DL7-波士顿房价预测问题：TensorFlow 2.0 实践

最新推荐文章于 2022-05-04 11:01:13 发布

Cheeky_man

最新推荐文章于 2022-05-04 11:01:13 发布

阅读量701

点赞数 1

分类专栏：学习总结深度学习文章标签： tensorflow 深度学习

本文链接：https://blog.csdn.net/qq_36045093/article/details/106167987

版权

学习总结同时被 2 个专栏收录

76 篇文章 151 订阅

订阅专栏

深度学习

9 篇文章 0 订阅

订阅专栏

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	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	LSTAT	MEDV
0	0.00632	18.0	2.31	0.538	6.575	65.2	4.0900	1	296	15.3	4.98	24.0
1	0.02731	0.0	7.07	0.469	6.421	78.9	4.9671	2	242	17.8	9.14	21.6
2	0.02729	0.0	7.07	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	INDUS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	LSTAT	MEDV
503	0.06076	11.93	0.573	6.976	91.0	2.1675	1	273	21.0	5.64	23.9
504	0.10959	11.93	0.573	6.794	89.3	2.3889	1	273	21.0	6.48	22.0
505	0.04741	11.93	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)

<tf.Variable 'Variable:0' shape=(12, 1) dtype=float32, numpy=
array([[-0.20106229],
       [-1.7443002 ],
       [-1.36172   ],
       [ 0.16418922],
       [-0.74266136],
       [-1.269902  ],
       [ 0.13221206],
       [ 0.8136817 ],
       [ 0.47367275],
       [ 0.58916664],
       [ 0.05464758],
       [-2.041994  ]], dtype=float32)> 

 <tf.Variable 'Variable:0' shape=(1,) dtype=float32, numpy=array([0.], dtype=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

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

<matplotlib.legend.Legend at 0x20932ff7808>

训练集、测试集的结果

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

Cheeky_man

关注

1
点赞
踩
7

收藏

觉得还不错? 一键收藏
打赏
0
评论
DL7-波士顿房价预测问题：TensorFlow 2.0 实践

导入库import tensorflow as tfimport numpy as npimport matplotlib.pyplot as plt%matplotlib inline #显示图像import pandas as pdfrom sklearn.utils import shufflefrom sklearn.preprocessing import scaleprint("TensorFlow版本是：",tf.__version__)TensorFlow版本是：
复制链接

扫一扫