c45.py

from sklearn.tree import DecisionTreeClassifier
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# Load dataset (Iris dataset for example)
data = datasets.load_iris()

X = data.data  # Features
y = data.target  # Target labels

# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# Initialize Decision Tree Classifier with 'entropy' (approximating C4.5)
clf = DecisionTreeClassifier(criterion="entropy", random_state=42)

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

# Predict on test data
y_pred = clf.predict(X_test)

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