keras里面调用sklearn

#%%
import numpy as np
import pandas as pd
from tensorflow import keras
import sklearn
from sklearn.model_selection import cross_val_score
from sklearn.preprocessing import LabelEncoder
from sklearn.pipeline import Pipeline
from sklearn.model_selection import StratifiedKFold
#%%
seed = 7
np.random.seed(seed)
#%%
date = pd.read_csv('E:\MyJupyterCode\Beifeng\ml\回归算法\课堂代码\datas\iris.data').to_numpy()
x = date[:,0:4]
y = date[:,4]
encoder = LabelEncoder()
y = encoder.fit_transform(y)
#%%
def create_baseline():
    model = keras.Sequential()
    model.add(keras.layers.Dense(10,activation='relu',input_shape=(4,))),
    model.add(keras.layers.Dense(3,activation='relu')),
    model.compile(optimizer=keras.optimizers.Adam(),
                  loss=keras.losses.categorical_crossentropy,
                  metrics=['accuracy'])
    return model
#%%
keras_classifier = keras.wrappers.scikit_learn.KerasClassifier(build_fn=create_baseline,epochs = 20,batch_size = 16)
estimators = []
estimators.append(('Standardize',sklearn.preprocessing.StandardScaler()))
estimators.append(('mlp',keras_classifier))
pipeline = Pipeline(estimators)
#%%
stratified_k_fold = StratifiedKFold(n_splits=10,shuffle=True,random_state=seed)
#%%
result = cross_val_score(pipeline,x,y,cv=stratified_k_fold)
print(result.mean()*100)
print(result.std()*100)

#%%