05、除Sequential外模型构建方法：函数式API与子类API - 东方耀AI技术分享

# -*- coding: utf-8 -*-
__author__ = u'东方耀微信：dfy_88888'
__date__ = '2019/10/30 10:10'
__product__ = 'PyCharm'
__filename__ = 'tf-keras-regression-wide&deep'
import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt
import sklearn
import pandas as pd
import os
import sys
import time
import tensorflow as tf
from tensorflow import keras
print(sys.version_info)
for module in mpl, np, pd, sklearn, tf, keras:
print(module.__name__, module.__version__)
from sklearn.datasets import fetch_california_housing
housing = fetch_california_housing()
# print(housing.DESCR)
print(housing.data.shape)
print(housing.target.shape)
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)
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)
def create_model_function():
# 第一种方法：函数式api实现wide&deep模型像使用函数一样
input_1 = keras.layers.Input(shape=x_train.shape[1])
# 复合函数的形式
hidden_1 = keras.layers.Dense(30, activation='relu')(input_1)
hidden_2 = keras.layers.Dense(30, activation='relu')(hidden_1)
# wide model
concat = keras.layers.concatenate(inputs=[input_1, hidden_2])
output = keras.layers.Dense(1)(concat)
model = keras.models.Model(inputs=[input_1], outputs=[output], name='wide_deep_model')
return model
class WideDeepModel(keras.models.Model):
# 第二种方法：子类api实现wide & deep模型
def __init__(self):
super(WideDeepModel, self).__init__()
# 定义模型的层
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
# 第一种方法
# model = create_model_function()
# 第二种方法（类的实例化对象 build方式指定input_shape）
model = WideDeepModel()
model.build(input_shape=(None, x_train.shape[1]))
model.summary()
model.compile(optimizer=keras.optimizers.Adam(0.001), loss='mean_squared_error')
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=50,
callbacks=callbacks)
print(type(history))
print(history.history)
def plot_learning_curve(history):
# ValueError: arrays must all be same length
# 表格型数据要求每一列的len一致这里即：history.history字典里每个key对应的value长度一致
df_history = pd.DataFrame(data=history.history)
print(df_history)
print(df_history.index)
print(df_history.columns)
print(df_history.dtypes)
df_history.plot(figsize=(8, 5))
plt.grid(True)
# x就是DataFrame的索引
plt.ylim(0, 1)
plt.show()
plot_learning_curve(history)
# Returns the loss value & metrics values for the model in test mode.
print(model.evaluate(x_test_scaled, y_test))

复制代码