import pandas as pd
import numpy as np
import tensorflow as tf
from tensorflow import keras
import matplotlib
import matplotlib.pyplot as plt
import sklearn
import os,sys
from sklearn.datasets import fetch_california_housing

housing=fetch_california_housing()

house=pd.DataFrame(housing.data)
house.columns=housing.feature_names
house['price']=housing.target
house.info()
house.head(10)


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,test_size=0.25,random_state=2)
x_train,x_valid,y_train,y_valid=train_test_split(x_train_all,y_train_all,test_size=0.25,random_state=2)



#标准化
from sklearn.preprocessing import StandardScaler

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


#构建自己的模型
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


import datetime
current_time = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
logdir = os.path.join('logs', current_time)
callbacks=[
    keras.callbacks.EarlyStopping(patience=3,min_delta=1e-3),
    keras.callbacks.TensorBoard(log_dir=logdir)
]

model=keras.wrappers.scikit_learn.KerasRegressor(build_model)

callback=[keras.callbacks.EarlyStopping(patience=3,min_delta=1e-3)]
#使用默认参数的模型
history=model.fit(x_train_scaled,y_train,validation_data=(x_valid_scaled,y_valid),epochs=100,callbacks=callback)


def plot_learning_curves(history):
    pd.DataFrame(history.history).plot(figsize=(8,5))
    plt.grid()
    plt.gca().set_ylim(0,1)
    plt.show()

plot_learning_curves(history)


#实现超参数搜索
from scipy.stats import reciprocal

param_distribution={
    "hidden_layers":[3,4],
    "layer_size":np.arange(24,27),
    "learning_rate":reciprocal(0.001,0.005)
}

#随机搜索
from sklearn.model_selection import RandomizedSearchCV

random_searchcv=RandomizedSearchCV(model,param_distribution,n_iter=10,verbose=0)
random_searchcv.fit(x_train_scaled,y_train,validation_data=(x_valid_scaled,y_valid),epochs=100)


print("得到的最好参数为:",random_searchcv.best_params_)
print("最好的得分为:",random_searchcv.best_score_)



model=random_searchcv.best_estimator_.model
history1=model.fit(x_train_scaled,y_train,validation_data=(x_valid_scaled,y_valid),epochs=100,callbacks=callbacks)

plot_learning_curves(history1)

print(model.evaluate(x_test_scaled,y_test,verbose=0))

默认参数的模型效果

使用随机搜索的结果

打开tensorboard看看模型

3.总结：

虽然使用超参数搜索很方便，但是也有一些需要注意的地方。比如需要知道哪些参数比较重要，就尽量精确；相反的就可以稍微放宽要求。毕竟不论是使用网格搜索还是随机搜索如果参数太多会导致计算时间很久。BTW，在使用超参数搜索的时候，我想把n_jobs设置成大于1的，运行就会报错，还没有找到很好的办法解决，这也就导致了对数据的计算时间会更久，终究调参还是一个需要经验的事情鸭！