如何修复元组错误、索引超出范围

Question

def r_model(input_shape):
  model = Sequential(name="likelihood")
  model.add(InputLayer(input_shape=input_shape))
  model.add(Dense(10, activation='relu'))
  model.add(Dense(1))
  opt = Adam(learning_rate=0.1)
  model.compile(loss='mse', metrics=['mae'], optimizer=opt)
  return model

numerical = ['Serial No.', 'GRE Score', 'TOEFL Score', 'University Rating', 'SOP', 'LOR ', 'CGPA', 'Research']  
labels = df['Chance of Admit ']
features = df[numerical]
features_train, labels_train, features_test, labels_test = train_test_split(features, labels, test_size = 0.33, random_state = 42)
ct = ColumnTransformer([('standardize', StandardScaler(), numerical)], remainder='passthrough')
features_train = ct.fit_transform(features_train)
features_test = ct.transform(features_test)

这是错误：

Traceback (most recent call last):
  File "script.py", line 36, in <module>
    features_test = ct.transform(features_test)
  File "/usr/local/lib/python3.6/dist-packages/sklearn/compose/_column_transformer.py", line 580, in transform
    if self._n_features > X.shape[1]:
IndexError: tuple index out of range

我尝试了很多东西，无法弄清楚，它必须简单明了，请纠正我）

通常，当 ColumnTransformer 中指定的列数与数据集中的实际列数不匹配时，就会发生这种情况。

Answer 1

• train_test_split

  函数返回四个单独的变量：

X_train, X_test, y_train, y_test = train_test_split(X,y ,
                                   random_state=42, 
                                   test_size=0.25, 
                                   shuffle=True)

• 您放置的变量是

  wrong order

  ，重新排列

  variables

的顺序

features_train, features_test, labels_train, labels_test = train_test_split(features, labels, test_size=0.33, random_state=42)