شجرة القرار والغابة

import pandas as pd
from sklearn.tree import DecisionTreeClassifier, export_text

df = pd.read_csv("churn.csv")
df["yearly"] = (df["contract"] == "yearly").astype(int)
features = ["tenure", "bill", "complaints", "data_gb", "yearly"]

tree = DecisionTreeClassifier(max_depth=3, random_state=42)
tree.fit(df[features], df["churned"])

print(export_text(tree, feature_names=features))

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import f1_score

df = pd.read_csv("churn.csv")
df["yearly"] = (df["contract"] == "yearly").astype(int)
features = ["tenure", "bill", "complaints", "data_gb", "yearly"]
X_train, X_test, y_train, y_test = train_test_split(
    df[features], df["churned"], test_size=0.2,
    random_state=42, stratify=df["churned"])

forest = RandomForestClassifier(n_estimators=300, min_samples_leaf=5,
                                random_state=42, n_jobs=-1)
forest.fit(X_train, y_train)
print("F1 (churned):", round(f1_score(y_test, forest.predict(X_test)), 3))

# Which features mattered most?
importance = pd.Series(forest.feature_importances_, index=features)
print(importance.sort_values(ascending=False).round(3))