every blog every motto: The hard part isn’t making the decision. It’s living with it.

0. 前言

wide & deep 模型，子类API的实现

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__)

在这里插入图片描述

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)

在这里插入图片描述

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. 子类API

# 子类API
class WideDeepModel(keras.models.Model):
    def __init__(self):
        super(WideDeepModel,self).__init__()
        """定义模型层次"""
        self.hidden1_layer = keras.layers.Dense(30,activation='relu')
        self.hidden2_layer = keras.layers.Dense(30,activation='relu')
        self.output_layer = keras.layers.Dense(1)
    
    def call(self,input):
        """完成模型的正向计算"""
        hidden1 = self.hidden1_layer(input)
        hidden2 = self.hidden2_layer(hidden1)
        concat = keras.layers.concatenate([input,hidden2])
        output = self.output_layer(concat)
        
        return output

5.2 构建模型

# model = WideDeepModel()
# 另一种方法
model = keras.models.Sequential([
    WideDeepModel(),
])


model.build(input_shape=(None,8))

5.3 回调函数，编译

# 打印model信息
model.summary()
# 编译
model.compile(loss='mean_squared_error',optimizer="adam")
# 回调函数
callbacks = [keras.callbacks.EarlyStopping(patience=5,min_delta=1e-2)]

在这里插入图片描述

6. 训练

#训练
history = model.fit(x_train_scaled,y_train,validation_data=(x_valid_scaled,y_valid),epochs=100,callbacks=callbacks)

7. 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)