Using Decision Tree Algorithm to predict Customer Buying pattern

decision_tree_customer_buying_prediction.py

"""
This Python script showcases the application of decision trees in the context of e-commerce data analysis. 
"""

# Import necessary libraries
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score, confusion_matrix
from sklearn.tree import export_text

# Generate a sample dataset
data = {
    'Time_Spent_on_Site': [10, 15, 5, 20, 8, 12, 18, 7],
    'Pages_Viewed': [5, 8, 3, 10, 4, 6, 9, 3],
    'Clicked_Purchase': [1, 1, 0, 1, 0, 1, 1, 0]
}

df = pd.DataFrame(data)

# Assume 'Clicked_Purchase' is the target variable, and others are features
X = df[['Time_Spent_on_Site', 'Pages_Viewed']]
y = df['Clicked_Purchase']

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Create a Decision Tree model
model = DecisionTreeClassifier()

# Train the model
model.fit(X_train, y_train)

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

# Calculate accuracy
accuracy = accuracy_score(y_test, y_pred)

# Display the confusion matrix
conf_matrix = confusion_matrix(y_test, y_pred)

# Display results
print(f'Test Accuracy: {accuracy:.2f}')
print('Confusion Matrix:')
print(conf_matrix)

# Visualize the decision tree rules
tree_rules = export_text(model, feature_names=['Time_Spent_on_Site', 'Pages_Viewed'])
print("Decision Tree Rules:")
print(tree_rules)