我在使用带有One Hot编码的GridSearch CV时遇到了以下错误：“Classification metrics can’t handle a mix of multilabel-indicator and multiclass targets”
我的y_train形状是：(64345, 37)，我的X_train形状是：(64345, 14)。
我无法找出哪里出了问题。任何指导/帮助将不胜感激。
在不使用GridSearchCV且使用固定参数的情况下，我的模型可以正常执行。不使用One Hot编码时，我会遇到索引超出范围的错误。该帖子的链接在这里： 我在使用GridSearchCV训练一个ANN机器学习模型时遇到了IndexError问题
这是我如何分割数据集的：
from sklearn.preprocessing import LabelEncoder, OneHotEncoderonehotencoder = OneHotEncoder(categorical_features = [0])df = onehotencoder.fit_transform(df).toarray()df=df[:,1:]target=df[:,0:37]dataset=df[:,37:51]from sklearn.model_selection import train_test_splitX_train,X_test,y_train,y_test=train_test_split(dataset,target,random_state=1)from sklearn.preprocessing import StandardScalersc = StandardScaler()X_train= sc.fit_transform(X_train)X_test=pd.DataFrame(X_test) 这是GridSearchCV的代码：
from keras.wrappers.scikit_learn import KerasClassifierfrom sklearn.model_selection import GridSearchCVfrom keras.models import Sequentialfrom keras.layers import Densedef build_classifier(optimizer, nb_layers,unit): classifier = Sequential() classifier.add(Dense(units = unit, kernel_initializer = 'uniform', activation = 'relu', input_dim = 14)) i = 1 while i <= nb_layers: classifier.add(Dense(activation="relu", units=unit, kernel_initializer="uniform")) i += 1 classifier.add(Dense(units = 37, kernel_initializer = 'uniform', activation = 'softmax')) classifier.compile(optimizer = optimizer, loss = 'categorical_crossentropy', metrics = ['accuracy']) return classifierclassifier = KerasClassifier(build_fn = build_classifier)parameters = {'batch_size': [10,25,32,64,128,256], 'epochs': [50,100, 200,500,1000,1500,2000], 'optimizer': ['adam'], 'nb_layers': [2,3,4,5,6], 'unit':[28,40,48,57] }grid_search = GridSearchCV(estimator = classifier, param_grid = parameters, scoring = 'accuracy', cv=10,n_jobs=-1)grid_search = grid_search.fit(X_train, y_train)best_parameters = grid_search.best_params_best_accuracy = grid_search.best_score_我应该在结果中得到最佳参数，但却遇到了错误-ValueError: Classification metrics can’t handle a mix of multilabel-indicator and multiclass targets
回答：
错误信息很明确。
这里，你的y_train:(64345, 37)表示每个样本是多标签的。每个样本有37个标签。
sklearn的分类指标无法处理多标签目标变量。
在应用GridSearch()之前，你应该找到一种方法使y_train变成(64345, 1)的形状。
对于可以处理多标签问题的模型，请阅读以下内容：
https://scikit-learn.org/stable/modules/multiclass.html
支持多标签：sklearn.tree.DecisionTreeClassifiersklearn.tree.ExtraTreeClassifiersklearn.ensemble.ExtraTreesClassifiersklearn.neighbors.KNeighborsClassifiersklearn.neural_network.MLPClassifiersklearn.neighbors.RadiusNeighborsClassifiersklearn.ensemble.RandomForestClassifiersklearn.linear_model.RidgeClassifierCV