import sklearn
from sklearn.datasets import load_breast_cancer
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, classification_report
from sklearn.model_selection import train_test_split


data = load_breast_cancer()
X_train, X_test, y_train, y_test = train_test_split(
    data.data,
    data.target,
    test_size=0.2,
    random_state=42,
    stratify=data.target,
)

model = RandomForestClassifier(
    n_estimators=200,
    max_depth=5,
    random_state=42,
)
model.fit(X_train, y_train)

predictions = model.predict(X_test)
accuracy = accuracy_score(y_test, predictions)
top_features = sorted(
    zip(data.feature_names, model.feature_importances_),
    key=lambda item: item[1],
    reverse=True,
)[:5]

print(f"sklearn version: {sklearn.__version__}")
print(f"train rows: {X_train.shape[0]}")
print(f"test rows: {X_test.shape[0]}")
print(f"classes: {data.target_names.tolist()}")
print(f"trees: {len(model.estimators_)}")
print(f"held-out accuracy: {accuracy:.3f}")
print(f"first predictions: {data.target_names[predictions[:5]].tolist()}")
print("top feature importances:")
for feature, importance in top_features:
    print(f"  {feature}: {importance:.3f}")
print("classification report:")
print(classification_report(y_test, predictions, target_names=data.target_names))