import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import StandardScaler

# Load the dataset (replace this with your actual dataset path)
# Assuming columns: 'Age', 'BrowsingTime', 'PastPurchases', 'CustomerType', 'ProductCategory', 'LikelyToPurchase'
# You may need to load data from CSV or database
df = pd.read_csv('customer_data.csv')

# Data Preprocessing
# Convert categorical variables into dummy variables (e.g., 'CustomerType', 'ProductCategory')
df = pd.get_dummies(df, drop_first=True)

# Features (independent variables)
X = df.drop('LikelyToPurchase', axis=1)  # Remove the target variable

# Target (dependent variable)
y = df['LikelyToPurchase']  # Target: Whether the customer will purchase (1) or not (0)

# Standardize the features (scaling to improve model performance)
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

# Train-test split (80% training, 20% testing)
X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)

# Build and train the Random Forest Classifier
model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X_train, y_train)

# Make predictions on the test data
y_pred = model.predict(X_test)

# Evaluate the model accuracy
accuracy = accuracy_score(y_test, y_pred)
print(f"Model Accuracy: {accuracy * 100:.2f}%")

# Predicting whether a new customer will purchase based on specific input features
new_customer_data = pd.DataFrame({
    'Age': [30],
    'BrowsingTime': [45],
    'PastPurchases': [5],
    'CustomerType_Regular': [1],  # Assuming the customer type is regular (1 = Regular, 0 = New)
    'ProductCategory_Electronics': [1]  # Assuming the product category is electronics (1 = Yes, 0 = No)
})

# Scale the new customer data using the same scaler
new_customer_scaled = scaler.transform(new_customer_data)

# Predict if the new customer will make a purchase
prediction = model.predict(new_customer_scaled)
print(f"Will the new customer purchase? {'Yes' if prediction[0] == 1 else 'No'}")