b/NLP_main.ipynb
@@ -0,0 +1,3619 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %pip install pandas numpy re warnings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#%pip install nltk"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# \n",
+    "# %pip install scikit-learn"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %pip install plotly"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#%pip install kneed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "executionInfo": {
+     "elapsed": 3090,
+     "status": "ok",
+     "timestamp": 1737043596670,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "VRIM9b6MElD5",
+    "outputId": "ffe3fa16-8c09-4803-b0a4-9e71b65eacaf"
+   },
+   "outputs": [],
+   "source": [
+    "# 📚 Basic Libraries\n",
+    "\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import os\n",
+    "import re # Regular Expression\n",
+    "import warnings\n",
+    "\n",
+    "# 📝 Text Processing\n",
+    "import nltk\n",
+    "from nltk.stem import WordNetLemmatizer # to lemmatize the words #\n",
+    "from nltk.tokenize import word_tokenize\n",
+    "from nltk.tokenize import sent_tokenize # sentence tokenizer\n",
+    "from nltk.corpus import wordnet # to get the wordnet pos tags\n",
+    "from nltk.corpus import stopwords # to remove the stopwords\n",
+    "from sklearn.feature_extraction.text import CountVectorizer # to create a bag of words\n",
+    "\n",
+    "# Machine Learning\n",
+    "from sklearn.cluster import KMeans\n",
+    "import plotly.graph_objects as go\n",
+    "from sklearn.metrics import silhouette_score\n",
+    "\n",
+    "# Ensure kneed is installed\n",
+    "from kneed import KneeLocator"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "OnHTm9l2ItAW"
+   },
+   "source": [
+    "***1***. **Load and Inspect the Data**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Training Data:\n",
+      "   0  \\\n",
+      "0  0   \n",
+      "1  0   \n",
+      "\n",
+      "  donald trump sends out embarrassing new year‚s eve message; this is disturbing  \n",
+      "0  drunk bragging trump staffer started russian c...                              \n",
+      "1  sheriff david clarke becomes an internet joke ...                              \n",
+      "\n",
+      "Testing Data:\n",
+      "   2 copycat muslim terrorist arrested with assault weapons\n",
+      "0  2  wow! chicago protester caught on camera admits...    \n",
+      "1  2   germany's fdp look to fill schaeuble's big shoes    \n"
+     ]
+    }
+   ],
+   "source": [
+    "\n",
+    "# Define the folder path\n",
+    "folder_path = './dataset'\n",
+    "\n",
+    "# Define file paths\n",
+    "training_file = os.path.join(folder_path, 'training_data.csv')\n",
+    "testing_file = os.path.join(folder_path, 'testing_data.csv')\n",
+    "\n",
+    "# Load the CSV files\n",
+    "train_data = pd.read_csv(training_file, sep=\"\\t\")\n",
+    "test_data = pd.read_csv(testing_file, sep=\"\\t\")\n",
+    "\n",
+    "# Inspect the loaded data\n",
+    "print(\"Training Data:\")\n",
+    "print(train_data.head(2))\n",
+    "\n",
+    "print(\"\\nTesting Data:\")\n",
+    "print(test_data.head(2))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "executionInfo": {
+     "elapsed": 1552,
+     "status": "ok",
+     "timestamp": 1737043598213,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "gF9NrzArC9ex",
+    "outputId": "66e7ece3-eaae-41fa-b18c-2ab9bbe4fe15"
+   },
+   "outputs": [],
+   "source": [
+    "#from google.colab import drive\n",
+    "#drive.mount('/content/drive')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 6,
+     "status": "ok",
+     "timestamp": 1737043598213,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "9jKl5a6rDL_x"
+   },
+   "outputs": [],
+   "source": [
+    "#\n",
+    "#folder_path  = \"/content/drive/MyDrive/project-3-nlp/dataset/training_data.csv\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 361,
+     "status": "ok",
+     "timestamp": 1737043598569,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "2E8hCRDGDq8S"
+   },
+   "outputs": [],
+   "source": [
+    "data = train_data\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 4,
+     "status": "ok",
+     "timestamp": 1737043598569,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "TMaexyk7JAbZ"
+   },
+   "outputs": [],
+   "source": [
+    "# 🔧 Make your functions:\n",
+    "# Save this file as my_functions.py\n",
+    "# Import your functions in your notebook\n",
+    "# from my_functions import *\n",
+    "def clean_data(data):\n",
+    "    \"\"\"\n",
+    "    Standarize and returns snake_case columns\n",
+    "    \"\"\"\n",
+    "    data.columns = [column.lower().replace(' ', '_') for column in data.columns]\n",
+    "\n",
+    "\n",
+    "def map_pos_tag(word):\n",
+    "    \"\"\"\n",
+    "    Map POS tag to first character lemmatize() accepts.\n",
+    "    \"\"\"\n",
+    "    tag = nltk.pos_tag([word])[0][1][0].upper() # get the first character of the POS tag\n",
+    "    tag_dict = { # dictionary to map POS tags\n",
+    "        \"J\": wordnet.ADJ,\n",
+    "        \"N\": wordnet.NOUN,\n",
+    "        \"V\": wordnet.VERB,\n",
+    "        \"R\": wordnet.ADV\n",
+    "    }\n",
+    "    return tag_dict.get(tag, wordnet.NOUN) # return the value of the key or the default value\n",
+    "\n",
+    "# ⚙️ Settings\n",
+    "pd.set_option('display.max_columns', None) # display all columns\n",
+    "warnings.filterwarnings('ignore') # ignore warnings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 3,
+     "status": "ok",
+     "timestamp": 1737043598569,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "vSe1_QV8KmU6"
+   },
+   "outputs": [],
+   "source": [
+    "df = data.copy()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 3,
+     "status": "ok",
+     "timestamp": 1737043598569,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "tGVzSBrWbCPZ"
+   },
+   "outputs": [],
+   "source": [
+    "clean_data(df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 206
+    },
+    "executionInfo": {
+     "elapsed": 265,
+     "status": "ok",
+     "timestamp": 1737043598831,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "NgdSn3P5E1zm",
+    "outputId": "327f0e58-359e-4627-dadc-b1a7ca998acb"
+   },
+   "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>0</th>\n",
+       "      <th>donald_trump_sends_out_embarrassing_new_year‚s_eve_message;_this_is_disturbing</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>drunk bragging trump staffer started russian c...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0</td>\n",
+       "      <td>sheriff david clarke becomes an internet joke ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0</td>\n",
+       "      <td>trump is so obsessed he even has obama‚s name ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0</td>\n",
+       "      <td>pope francis just called out donald trump duri...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0</td>\n",
+       "      <td>racist alabama cops brutalize black boy while ...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   0  \\\n",
+       "0  0   \n",
+       "1  0   \n",
+       "2  0   \n",
+       "3  0   \n",
+       "4  0   \n",
+       "\n",
+       "  donald_trump_sends_out_embarrassing_new_year‚s_eve_message;_this_is_disturbing  \n",
+       "0  drunk bragging trump staffer started russian c...                              \n",
+       "1  sheriff david clarke becomes an internet joke ...                              \n",
+       "2  trump is so obsessed he even has obama‚s name ...                              \n",
+       "3  pope francis just called out donald trump duri...                              \n",
+       "4  racist alabama cops brutalize black boy while ...                              "
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 424
+    },
+    "executionInfo": {
+     "elapsed": 13,
+     "status": "ok",
+     "timestamp": 1737043598832,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "OdxZaVSLNliy",
+    "outputId": "3a896044-4bd1-42a7-ab7d-c6298a19607c"
+   },
+   "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>classification</th>\n",
+       "      <th>news</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>drunk bragging trump staffer started russian c...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0</td>\n",
+       "      <td>sheriff david clarke becomes an internet joke ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0</td>\n",
+       "      <td>trump is so obsessed he even has obama‚s name ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0</td>\n",
+       "      <td>pope francis just called out donald trump duri...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0</td>\n",
+       "      <td>racist alabama cops brutalize black boy while ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>34146</th>\n",
+       "      <td>1</td>\n",
+       "      <td>tears in rain as thais gather for late king's ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>34147</th>\n",
+       "      <td>1</td>\n",
+       "      <td>pyongyang university needs non-u.s. teachers a...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>34148</th>\n",
+       "      <td>1</td>\n",
+       "      <td>philippine president duterte to visit japan ah...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>34149</th>\n",
+       "      <td>1</td>\n",
+       "      <td>japan's abe may have won election\\tbut many do...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>34150</th>\n",
+       "      <td>1</td>\n",
+       "      <td>demoralized and divided: inside catalonia's po...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>34151 rows × 2 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       classification                                               news\n",
+       "0                   0  drunk bragging trump staffer started russian c...\n",
+       "1                   0  sheriff david clarke becomes an internet joke ...\n",
+       "2                   0  trump is so obsessed he even has obama‚s name ...\n",
+       "3                   0  pope francis just called out donald trump duri...\n",
+       "4                   0  racist alabama cops brutalize black boy while ...\n",
+       "...               ...                                                ...\n",
+       "34146               1  tears in rain as thais gather for late king's ...\n",
+       "34147               1  pyongyang university needs non-u.s. teachers a...\n",
+       "34148               1  philippine president duterte to visit japan ah...\n",
+       "34149               1  japan's abe may have won election\\tbut many do...\n",
+       "34150               1  demoralized and divided: inside catalonia's po...\n",
+       "\n",
+       "[34151 rows x 2 columns]"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.columns = ['classification', 'news'] # classifictaion of the columns\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "f5M65F-i3mN0"
+   },
+   "source": [
+    "***2***. **EDA**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 147
+    },
+    "executionInfo": {
+     "elapsed": 11,
+     "status": "ok",
+     "timestamp": 1737043598832,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "IQ2TG9sON0fD",
+    "outputId": "cb472468-beef-4fc4-95c1-694da851dd9f"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "classification     int64\n",
+       "news              object\n",
+       "dtype: object"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.dtypes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 178
+    },
+    "executionInfo": {
+     "elapsed": 26,
+     "status": "ok",
+     "timestamp": 1737043599096,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "x5GcGruFQ6xE",
+    "outputId": "34c20544-0d38-487f-fa01-49c1863f4dd9"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "classification\n",
+       "0    17571\n",
+       "1    16580\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_class = df.classification.value_counts()\n",
+    "df_class"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 88,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 178
+    },
+    "executionInfo": {
+     "elapsed": 25,
+     "status": "ok",
+     "timestamp": 1737043599097,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "sUK-CwvfOElY",
+    "outputId": "69ee3a87-378d-482a-a4d6-4d2ac5dfb4d7"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "classification\n",
+       "0    0.514509\n",
+       "1    0.485491\n",
+       "Name: count, dtype: float64"
+      ]
+     },
+     "execution_count": 88,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "total_count_class = len(df['classification'])\n",
+    "\n",
+    "frequency_class = df_class / total_count_class\n",
+    "\n",
+    "frequency_class"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 147
+    },
+    "executionInfo": {
+     "elapsed": 24,
+     "status": "ok",
+     "timestamp": 1737043599097,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "aR6osh1jg9Nf",
+    "outputId": "21a3f9e0-361a-42ca-b293-01ee76c7d505"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "classification    0\n",
+       "news              0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 398
+    },
+    "executionInfo": {
+     "elapsed": 23,
+     "status": "ok",
+     "timestamp": 1737043599097,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "9rzO8uSXR19t",
+    "outputId": "9bad1a4b-a240-4ca3-9c9d-e5b6f6f6221d"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "7703     fox news shows real reaction from demoralized ...\n",
+       "23500    new u.s. u.n. envoy warns allies: back us or w...\n",
+       "25138    north carolina republican office painted with ...\n",
+       "13189    why hillary loves the idea of barack obama as ...\n",
+       "5280     father of purple heart-winning muslim soldier ...\n",
+       "4216                             trump terrified of losing\n",
+       "33093    purge of saudi princes\\tbusinessmen widens\\ttr...\n",
+       "21432    the firing line: ouster of fbi's comey tests n...\n",
+       "162      this 2016 hannity tweet is now like a knife in...\n",
+       "12965    why trump supporters are laughing after wikile...\n",
+       "Name: news, dtype: object"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['news'].sample(10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 36
+    },
+    "executionInfo": {
+     "elapsed": 22,
+     "status": "ok",
+     "timestamp": 1737043599097,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "FS927o5IZq9H",
+    "outputId": "5dc83fef-3c02-43ca-a791-5e9c5dd5a934"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'sheriff david clarke becomes an internet joke for threatening to poke people ‚in the eye‚'"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "example1 = df['news'][1]\n",
+    "example1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 36
+    },
+    "executionInfo": {
+     "elapsed": 22,
+     "status": "ok",
+     "timestamp": 1737043599098,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "MNuqSfoDZq5t",
+    "outputId": "857c4cb7-abf1-4363-db14-c9d071e592ae"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'trump is so obsessed he even has obama‚s name coded into his website (images)'"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "exemple2 = df['news'][2]\n",
+    "exemple2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 36
+    },
+    "executionInfo": {
+     "elapsed": 21,
+     "status": "ok",
+     "timestamp": 1737043599098,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "R48Km1jFZqyc",
+    "outputId": "a3e1e1be-31b0-463d-8e4d-4230a6c068f0"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'racist alabama cops brutalize black boy while he is in handcuffs (graphic images)'"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "example4 = df['news'][4]\n",
+    "example4"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 36
+    },
+    "executionInfo": {
+     "elapsed": 369,
+     "status": "ok",
+     "timestamp": 1737043599447,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "D498WlayZqn4",
+    "outputId": "51c23b3a-96f9-4e4e-de5c-89f4ed0da79a"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'brand-new pro-trump ad features so much a** kissing it will make you sick'"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "example = df['news'][8]\n",
+    "example"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 36
+    },
+    "executionInfo": {
+     "elapsed": 25,
+     "status": "ok",
+     "timestamp": 1737043599447,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "ILaBwX-DYr_R",
+    "outputId": "21df434e-d9b5-4ed5-f6d6-d3a8d3443358"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'lindsey graham trashes media for portraying trump as ‚kooky‚ forgets his own words\"'"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "example = df['news'][12]\n",
+    "example"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 36
+    },
+    "executionInfo": {
+     "elapsed": 24,
+     "status": "ok",
+     "timestamp": 1737043599447,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "E4bIoM8Jc7V6",
+    "outputId": "35ad697d-6b19-4d3f-955c-6a47dede2f48"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'ky gop state rep. commits suicide over allegations he molested a teen girl (details)'"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "example11 = df['news'][20]\n",
+    "example11"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 36
+    },
+    "executionInfo": {
+     "elapsed": 23,
+     "status": "ok",
+     "timestamp": 1737043599447,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "UVd9r8pMZqiX",
+    "outputId": "65f3ae8d-eaf5-459d-8e40-317a1c1cc48a"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'snl hilariously mocks accused child molester roy moore for losing al senate race (video)'"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "example = df['news'][17]\n",
+    "example"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 36
+    },
+    "executionInfo": {
+     "elapsed": 22,
+     "status": "ok",
+     "timestamp": 1737043599447,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "MyZ6lTSWZq18",
+    "outputId": "fc930960-8919-45b2-a79f-1d546e429b65"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'meghan mccain tweets the most amazing response to doug jones‚ win in deep-red alabama'"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "example3 = df['news'][21]\n",
+    "example3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 36
+    },
+    "executionInfo": {
+     "elapsed": 22,
+     "status": "ok",
+     "timestamp": 1737043599448,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "wr48DFLcZqvJ",
+    "outputId": "216c53a4-39b3-4c81-c44d-5352f5ff8aa3"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'cnn calls it: a democrat will represent alabama in the senate for the first time in 25 years'"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "example5 = df['news'][22]\n",
+    "example5"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 36
+    },
+    "executionInfo": {
+     "elapsed": 22,
+     "status": "ok",
+     "timestamp": 1737043599448,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "KC1tWjB9dTGp",
+    "outputId": "8bd4846a-f264-463d-8d01-5c4e8319ac20"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'tone deaf trump: congrats rep. scalise on losing weight after you almost died'"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "example4 = df['news'][14]\n",
+    "example4"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 36
+    },
+    "executionInfo": {
+     "elapsed": 21,
+     "status": "ok",
+     "timestamp": 1737043599448,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "Fs8N82vIZqrv",
+    "outputId": "562c5509-1b5e-4371-fb4c-5ada4763c583"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'mueller spokesman just f-cked up donald trump‚s christmas'"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "example = df['news'][16]\n",
+    "example"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 36
+    },
+    "executionInfo": {
+     "elapsed": 20,
+     "status": "ok",
+     "timestamp": 1737043599448,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "Os-TRBgRZqY4",
+    "outputId": "1a0e7057-3732-49b6-d97d-4dac596b6d50"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'republican senator gets dragged for going after robert mueller'"
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "exemple10 = df['news'][18]\n",
+    "exemple10"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 36
+    },
+    "executionInfo": {
+     "elapsed": 20,
+     "status": "ok",
+     "timestamp": 1737043599448,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "AwJlGedtZqII",
+    "outputId": "dc3bc56d-f742-4d56-8631-3fe9016f2805"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'in a heartless rebuke to victims'"
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "exemple11 = df['news'][19]\n",
+    "exemple11"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "p8ngkkLtmHJX"
+   },
+   "source": [
+    "Extra cleaning"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 652,
+     "status": "ok",
+     "timestamp": 1737043600081,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "MwKywyOaiT36"
+   },
+   "outputs": [],
+   "source": [
+    "# probably i will joint to myfuntions\n",
+    "# listo of bad words\n",
+    "bad_words = [\"fcked\", \"sht\", \"fck\"]\n",
+    "\n",
+    "# Function to clean text\n",
+    "def clean_text(text):\n",
+    "    text = text.lower()  # Convert to lowercase\n",
+    "    text = re.sub(r'http\\S+', '', text)  # Remove URLs\n",
+    "    text = re.sub(r'\\([^\\)]+\\)', '', text)  # Remove text inside parentheses\n",
+    "    text = re.sub(r'[^a-zA-Z\\s]', '', text)  # Remove non-alphabetic characters\n",
+    "    text = re.sub(r'\\s+', ' ', text).strip()  # Remove extra whitespace\n",
+    "    for bad_word in bad_words:\n",
+    "        text = text.replace(bad_word, '')  # Remove bad words\n",
+    "    return text\n",
+    "    return text\n",
+    "\n",
+    "# Apply the cleaning function\n",
+    "df['news'] = df['news'].apply(clean_text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 36
+    },
+    "executionInfo": {
+     "elapsed": 12,
+     "status": "ok",
+     "timestamp": 1737043600081,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "mMcbnaAFj1hP",
+    "outputId": "bb728bb8-6945-4f78-af6b-53aa7859b141"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'trump sends crazytime tweet to the wrong account after losing his  over world leaders remarks'"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "example21 = df['news'][50]\n",
+    "example21"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 36
+    },
+    "executionInfo": {
+     "elapsed": 11,
+     "status": "ok",
+     "timestamp": 1737043600081,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "rWv0rFjPkEh_",
+    "outputId": "6a41b62e-0720-437b-a0eb-b80a197a0b8c"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'just back from a golfing vacay'"
+      ]
+     },
+     "execution_count": 36,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "example22 = df['news'][62]\n",
+    "example22"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 36
+    },
+    "executionInfo": {
+     "elapsed": 311,
+     "status": "ok",
+     "timestamp": 1737043600383,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "w51aeQkVkBoW",
+    "outputId": "a624c7fe-a8a5-48fe-a2f9-c32094479392"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'fox news bans gene simmons for life for harassing staff off camera'"
+      ]
+     },
+     "execution_count": 37,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "example23 = df['news'][74]\n",
+    "example23"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 36
+    },
+    "executionInfo": {
+     "elapsed": 15,
+     "status": "ok",
+     "timestamp": 1737043600384,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "a99o5jGBkEfb",
+    "outputId": "8fc7e3c9-a6d7-4d52-8cdf-3f6879d18c1d"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'newsweek just made their best cover ever and people are freaking out'"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "example24 = df['news'][108]\n",
+    "example24"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 36
+    },
+    "executionInfo": {
+     "elapsed": 13,
+     "status": "ok",
+     "timestamp": 1737043600384,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "yKdbT8UAkEcD",
+    "outputId": "58f4f554-9700-4396-c356-8e5b5c1ae2ca"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'trump tells japanese diplomats he never knew there were so many countries in the world'"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "example25 = df['news'][126]\n",
+    "example25"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 677
+    },
+    "executionInfo": {
+     "elapsed": 12,
+     "status": "ok",
+     "timestamp": 1737043600384,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "vCA6-4u3mbpT",
+    "outputId": "006c0d7e-9950-4170-f22c-8d118f3b46d8"
+   },
+   "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>classification</th>\n",
+       "      <th>news</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>11184</th>\n",
+       "      <td>0</td>\n",
+       "      <td>lawyer for illegal alien rapists hysteria over...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14536</th>\n",
+       "      <td>0</td>\n",
+       "      <td>epic backfire the left makes video warning fol...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23943</th>\n",
+       "      <td>1</td>\n",
+       "      <td>att chief executive trump meet amid planned ti...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32777</th>\n",
+       "      <td>1</td>\n",
+       "      <td>tillerson speaks to saudi counterpart about ar...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29978</th>\n",
+       "      <td>1</td>\n",
+       "      <td>italy national election likely set for march p...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29326</th>\n",
+       "      <td>1</td>\n",
+       "      <td>un mediator de mistura to attend syria talks o...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>22764</th>\n",
+       "      <td>1</td>\n",
+       "      <td>trump trade office takes aggressive view of wt...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16649</th>\n",
+       "      <td>0</td>\n",
+       "      <td>obama suggests gun confiscation is solutioncit...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>28363</th>\n",
+       "      <td>1</td>\n",
+       "      <td>obama to make historic trip to cuba in coming ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32901</th>\n",
+       "      <td>1</td>\n",
+       "      <td>senior thai royal official dismissed in latest...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>31760</th>\n",
+       "      <td>1</td>\n",
+       "      <td>us sanctions chinese and north korean organiza...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17600</th>\n",
+       "      <td>1</td>\n",
+       "      <td>senate leader mcconnell sees a more collegial</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>30012</th>\n",
+       "      <td>1</td>\n",
+       "      <td>window falls from us marines helicopter onto s...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>24789</th>\n",
+       "      <td>1</td>\n",
+       "      <td>chinas interference in hong kong reaching alar...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17989</th>\n",
+       "      <td>1</td>\n",
+       "      <td>us attorney general sessions evasive on russia...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>28712</th>\n",
+       "      <td>1</td>\n",
+       "      <td>us appeals court declines to block obama carbo...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23853</th>\n",
+       "      <td>1</td>\n",
+       "      <td>putin says he doubts trump met with moscow pro...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11072</th>\n",
+       "      <td>0</td>\n",
+       "      <td>sec of state rex tillerson steps are under way...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>20061</th>\n",
+       "      <td>1</td>\n",
+       "      <td>senate aims for a skinny obamacare repeal as o...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>24554</th>\n",
+       "      <td>1</td>\n",
+       "      <td>senior senators want to amend saudi september law</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       classification                                               news\n",
+       "11184               0  lawyer for illegal alien rapists hysteria over...\n",
+       "14536               0  epic backfire the left makes video warning fol...\n",
+       "23943               1  att chief executive trump meet amid planned ti...\n",
+       "32777               1  tillerson speaks to saudi counterpart about ar...\n",
+       "29978               1  italy national election likely set for march p...\n",
+       "29326               1  un mediator de mistura to attend syria talks o...\n",
+       "22764               1  trump trade office takes aggressive view of wt...\n",
+       "16649               0  obama suggests gun confiscation is solutioncit...\n",
+       "28363               1  obama to make historic trip to cuba in coming ...\n",
+       "32901               1  senior thai royal official dismissed in latest...\n",
+       "31760               1  us sanctions chinese and north korean organiza...\n",
+       "17600               1      senate leader mcconnell sees a more collegial\n",
+       "30012               1  window falls from us marines helicopter onto s...\n",
+       "24789               1  chinas interference in hong kong reaching alar...\n",
+       "17989               1  us attorney general sessions evasive on russia...\n",
+       "28712               1  us appeals court declines to block obama carbo...\n",
+       "23853               1  putin says he doubts trump met with moscow pro...\n",
+       "11072               0  sec of state rex tillerson steps are under way...\n",
+       "20061               1  senate aims for a skinny obamacare repeal as o...\n",
+       "24554               1  senior senators want to amend saudi september law"
+      ]
+     },
+     "execution_count": 40,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.sample(20) # found some bad names at the first time, however they are incomplete"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "lAms-mbn3-EJ"
+   },
+   "source": [
+    "***3***. **Text processing**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "JiND6eDIl8J-"
+   },
+   "source": [
+    "Tokenization"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "executionInfo": {
+     "elapsed": 11,
+     "status": "ok",
+     "timestamp": 1737043600384,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "48-PO0AmkEJX",
+    "outputId": "7a52a5c0-6fb3-4f3b-ae8d-c4df2c47b194"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[nltk_data] Downloading package punkt_tab to\n",
+      "[nltk_data]     C:\\Users\\ggsan\\AppData\\Roaming\\nltk_data...\n",
+      "[nltk_data]   Package punkt_tab is already up-to-date!\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 41,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "nltk.download('punkt_tab') #tokenizer package however in googlecolab is \"punkt_tab\" instead of \"punkt\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "executionInfo": {
+     "elapsed": 9,
+     "status": "ok",
+     "timestamp": 1737043600385,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "9QATpKZrkEDY",
+    "outputId": "319cfe31-bc93-428c-eb05-8b6013649de1"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['mueller spokesman just f-cked up donald trump‚s christmas']"
+      ]
+     },
+     "execution_count": 42,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "example.split(\",\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "executionInfo": {
+     "elapsed": 8,
+     "status": "ok",
+     "timestamp": 1737043600385,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "Uhfc7nEGsu1O",
+    "outputId": "6e3f1059-831c-471d-c90e-1edd72d120df"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['mueller',\n",
+       " 'spokesman',\n",
+       " 'just',\n",
+       " 'f-cked',\n",
+       " 'up',\n",
+       " 'donald',\n",
+       " 'trump‚s',\n",
+       " 'christmas']"
+      ]
+     },
+     "execution_count": 43,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tokens = nltk.word_tokenize(example)\n",
+    "tokens[:10]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "executionInfo": {
+     "elapsed": 258,
+     "status": "ok",
+     "timestamp": 1737043600637,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "qapo_oJmsuwA",
+    "outputId": "af9287e8-7457-4f20-a5aa-cadff5d2747b"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "8"
+      ]
+     },
+     "execution_count": 44,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(tokens)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "IEvuPbne5NNi"
+   },
+   "source": [
+    "**Tokenization** of the Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 206
+    },
+    "executionInfo": {
+     "elapsed": 8886,
+     "status": "ok",
+     "timestamp": 1737043609521,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "COkg0OwssupK",
+    "outputId": "06bd3182-23e5-4316-bd07-1ff513ce86a4"
+   },
+   "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>classification</th>\n",
+       "      <th>news</th>\n",
+       "      <th>tokens</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>drunk bragging trump staffer started russian c...</td>\n",
+       "      <td>[drunk, bragging, trump, staffer, started, rus...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0</td>\n",
+       "      <td>sheriff david clarke becomes an internet joke ...</td>\n",
+       "      <td>[sheriff, david, clarke, becomes, an, internet...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0</td>\n",
+       "      <td>trump is so obsessed he even has obamas name c...</td>\n",
+       "      <td>[trump, is, so, obsessed, he, even, has, obama...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0</td>\n",
+       "      <td>pope francis just called out donald trump duri...</td>\n",
+       "      <td>[pope, francis, just, called, out, donald, tru...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0</td>\n",
+       "      <td>racist alabama cops brutalize black boy while ...</td>\n",
+       "      <td>[racist, alabama, cops, brutalize, black, boy,...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   classification                                               news  \\\n",
+       "0               0  drunk bragging trump staffer started russian c...   \n",
+       "1               0  sheriff david clarke becomes an internet joke ...   \n",
+       "2               0  trump is so obsessed he even has obamas name c...   \n",
+       "3               0  pope francis just called out donald trump duri...   \n",
+       "4               0  racist alabama cops brutalize black boy while ...   \n",
+       "\n",
+       "                                              tokens  \n",
+       "0  [drunk, bragging, trump, staffer, started, rus...  \n",
+       "1  [sheriff, david, clarke, becomes, an, internet...  \n",
+       "2  [trump, is, so, obsessed, he, even, has, obama...  \n",
+       "3  [pope, francis, just, called, out, donald, tru...  \n",
+       "4  [racist, alabama, cops, brutalize, black, boy,...  "
+      ]
+     },
+     "execution_count": 45,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['tokens'] = df['news'].apply(nltk.word_tokenize)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "executionInfo": {
+     "elapsed": 11,
+     "status": "ok",
+     "timestamp": 1737043609521,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "tEvDCx9Vsug2",
+    "outputId": "1f2010bf-2747-4960-df92-d81d494b8b31"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['classification', 'news', 'tokens'], dtype='object')"
+      ]
+     },
+     "execution_count": 46,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.columns"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "LsHxwDy7rirN"
+   },
+   "source": [
+    "NLTK Download packages"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "executionInfo": {
+     "elapsed": 8,
+     "status": "ok",
+     "timestamp": 1737043609521,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "1mPwai4brf3P",
+    "outputId": "e055aa1f-b041-4757-f00b-b4efc5c1c81a"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[nltk_data] Downloading package averaged_perceptron_tagger_eng to\n",
+      "[nltk_data]     C:\\Users\\ggsan\\AppData\\Roaming\\nltk_data...\n",
+      "[nltk_data]   Package averaged_perceptron_tagger_eng is already up-to-\n",
+      "[nltk_data]       date!\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 47,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import nltk\n",
+    "nltk.download('averaged_perceptron_tagger_eng') # This is a resource to determine the part-of-speech of a word."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 41828,
+     "status": "ok",
+     "timestamp": 1737043651345,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "iXpJ48KSrzyz"
+   },
+   "outputs": [],
+   "source": [
+    "df['pos_tags'] = df['tokens'].apply(lambda tokens: nltk.pos_tag(tokens, lang='eng'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 206
+    },
+    "executionInfo": {
+     "elapsed": 8,
+     "status": "ok",
+     "timestamp": 1737043651346,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "oiDKwfLCrzu6",
+    "outputId": "3a8c0581-2eee-4e90-bb62-7b58245ad331"
+   },
+   "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>classification</th>\n",
+       "      <th>news</th>\n",
+       "      <th>tokens</th>\n",
+       "      <th>pos_tags</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>21050</th>\n",
+       "      <td>1</td>\n",
+       "      <td>vatican would see us paris deal exit as slap i...</td>\n",
+       "      <td>[vatican, would, see, us, paris, deal, exit, a...</td>\n",
+       "      <td>[(vatican, JJ), (would, MD), (see, VB), (us, P...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>22340</th>\n",
+       "      <td>1</td>\n",
+       "      <td>key democrat cites profound doubt about intell...</td>\n",
+       "      <td>[key, democrat, cites, profound, doubt, about,...</td>\n",
+       "      <td>[(key, JJ), (democrat, NN), (cites, NNS), (pro...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2075</th>\n",
+       "      <td>0</td>\n",
+       "      <td>ivanka trump just actually became our new firs...</td>\n",
+       "      <td>[ivanka, trump, just, actually, became, our, n...</td>\n",
+       "      <td>[(ivanka, JJ), (trump, NN), (just, RB), (actua...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27408</th>\n",
+       "      <td>1</td>\n",
+       "      <td>us capitol replacing flag display over confede...</td>\n",
+       "      <td>[us, capitol, replacing, flag, display, over, ...</td>\n",
+       "      <td>[(us, PRP), (capitol, VBP), (replacing, VBG), ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>30584</th>\n",
+       "      <td>1</td>\n",
+       "      <td>spd leader promises to push germany to embrace...</td>\n",
+       "      <td>[spd, leader, promises, to, push, germany, to,...</td>\n",
+       "      <td>[(spd, JJ), (leader, NN), (promises, NNS), (to...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       classification                                               news  \\\n",
+       "21050               1  vatican would see us paris deal exit as slap i...   \n",
+       "22340               1  key democrat cites profound doubt about intell...   \n",
+       "2075                0  ivanka trump just actually became our new firs...   \n",
+       "27408               1  us capitol replacing flag display over confede...   \n",
+       "30584               1  spd leader promises to push germany to embrace...   \n",
+       "\n",
+       "                                                  tokens  \\\n",
+       "21050  [vatican, would, see, us, paris, deal, exit, a...   \n",
+       "22340  [key, democrat, cites, profound, doubt, about,...   \n",
+       "2075   [ivanka, trump, just, actually, became, our, n...   \n",
+       "27408  [us, capitol, replacing, flag, display, over, ...   \n",
+       "30584  [spd, leader, promises, to, push, germany, to,...   \n",
+       "\n",
+       "                                                pos_tags  \n",
+       "21050  [(vatican, JJ), (would, MD), (see, VB), (us, P...  \n",
+       "22340  [(key, JJ), (democrat, NN), (cites, NNS), (pro...  \n",
+       "2075   [(ivanka, JJ), (trump, NN), (just, RB), (actua...  \n",
+       "27408  [(us, PRP), (capitol, VBP), (replacing, VBG), ...  \n",
+       "30584  [(spd, JJ), (leader, NN), (promises, NNS), (to...  "
+      ]
+     },
+     "execution_count": 49,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.sample(5)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "7sqBWc8jtZ5E"
+   },
+   "source": [
+    "**Stemming** the Data with Porter Stemmer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 6,
+     "status": "ok",
+     "timestamp": 1737043651346,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "nnHbSLs7sFDr"
+   },
+   "outputs": [],
+   "source": [
+    "from nltk.stem import PorterStemmer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 6,
+     "status": "ok",
+     "timestamp": 1737043651346,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "Pom5ykR9rzq-"
+   },
+   "outputs": [],
+   "source": [
+    "ps = PorterStemmer()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 6177,
+     "status": "ok",
+     "timestamp": 1737043657517,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "46nXeDaEso6K"
+   },
+   "outputs": [],
+   "source": [
+    "# Applying Stemmed to tokens\n",
+    "df['stemmed'] = df['tokens'].apply(lambda tokens_list: [ps.stem(word) for word in tokens_list])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 206
+    },
+    "executionInfo": {
+     "elapsed": 15,
+     "status": "ok",
+     "timestamp": 1737043657518,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "SyrqD53ysJau",
+    "outputId": "47d17fed-8a06-4212-edab-f2042ea69272"
+   },
+   "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>classification</th>\n",
+       "      <th>news</th>\n",
+       "      <th>tokens</th>\n",
+       "      <th>pos_tags</th>\n",
+       "      <th>stemmed</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>13947</th>\n",
+       "      <td>0</td>\n",
+       "      <td>obamas epa gestapo to skip hearing on co mine</td>\n",
+       "      <td>[obamas, epa, gestapo, to, skip, hearing, on, ...</td>\n",
+       "      <td>[(obamas, RB), (epa, JJ), (gestapo, NN), (to, ...</td>\n",
+       "      <td>[obama, epa, gestapo, to, skip, hear, on, co, ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32242</th>\n",
+       "      <td>1</td>\n",
+       "      <td>china foreign minister to visit myanmar amid r...</td>\n",
+       "      <td>[china, foreign, minister, to, visit, myanmar,...</td>\n",
+       "      <td>[(china, NNS), (foreign, JJ), (minister, NN), ...</td>\n",
+       "      <td>[china, foreign, minist, to, visit, myanmar, a...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9832</th>\n",
+       "      <td>0</td>\n",
+       "      <td>look who the view hired to replace only conser...</td>\n",
+       "      <td>[look, who, the, view, hired, to, replace, onl...</td>\n",
+       "      <td>[(look, NN), (who, WP), (the, DT), (view, NN),...</td>\n",
+       "      <td>[look, who, the, view, hire, to, replac, onli,...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17856</th>\n",
+       "      <td>1</td>\n",
+       "      <td>us appeals court hears arguments on trump trav...</td>\n",
+       "      <td>[us, appeals, court, hears, arguments, on, tru...</td>\n",
+       "      <td>[(us, PRP), (appeals, NNS), (court, NN), (hear...</td>\n",
+       "      <td>[us, appeal, court, hear, argument, on, trump,...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11913</th>\n",
+       "      <td>0</td>\n",
+       "      <td>prince charles uses christmas radio broadcast ...</td>\n",
+       "      <td>[prince, charles, uses, christmas, radio, broa...</td>\n",
+       "      <td>[(prince, NN), (charles, NNS), (uses, VBZ), (c...</td>\n",
+       "      <td>[princ, charl, use, christma, radio, broadcast...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       classification                                               news  \\\n",
+       "13947               0      obamas epa gestapo to skip hearing on co mine   \n",
+       "32242               1  china foreign minister to visit myanmar amid r...   \n",
+       "9832                0  look who the view hired to replace only conser...   \n",
+       "17856               1  us appeals court hears arguments on trump trav...   \n",
+       "11913               0  prince charles uses christmas radio broadcast ...   \n",
+       "\n",
+       "                                                  tokens  \\\n",
+       "13947  [obamas, epa, gestapo, to, skip, hearing, on, ...   \n",
+       "32242  [china, foreign, minister, to, visit, myanmar,...   \n",
+       "9832   [look, who, the, view, hired, to, replace, onl...   \n",
+       "17856  [us, appeals, court, hears, arguments, on, tru...   \n",
+       "11913  [prince, charles, uses, christmas, radio, broa...   \n",
+       "\n",
+       "                                                pos_tags  \\\n",
+       "13947  [(obamas, RB), (epa, JJ), (gestapo, NN), (to, ...   \n",
+       "32242  [(china, NNS), (foreign, JJ), (minister, NN), ...   \n",
+       "9832   [(look, NN), (who, WP), (the, DT), (view, NN),...   \n",
+       "17856  [(us, PRP), (appeals, NNS), (court, NN), (hear...   \n",
+       "11913  [(prince, NN), (charles, NNS), (uses, VBZ), (c...   \n",
+       "\n",
+       "                                                 stemmed  \n",
+       "13947  [obama, epa, gestapo, to, skip, hear, on, co, ...  \n",
+       "32242  [china, foreign, minist, to, visit, myanmar, a...  \n",
+       "9832   [look, who, the, view, hire, to, replac, onli,...  \n",
+       "17856  [us, appeal, court, hear, argument, on, trump,...  \n",
+       "11913  [princ, charl, use, christma, radio, broadcast...  "
+      ]
+     },
+     "execution_count": 53,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.sample(5)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "ni3RROR0tsWO"
+   },
+   "source": [
+    "**Lemmatization** the Data with wordnet"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "executionInfo": {
+     "elapsed": 12,
+     "status": "ok",
+     "timestamp": 1737043657518,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "oRYIdmKXsJW3",
+    "outputId": "3bd278cd-9986-4208-f0bd-1cf15f2bdef9"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[nltk_data] Downloading package wordnet to\n",
+      "[nltk_data]     C:\\Users\\ggsan\\AppData\\Roaming\\nltk_data...\n",
+      "[nltk_data]   Package wordnet is already up-to-date!\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 54,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "nltk.download('wordnet')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 9,
+     "status": "ok",
+     "timestamp": 1737043657518,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "4MnMhQK_sJTS"
+   },
+   "outputs": [],
+   "source": [
+    "from nltk.stem import WordNetLemmatizer # lemmatize\n",
+    "from nltk.corpus import wordnet # wordnet is a lexical database for the English language"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 8,
+     "status": "ok",
+     "timestamp": 1737043657518,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "J30B_OGisJQI"
+   },
+   "outputs": [],
+   "source": [
+    "lemmatizer = WordNetLemmatizer()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 35055,
+     "status": "ok",
+     "timestamp": 1737043692565,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "KdZWRnuru802"
+   },
+   "outputs": [],
+   "source": [
+    "# Applying lemmatiz to Stemmed\n",
+    "df['lemmatized'] = df['stemmed'].apply(lambda tokens_list: [lemmatizer.lemmatize(word, pos=map_pos_tag(word)) for word in tokens_list])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 293
+    },
+    "executionInfo": {
+     "elapsed": 23,
+     "status": "ok",
+     "timestamp": 1737043692567,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "4EF6zBxfsJF9",
+    "outputId": "2e30fd83-4728-46f8-85e1-3635ad5eccd8"
+   },
+   "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>classification</th>\n",
+       "      <th>news</th>\n",
+       "      <th>tokens</th>\n",
+       "      <th>pos_tags</th>\n",
+       "      <th>stemmed</th>\n",
+       "      <th>lemmatized</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1560</th>\n",
+       "      <td>0</td>\n",
+       "      <td>trump hired flynn after obama specifically war...</td>\n",
+       "      <td>[trump, hired, flynn, after, obama, specifical...</td>\n",
+       "      <td>[(trump, NN), (hired, VBD), (flynn, NN), (afte...</td>\n",
+       "      <td>[trump, hire, flynn, after, obama, specif, war...</td>\n",
+       "      <td>[trump, hire, flynn, after, obama, specif, war...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2429</th>\n",
+       "      <td>0</td>\n",
+       "      <td>swedish police appalled at level of deception ...</td>\n",
+       "      <td>[swedish, police, appalled, at, level, of, dec...</td>\n",
+       "      <td>[(swedish, JJ), (police, NN), (appalled, VBD),...</td>\n",
+       "      <td>[swedish, polic, appal, at, level, of, decept,...</td>\n",
+       "      <td>[swedish, polic, appal, at, level, of, decept,...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>21969</th>\n",
+       "      <td>1</td>\n",
+       "      <td>russian tv says us missile strikes on syria de...</td>\n",
+       "      <td>[russian, tv, says, us, missile, strikes, on, ...</td>\n",
+       "      <td>[(russian, JJ), (tv, NN), (says, VBZ), (us, PR...</td>\n",
+       "      <td>[russian, tv, say, us, missil, strike, on, syr...</td>\n",
+       "      <td>[russian, tv, say, u, missil, strike, on, syri...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9389</th>\n",
+       "      <td>0</td>\n",
+       "      <td>democrat senator al franken thought it would b...</td>\n",
+       "      <td>[democrat, senator, al, franken, thought, it, ...</td>\n",
+       "      <td>[(democrat, NNS), (senator, VBP), (al, IN), (f...</td>\n",
+       "      <td>[democrat, senat, al, franken, thought, it, wo...</td>\n",
+       "      <td>[democrat, senat, al, franken, thought, it, wo...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>30775</th>\n",
+       "      <td>1</td>\n",
+       "      <td>saleh was killed in rpg gun attack on his car ...</td>\n",
+       "      <td>[saleh, was, killed, in, rpg, gun, attack, on,...</td>\n",
+       "      <td>[(saleh, NN), (was, VBD), (killed, VBN), (in, ...</td>\n",
+       "      <td>[saleh, wa, kill, in, rpg, gun, attack, on, hi...</td>\n",
+       "      <td>[saleh, wa, kill, in, rpg, gun, attack, on, hi...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       classification                                               news  \\\n",
+       "1560                0  trump hired flynn after obama specifically war...   \n",
+       "2429                0  swedish police appalled at level of deception ...   \n",
+       "21969               1  russian tv says us missile strikes on syria de...   \n",
+       "9389                0  democrat senator al franken thought it would b...   \n",
+       "30775               1  saleh was killed in rpg gun attack on his car ...   \n",
+       "\n",
+       "                                                  tokens  \\\n",
+       "1560   [trump, hired, flynn, after, obama, specifical...   \n",
+       "2429   [swedish, police, appalled, at, level, of, dec...   \n",
+       "21969  [russian, tv, says, us, missile, strikes, on, ...   \n",
+       "9389   [democrat, senator, al, franken, thought, it, ...   \n",
+       "30775  [saleh, was, killed, in, rpg, gun, attack, on,...   \n",
+       "\n",
+       "                                                pos_tags  \\\n",
+       "1560   [(trump, NN), (hired, VBD), (flynn, NN), (afte...   \n",
+       "2429   [(swedish, JJ), (police, NN), (appalled, VBD),...   \n",
+       "21969  [(russian, JJ), (tv, NN), (says, VBZ), (us, PR...   \n",
+       "9389   [(democrat, NNS), (senator, VBP), (al, IN), (f...   \n",
+       "30775  [(saleh, NN), (was, VBD), (killed, VBN), (in, ...   \n",
+       "\n",
+       "                                                 stemmed  \\\n",
+       "1560   [trump, hire, flynn, after, obama, specif, war...   \n",
+       "2429   [swedish, polic, appal, at, level, of, decept,...   \n",
+       "21969  [russian, tv, say, us, missil, strike, on, syr...   \n",
+       "9389   [democrat, senat, al, franken, thought, it, wo...   \n",
+       "30775  [saleh, wa, kill, in, rpg, gun, attack, on, hi...   \n",
+       "\n",
+       "                                              lemmatized  \n",
+       "1560   [trump, hire, flynn, after, obama, specif, war...  \n",
+       "2429   [swedish, polic, appal, at, level, of, decept,...  \n",
+       "21969  [russian, tv, say, u, missil, strike, on, syri...  \n",
+       "9389   [democrat, senat, al, franken, thought, it, wo...  \n",
+       "30775  [saleh, wa, kill, in, rpg, gun, attack, on, hi...  "
+      ]
+     },
+     "execution_count": 58,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.sample(5)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "iFMW_pxnzzXw"
+   },
+   "source": [
+    "**StopWord Removal**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 21,
+     "status": "ok",
+     "timestamp": 1737043692567,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "YrDQgOensJCh"
+   },
+   "outputs": [],
+   "source": [
+    "from nltk.corpus import stopwords"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "executionInfo": {
+     "elapsed": 20,
+     "status": "ok",
+     "timestamp": 1737043692567,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "uNWkgAV-sI_L",
+    "outputId": "5636c480-1423-4d4d-e242-13680fa58e15"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[nltk_data] Downloading package stopwords to\n",
+      "[nltk_data]     C:\\Users\\ggsan\\AppData\\Roaming\\nltk_data...\n",
+      "[nltk_data]   Package stopwords is already up-to-date!\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 60,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "nltk.download('stopwords')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 36891,
+     "status": "ok",
+     "timestamp": 1737043869298,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "ZvBj9gH3sI71"
+   },
+   "outputs": [],
+   "source": [
+    "df['news_w_out_sw'] = df['lemmatized'].apply(lambda tokens_list: [word for word in tokens_list if word not in stopwords.words('english')])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 196
+    },
+    "executionInfo": {
+     "elapsed": 268,
+     "status": "ok",
+     "timestamp": 1737043872604,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "-6S7Ygz8sI4s",
+    "outputId": "b10b10b6-8e0d-4cb6-87bb-b06ecdd2b6a5"
+   },
+   "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>classification</th>\n",
+       "      <th>news</th>\n",
+       "      <th>tokens</th>\n",
+       "      <th>pos_tags</th>\n",
+       "      <th>stemmed</th>\n",
+       "      <th>lemmatized</th>\n",
+       "      <th>news_w_out_sw</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>13536</th>\n",
+       "      <td>0</td>\n",
+       "      <td>btch of benghazi wins democrat nomination im e...</td>\n",
+       "      <td>[btch, of, benghazi, wins, democrat, nominatio...</td>\n",
+       "      <td>[(btch, NN), (of, IN), (benghazi, NN), (wins, ...</td>\n",
+       "      <td>[btch, of, benghazi, win, democrat, nomin, im,...</td>\n",
+       "      <td>[btch, of, benghazi, win, democrat, nomin, im,...</td>\n",
+       "      <td>[btch, benghazi, win, democrat, nomin, im, enc...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>30250</th>\n",
+       "      <td>1</td>\n",
+       "      <td>mexico rightleft coalition presents bid to run...</td>\n",
+       "      <td>[mexico, rightleft, coalition, presents, bid, ...</td>\n",
+       "      <td>[(mexico, NN), (rightleft, NN), (coalition, NN...</td>\n",
+       "      <td>[mexico, rightleft, coalit, present, bid, to, ...</td>\n",
+       "      <td>[mexico, rightleft, coalit, present, bid, to, ...</td>\n",
+       "      <td>[mexico, rightleft, coalit, present, bid, run,...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13831</th>\n",
+       "      <td>0</td>\n",
+       "      <td>trumps got em on the run rhode island supporte...</td>\n",
+       "      <td>[trumps, got, em, on, the, run, rhode, island,...</td>\n",
+       "      <td>[(trumps, NNS), (got, VBD), (em, RB), (on, IN)...</td>\n",
+       "      <td>[trump, got, em, on, the, run, rhode, island, ...</td>\n",
+       "      <td>[trump, get, em, on, the, run, rhode, island, ...</td>\n",
+       "      <td>[trump, get, em, run, rhode, island, support, ...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       classification                                               news  \\\n",
+       "13536               0  btch of benghazi wins democrat nomination im e...   \n",
+       "30250               1  mexico rightleft coalition presents bid to run...   \n",
+       "13831               0  trumps got em on the run rhode island supporte...   \n",
+       "\n",
+       "                                                  tokens  \\\n",
+       "13536  [btch, of, benghazi, wins, democrat, nominatio...   \n",
+       "30250  [mexico, rightleft, coalition, presents, bid, ...   \n",
+       "13831  [trumps, got, em, on, the, run, rhode, island,...   \n",
+       "\n",
+       "                                                pos_tags  \\\n",
+       "13536  [(btch, NN), (of, IN), (benghazi, NN), (wins, ...   \n",
+       "30250  [(mexico, NN), (rightleft, NN), (coalition, NN...   \n",
+       "13831  [(trumps, NNS), (got, VBD), (em, RB), (on, IN)...   \n",
+       "\n",
+       "                                                 stemmed  \\\n",
+       "13536  [btch, of, benghazi, win, democrat, nomin, im,...   \n",
+       "30250  [mexico, rightleft, coalit, present, bid, to, ...   \n",
+       "13831  [trump, got, em, on, the, run, rhode, island, ...   \n",
+       "\n",
+       "                                              lemmatized  \\\n",
+       "13536  [btch, of, benghazi, win, democrat, nomin, im,...   \n",
+       "30250  [mexico, rightleft, coalit, present, bid, to, ...   \n",
+       "13831  [trump, get, em, on, the, run, rhode, island, ...   \n",
+       "\n",
+       "                                           news_w_out_sw  \n",
+       "13536  [btch, benghazi, win, democrat, nomin, im, enc...  \n",
+       "30250  [mexico, rightleft, coalit, present, bid, run,...  \n",
+       "13831  [trump, get, em, run, rhode, island, support, ...  "
+      ]
+     },
+     "execution_count": 62,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.sample(3)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Spliting the data**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "df_class\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "classification\n",
+       "0    17571\n",
+       "1    16580\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 63,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_class"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "classification\n",
+       "0    0.514509\n",
+       "1    0.485491\n",
+       "Name: count, dtype: float64"
+      ]
+     },
+     "execution_count": 64,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "frequency_class"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 34151 entries, 0 to 34150\n",
+      "Data columns (total 7 columns):\n",
+      " #   Column          Non-Null Count  Dtype \n",
+      "---  ------          --------------  ----- \n",
+      " 0   classification  34151 non-null  int64 \n",
+      " 1   news            34151 non-null  object\n",
+      " 2   tokens          34151 non-null  object\n",
+      " 3   pos_tags        34151 non-null  object\n",
+      " 4   stemmed         34151 non-null  object\n",
+      " 5   lemmatized      34151 non-null  object\n",
+      " 6   news_w_out_sw   34151 non-null  object\n",
+      "dtypes: int64(1), object(6)\n",
+      "memory usage: 1.8+ MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "classification    0\n",
+       "news              0\n",
+       "tokens            0\n",
+       "pos_tags          0\n",
+       "stemmed           0\n",
+       "lemmatized        0\n",
+       "news_w_out_sw     0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 66,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isna().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 67,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 34151 * 0.8 #  result = 27320.800000000003 *"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# train_data = df.sample(1000)\n",
+    "# test_data = df.sample(1000)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "4PtRWPeF4d62"
+   },
+   "source": [
+    "***4*** . **Feature extraction**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "g7KdqJai5Ru-"
+   },
+   "source": [
+    "**Bag-of words** vectorization"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 69,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 222,
+     "status": "ok",
+     "timestamp": 1737044176425,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "t-kScL4rsIy1"
+   },
+   "outputs": [],
+   "source": [
+    "from sklearn.feature_extraction.text import CountVectorizer\n",
+    "\n",
+    "# Join tokens back into strings\n",
+    "df['news_w_out_sw_joined'] = df['news_w_out_sw'].apply(lambda tokens: ' '.join(tokens))\n",
+    "\n",
+    "# Initialize CountVectorizer\n",
+    "vectorizer = CountVectorizer()\n",
+    "\n",
+    "# Fit and transform text data\n",
+    "X = vectorizer.fit_transform(df['news_w_out_sw_joined'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 70,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "\n",
+    "# Initialize TfidfVectorizer\n",
+    "tfidf = TfidfVectorizer()\n",
+    "\n",
+    "# Fit and transform text data\n",
+    "X = tfidf.fit_transform(df['news_w_out_sw_joined'])\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "***5*** . **Model**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 71,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 5,
+     "status": "aborted",
+     "timestamp": 1737043692785,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "2WiqsM400ALS"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Train data size: 27320\n",
+      "Test data size: 6831\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "\n",
+    "# train test split\n",
+    "train_data, test_data = train_test_split(df, test_size=0.2, random_state=42)\n",
+    "\n",
+    "# Check the sizes of the splits\n",
+    "print(f\"Train data size: {len(train_data)}\")\n",
+    "print(f\"Test data size: {len(test_data)}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 4,
+     "status": "aborted",
+     "timestamp": 1737043692785,
+     "user": {
+      "displayName": "Tiago Santos",
+      "userId": "01739492997383215152"
+     },
+     "user_tz": 0
+    },
+    "id": "9YGp28uQsIpe"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Training data class\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "classification\n",
+       "0    14054\n",
+       "1    13266\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 72,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Ensure the column names are standardized\n",
+    "clean_data(train_data)\n",
+    "\n",
+    "# Rename the columns if necessary\n",
+    "train_data.rename(columns={'0': 'classification', '1': 'news_w_out_sw_joined'}, inplace=True)\n",
+    "\n",
+    "# Now access the 'classification' column\n",
+    "print(f\"Training data class\")\n",
+    "train_data[\"classification\"].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 73,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Test data class\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "classification\n",
+       "0    3517\n",
+       "1    3314\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 73,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Ensure the column names are standardized\n",
+    "clean_data(test_data)\n",
+    "\n",
+    "# Select only the relevant columns\n",
+    "test_data = test_data[['classification', 'news_w_out_sw_joined']]\n",
+    "\n",
+    "# Now access the 'classification' column\n",
+    "print(f\"Test data class\")\n",
+    "test_data[\"classification\"].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 74,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "\n",
+    "# Define X_train and X_test\n",
+    "X_train = train_data['news_w_out_sw_joined']\n",
+    "X_test = test_data['news_w_out_sw_joined']\n",
+    "\n",
+    "# Initialize the vectorizer\n",
+    "vectorizer = TfidfVectorizer(max_features=5000)\n",
+    "\n",
+    "# Transform the text data\n",
+    "X_train_vectorized = vectorizer.fit_transform(X_train)\n",
+    "X_test_vectorized = vectorizer.transform(X_test)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 75,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "from sklearn.metrics import classification_report, accuracy_score\n",
+    "\n",
+    "# Define y_train and y_test\n",
+    "y_train = train_data['classification']\n",
+    "y_test = test_data['classification']\n",
+    "\n",
+    "# Initialize and train the classifier\n",
+    "classifier = RandomForestClassifier()\n",
+    "classifier.fit(X_train_vectorized, y_train)\n",
+    "\n",
+    "# Make predictions\n",
+    "y_pred = classifier.predict(X_test_vectorized)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 76,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.8997218562435954\n",
+      "\n",
+      "Classification Report:\n",
+      "               precision    recall  f1-score   support\n",
+      "\n",
+      "           0       0.90      0.91      0.90      3517\n",
+      "           1       0.90      0.89      0.90      3314\n",
+      "\n",
+      "    accuracy                           0.90      6831\n",
+      "   macro avg       0.90      0.90      0.90      6831\n",
+      "weighted avg       0.90      0.90      0.90      6831\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Evaluate the model\n",
+    "print(\"Accuracy:\", accuracy_score(y_test, y_pred))\n",
+    "print(\"\\nClassification Report:\\n\", classification_report(y_test, y_pred))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 98,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 600x400 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from sklearn.metrics import confusion_matrix\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "\n",
+    "# Define class names\n",
+    "class_names = ['Class 0', 'Class 1']  # Update this list based on your actual class names\n",
+    "\n",
+    "# Confusion matrix\n",
+    "conf_matrix = confusion_matrix(y_test, y_pred)\n",
+    "\n",
+    "# Plot the confusion matrix\n",
+    "plt.figure(figsize=(6, 4))\n",
+    "sns.heatmap(conf_matrix, annot=True, fmt='d', cmap='Blues', xticklabels=class_names, yticklabels=class_names)\n",
+    "plt.xlabel('Predicted')\n",
+    "plt.ylabel('Actual')\n",
+    "plt.title('Confusion Matrix')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "***6*** . **try other Models**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 77,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Initialize the model\n",
+    "rf = RandomForestClassifier(random_state=42)\n",
+    "\n",
+    "# Train the model\n",
+    "rf.fit(X_train_vectorized, y_train)\n",
+    "\n",
+    "# Predict on the test set\n",
+    "y_pred = rf.predict(X_test_vectorized)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 78,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.8954765041721563\n"
+     ]
+    }
+   ],
+   "source": [
+    "rf = RandomForestClassifier(\n",
+    "    n_estimators=200,\n",
+    "    max_depth=200,\n",
+    "    min_samples_split=5,\n",
+    "    min_samples_leaf=1,\n",
+    "    random_state=42\n",
+    ")\n",
+    "rf.fit(X_train_vectorized, y_train)\n",
+    "y_pred = rf.predict(X_test_vectorized)\n",
+    "print(f\"Accuracy: {accuracy_score(y_test, y_pred)}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 80,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#from sklearn.model_selection import GridSearchCV\n",
+    "\n",
+    "# param_grid = {\n",
+    "#    'n_estimators': [200, 500, 1000],\n",
+    "#    'max_depth': [50, 100, 200],\n",
+    "#    'min_samples_split': [2, 5, 10],\n",
+    "#    'min_samples_leaf': [1, 2, 5]\n",
+    "#}\n",
+    "\n",
+    "#grid_search = GridSearchCV(\n",
+    "#    estimator=RandomForestClassifier(random_state=42),\n",
+    "#    param_grid=param_grid,\n",
+    "#    cv=5,\n",
+    "#    scoring='accuracy',\n",
+    "#    n_jobs=-1\n",
+    "#)\n",
+    "\n",
+    "#grid_search.fit(X_train_vectorized, y_train)\n",
+    "\n",
+    "#print(f\"Best Parameters: {grid_search.best_params_}\")\n",
+    "#print(f\"Best Accuracy: {grid_search.best_score_}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 81,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "XGBoost Accuracy: 0.8846435368174499\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Ensure xgboost is installed\n",
+    "\n",
+    "from xgboost import XGBClassifier\n",
+    "\n",
+    "xgb = XGBClassifier(random_state=42)\n",
+    "xgb.fit(X_train_vectorized, y_train)\n",
+    "y_pred = xgb.predict(X_test_vectorized)\n",
+    "\n",
+    "print(f\"XGBoost Accuracy: {accuracy_score(y_test, y_pred)}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 82,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Gradient Boosting Accuracy: 0.8230127360562143\n",
+      "\n",
+      "Classification Report:\n",
+      "               precision    recall  f1-score   support\n",
+      "\n",
+      "           0       0.91      0.73      0.81      3517\n",
+      "           1       0.76      0.93      0.84      3314\n",
+      "\n",
+      "    accuracy                           0.82      6831\n",
+      "   macro avg       0.84      0.83      0.82      6831\n",
+      "weighted avg       0.84      0.82      0.82      6831\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.ensemble import GradientBoostingClassifier\n",
+    "from sklearn.metrics import classification_report, accuracy_score\n",
+    "\n",
+    "# Initialize and train the Gradient Boosting classifier\n",
+    "gb = GradientBoostingClassifier(random_state=42)\n",
+    "gb.fit(X_train_vectorized, y_train)\n",
+    "\n",
+    "# Make predictions\n",
+    "y_pred_gb = gb.predict(X_test_vectorized)\n",
+    "\n",
+    "# Evaluate the model\n",
+    "print(\"Gradient Boosting Accuracy:\", accuracy_score(y_test, y_pred_gb))\n",
+    "print(\"\\nClassification Report:\\n\", classification_report(y_test, y_pred_gb))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 84,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#pip install streamlit"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 85,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['vectorizer.pkl']"
+      ]
+     },
+     "execution_count": 85,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import joblib\n",
+    "\n",
+    "# Save the model and vectorizer\n",
+    "joblib.dump(classifier, 'model.pkl')\n",
+    "joblib.dump(vectorizer, 'vectorizer.pkl')\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 86,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2025-01-21 16:49:33.907 WARNING streamlit.runtime.scriptrunner_utils.script_run_context: Thread 'MainThread': missing ScriptRunContext! This warning can be ignored when running in bare mode.\n",
+      "2025-01-21 16:49:34.022 \n",
+      "  \u001b[33m\u001b[1mWarning:\u001b[0m to view this Streamlit app on a browser, run it with the following\n",
+      "  command:\n",
+      "\n",
+      "    streamlit run c:\\Users\\ggsan\\miniconda3\\envs\\IronHack\\Lib\\site-packages\\ipykernel_launcher.py [ARGUMENTS]\n",
+      "2025-01-21 16:49:34.023 Thread 'MainThread': missing ScriptRunContext! This warning can be ignored when running in bare mode.\n",
+      "2025-01-21 16:49:34.023 Thread 'MainThread': missing ScriptRunContext! This warning can be ignored when running in bare mode.\n",
+      "2025-01-21 16:49:34.024 Thread 'MainThread': missing ScriptRunContext! This warning can be ignored when running in bare mode.\n",
+      "2025-01-21 16:49:34.024 Thread 'MainThread': missing ScriptRunContext! This warning can be ignored when running in bare mode.\n",
+      "2025-01-21 16:49:34.025 Thread 'MainThread': missing ScriptRunContext! This warning can be ignored when running in bare mode.\n",
+      "2025-01-21 16:49:34.025 Session state does not function when running a script without `streamlit run`\n",
+      "2025-01-21 16:49:34.027 Thread 'MainThread': missing ScriptRunContext! This warning can be ignored when running in bare mode.\n",
+      "2025-01-21 16:49:34.027 Thread 'MainThread': missing ScriptRunContext! This warning can be ignored when running in bare mode.\n",
+      "2025-01-21 16:49:34.028 Thread 'MainThread': missing ScriptRunContext! This warning can be ignored when running in bare mode.\n",
+      "2025-01-21 16:49:34.028 Thread 'MainThread': missing ScriptRunContext! This warning can be ignored when running in bare mode.\n",
+      "2025-01-21 16:49:34.028 Thread 'MainThread': missing ScriptRunContext! This warning can be ignored when running in bare mode.\n",
+      "2025-01-21 16:49:34.029 Thread 'MainThread': missing ScriptRunContext! This warning can be ignored when running in bare mode.\n",
+      "2025-01-21 16:49:34.029 Thread 'MainThread': missing ScriptRunContext! This warning can be ignored when running in bare mode.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "0"
+      ]
+     },
+     "execution_count": 86,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import streamlit as st\n",
+    "import joblib\n",
+    "\n",
+    "# Load the model and vectorizer\n",
+    "model = joblib.load('model.pkl')\n",
+    "vectorizer = joblib.load('vectorizer.pkl')\n",
+    "\n",
+    "# App title\n",
+    "st.title(\"Fake News Detection App\")\n",
+    "\n",
+    "# Input text box\n",
+    "user_input = st.text_area(\"Enter the news headline:\")\n",
+    "\n",
+    "# Predict button\n",
+    "if st.button(\"Predict\"):\n",
+    "    if user_input.strip():\n",
+    "        # Preprocess and predict\n",
+    "        user_input_vectorized = vectorizer.transform([user_input])\n",
+    "        prediction = model.predict(user_input_vectorized)\n",
+    "        prediction_label = \"Real News\" if prediction[0] == 1 else \"Fake News\"\n",
+    "        st.success(f\"Prediction: {prediction_label}\")\n",
+    "    else:\n",
+    "        st.error(\"Please enter a news headline.\")\n",
+    "0"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "authorship_tag": "ABX9TyPYIwndgNfqsBlnv9Y5j0aO",
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
diff --git a/model.pkl b/model.pkl
new file mode 100644
index 0000000..1deb63f
Binary files /dev/null and b/model.pkl differ
diff --git a/news headline is real or fake news.pdf b/news headline is real or fake news.pdf
new file mode 100644
index 0000000..d1000a4
Binary files /dev/null and b/news headline is real or fake news.pdf differ
diff --git a/vectorizer.pkl b/vectorizer.pkl
new file mode 100644
index 0000000..dfeae1d
Binary files /dev/null and b/vectorizer.pkl differ