从零基础入门Tensorflow2.0 ----5.3 实战sklearn超参数搜索

every blog every motto: Until you make peace with who you are, you’ll never be content with what you have.

0. 前言

实战sklearn超参数搜索。
注： 训练时间较长。

1. 代码部分

1. 导入模块

import matplotlib as mpl
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
import tensorflow as tf
from tensorflow import keras

print(tf.__version__)
print(sys.version_info)
for module in mpl,np,pd,sklearn,tf,keras:
    print(module.__name__,module.__version__)

2. 读取数据

from sklearn.datasets import fetch_california_housing

# 房价预测
housing = fetch_california_housing()
print(housing.DESCR)
print(housing.data.shape)
print(housing.target.shape)

3. 划分样本

# 划分样本
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)

print(x_train.shape,y_train.shape)
print(x_valid.shape,y_valid.shape)
print(x_test.shape,y_test.shape)

4. 数据归一化

# 归一化
from sklearn.preprocessing import StandardScaler

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

5. 构建模型、训练

RandomizedSearchCV
步骤：

1. 转换为sklearn的model（上节实现）
2. 定义参数集合（本节实现）
3. 搜索参数（本节实现）

# RandomizedSearchCV
# 步骤
# 1. 转换为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

# 转成sklearn model
sklearn_model = keras.wrappers.scikit_learn.KerasRegressor(build_model)

# 回调函数
callbacks = [keras.callbacks.EarlyStopping(patience=5,min_delta=1e-3)]
# 训练
history = sklearn_model.fit(x_train_scaled,y_train,epochs=100,validation_data=(x_valid_scaled,y_valid),callbacks=callbacks)

6. 学习曲线

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

7. 超参数搜索

cross_validation:训练集分成n份，n-1训练，最后一份验证

from scipy.stats import reciprocal
# f(x) = 1/(x*log(b/a)) a<=x <=b
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 = 10,n_jobs=1)
random_search_cv.fit(x_train_scaled,y_train,epochs=100,validation_data=(x_valid_scaled,y_valid),callbacks=callbacks)
# cross_validation:训练集分成n份，n-1训练，最后一份验证

8. 查询最好参数、分值、模型

# 查询最好参数、分值、模型
print(random_search_cv.best_params_)
print(random_search_cv.best_score_)
print(random_search_cv.best_estimator_)

9. 获取最好模型，并在测试集上验证

# 获取最好模型，对测试集进行测试
model = random_search_cv.best_estimator_.model
model.evaluate(x_test_scaled,y_test)