Upload 9 files

Dockerfile

@@ -0,0 +1,26 @@
+# 1. Use official Python image
+FROM python:3.12-slim
+
+# 2. Set working directory
+WORKDIR /app
+
+# 3. Install system dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    && rm -rf /var/lib/apt/lists/*
+
+# 4. Copy project files
+COPY . /app
+
+# 5. Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# 6. Download NLTK Data
+RUN python -m nltk.downloader wordnet stopwords
+
+
+# 7. Expose Streamlit Port
+EXPOSE 8501
+
+# 8. Run the Streamlit App
+CMD ["streamlit", "run", "app.py", "--server.address=0.0.0.0"]

LICENSE

@@ -0,0 +1 @@
+

app.py

@@ -0,0 +1,84 @@
+import os
+import pickle
+import streamlit as st 
+import re
+import nltk
+import contractions
+from nltk.corpus import stopwords
+from nltk.stem import WordNetLemmatizer
+nltk.download('wordnet')
+nltk.download('stopwords')
+
+## Setting Page Configuration and Header
+st.set_page_config(
+    page_title="Spam Email Classifier",
+    page_icon="📧",
+    layout="wide",
+) 
+
+st.title("📧 Spam Email Classifier")
+st.write("Enter your email content below and the model will predict whether it is Spam or Ham (Not Spam).")
+
+
+## Preprocessing Function
+def preprocess_text(text):
+
+    # Converting text to lowercase
+    text = text.lower()
+
+    # Removing Extra Spaces
+    text = re.sub(r'\s+', ' ', text).strip()
+
+    # Replacing Numbers with a Token
+    text = re.sub(r'\d+', '<NUM>', text)
+
+    # Normalize Elongated Words
+    text = re.sub(r'(.)\1+', r'\1\1', text) 
+
+    # Expand Contractions (e.g.: weren't => were not)
+    text = contractions.fix(text)
+    
+    # Removing Punctuations and Non-English Charachters
+    text = re.sub(r'[^a-z0-9\s]', '', text) 
+
+    # Lemmatization  
+    words = text.split()
+    lemmatizer = WordNetLemmatizer()
+    words = [lemmatizer.lemmatize(word) for word in words]
+
+    # Returning the Cleaned Text 
+    cleaned_text = ' '.join(words)
+    return cleaned_text
+    
+
+## Loading the Model and Vectorizer
+with open('models/logistic_regression.pkl', "rb") as file:
+    model = pickle.load(file)
+
+with open("models/vectorizer.pkl", "rb") as file:
+    vectorizer = pickle.load(file)
+
+
+## Prediction
+email_text = st.text_area("Email Content:")
+
+if st.button("Predict"):
+
+    if email_text:
+        processed_text = preprocess_text(email_text)
+        vect_text = vectorizer.transform([processed_text])
+        
+        prediction = model.predict(vect_text)[0]
+        prediction_proba = model.predict_proba(vect_text)[0]
+
+        st.subheader("Prediction Result:")
+        if prediction == 1:
+            st.error("🚫 This email is Spam")
+        else:
+            st.success("✅ This email is Not Spam")
+
+        st.subheader("Prediction Probabilities:")
+        st.write(f"Ham: {prediction_proba[0]:.2f}, Spam: {prediction_proba[1]:.2f}")
+
+    else:
+        st.warning("Please enter email content to predict.")

models/logistic_regression.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a739634741c73481ef0b0441469f0dad901a3b67d01284d11b681efa263862
+size 1704165

models/vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01fc04703cb257ef9d48ce94b8ae018bb2c0179e07f73091cf0e5ad8038c3675
+size 4988967

notebooks/Logistic_Regression.ipynb

@@ -0,0 +1,1530 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "17c590a6",
+   "metadata": {},
+   "source": [
+    "## 1. Reading and Exploring Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "fdbfdfe0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "a122aae2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>label</th>\n",
+       "      <th>text</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>ounce feather bowl hummingbird opec moment ala...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>wulvob get your medircations online qnb ikud v...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0</td>\n",
+       "      <td>computer connection from cnn com wednesday es...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1</td>\n",
+       "      <td>university degree obtain a prosperous future m...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0</td>\n",
+       "      <td>thanks for all your answers guys i know i shou...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   label                                               text\n",
+       "0      1  ounce feather bowl hummingbird opec moment ala...\n",
+       "1      1  wulvob get your medircations online qnb ikud v...\n",
+       "2      0   computer connection from cnn com wednesday es...\n",
+       "3      1  university degree obtain a prosperous future m...\n",
+       "4      0  thanks for all your answers guys i know i shou..."
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.read_csv('../data/raw/data.csv')\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "713d51b3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 83448 entries, 0 to 83447\n",
+      "Data columns (total 2 columns):\n",
+      " #   Column  Non-Null Count  Dtype \n",
+      "---  ------  --------------  ----- \n",
+      " 0   label   83448 non-null  int64 \n",
+      " 1   text    83448 non-null  object\n",
+      "dtypes: int64(1), object(1)\n",
+      "memory usage: 1.3+ MB\n"
+     ]
+    }
+   ],
+   "source": [
+    "df.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "9a2f29b3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Number of Null Values = 0\n",
+      "Number of Duplicated Rows = 0\n"
+     ]
+    }
+   ],
+   "source": [
+    "nulls = sum(df.isnull().sum())\n",
+    "duplicated = sum(df.duplicated())\n",
+    "\n",
+    "print(f\"Number of Null Values = {nulls}\")\n",
+    "print(f\"Number of Duplicated Rows = {duplicated}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "78bc23cd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Not Spam    39538\n",
+       "Spam        43910\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Checking Dataset Balance\n",
+    "value_counts = df['label'].value_counts().sort_index()\n",
+    "value_counts.index = ['Not Spam', 'Spam']\n",
+    "\n",
+    "value_counts"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "3f8e082e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.figure(figsize = (8, 5), tight_layout = True)\n",
+    "plt.bar(value_counts.index, value_counts.values, color=['DodgerBlue', 'Crimson'])\n",
+    "\n",
+    "plt.xlabel(\"Label\")\n",
+    "plt.ylabel(\"Count\")\n",
+    "plt.title(\"Value Counts\")\n",
+    "\n",
+    "plt.tight_layout()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8d41f8c8",
+   "metadata": {},
+   "source": [
+    "## 2. Preprocessing"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "37ea4009",
+   "metadata": {},
+   "source": [
+    "## 2.1. Dropping Non-English Rows"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "f8ef682a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langdetect import detect\n",
+    "\n",
+    "def is_english(tweet):\n",
+    "\n",
+    "    try:\n",
+    "        return detect(tweet) == 'en'\n",
+    "\n",
+    "    except:\n",
+    "        return False"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "cc62ea88",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Shape of DataFrame after dropping non-English Emails: (78940, 2)\n"
+     ]
+    },
+    {
+     "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>label</th>\n",
+       "      <th>text</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>ounce feather bowl hummingbird opec moment ala...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>wulvob get your medircations online qnb ikud v...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0</td>\n",
+       "      <td>computer connection from cnn com wednesday es...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1</td>\n",
+       "      <td>university degree obtain a prosperous future m...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0</td>\n",
+       "      <td>thanks for all your answers guys i know i shou...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   label                                               text\n",
+       "0      1  ounce feather bowl hummingbird opec moment ala...\n",
+       "1      1  wulvob get your medircations online qnb ikud v...\n",
+       "2      0   computer connection from cnn com wednesday es...\n",
+       "3      1  university degree obtain a prosperous future m...\n",
+       "4      0  thanks for all your answers guys i know i shou..."
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = df[df['text'].apply(is_english)]\n",
+    "\n",
+    "print(\"Shape of DataFrame after dropping non-English Emails:\", df.shape)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "486a363d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['\\x01', '\\x02', '\\x03', '\\x05', '\\x07', '\\x08', '\\n', '\\x0e', '\\x0f', '\\x10', '\\x11', '\\x12', '\\x13', '\\x14', '\\x15', '\\x16', '\\x17', '\\x19', '\\x1b', ' ', '!', '\"', '#', '$', '%', '&', \"'\", '(', ')', '*', '+', ',', '-', '.', '/', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', ':', ';', '<', '=', '>', '?', '@', '[', '\\\\', ']', '^', '_', '`', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', '{', '|', '}', '~', '\\x7f', '\\x80', '\\x81', '\\x82', '\\x83', '\\x84', '\\x85', '\\x86', '\\x87', '\\x88', '\\x89', '\\x8a', '\\x8b', '\\x8c', '\\x8d', '\\x8e', '\\x8f', '\\x90', '\\x91', '\\x92', '\\x93', '\\x94', '\\x95', '\\x96', '\\x97', '\\x98', '\\x99', '\\x9a', '\\x9b', '\\x9c', '\\x9d', '\\x9e', '\\x9f', '¡', '¢', '£', '¤', '¥', '¦', '§', '¨', '©', 'ª', '«', '¬', '\\xad', '®', '¯', '°', '±', '²', '³', '´', 'µ', '¶', '·', '¸', '¹', 'º', '»', '¼', '½', '¾', '¿', 'À', '×', 'Ü', 'Ý', 'Þ', 'ß', 'à', 'á', 'â', 'ã', 'ä', 'å', 'æ', 'ç', 'è', 'é', 'ê', 'ë', 'ì', 'í', 'î', 'ï', 'ð', 'ñ', 'ò', 'ó', 'ô', 'õ', 'ö', '÷', 'ø', 'ù', 'ú', 'û', 'ü', 'ý', 'þ', 'ÿ', 'ć', 'č', 'ę', 'ğ', 'ī', 'ł', 'ń', 'ś', 'ż', 'ș', 'ɤ', '̇', 'ͨ', 'β', 'θ', 'π', 'а', 'б', 'в', 'г', 'д', 'е', 'ж', 'з', 'и', 'к', 'л', 'м', 'н', 'о', 'п', 'р', 'с', 'т', 'у', 'х', 'ц', 'ч', 'ш', 'щ', 'ъ', 'ь', 'э', 'ю', 'я', 'ё', 'ђ', 'ѕ', 'њ', 'ќ', 'ӿ', 'א', 'ב', 'ו', 'ח', 'י', 'ל', 'ם', 'מ', 'נ', 'פ', 'ר', 'ש', 'ת', 'ث', 'ڶ', 'ṁ', '–', '—', '‘', '’', '“', '”', '†', '‡', '•', '…', '⁄', '€', '№', '™', '−', '∷', '⌂', '☺', '♣', '✗', '。', 'み', 'む', 'も', 'シ', 'デ', 'モ', 'ュ', 'リ', 'ル', 'ン', '・', 'ㄞ', 'ㄢ', '上', '世', '中', '享', '件', '俊', '信', '写', '劎', '大', '子', '小', '我', '拒', '文', '最', '李', '杰', '楊', '用', '电', '界', '的', '系', '统', '膄', '膅', '膆', '道', '邮', 'fi', '（', '）', '', '�']\n"
+     ]
+    }
+   ],
+   "source": [
+    "all_text = ''.join(df['text'].tolist())\n",
+    "unique_letters = sorted(list(set(all_text)))\n",
+    "\n",
+    "print(unique_letters)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1069a4c0",
+   "metadata": {},
+   "source": [
+    "# 2.2. Text Cleaning"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "0d57fec8",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[nltk_data] Downloading package wordnet to /home/mohamed-\n",
+      "[nltk_data]     hamdy/nltk_data...\n",
+      "[nltk_data]   Package wordnet is already up-to-date!\n",
+      "[nltk_data] Downloading package stopwords to /home/mohamed-\n",
+      "[nltk_data]     hamdy/nltk_data...\n",
+      "[nltk_data]   Package stopwords is already up-to-date!\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import re\n",
+    "import nltk\n",
+    "import contractions\n",
+    "from nltk.corpus import stopwords\n",
+    "from nltk.stem import WordNetLemmatizer\n",
+    "\n",
+    "nltk.download('wordnet')\n",
+    "nltk.download('stopwords')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9fd59c29",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def text_cleaning(text):\n",
+    "\n",
+    "    # Converting text to lowercase\n",
+    "    text = text.lower()\n",
+    "\n",
+    "    # Removing Extra Spaces\n",
+    "    text = re.sub(r'\\s+', ' ', text).strip()\n",
+    "\n",
+    "    # Replacing Numbers with a Token\n",
+    "    text = re.sub(r'\\d+', '<NUM>', text)\n",
+    "\n",
+    "    # Normalize Elongated Words\n",
+    "    text = re.sub(r'(.)\\1+', r'\\1\\1', text) \n",
+    "\n",
+    "    # Expand Contractions (e.g.: weren't => were not)\n",
+    "    text = contractions.fix(text)\n",
+    "    \n",
+    "    # Removing Punctuations and Non-English Charachters\n",
+    "    text = re.sub(r'[^a-z0-9\\s]', '', text) \n",
+    "\n",
+    "    # Lemmatization  \n",
+    "    words = text.split()\n",
+    "    lemmatizer = WordNetLemmatizer()\n",
+    "    words = [lemmatizer.lemmatize(word) for word in words]\n",
+    "\n",
+    "    # Returning the Cleaned Text \n",
+    "    cleaned_text = ' '.join(words)\n",
+    "    return cleaned_text"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "4b0d2f0c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0    ounce feather bowl hummingbird opec moment ala...\n",
+       "1    wulvob get your medircations online qnb ikud v...\n",
+       "2    computer connection from cnn com wednesday esc...\n",
+       "3    university degree obtain a prosperous future m...\n",
+       "4    thanks for all your answer guy i know i should...\n",
+       "Name: text, dtype: object"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['text'] = df['text'].apply(text_cleaning)\n",
+    "df['text'].head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "786e21f6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[' ', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z']\n"
+     ]
+    }
+   ],
+   "source": [
+    "all_text = ''.join(df['text'].tolist())\n",
+    "unique_letters = sorted(list(set(all_text)))\n",
+    "\n",
+    "print(unique_letters)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e9d4da45",
+   "metadata": {},
+   "source": [
+    "## 2.3. Train Test Split"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "15306c73",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>label</th>\n",
+       "      <th>text</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>51626</th>\n",
+       "      <td>0</td>\n",
+       "      <td>below is a list of the major item that are sti...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>76658</th>\n",
+       "      <td>0</td>\n",
+       "      <td>escapenumberfxml version escapenumberd escapen...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5491</th>\n",
+       "      <td>1</td>\n",
+       "      <td>our offer are unbeatable and we always update ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6697</th>\n",
+       "      <td>1</td>\n",
+       "      <td>chms pioneering explosive wireless niche in ch...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>66300</th>\n",
+       "      <td>1</td>\n",
+       "      <td>hi there try our market leading product c i a ...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       label                                               text\n",
+       "51626      0  below is a list of the major item that are sti...\n",
+       "76658      0  escapenumberfxml version escapenumberd escapen...\n",
+       "5491       1  our offer are unbeatable and we always update ...\n",
+       "6697       1  chms pioneering explosive wireless niche in ch...\n",
+       "66300      1  hi there try our market leading product c i a ..."
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "\n",
+    "train_df, test_df = train_test_split(\n",
+    "    df, \n",
+    "    test_size = 0.2, \n",
+    "    random_state = 42, \n",
+    "    stratify = df['label'],\n",
+    "    shuffle = True\n",
+    ")\n",
+    "\n",
+    "pd.DataFrame(train_df).to_csv('../data/processed/train.csv', index = False)\n",
+    "pd.DataFrame(test_df).to_csv('../data/processed/test.csv', index = False)\n",
+    "test_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "187269f3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train = train_df['text']\n",
+    "X_test = test_df['text']\n",
+    "y_train = train_df['label']\n",
+    "y_test = test_df['label']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "1ed04b87",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Shape of X_train: (63152,)\n",
+      "Shape of X_test: (15788,)\n",
+      "Shape of y_train: (63152,)\n",
+      "Shape of y_test: (15788,)\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(f\"Shape of X_train: {X_train.shape}\")\n",
+    "print(f\"Shape of X_test: {X_test.shape}\")\n",
+    "print(f\"Shape of y_train: {y_train.shape}\")\n",
+    "print(f\"Shape of y_test: {y_test.shape}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cc846c18",
+   "metadata": {},
+   "source": [
+    "# 2.4. Vectorization"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "a2587078",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Compressed Sparse Row sparse matrix of dtype 'float64'\n",
+       "\twith 5462956 stored elements and shape (63152, 212929)>"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "\n",
+    "vectorizer = TfidfVectorizer(stop_words = 'english')\n",
+    "X_train = vectorizer.fit_transform(X_train) \n",
+    "X_test = vectorizer.transform(X_test)\n",
+    "\n",
+    "X_train "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4b3b4cba",
+   "metadata": {},
+   "source": [
+    "# 3. Model"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a81b3b8c",
+   "metadata": {},
+   "source": [
+    "# 3.1. Training"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "id": "d234d65f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-5 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: #000;\n",
+       "  --sklearn-color-text-muted: #666;\n",
+       "  --sklearn-color-line: gray;\n",
+       "  /* Definition of color scheme for unfitted estimators */\n",
+       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+       "  --sklearn-color-unfitted-level-3: chocolate;\n",
+       "  /* Definition of color scheme for fitted estimators */\n",
+       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+       "\n",
+       "  /* Specific color for light theme */\n",
+       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-icon: #696969;\n",
+       "\n",
+       "  @media (prefers-color-scheme: dark) {\n",
+       "    /* Redefinition of color scheme for dark theme */\n",
+       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-icon: #878787;\n",
+       "  }\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 pre {\n",
+       "  padding: 0;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 input.sk-hidden--visually {\n",
+       "  border: 0;\n",
+       "  clip: rect(1px 1px 1px 1px);\n",
+       "  clip: rect(1px, 1px, 1px, 1px);\n",
+       "  height: 1px;\n",
+       "  margin: -1px;\n",
+       "  overflow: hidden;\n",
+       "  padding: 0;\n",
+       "  position: absolute;\n",
+       "  width: 1px;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 div.sk-dashed-wrapped {\n",
+       "  border: 1px dashed var(--sklearn-color-line);\n",
+       "  margin: 0 0.4em 0.5em 0.4em;\n",
+       "  box-sizing: border-box;\n",
+       "  padding-bottom: 0.4em;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 div.sk-container {\n",
+       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+       "     so we also need the `!important` here to be able to override the\n",
+       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+       "  display: inline-block !important;\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 div.sk-text-repr-fallback {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-parallel-item,\n",
+       "div.sk-serial,\n",
+       "div.sk-item {\n",
+       "  /* draw centered vertical line to link estimators */\n",
+       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+       "  background-size: 2px 100%;\n",
+       "  background-repeat: no-repeat;\n",
+       "  background-position: center center;\n",
+       "}\n",
+       "\n",
+       "/* Parallel-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-5 div.sk-parallel-item::after {\n",
+       "  content: \"\";\n",
+       "  width: 100%;\n",
+       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+       "  flex-grow: 1;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 div.sk-parallel {\n",
+       "  display: flex;\n",
+       "  align-items: stretch;\n",
+       "  justify-content: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 div.sk-parallel-item {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 div.sk-parallel-item:first-child::after {\n",
+       "  align-self: flex-end;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 div.sk-parallel-item:last-child::after {\n",
+       "  align-self: flex-start;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 div.sk-parallel-item:only-child::after {\n",
+       "  width: 0;\n",
+       "}\n",
+       "\n",
+       "/* Serial-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-5 div.sk-serial {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "  align-items: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  padding-right: 1em;\n",
+       "  padding-left: 1em;\n",
+       "}\n",
+       "\n",
+       "\n",
+       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+       "clickable and can be expanded/collapsed.\n",
+       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+       "*/\n",
+       "\n",
+       "/* Pipeline and ColumnTransformer style (default) */\n",
+       "\n",
+       "#sk-container-id-5 div.sk-toggleable {\n",
+       "  /* Default theme specific background. It is overwritten whether we have a\n",
+       "  specific estimator or a Pipeline/ColumnTransformer */\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable label */\n",
+       "#sk-container-id-5 label.sk-toggleable__label {\n",
+       "  cursor: pointer;\n",
+       "  display: flex;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "  align-items: start;\n",
+       "  justify-content: space-between;\n",
+       "  gap: 0.5em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 label.sk-toggleable__label .caption {\n",
+       "  font-size: 0.6rem;\n",
+       "  font-weight: lighter;\n",
+       "  color: var(--sklearn-color-text-muted);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 label.sk-toggleable__label-arrow:before {\n",
+       "  /* Arrow on the left of the label */\n",
+       "  content: \"▸\";\n",
+       "  float: left;\n",
+       "  margin-right: 0.25em;\n",
+       "  color: var(--sklearn-color-icon);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 label.sk-toggleable__label-arrow:hover:before {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable content - dropdown */\n",
+       "\n",
+       "#sk-container-id-5 div.sk-toggleable__content {\n",
+       "  display: none;\n",
+       "  text-align: left;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 div.sk-toggleable__content.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 div.sk-toggleable__content pre {\n",
+       "  margin: 0.2em;\n",
+       "  border-radius: 0.25em;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 div.sk-toggleable__content.fitted pre {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "  /* Expand drop-down */\n",
+       "  display: block;\n",
+       "  width: 100%;\n",
+       "  overflow: visible;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "  content: \"▾\";\n",
+       "}\n",
+       "\n",
+       "/* Pipeline/ColumnTransformer-specific style */\n",
+       "\n",
+       "#sk-container-id-5 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific style */\n",
+       "\n",
+       "/* Colorize estimator box */\n",
+       "#sk-container-id-5 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-5 div.sk-label label {\n",
+       "  /* The background is the default theme color */\n",
+       "  color: var(--sklearn-color-text-on-default-background);\n",
+       "}\n",
+       "\n",
+       "/* On hover, darken the color of the background */\n",
+       "#sk-container-id-5 div.sk-label:hover label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Label box, darken color on hover, fitted */\n",
+       "#sk-container-id-5 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator label */\n",
+       "\n",
+       "#sk-container-id-5 div.sk-label label {\n",
+       "  font-family: monospace;\n",
+       "  font-weight: bold;\n",
+       "  display: inline-block;\n",
+       "  line-height: 1.2em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 div.sk-label-container {\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific */\n",
+       "#sk-container-id-5 div.sk-estimator {\n",
+       "  font-family: monospace;\n",
+       "  border: 1px dotted var(--sklearn-color-border-box);\n",
+       "  border-radius: 0.25em;\n",
+       "  box-sizing: border-box;\n",
+       "  margin-bottom: 0.5em;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 div.sk-estimator.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "/* on hover */\n",
+       "#sk-container-id-5 div.sk-estimator:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 div.sk-estimator.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+       "\n",
+       "/* Common style for \"i\" and \"?\" */\n",
+       "\n",
+       ".sk-estimator-doc-link,\n",
+       "a:link.sk-estimator-doc-link,\n",
+       "a:visited.sk-estimator-doc-link {\n",
+       "  float: right;\n",
+       "  font-size: smaller;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1em;\n",
+       "  height: 1em;\n",
+       "  width: 1em;\n",
+       "  text-decoration: none !important;\n",
+       "  margin-left: 0.5em;\n",
+       "  text-align: center;\n",
+       "  /* unfitted */\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted,\n",
+       "a:link.sk-estimator-doc-link.fitted,\n",
+       "a:visited.sk-estimator-doc-link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "/* Span, style for the box shown on hovering the info icon */\n",
+       ".sk-estimator-doc-link span {\n",
+       "  display: none;\n",
+       "  z-index: 9999;\n",
+       "  position: relative;\n",
+       "  font-weight: normal;\n",
+       "  right: .2ex;\n",
+       "  padding: .5ex;\n",
+       "  margin: .5ex;\n",
+       "  width: min-content;\n",
+       "  min-width: 20ex;\n",
+       "  max-width: 50ex;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  box-shadow: 2pt 2pt 4pt #999;\n",
+       "  /* unfitted */\n",
+       "  background: var(--sklearn-color-unfitted-level-0);\n",
+       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted span {\n",
+       "  /* fitted */\n",
+       "  background: var(--sklearn-color-fitted-level-0);\n",
+       "  border: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link:hover span {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+       "\n",
+       "#sk-container-id-5 a.estimator_doc_link {\n",
+       "  float: right;\n",
+       "  font-size: 1rem;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1rem;\n",
+       "  height: 1rem;\n",
+       "  width: 1rem;\n",
+       "  text-decoration: none;\n",
+       "  /* unfitted */\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 a.estimator_doc_link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "#sk-container-id-5 a.estimator_doc_link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-5 a.estimator_doc_link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".estimator-table summary {\n",
+       "    padding: .5rem;\n",
+       "    font-family: monospace;\n",
+       "    cursor: pointer;\n",
+       "}\n",
+       "\n",
+       ".estimator-table details[open] {\n",
+       "    padding-left: 0.1rem;\n",
+       "    padding-right: 0.1rem;\n",
+       "    padding-bottom: 0.3rem;\n",
+       "}\n",
+       "\n",
+       ".estimator-table .parameters-table {\n",
+       "    margin-left: auto !important;\n",
+       "    margin-right: auto !important;\n",
+       "}\n",
+       "\n",
+       ".estimator-table .parameters-table tr:nth-child(odd) {\n",
+       "    background-color: #fff;\n",
+       "}\n",
+       "\n",
+       ".estimator-table .parameters-table tr:nth-child(even) {\n",
+       "    background-color: #f6f6f6;\n",
+       "}\n",
+       "\n",
+       ".estimator-table .parameters-table tr:hover {\n",
+       "    background-color: #e0e0e0;\n",
+       "}\n",
+       "\n",
+       ".estimator-table table td {\n",
+       "    border: 1px solid rgba(106, 105, 104, 0.232);\n",
+       "}\n",
+       "\n",
+       ".user-set td {\n",
+       "    color:rgb(255, 94, 0);\n",
+       "    text-align: left;\n",
+       "}\n",
+       "\n",
+       ".user-set td.value pre {\n",
+       "    color:rgb(255, 94, 0) !important;\n",
+       "    background-color: transparent !important;\n",
+       "}\n",
+       "\n",
+       ".default td {\n",
+       "    color: black;\n",
+       "    text-align: left;\n",
+       "}\n",
+       "\n",
+       ".user-set td i,\n",
+       ".default td i {\n",
+       "    color: black;\n",
+       "}\n",
+       "\n",
+       ".copy-paste-icon {\n",
+       "    background-image: url(data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCA0NDggNTEyIj48IS0tIUZvbnQgQXdlc29tZSBGcmVlIDYuNy4yIGJ5IEBmb250YXdlc29tZSAtIGh0dHBzOi8vZm9udGF3ZXNvbWUuY29tIExpY2Vuc2UgLSBodHRwczovL2ZvbnRhd2Vzb21lLmNvbS9saWNlbnNlL2ZyZWUgQ29weXJpZ2h0IDIwMjUgRm9udGljb25zLCBJbmMuLS0+PHBhdGggZD0iTTIwOCAwTDMzMi4xIDBjMTIuNyAwIDI0LjkgNS4xIDMzLjkgMTQuMWw2Ny45IDY3LjljOSA5IDE0LjEgMjEuMiAxNC4xIDMzLjlMNDQ4IDMzNmMwIDI2LjUtMjEuNSA0OC00OCA0OGwtMTkyIDBjLTI2LjUgMC00OC0yMS41LTQ4LTQ4bDAtMjg4YzAtMjYuNSAyMS41LTQ4IDQ4LTQ4ek00OCAxMjhsODAgMCAwIDY0LTY0IDAgMCAyNTYgMTkyIDAgMC0zMiA2NCAwIDAgNDhjMCAyNi41LTIxLjUgNDgtNDggNDhMNDggNTEyYy0yNi41IDAtNDgtMjEuNS00OC00OEwwIDE3NmMwLTI2LjUgMjEuNS00OCA0OC00OHoiLz48L3N2Zz4=);\n",
+       "    background-repeat: no-repeat;\n",
+       "    background-size: 14px 14px;\n",
+       "    background-position: 0;\n",
+       "    display: inline-block;\n",
+       "    width: 14px;\n",
+       "    height: 14px;\n",
+       "    cursor: pointer;\n",
+       "}\n",
+       "</style><body><div id=\"sk-container-id-5\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" checked><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>LogisticRegression</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.7/modules/generated/sklearn.linear_model.LogisticRegression.html\">?<span>Documentation for LogisticRegression</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\" data-param-prefix=\"\">\n",
+       "        <div class=\"estimator-table\">\n",
+       "            <details>\n",
+       "                <summary>Parameters</summary>\n",
+       "                <table class=\"parameters-table\">\n",
+       "                  <tbody>\n",
+       "                    \n",
+       "        <tr class=\"default\">\n",
+       "            <td><i class=\"copy-paste-icon\"\n",
+       "                 onclick=\"copyToClipboard('penalty',\n",
+       "                          this.parentElement.nextElementSibling)\"\n",
+       "            ></i></td>\n",
+       "            <td class=\"param\">penalty&nbsp;</td>\n",
+       "            <td class=\"value\">&#x27;l2&#x27;</td>\n",
+       "        </tr>\n",
+       "    \n",
+       "\n",
+       "        <tr class=\"default\">\n",
+       "            <td><i class=\"copy-paste-icon\"\n",
+       "                 onclick=\"copyToClipboard('dual',\n",
+       "                          this.parentElement.nextElementSibling)\"\n",
+       "            ></i></td>\n",
+       "            <td class=\"param\">dual&nbsp;</td>\n",
+       "            <td class=\"value\">False</td>\n",
+       "        </tr>\n",
+       "    \n",
+       "\n",
+       "        <tr class=\"default\">\n",
+       "            <td><i class=\"copy-paste-icon\"\n",
+       "                 onclick=\"copyToClipboard('tol',\n",
+       "                          this.parentElement.nextElementSibling)\"\n",
+       "            ></i></td>\n",
+       "            <td class=\"param\">tol&nbsp;</td>\n",
+       "            <td class=\"value\">0.0001</td>\n",
+       "        </tr>\n",
+       "    \n",
+       "\n",
+       "        <tr class=\"default\">\n",
+       "            <td><i class=\"copy-paste-icon\"\n",
+       "                 onclick=\"copyToClipboard('C',\n",
+       "                          this.parentElement.nextElementSibling)\"\n",
+       "            ></i></td>\n",
+       "            <td class=\"param\">C&nbsp;</td>\n",
+       "            <td class=\"value\">1.0</td>\n",
+       "        </tr>\n",
+       "    \n",
+       "\n",
+       "        <tr class=\"default\">\n",
+       "            <td><i class=\"copy-paste-icon\"\n",
+       "                 onclick=\"copyToClipboard('fit_intercept',\n",
+       "                          this.parentElement.nextElementSibling)\"\n",
+       "            ></i></td>\n",
+       "            <td class=\"param\">fit_intercept&nbsp;</td>\n",
+       "            <td class=\"value\">True</td>\n",
+       "        </tr>\n",
+       "    \n",
+       "\n",
+       "        <tr class=\"default\">\n",
+       "            <td><i class=\"copy-paste-icon\"\n",
+       "                 onclick=\"copyToClipboard('intercept_scaling',\n",
+       "                          this.parentElement.nextElementSibling)\"\n",
+       "            ></i></td>\n",
+       "            <td class=\"param\">intercept_scaling&nbsp;</td>\n",
+       "            <td class=\"value\">1</td>\n",
+       "        </tr>\n",
+       "    \n",
+       "\n",
+       "        <tr class=\"default\">\n",
+       "            <td><i class=\"copy-paste-icon\"\n",
+       "                 onclick=\"copyToClipboard('class_weight',\n",
+       "                          this.parentElement.nextElementSibling)\"\n",
+       "            ></i></td>\n",
+       "            <td class=\"param\">class_weight&nbsp;</td>\n",
+       "            <td class=\"value\">None</td>\n",
+       "        </tr>\n",
+       "    \n",
+       "\n",
+       "        <tr class=\"default\">\n",
+       "            <td><i class=\"copy-paste-icon\"\n",
+       "                 onclick=\"copyToClipboard('random_state',\n",
+       "                          this.parentElement.nextElementSibling)\"\n",
+       "            ></i></td>\n",
+       "            <td class=\"param\">random_state&nbsp;</td>\n",
+       "            <td class=\"value\">None</td>\n",
+       "        </tr>\n",
+       "    \n",
+       "\n",
+       "        <tr class=\"default\">\n",
+       "            <td><i class=\"copy-paste-icon\"\n",
+       "                 onclick=\"copyToClipboard('solver',\n",
+       "                          this.parentElement.nextElementSibling)\"\n",
+       "            ></i></td>\n",
+       "            <td class=\"param\">solver&nbsp;</td>\n",
+       "            <td class=\"value\">&#x27;lbfgs&#x27;</td>\n",
+       "        </tr>\n",
+       "    \n",
+       "\n",
+       "        <tr class=\"default\">\n",
+       "            <td><i class=\"copy-paste-icon\"\n",
+       "                 onclick=\"copyToClipboard('max_iter',\n",
+       "                          this.parentElement.nextElementSibling)\"\n",
+       "            ></i></td>\n",
+       "            <td class=\"param\">max_iter&nbsp;</td>\n",
+       "            <td class=\"value\">100</td>\n",
+       "        </tr>\n",
+       "    \n",
+       "\n",
+       "        <tr class=\"default\">\n",
+       "            <td><i class=\"copy-paste-icon\"\n",
+       "                 onclick=\"copyToClipboard('multi_class',\n",
+       "                          this.parentElement.nextElementSibling)\"\n",
+       "            ></i></td>\n",
+       "            <td class=\"param\">multi_class&nbsp;</td>\n",
+       "            <td class=\"value\">&#x27;deprecated&#x27;</td>\n",
+       "        </tr>\n",
+       "    \n",
+       "\n",
+       "        <tr class=\"default\">\n",
+       "            <td><i class=\"copy-paste-icon\"\n",
+       "                 onclick=\"copyToClipboard('verbose',\n",
+       "                          this.parentElement.nextElementSibling)\"\n",
+       "            ></i></td>\n",
+       "            <td class=\"param\">verbose&nbsp;</td>\n",
+       "            <td class=\"value\">0</td>\n",
+       "        </tr>\n",
+       "    \n",
+       "\n",
+       "        <tr class=\"default\">\n",
+       "            <td><i class=\"copy-paste-icon\"\n",
+       "                 onclick=\"copyToClipboard('warm_start',\n",
+       "                          this.parentElement.nextElementSibling)\"\n",
+       "            ></i></td>\n",
+       "            <td class=\"param\">warm_start&nbsp;</td>\n",
+       "            <td class=\"value\">False</td>\n",
+       "        </tr>\n",
+       "    \n",
+       "\n",
+       "        <tr class=\"default\">\n",
+       "            <td><i class=\"copy-paste-icon\"\n",
+       "                 onclick=\"copyToClipboard('n_jobs',\n",
+       "                          this.parentElement.nextElementSibling)\"\n",
+       "            ></i></td>\n",
+       "            <td class=\"param\">n_jobs&nbsp;</td>\n",
+       "            <td class=\"value\">None</td>\n",
+       "        </tr>\n",
+       "    \n",
+       "\n",
+       "        <tr class=\"default\">\n",
+       "            <td><i class=\"copy-paste-icon\"\n",
+       "                 onclick=\"copyToClipboard('l1_ratio',\n",
+       "                          this.parentElement.nextElementSibling)\"\n",
+       "            ></i></td>\n",
+       "            <td class=\"param\">l1_ratio&nbsp;</td>\n",
+       "            <td class=\"value\">None</td>\n",
+       "        </tr>\n",
+       "    \n",
+       "                  </tbody>\n",
+       "                </table>\n",
+       "            </details>\n",
+       "        </div>\n",
+       "    </div></div></div></div></div><script>function copyToClipboard(text, element) {\n",
+       "    // Get the parameter prefix from the closest toggleable content\n",
+       "    const toggleableContent = element.closest('.sk-toggleable__content');\n",
+       "    const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
+       "    const fullParamName = paramPrefix ? `${paramPrefix}${text}` : text;\n",
+       "\n",
+       "    const originalStyle = element.style;\n",
+       "    const computedStyle = window.getComputedStyle(element);\n",
+       "    const originalWidth = computedStyle.width;\n",
+       "    const originalHTML = element.innerHTML.replace('Copied!', '');\n",
+       "\n",
+       "    navigator.clipboard.writeText(fullParamName)\n",
+       "        .then(() => {\n",
+       "            element.style.width = originalWidth;\n",
+       "            element.style.color = 'green';\n",
+       "            element.innerHTML = \"Copied!\";\n",
+       "\n",
+       "            setTimeout(() => {\n",
+       "                element.innerHTML = originalHTML;\n",
+       "                element.style = originalStyle;\n",
+       "            }, 2000);\n",
+       "        })\n",
+       "        .catch(err => {\n",
+       "            console.error('Failed to copy:', err);\n",
+       "            element.style.color = 'red';\n",
+       "            element.innerHTML = \"Failed!\";\n",
+       "            setTimeout(() => {\n",
+       "                element.innerHTML = originalHTML;\n",
+       "                element.style = originalStyle;\n",
+       "            }, 2000);\n",
+       "        });\n",
+       "    return false;\n",
+       "}\n",
+       "\n",
+       "document.querySelectorAll('.fa-regular.fa-copy').forEach(function(element) {\n",
+       "    const toggleableContent = element.closest('.sk-toggleable__content');\n",
+       "    const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
+       "    const paramName = element.parentElement.nextElementSibling.textContent.trim();\n",
+       "    const fullParamName = paramPrefix ? `${paramPrefix}${paramName}` : paramName;\n",
+       "\n",
+       "    element.setAttribute('title', fullParamName);\n",
+       "});\n",
+       "</script></body>"
+      ],
+      "text/plain": [
+       "LogisticRegression()"
+      ]
+     },
+     "execution_count": 47,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.linear_model import LogisticRegression\n",
+    "\n",
+    "model = LogisticRegression()\n",
+    "model.fit(X_train, y_train)  "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "44e69e07",
+   "metadata": {},
+   "source": [
+    "# 3.2. Evaluation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "id": "9854e091",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([0, 0, 1, 1, 1])"
+      ]
+     },
+     "execution_count": 48,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "y_pred = model.predict(X_test)\n",
+    "y_pred[:5] "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "id": "6a2e267d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       0.98      0.99      0.98      7548\n",
+      "           1       0.99      0.98      0.98      8240\n",
+      "\n",
+      "    accuracy                           0.98     15788\n",
+      "   macro avg       0.98      0.98      0.98     15788\n",
+      "weighted avg       0.98      0.98      0.98     15788\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.metrics import classification_report\n",
+    "\n",
+    "report = classification_report(y_pred, y_test)\n",
+    "print(report)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "26427da2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "accuracy = 97.5%\n",
+      "precision_macro = 97.5%\n",
+      "recall_macro = 97.5%\n",
+      "f1_macro = 97.5%\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "from sklearn.model_selection import StratifiedKFold, cross_validate \n",
+    "\n",
+    "metrics = ['accuracy', 'precision_macro', 'recall_macro', 'f1_macro']\n",
+    "k_fold_cv = StratifiedKFold(n_splits = 5, shuffle = True, random_state = 42)\n",
+    "scoring = cross_validate(model, X_test, y_test, scoring = metrics, cv = k_fold_cv)\n",
+    "\n",
+    "for metric in metrics:\n",
+    "    score = np.mean(scoring[f'test_{metric}'])\n",
+    "    score = round(score, 3) * 100\n",
+    "    print(f\"{metric} = {score}%\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "95789a38",
+   "metadata": {},
+   "source": [
+    "# 3.3. Saving Model and Vectorizer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3c63ead2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pickle \n",
+    "\n",
+    "with open('../models/logistic_regression.pkl', 'wb') as file:\n",
+    "    pickle.dump(model, file)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "id": "36d617fa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('../models/vectorizer.pkl', 'wb') as file:\n",
+    "    pickle.dump(vectorizer, file)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c8277f43",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "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": "3.12.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

notebooks/Naive_Bayes.ipynb

@@ -0,0 +1,216 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "cf0be37c",
+   "metadata": {},
+   "source": [
+    "# Reading Processed Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "43a52e6b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "34291c43",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>label</th>\n",
+       "      <th>text</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>subscribe change profile contact u long term e...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>hi we have a new opportunity for you and your ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0</td>\n",
+       "      <td>sally i forgot to attach the list of student c...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0</td>\n",
+       "      <td>original message from swisher stephen sent tue...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0</td>\n",
+       "      <td>h hermann writes h hello hynek speech dispatch...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   label                                               text\n",
+       "0      0  subscribe change profile contact u long term e...\n",
+       "1      1  hi we have a new opportunity for you and your ...\n",
+       "2      0  sally i forgot to attach the list of student c...\n",
+       "3      0  original message from swisher stephen sent tue...\n",
+       "4      0  h hermann writes h hello hynek speech dispatch..."
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_df = pd.read_csv('../data/processed/train.csv')\n",
+    "test_df = pd.read_csv('../data/processed/test.csv')\n",
+    "\n",
+    "train_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "bd924063",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train = train_df['text']\n",
+    "X_test = test_df['text']\n",
+    "y_train = train_df['label']\n",
+    "y_test = test_df['label']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "17a6bbf8",
+   "metadata": {},
+   "source": [
+    "# Vectorization"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3871f79f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "\n",
+    "## Code"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f1807de9",
+   "metadata": {},
+   "source": [
+    "# Model Training"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "129e33cf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.naive_bayes import MultinomialNB\n",
+    "\n",
+    "## Code"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7fa92718",
+   "metadata": {},
+   "source": [
+    "## Model Evaluation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ba1f46c4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics import classification_report \n",
+    "\n",
+    "## Code"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c666bfa7",
+   "metadata": {},
+   "source": [
+    "## Model Saving"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "64f48ba0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## Code"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "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": "3.12.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

notebooks/SVM.ipynb

@@ -0,0 +1,216 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "cf0be37c",
+   "metadata": {},
+   "source": [
+    "# Reading Processed Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "43a52e6b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "34291c43",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>label</th>\n",
+       "      <th>text</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>subscribe change profile contact u long term e...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>hi we have a new opportunity for you and your ...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0</td>\n",
+       "      <td>sally i forgot to attach the list of student c...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0</td>\n",
+       "      <td>original message from swisher stephen sent tue...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0</td>\n",
+       "      <td>h hermann writes h hello hynek speech dispatch...</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   label                                               text\n",
+       "0      0  subscribe change profile contact u long term e...\n",
+       "1      1  hi we have a new opportunity for you and your ...\n",
+       "2      0  sally i forgot to attach the list of student c...\n",
+       "3      0  original message from swisher stephen sent tue...\n",
+       "4      0  h hermann writes h hello hynek speech dispatch..."
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_df = pd.read_csv('../data/processed/train.csv')\n",
+    "test_df = pd.read_csv('../data/processed/test.csv')\n",
+    "\n",
+    "train_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "bd924063",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train = train_df['text']\n",
+    "X_test = test_df['text']\n",
+    "y_train = train_df['label']\n",
+    "y_test = test_df['label']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "17a6bbf8",
+   "metadata": {},
+   "source": [
+    "# Vectorization"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3871f79f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "\n",
+    "## Code"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f1807de9",
+   "metadata": {},
+   "source": [
+    "# Model Training"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "129e33cf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.svm import SVC\n",
+    "\n",
+    "## Code"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7fa92718",
+   "metadata": {},
+   "source": [
+    "## Model Evaluation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ba1f46c4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics import classification_report \n",
+    "\n",
+    "## Code"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c666bfa7",
+   "metadata": {},
+   "source": [
+    "## Model Saving"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "64f48ba0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## Code"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "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": "3.12.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

requirements.txt

@@ -0,0 +1,13 @@
+## Data Analysis and ML Libraries
+scikit-learn
+pandas
+matplotlib
+ipykernel
+
+## NLP Libraries 
+langdetect
+nltk
+contractions
+
+## UI Library 
+streamlit