小编zdz*_*zdz的帖子

我有以下代码：

    most_important = features_importance_chi(importance_score_tresh, 
    df_user.drop(columns = 'CHURN'),churn)
    X = df_user.drop(columns = 'CHURN')
    churn[churn==2] = 1
    y = churn

    # handle undersample problem
    X,y = handle_undersampe(X,y)

    # train the model

    X=X.loc[:,X.columns.isin(most_important)].values
    y=y.values

    parameters = {
    'application': 'binary',
    'objective': 'binary',
    'metric': 'auc',
    'is_unbalance': 'true',
    'boosting': 'gbdt',
    'num_leaves': 31,
    'feature_fraction': 0.5,
    'bagging_fraction': 0.5,
    'bagging_freq': 20,
    'learning_rate': 0.05,
    'verbose': 0
    }

    # split data
    x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)

    train_data = lightgbm.Dataset(x_train, label=y_train)
    test_data = lightgbm.Dataset(x_test, label=y_test)
    model = …