构建Pipeline

def solve():
    import pandas as pd
    from sklearn.pipeline import Pipeline
    from sklearn.preprocessing import StandardScaler
    from sklearn.linear_model import LogisticRegression
    from sklearn.model_selection import train_test_split
    df = pd.read_csv("https://data.zuihe.com/breast_cancer.csv")
    X = df.drop("target", axis=1); y = df["target"]
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
    pipe = Pipeline([("scaler", StandardScaler()), ("lr", LogisticRegression(max_iter=5000, random_state=42))])
    pipe.fit(X_train, y_train)
    print(f"{pipe.score(X_test, y_test):.4f}")