tensorflow2.0学习笔记：简单的回归模型

california_housing:数据集，实现简单的回归模型。
数据集：from sklearn.datasets import fetch_california_housing

import matplotlib as mpl
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import sklearn
import pandas as pd

import tensorflow as tf

from tensorflow import keras

数据集载入

from sklearn.datasets import fetch_california_housing
housing = fetch_california_housing()
# print(housing.DESCR)
# print(housing.data.shape)
# print(housing.target.shape)

查看数据

import pprint
# pprint 打印，对format有优化
pprint.pprint(housing.data[0:5])
pprint.pprint(housing.target[0:5])

array([[ 8.32520000e+00,  4.10000000e+01,  6.98412698e+00,
         1.02380952e+00,  3.22000000e+02,  2.55555556e+00,
         3.78800000e+01, -1.22230000e+02],
       [ 8.30140000e+00,  2.10000000e+01,  6.23813708e+00,
         9.71880492e-01,  2.40100000e+03,  2.10984183e+00,
         3.78600000e+01, -1.22220000e+02],
       [ 7.25740000e+00,  5.20000000e+01,  8.28813559e+00,
         1.07344633e+00,  4.96000000e+02,  2.80225989e+00,
         3.78500000e+01, -1.22240000e+02],
       [ 5.64310000e+00,  5.20000000e+01,  5.81735160e+00,
         1.07305936e+00,  5.58000000e+02,  2.54794521e+00,
         3.78500000e+01, -1.22250000e+02],
       [ 3.84620000e+00,  5.20000000e+01,  6.28185328e+00,
         1.08108108e+00,  5.65000000e+02,  2.18146718e+00,
         3.78500000e+01, -1.22250000e+02]])
array([4.526, 3.585, 3.521, 3.413, 3.422])

数据处理：训练集，测试集

from sklearn.model_selection import train_test_split
# 默认3:1,test_size=0.25
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)

(11610, 8) (11610,)
(3870, 8) (3870,)
(5160, 8) (5160,)

归一化(标准化)处理

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)

建立模型

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-3)]

Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_2 (Dense)              (None, 30)                270       
_________________________________________________________________
dense_3 (Dense)              (None, 1)                 31        
=================================================================
Total params: 301
Trainable params: 301
Non-trainable params: 0
_________________________________________________________________

模型训练

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)

验证

model.evaluate(x_test_scaled,y_test)

0s 29us/sample - loss: 0.5563
0.3711079419583313