5种模型构建解决回归问题（california房价预测)
用tf.keras构建模型处理房价预测问题
-
- 1.引入所需要的包
- 2.从sklearn.datasets中调用数据集
-
- 输出
- 3.对数据集进行train,valid,test的划分
-
- 输出
- 4.对数据进行标准归一化
- 5.模型的构建及训练
-
- 1.一般单层级网络模型
-
- 1.构建模型
- 2.模型训练
- 3.绘制训练曲线
- 4.模型评估
- 2.用函数式api构建wide&deep模型
-
- 1.构建模型
- 2.训练模型
- 3.绘制训练曲线
- 4.模型评估
- 3.用子类api实现wide&deep模型训练
-
- 1.构建模型
- 2.训练模型
- 3.绘制训练曲线
- 4.模型评估
- 4.wide&deep实现多输入
-
- 1.模型构建
- 2.将多组数据传入fit,进行训练
- 3.绘制训练曲线
- 4.模型评估
- 5.wide&deep实现多输入和多输出
-
- 1.模型构建
- 2.进行训练
- 3.打印训练曲线
- 4.模型评估
1.引入所需要的包
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.从sklearn.datasets中调用数据集
from sklearn.datasets import fetch_california_housing
housing = fetch_california_housing()
print(housing.DESCR)
print(housing.data.shape)
print(housing.target.shape)
输出
3.对数据集进行train,valid,test的划分
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
输出
(11610, 8) (11610,)
(3870, 8) (3870,)
(5160, 8) (5160,)
4.对数据进行标准归一化
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.模型的构建及训练
1.一般单层级网络模型
1.构建模型
model = keras.models.Sequential([
keras.layers.Dense(30, activation='relu',
input_shape=x_train.shape[1:]),
keras.layers.Dense(1),
])
model.summary()
model.compile(loss="mean_squared_error", optimizer="sgd")
callbacks = [keras.callbacks.EarlyStopping(
patience=5, min_delta=1e-2)]
2.模型训练
history = model.fit(x_train_scaled, y_train,
validation_data = (x_valid_scaled, y_valid),
epochs = 100,
callbacks = callbacks)
3.绘制训练曲线
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)
4.模型评估
model.evaluate(x_test_scaled, y_test)
2.用函数式api构建wide&deep模型
1.构建模型
# 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])
model.summary()
model.compile(loss="mean_squared_error", optimizer="sgd")
callbacks = [keras.callbacks.EarlyStopping(
patience=5, min_delta=1e-2)]
2.训练模型
history = model.fit(x_train_scaled, y_train,
validation_data = (x_valid_scaled, y_valid),
epochs = 100,
callbacks = callbacks)
3.绘制训练曲线
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)
4.模型评估
model.evaluate(x_test_scaled, y_test)
3.用子类api实现wide&deep模型训练
1.构建模型
# 子类API
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)
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
# model = WideDeepModel()
model = keras.models.Sequential([
WideDeepModel(),
])
model.build(input_shape=(None, 8))
model.summary()
model.compile(loss="mean_squared_error", optimizer="sgd")
callbacks = [keras.callbacks.EarlyStopping(
patience=5, min_delta=1e-2)]
2.训练模型
history = model.fit(x_train_scaled, y_train,
validation_data = (x_valid_scaled, y_valid),
epochs = 1,
callbacks = callbacks)
3.绘制训练曲线
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)
4.模型评估
model.evaluate(x_test_scaled, y_test)
4.wide&deep实现多输入
1.模型构建
# 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.compile(loss="mean_squared_error", optimizer="sgd")
callbacks = [keras.callbacks.EarlyStopping(
patience=5, min_delta=1e-2)]
model.summary()
2.将多组数据传入fit,进行训练
x_train_scaled_wide = x_train_scaled[:, :5]
x_train_scaled_deep = x_train_scaled[:, 2:]
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)
3.绘制训练曲线
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)
4.模型评估
model.evaluate([x_test_scaled_wide, x_test_scaled_deep], y_test)
5.wide&deep实现多输入和多输出
1.模型构建
# 多输出
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)
output2 = keras.layers.Dense(1)(hidden2)
model = keras.models.Model(inputs = [input_wide, input_deep],
outputs = [output, output2])#固化模型
model.compile(loss="mean_squared_error", optimizer="sgd")
callbacks = [keras.callbacks.EarlyStopping(
patience=5, min_delta=1e-2)]
model.summary()
2.进行训练
x_train_scaled_wide = x_train_scaled[:, :5]
x_train_scaled_deep = x_train_scaled[:, 2:]
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)
3.打印训练曲线
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)
4.模型评估
model.evaluate([x_test_scaled_wide, x_test_scaled_deep],
[y_test, y_test])
