DL7-波士顿房价预测问题：TensorFlow 2.0 实践
导入库
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
#显示图像
import pandas as pd
from sklearn.utils import shuffle
from sklearn.preprocessing import scale
print("TensorFlow版本是：",tf.__version__)
TensorFlow版本是： 2.0.0
通过pandas导入数据
df = pd.read_csv("data/boston.csv",header = 0)
#显示数据摘要描述信息
print(df.describe())
CRIM ZN INDUS CHAS NOX RM \
count 506.000000 506.000000 506.000000 506.000000 506.000000 506.000000
mean 3.613524 11.363636 11.136779 0.069170 0.554695 6.284634
std 8.601545 23.322453 6.860353 0.253994 0.115878 0.702617
min 0.006320 0.000000 0.460000 0.000000 0.385000 3.561000
25% 0.082045 0.000000 5.190000 0.000000 0.449000 5.885500
50% 0.256510 0.000000 9.690000 0.000000 0.538000 6.208500
75% 3.677082 12.500000 18.100000 0.000000 0.624000 6.623500
max 88.976200 100.000000 27.740000 1.000000 0.871000 8.780000
AGE DIS RAD TAX PTRATIO LSTAT \
count 506.000000 506.000000 506.000000 506.000000 506.000000 506.000000
mean 68.574901 3.795043 9.549407 408.237154 18.455534 12.653063
std 28.148861 2.105710 8.707259 168.537116 2.164946 7.141062
min 2.900000 1.129600 1.000000 187.000000 12.600000 1.730000
25% 45.025000 2.100175 4.000000 279.000000 17.400000 6.950000
50% 77.500000 3.207450 5.000000 330.000000 19.050000 11.360000
75% 94.075000 5.188425 24.000000 666.000000 20.200000 16.955000
max 100.000000 12.126500 24.000000 711.000000 22.000000 37.970000
MEDV
count 506.000000
mean 22.532806
std 9.197104
min 5.000000
25% 17.025000
50% 21.200000
75% 25.000000
max 50.000000
# Pandas 读取 数据
# 显示前3条数据
df.head(3)
| CRIM | ZN | INDUS | CHAS | NOX | RM | AGE | DIS | RAD | TAX | PTRATIO | LSTAT | MEDV | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0.00632 | 18.0 | 2.31 | 0 | 0.538 | 6.575 | 65.2 | 4.0900 | 1 | 296 | 15.3 | 4.98 | 24.0 |
| 1 | 0.02731 | 0.0 | 7.07 | 0 | 0.469 | 6.421 | 78.9 | 4.9671 | 2 | 242 | 17.8 | 9.14 | 21.6 |
| 2 | 0.02729 | 0.0 | 7.07 | 0 | 0.469 | 7.185 | 61.1 | 4.9671 | 2 | 242 | 17.8 | 4.03 | 34.7 |
# 显示后3条数据
df.tail(3)
| CRIM | ZN | INDUS | CHAS | NOX | RM | AGE | DIS | RAD | TAX | PTRATIO | LSTAT | MEDV | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 503 | 0.06076 | 0.0 | 11.93 | 0 | 0.573 | 6.976 | 91.0 | 2.1675 | 1 | 273 | 21.0 | 5.64 | 23.9 |
| 504 | 0.10959 | 0.0 | 11.93 | 0 | 0.573 | 6.794 | 89.3 | 2.3889 | 1 | 273 | 21.0 | 6.48 | 22.0 |
| 505 | 0.04741 | 0.0 | 11.93 | 0 | 0.573 | 6.030 | 80.8 | 2.5050 | 1 | 273 | 21.0 | 7.88 | 11.9 |
# 获取数据集的值
ds = df.values
print(ds.shape)
(506, 13)
ds
array([[6.3200e-03, 1.8000e+01, 2.3100e+00, ..., 1.5300e+01, 4.9800e+00,
2.4000e+01],
[2.7310e-02, 0.0000e+00, 7.0700e+00, ..., 1.7800e+01, 9.1400e+00,
2.1600e+01],
[2.7290e-02, 0.0000e+00, 7.0700e+00, ..., 1.7800e+01, 4.0300e+00,
3.4700e+01],
...,
[6.0760e-02, 0.0000e+00, 1.1930e+01, ..., 2.1000e+01, 5.6400e+00,
2.3900e+01],
[1.0959e-01, 0.0000e+00, 1.1930e+01, ..., 2.1000e+01, 6.4800e+00,
2.2000e+01],
[4.7410e-02, 0.0000e+00, 1.1930e+01, ..., 2.1000e+01, 7.8800e+00,
1.1900e+01]])
划分特征数据和标签数据
x_data = ds[:,:12] #取前12列数据：506*12
y_data = ds[:,12] #取最后1列：506*1
划分数据集：训练集、验证集和测试集
train_num = 300 #训练集的数目
valid_num = 100 #验证集的数目
test_num = len(x_data) - train_num - valid_num # 测试集的数目 = 506 - 训练集 - 验证集
# 训练集划分
x_train = x_data[:train_num]
y_train = y_data[:train_num]
# 验证集划分
x_valid = x_data[train_num : train_num + valid_num]
y_valid = y_data[train_num : train_num + valid_num]
# 测试集划分
x_test = x_data[train_num + valid_num : ]
y_test = y_data[train_num + valid_num : train_num + valid_num + test_num]
特征数据的类型转换
x_train = tf.cast(x_train, dtype=tf.float32)
x_valid = tf.cast(x_valid, dtype=tf.float32)
x_test = tf.cast(x_test, dtype=tf.float32)
定义模型
def model(x, w, b):
return tf.matmul(x,w) + b
创建变量
W = tf.Variable(tf.random.normal([12,1],mean = 0.0, stddev = 1.0, dtype = tf.float32))
B = tf.Variable(tf.zeros(1), dtype = tf.float32)
tf.random_normal(shape, mean=0.0, stddev=1.0, dtype=tf.float32, seed=None, name=None)
shape: 输出张量的形状，必选
mean: 正态分布的均值，默认为0
stddev: 正态分布的标准差，默认为1.0
dtype: 输出的类型，默认为tf.float32
seed: 随机数种子，是一个整数，当设置之后，每次生成的随机数都一样
name: 操作的名称
print(W,"\n\n",B)
设置训练参数
training_epochs = 50
leraning_rate = 0.001
batch_size = 10 # 批量训练一次的样本数
定义均方差损失函数
def loss(x,y,w,b):
err = model(x,w,b) - y
squared_err = tf.square(err) #求平方，得出方差
return tf.reduce_mean(squared_err) # 求均值，得出均方差
定义梯度计算函数
# 计算样本数据[x,y]在参数[w,b]点上的梯度
def grad(x,y,w,b):
with tf.GradientTape() as tape:
loss_ = loss(x,y,w,b)
return tape.gradient(loss_, [w,b]) # 返回梯度向量
选择优化器
optimizer = tf.keras.optimizers.SGD(leraning_rate) # 随机梯度下降优化器，并乘上学习率
迭代训练
loss_list_train = [] # 用于保存训练集loss值的列表
loss_list_valid = [] # 用于保存验证集loss值的列表
total_step = int(train_num / batch_size)
for epoch in range(training_epochs):
for step in range(total_step):
xs = x_train[step * batch_size : (step+1) * batch_size, :]
# 对x_train（300*12）依次存入第0-10，10-20行......数据
ys = y_train[step * batch_size : (step+1) * batch_size] # 对y_train（300*1）
grads = grad(xs,ys,W,B) #计算梯度
optimizer.apply_gradients(zip(grads,[W,B])) # 优化器根据梯度自动调整变量 W和B
loss_train = loss(x_train, y_train, W, B).numpy() # 计算当前轮训练损失
loss_valid = loss(x_valid, y_valid, W, B).numpy() # 计算当前轮验证损失
loss_list_train.append(loss_train)
loss_list_valid.append(loss_valid)
print("epoch={:3d}, train_loss={:.4f}, valid_loss = {:.4f}".format(epoch+1,loss_train,loss_valid))
epoch= 1, train_loss=nan, valid_loss = nan
epoch= 2, train_loss=nan, valid_loss = nan
epoch= 3, train_loss=nan, valid_loss = nan
epoch= 4, train_loss=nan, valid_loss = nan
epoch= 5, train_loss=nan, valid_loss = nan
epoch= 6, train_loss=nan, valid_loss = nan
epoch= 7, train_loss=nan, valid_loss = nan
epoch= 8, train_loss=nan, valid_loss = nan
epoch= 9, train_loss=nan, valid_loss = nan
epoch= 10, train_loss=nan, valid_loss = nan
epoch= 11, train_loss=nan, valid_loss = nan
epoch= 12, train_loss=nan, valid_loss = nan
epoch= 13, train_loss=nan, valid_loss = nan
epoch= 14, train_loss=nan, valid_loss = nan
epoch= 15, train_loss=nan, valid_loss = nan
epoch= 16, train_loss=nan, valid_loss = nan
epoch= 17, train_loss=nan, valid_loss = nan
epoch= 18, train_loss=nan, valid_loss = nan
epoch= 19, train_loss=nan, valid_loss = nan
epoch= 20, train_loss=nan, valid_loss = nan
epoch= 21, train_loss=nan, valid_loss = nan
epoch= 22, train_loss=nan, valid_loss = nan
epoch= 23, train_loss=nan, valid_loss = nan
epoch= 24, train_loss=nan, valid_loss = nan
epoch= 25, train_loss=nan, valid_loss = nan
epoch= 26, train_loss=nan, valid_loss = nan
epoch= 27, train_loss=nan, valid_loss = nan
epoch= 28, train_loss=nan, valid_loss = nan
epoch= 29, train_loss=nan, valid_loss = nan
epoch= 30, train_loss=nan, valid_loss = nan
epoch= 31, train_loss=nan, valid_loss = nan
epoch= 32, train_loss=nan, valid_loss = nan
epoch= 33, train_loss=nan, valid_loss = nan
epoch= 34, train_loss=nan, valid_loss = nan
epoch= 35, train_loss=nan, valid_loss = nan
epoch= 36, train_loss=nan, valid_loss = nan
epoch= 37, train_loss=nan, valid_loss = nan
epoch= 38, train_loss=nan, valid_loss = nan
epoch= 39, train_loss=nan, valid_loss = nan
epoch= 40, train_loss=nan, valid_loss = nan
epoch= 41, train_loss=nan, valid_loss = nan
epoch= 42, train_loss=nan, valid_loss = nan
epoch= 43, train_loss=nan, valid_loss = nan
epoch= 44, train_loss=nan, valid_loss = nan
epoch= 45, train_loss=nan, valid_loss = nan
epoch= 46, train_loss=nan, valid_loss = nan
epoch= 47, train_loss=nan, valid_loss = nan
epoch= 48, train_loss=nan, valid_loss = nan
epoch= 49, train_loss=nan, valid_loss = nan
epoch= 50, train_loss=nan, valid_loss = nan
版本2：特征数据归一化
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
#显示图像
import pandas as pd
from sklearn.utils import shuffle
from sklearn.preprocessing import scale
df = pd.read_csv("data/boston.csv",header = 0)
# 获取数据集的值
ds = df.values
# 划分特征数据和标签数据
x_data = ds[:,:12] #取前12列数据：506*12
y_data = ds[:,12] #取最后1列：506*1
# 特征数据归一化
# (特征值-特征值最小值) / (特征值最大值-特征值最小值)
# 对第i列的所有数据进行归一化
for i in range(12):
x_data[:,i] = (x_data[:,i] - x_data[:,i].min()) / (x_data[:,i].max() - x_data[:,i].min())
# 划分数据集：训练集、验证集和测试集
train_num = 300 #训练集的数目
valid_num = 100 #验证集的数目
test_num = len(x_data) - train_num - valid_num # 测试集的数目 = 506 - 训练集 - 验证集
# 训练集划分
x_train = x_data[:train_num]
y_train = y_data[:train_num]
# 验证集划分
x_valid = x_data[train_num : train_num + valid_num]
y_valid = y_data[train_num : train_num + valid_num]
# 测试集划分
x_test = x_data[train_num + valid_num : ]
y_test = y_data[train_num + valid_num : train_num + valid_num + test_num]
# 特征数据的类型转换
x_train = tf.cast(x_train, dtype=tf.float32)
x_valid = tf.cast(x_valid, dtype=tf.float32)
x_test = tf.cast(x_test, dtype=tf.float32)
# 定义模型
def model(x, w, b):
return tf.matmul(x,w) + b
# 创建变量
W = tf.Variable(tf.random.normal([12,1],mean = 0.0, stddev = 1.0, dtype = tf.float32))
B = tf.Variable(tf.zeros(1), dtype = tf.float32)
# 设置训练参数
training_epochs = 50
leraning_rate = 0.001
batch_size = 10 # 批量训练一次的样本数
# 定义均方差损失函数
def loss(x,y,w,b):
err = model(x,w,b) - y
squared_err = tf.square(err) #求平方，得出方差
return tf.reduce_mean(squared_err) # 求均值，得出均方差
# 定义梯度计算函数
# 计算样本数据[x,y]在参数[w,b]点上的梯度
def grad(x,y,w,b):
with tf.GradientTape() as tape:
loss_ = loss(x,y,w,b)
return tape.gradient(loss_, [w,b]) # 返回梯度向量
loss_list_train = [] # 用于保存训练集loss值的列表
loss_list_valid = [] # 用于保存验证集loss值的列表
total_step = int(train_num / batch_size)
# 选择优化器
optimizer = tf.keras.optimizers.SGD(leraning_rate) # 随机梯度下降优化器，并乘上学习率
for epoch in range(training_epochs):
for step in range(total_step):
xs = x_train[step * batch_size : (step+1) * batch_size, :]
# 对x_train（300*12）依次存入第0-10，10-20行......数据
ys = y_train[step * batch_size : (step+1) * batch_size] # 对y_train（300*1）
grads = grad(xs,ys,W,B) #计算梯度
optimizer.apply_gradients(zip(grads,[W,B])) # 优化器根据梯度自动调整变量 W和B
loss_train = loss(x_train, y_train, W, B).numpy() # 计算当前轮训练损失
loss_valid = loss(x_valid, y_valid, W, B).numpy() # 计算当前轮验证损失
loss_list_train.append(loss_train)
loss_list_valid.append(loss_valid)
print("epoch={:3d}, train_loss={:.4f}, valid_loss = {:.4f}".format(epoch+1,loss_train,loss_valid))
epoch= 1, train_loss=515.6136, valid_loss = 333.1685
epoch= 2, train_loss=408.4633, valid_loss = 247.1792
epoch= 3, train_loss=328.1588, valid_loss = 188.2397
epoch= 4, train_loss=267.9438, valid_loss = 148.7497
epoch= 5, train_loss=222.7648, valid_loss = 123.1357
epoch= 6, train_loss=188.8417, valid_loss = 107.3244
epoch= 7, train_loss=163.3470, valid_loss = 98.3509
epoch= 8, train_loss=144.1651, valid_loss = 94.0675
epoch= 9, train_loss=129.7130, valid_loss = 92.9281
epoch= 10, train_loss=118.8064, valid_loss = 93.8281
epoch= 11, train_loss=110.5585, valid_loss = 95.9854
epoch= 12, train_loss=104.3058, valid_loss = 98.8533
epoch= 13, train_loss=99.5513, valid_loss = 102.0555
epoch= 14, train_loss=95.9230, valid_loss = 105.3386
epoch= 15, train_loss=93.1419, valid_loss = 108.5374
epoch= 16, train_loss=90.9991, valid_loss = 111.5489
epoch= 17, train_loss=89.3381, valid_loss = 114.3139
epoch= 18, train_loss=88.0412, valid_loss = 116.8035
epoch= 19, train_loss=87.0202, valid_loss = 119.0092
epoch= 20, train_loss=86.2090, valid_loss = 120.9360
epoch= 21, train_loss=85.5577, valid_loss = 122.5972
epoch= 22, train_loss=85.0289, valid_loss = 124.0113
epoch= 23, train_loss=84.5942, valid_loss = 125.1992
epoch= 24, train_loss=84.2325, valid_loss = 126.1827
epoch= 25, train_loss=83.9277, valid_loss = 126.9833
epoch= 26, train_loss=83.6676, valid_loss = 127.6219
epoch= 27, train_loss=83.4428, valid_loss = 128.1178
epoch= 28, train_loss=83.2465, valid_loss = 128.4888
epoch= 29, train_loss=83.0732, valid_loss = 128.7511
epoch= 30, train_loss=82.9189, valid_loss = 128.9193
epoch= 31, train_loss=82.7803, valid_loss = 129.0065
epoch= 32, train_loss=82.6550, valid_loss = 129.0242
epoch= 33, train_loss=82.5412, valid_loss = 128.9827
epoch= 34, train_loss=82.4372, valid_loss = 128.8908
epoch= 35, train_loss=82.3420, valid_loss = 128.7564
epoch= 36, train_loss=82.2546, valid_loss = 128.5863
epoch= 37, train_loss=82.1743, valid_loss = 128.3865
epoch= 38, train_loss=82.1004, valid_loss = 128.1621
epoch= 39, train_loss=82.0323, valid_loss = 127.9175
epoch= 40, train_loss=81.9698, valid_loss = 127.6566
epoch= 41, train_loss=81.9125, valid_loss = 127.3827
epoch= 42, train_loss=81.8599, valid_loss = 127.0987
epoch= 43, train_loss=81.8119, valid_loss = 126.8069
epoch= 44, train_loss=81.7683, valid_loss = 126.5096
epoch= 45, train_loss=81.7288, valid_loss = 126.2083
epoch= 46, train_loss=81.6932, valid_loss = 125.9047
epoch= 47, train_loss=81.6614, valid_loss = 125.6000
epoch= 48, train_loss=81.6332, valid_loss = 125.2954
epoch= 49, train_loss=81.6085, valid_loss = 124.9918
epoch= 50, train_loss=81.5871, valid_loss = 124.6898
plt.xlabel("Epochs")
plt.ylabel("Loss")
plt.plot(loss_list_train, 'blue', label = "Train Loss")
plt.plot(loss_list_valid,'red', label = "Valid Loss")
plt.legend(loc = 1)# 通过参数loc指定图例位置
查看测试集损失
print("Test_loss:{:.4f}".format(loss(x_test, y_test, W, B).numpy()))
Test_loss:198.1025
应用模型
test_house_id = np.random.randint(0, test_num)
y = y_test[test_house_id]
y_pred = model(x_test, W, B)[test_house_id]
y_predict = tf.reshape(y_pred,()).numpy()
print("House id:", test_house_id, "\nActual value:", y, "\nPredicted value:", y_predict)
House id: 83
Actual value: 21.8
Predicted value: 26.273846