Syn_flood.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
    "from sklearn.impute import SimpleImputer\n",
    "from sklearn.compose import ColumnTransformer\n",
    "from sklearn.pipeline import Pipeline\n",
    "\n",
    "\n",
    "# Define file paths\n",
    "train_path = 'C:\\\\Users\\\\Deepak DR\\\\Downloads\\\\Train_Data.csv'\n",
    "test_path = 'C:\\\\Users\\\\Deepak DR\\\\Downloads\\\\Test_Data.csv'\n",
    "\n",
    "# Load datasets\n",
    "train_df = pd.read_csv(train_path)\n",
    "test_df = pd.read_csv(test_path)\n",
    "\n",
    "# Assuming 'attack' is the target column in train.csv\n",
    "X = train_df.drop(columns=['attack'])  # Features\n",
    "y = train_df['attack']  # Target\n",
    "\n",
    "# Step 2: Preprocessing pipeline\n",
    "# Separate numerical and categorical columns\n",
    "numerical_cols = X.select_dtypes(include=['float64', 'int64']).columns\n",
    "categorical_cols = X.select_dtypes(include=['object']).columns\n",
    "\n",
    "# Pipeline for numerical features\n",
    "numerical_transformer = Pipeline(steps=[\n",
    "    ('imputer', SimpleImputer(strategy='median')),\n",
    "    ('scaler', StandardScaler())\n",
    "])\n",
    "\n",
    "# Pipeline for categorical features\n",
    "categorical_transformer = Pipeline(steps=[\n",
    "    ('imputer', SimpleImputer(strategy='constant', fill_value='missing')),\n",
    "    ('onehot', OneHotEncoder(handle_unknown='ignore'))\n",
    "])\n",
    "\n",
    "# Bundle preprocessing for numerical and categorical features\n",
    "preprocessor = ColumnTransformer(\n",
    "    transformers=[\n",
    "        ('num', numerical_transformer, numerical_cols),\n",
    "        ('cat', categorical_transformer, categorical_cols)\n",
    "    ])\n",
    "\n",
    "# Step 3: Training the model\n",
    "# Split data into training and validation sets\n",
    "X_train, X_valid, y_train, y_valid = train_test_split(X, y, test_size=0.2, random_state=42)\n",
    "\n",
    "# Append classifier to preprocessing pipeline\n",
    "pipeline = Pipeline(steps=[('preprocessor', preprocessor),\n",
    "                           ('classifier', RandomForestClassifier(random_state=42))])\n",
    "\n",
    "# Fit the model\n",
    "pipeline.fit(X_train, y_train)\n",
    "\n",
    "# Step 4: Prediction on test data\n",
    "# Assuming 'test_df' is loaded and processed similarly to 'X_train'\n",
    "# Preprocess the test data\n",
    "X_test = test_df  # Assuming no target column in test.csv, just features\n",
    "\n",
    "# Predict on test data\n",
    "predictions = pipeline.predict(X_test)\n",
    "\n",
    "# Optional: Save predictions to a CSV file as per submission requirements\n",
    "submission_df = pd.DataFrame({'attack': predictions})\n",
    "submission_df.to_csv('C:\\\\Users\\\\Deepak DR\\\\Downloads\\\\Submission.csv', index=False)\n",
    "\n",
    "\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.11.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}