两种方式实现wide & deep模型

1.子类API实现wide & deep模型

Wide输入和Deep输入时一样的

import tensorflow as tf
import matplotlib as mpl
import matplotlib.pyplot as plt

import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
from tensorflow import keras

# 获取数据集 加利福利亚房价的数据集
from sklearn.datasets import fetch_california_housing

housing = fetch_california_housing()
print(housing.DESCR)#总共 20640 个数据，每个数据都有8个特征 MedInc、HouseAge、AveRooms、AveBedrms、Population、AveOccup、Latitude      、Longitude
print(housing.data.shape)#相当于x_data:结构 （20640*8）
print(housing.target.shape)#相当于y_data:index（20640个值）

import pprint
pprint.pprint(housing.data[0:5])#5 行 8 列
pprint.pprint(housing.target[0:5])#5 行 1 列

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)#按3比1比例划分，可以添加test_size = 0.25 来修改比例。拆分成 全部集和测试集
x_train,x_valid,y_train,y_valid = train_test_split(
    x_train_all,y_train_all,random_state=11)#训练集 和 验证集

#查看数据的大小
print(x_train.shape,y_train.shape)
print(x_valid.shape,y_train.shape)
print(x_test.shape,y_test.shape)

#数据归一化
from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
x_train_scaled = scaler.fit_transform(x_train)#在训练集上获得均值和方差
x_valid_scaled = scaler.fit_transform(x_valid)
x_test_scaled = scaler.fit_transform(x_test)

# 函数式API 功能API
'''input = keras.layers.Input(shape=x_train.shape[1:])
hidden1 = keras.layers.Dense(30, activation='relu')(input)
hidden2 = keras.layers.Dense(30, activation='relu')(hidden1)# 复合函数: f(x) = h(g(x))
concat = keras.layers.concatenate([input, hidden2])
output = keras.layers.Dense(1)(concat)
model = keras.models.Model(inputs = [input],outputs = [output])
'''
class WideDeepModel(keras.models.Model):
    def __init__(self):
        super(WideDeepModel,self).__init__()
        '''定义模型的层次'''
        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)#全连接层
    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
#两种方式：model = WideDeepModel()
model = keras.models.Sequential([
    WideDeepModel(),
])
model.build(input_shape = (None,8))

model.summary()
model.compile(loss="mean_squared_error", optimizer="adam")
callbacks = [keras.callbacks.EarlyStopping(patience=5, min_delta=1e-2)]

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

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)

model.evaluate(x_test_scaled,y_test)

运行结果：


结果跟之前差不多……

2.多输入实现模型（Wide 和 Deep输入不一样）

import tensorflow as tf
import matplotlib as mpl
import matplotlib.pyplot as plt

import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
from tensorflow import keras

# 获取数据集 加利福利亚房价的数据集
from sklearn.datasets import fetch_california_housing

housing = fetch_california_housing()
print(housing.DESCR)#总共 20640 个数据，每个数据都有8个特征 MedInc、HouseAge、AveRooms、AveBedrms、Population、AveOccup、Latitude      、Longitude
print(housing.data.shape)#相当于x_data:结构 （20640*8）
print(housing.target.shape)#相当于y_data:index（20640个值）

import pprint
pprint.pprint(housing.data[0:5])#5 行 8 列
pprint.pprint(housing.target[0:5])#5 行 1 列

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)#按3比1比例划分，可以添加test_size = 0.25 来修改比例。拆分成 全部集和测试集
x_train,x_valid,y_train,y_valid = train_test_split(
    x_train_all,y_train_all,random_state=11)#训练集 和 验证集

#查看数据的大小
print(x_train.shape,y_train.shape)
print(x_valid.shape,y_train.shape)
print(x_test.shape,y_test.shape)

#数据归一化
from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
x_train_scaled = scaler.fit_transform(x_train)#在训练集上获得均值和方差
x_valid_scaled = scaler.fit_transform(x_valid)
x_test_scaled = scaler.fit_transform(x_test)

# 定义模型 实现多输入
input_wide = keras.layers.Input(shape=[5])
input_deep = keras.layers.Input(shape=[6])
hidden1 = keras.layers.Dense(30,activation="relu")(input_deep)
hidden2 = keras.layers.Dense(30,activation="relu")(hidden1)
concat = keras.layers.concatenate([input_wide,hidden2])
output = keras.layers.Dense(1)(concat)
model = keras.models.Model(inputs = [input_wide,input_deep],
                          outputs = [output])

model.summary()
model.compile(loss="mean_squared_error", optimizer="adam")
callbacks = [keras.callbacks.EarlyStopping(patience=5, min_delta=1e-2)]

#对训练数据做拆分
x_train_scaled_wide = x_train_scaled[:,:5]#前 5 个feature
x_train_scaled_deep = x_train_scaled[:,2:]#后 6 个feature
x_valid_scaled_wide = x_valid_scaled[:,:5]
x_valid_scaled_deep = x_valid_scaled[:,2:]
x_test_scaled_wide = x_test_scaled[:,:5]
x_test_scaled_deep = x_test_scaled[:,2:]

history = model.fit([x_train_scaled_wide,x_train_scaled_deep], y_train,
                    validation_data = ([x_valid_scaled_wide,x_valid_scaled_deep],y_valid),
                    epochs = 100,
                    callbacks=callbacks)

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)

model.evaluate([x_test_scaled_wide,x_test_scaled_deep],y_test)

3.多输出的神经网络

import tensorflow as tf
import matplotlib as mpl
import matplotlib.pyplot as plt

import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
from tensorflow import keras

# 获取数据集 加利福利亚房价的数据集
from sklearn.datasets import fetch_california_housing

housing = fetch_california_housing()
print(housing.DESCR)#总共 20640 个数据，每个数据都有8个特征 MedInc、HouseAge、AveRooms、AveBedrms、Population、AveOccup、Latitude      、Longitude
print(housing.data.shape)#相当于x_data:结构 （20640*8）
print(housing.target.shape)#相当于y_data:index（20640个值）

import pprint
pprint.pprint(housing.data[0:5])#5 行 8 列
pprint.pprint(housing.target[0:5])#5 行 1 列

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)#按3比1比例划分，可以添加test_size = 0.25 来修改比例。拆分成 全部集和测试集
x_train,x_valid,y_train,y_valid = train_test_split(
    x_train_all,y_train_all,random_state=11)#训练集 和 验证集

#查看数据的大小
print(x_train.shape,y_train.shape)
print(x_valid.shape,y_train.shape)
print(x_test.shape,y_test.shape)

#数据归一化
from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
x_train_scaled = scaler.fit_transform(x_train)#在训练集上获得均值和方差
x_valid_scaled = scaler.fit_transform(x_valid)
x_test_scaled = scaler.fit_transform(x_test)

# 定义模型 实现多输入
input_wide = keras.layers.Input(shape=[5])
input_deep = keras.layers.Input(shape=[6])
hidden1 = keras.layers.Dense(30,activation="relu")(input_deep)
hidden2 = keras.layers.Dense(30,activation="relu")(hidden1)
concat = keras.layers.concatenate([input_wide,hidden2])
#两个输出
output = keras.layers.Dense(1)(concat)
output2 = keras.layers.Dense(1)(hidden2)

model = keras.models.Model(inputs = [input_wide,input_deep],
                          outputs = [output,output2])

model.summary()
model.compile(loss="mean_squared_error", optimizer="adam")
callbacks = [keras.callbacks.EarlyStopping(patience=5, min_delta=1e-2)]

#对训练数据做拆分
x_train_scaled_wide = x_train_scaled[:,:5]#前 5 个feature
x_train_scaled_deep = x_train_scaled[:,2:]#后 6 个feature
x_valid_scaled_wide = x_valid_scaled[:,:5]
x_valid_scaled_deep = x_valid_scaled[:,2:]
x_test_scaled_wide = x_test_scaled[:,:5]
x_test_scaled_deep = x_test_scaled[:,2:]

history = model.fit([x_train_scaled_wide,x_train_scaled_deep], [y_train,y_train],
                    validation_data = ([x_valid_scaled_wide,x_valid_scaled_deep],
                                       [y_valid,y_valid]),
                    epochs = 100,
                    callbacks=callbacks)

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)

model.evaluate([x_test_scaled_wide,x_test_scaled_deep],[y_test,y_test])

运行结果：