tensorflow2 结合sklearn做网格搜索

from tensorflow import keras
import numpy as np
# load dataset
from sklearn.datasets import fetch_california_housing

housing = fetch_california_housing()
from sklearn.model_selection import train_test_split

x_train_all, x_test, y_train_all, y_test = train_test_split(housing.data, housing.target, random_state=7)
x_train, x_valid, y_train, y_valid = train_test_split(x_train_all, y_train_all, random_state=11)

from sklearn.preprocessing import StandardScaler

#  normalization
scaler = StandardScaler()
x_train_scaled = scaler.fit_transform(x_train)
x_valid_scaled = scaler.transform(x_valid)
x_test_scaled = scaler.transform(x_test)


# RandomizedSearchCV
# 1. 转化为sklearn的model
# 2. 定义参数集合
# 3. 搜索参数

def build_model(hidden_layers=1,
                layer_size=30,
                learning_rate=3e-3):
    model = keras.models.Sequential()
    model.add(keras.layers.Dense(layer_size, activation='relu',
                                 input_shape=x_train.shape[1:]))
    for _ in range(hidden_layers - 1):
        model.add(keras.layers.Dense(layer_size,
                                     activation='relu'))
    model.add(keras.layers.Dense(1))
    optimizer = keras.optimizers.SGD(learning_rate)
    model.compile(loss='mse', optimizer=optimizer)
    return model

from tensorflow.python.keras.wrappers.scikit_learn import KerasRegressor

sklearn_model = KerasRegressor(build_fn=build_model)
#回调函数
callbacks = [keras.callbacks.EarlyStopping(patience=5, min_delta=1e-2)]

history = sklearn_model.fit(x_train_scaled, y_train,
                            epochs=10,
                            validation_data=(x_valid_scaled, y_valid),
                            callbacks=callbacks)
# 导入learning_rate的随机分布
from scipy.stats import reciprocal
# f(x) = 1/(x*log(b/a)) a <= x <= b

#需要搜索的参数
param_distribution = {
    
    
    "hidden_layers":[1, 2, 3, 4],
    "layer_size": np.arange(1, 100),
    "learning_rate": reciprocal(1e-4, 1e-2),
}

from sklearn.model_selection import RandomizedSearchCV

random_search_cv = RandomizedSearchCV(sklearn_model,
                                      param_distribution,
                                      n_iter = 2,
                                      cv = 3,
                                      n_jobs = 1)
random_search_cv.fit(x_train_scaled, y_train, epochs = 10,
                     validation_data = (x_valid_scaled, y_valid),
                     callbacks = callbacks)
#打印最好的结果
print(random_search_cv.best_params_)
print(random_search_cv.best_score_)
print(random_search_cv.best_estimator_)