使用python返回函数时出错

Question

def random_model_predictions（丢弃，特征）： # 拟合模型

df_telecom_train, df_telecom_test = train_test_split(droping, test_size=0.25)

############## Random Forest Classifier ##############


# Set up our RandomForestClassifier instance and fit to data

clf = RandomForestClassifier(n_estimators=30)
clf = clf.fit(df_telecom_train[features], df_telecom_train["Churn"])
print(clf)

# Make predictions

prediction1 = clf.predict(df_telecom_test[features])
print(prediction1)

probs = clf.predict_proba(df_telecom_test[features])
print(probs)

# Accuracy

score1 = clf.score(df_telecom_test[features], df_telecom_test["Churn"])
print("Accuracy: ", score1)

# Confusion matrix

confusion_matrix1 = pd.DataFrame(
    confusion_matrix(df_telecom_test["Churn"], prediction1),
    columns=["Predicted False", "Predicted True"],
    index=["Actual False", "Actual True"]
)
print(confusion_matrix1)

return df_telecom_test

return df_telecom_train

return probs

return clf

deflogistic_model_prediction(df_telecom_train, features, df_telecom_test):

#############Logistic Regression############

# Import Library

from sklearn.linear_model import LogisticRegression

# Create logistic regression object

model2 = LogisticRegression()

# Train the model using the training sets and check score

model2.fit([features], df_telecom_train["Churn"])
score2 = model2.score(df_telecom_train[features], df_telecom_train["Churn"])
print("Accuracy: ", score2)

# Equation coefficient and Intercept

print('Coefficient: \n', model2.coef_)
print('Intercept: \n', model2.intercept_)

# Predict Output

prediction2 = model2.predict(df_telecom_test[features])
print(prediction2)

# Confusion matrix

confusion_matrix2 = pd.DataFrame(
    confusion_matrix(df_telecom_test["Churn"], prediction2),
    columns=["Predicted False", "Predicted True"],
    index=["Actual False", "Actual True"]
)
print(confusion_matrix2)

如果 name == 'ma​​in'： df_telecom_test, df_telecom_train, probs, clf = random_model_predictions（丢弃，特征） logistic_model_prediction(df_telecom_train, features, df_telecom_test)

当我使用 2 个或更多返回类型时，它显示了这种类型的错误

ValueError: 必须只传递带有布尔值的 DataFrame

Answer 1

原因是out2 在if __name__ == "__main__": 中未定义，因为您没有保存来自removing_outliers() 的返回值。所以改成

if __name__ == "__main__":
     out2 = removing_outliers()
     removing_unwanted_columns(out2)

应该没问题