Question

我已经从数据集中选择了要素，然后当我尝试从数据集中选择那些要素时，出现此错误。为什么会这样？

    dataset = pd.read_csv('Banking Dataset.csv')
    LabelEncoder1 = LabelEncoder()
    independent_variables[:,1] = LabelEncoder1.fit_transform(independent_variables[:,1])
    LabelEncoder2 = LabelEncoder()
    independent_variables[:,2] = LabelEncoder2.fit_transform(independent_variables[:,2])


    onehotencoder = OneHotEncoder(categorical_features=[1])
    independent_variables = onehotencoder.fit_transform(independent_variables).toarray()

    X_train, X_test, Y_train,Y_test = train_test_split(independent_variables,target_values  ,test_size=0.25,random_state=0)

    c = DecisionTreeClassifier(min_samples_split=100)
    features =["CreditScore","Geography","Gender","Age","Tenure","Balance","NumOfProducts","HasCrCard","IsActiveMember","EstimatedSalary"]
    X = X_train(features)

输出：

FutureWarning：不建议使用非元组序列进行多维索引编制；使用arr[tuple(seq)]而不是arr[seq]。将来，它将被解释为数组索引arr[np.array(seq)]，它将导致错误或不同的结果。 X_train = X_train [功能] 追溯（最近一次通话）：

X_train=X_train[features]

IndexError：只有整数，切片（:），省略号（...），numpy.newaxis（None）和整数或布尔数组都是有效索引

Process finished with exit code 1

Answer 1

使用以下

X=X_train[features]

代替

X=X_train(features)

调用numpy数组时使用[]

Answer 2

错误代码说的是具体行

X=X_train(features)

应该在（）的特征周围有方括号[]。即

X=X_train[features]

仅整数，切片（`：`），省略号（`...`），numpy.newaxis（`None`）和整数或布尔数组有效

2 个答案: