波士顿房价预测模型-优快云博客

本文链接：https://blog.youkuaiyun.com/luyakuncsdnzc/article/details/102558041

本文介绍了一个使用TensorFlow实现的波士顿房价预测模型。该模型通过预处理数据、构建线性回归模型并进行训练，最终实现了对波士顿房价的准确预测。文中详细展示了数据读取、数据标准化、模型构建、损失函数定义、优化器选择、模型训练及预测的全过程。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from sklearn.utils import shuffle

df = pd.read_csv('data/boston.csv', header=0)

df = df.values
df = np.array(df)
for i in range(12):
    df[:, i] = df[:, i]/(df[:, i].max()-df[:, i].min())
x_data = df[:, :12]
y_data = df[:, 12]

x = tf.placeholder(tf.float32, [None, 12], name='X')
y = tf.placeholder(tf.float32, [None, 1], name='Y')

with tf.name_scope('Model'):
    w = tf.Variable(tf.random_normal([12, 1], stddev=0.01), name='w')
    b = tf.Variable(1.0, name='b')

    def model(x, w, b):
        wx_b = tf.matmul(x, w) + b
        return wx_b

L2 = model(x, w, b)


train_epochs = 50
learning_rate = 0.01

with tf.name_scope('Loss'):
    loss = tf.reduce_mean(tf.square(y-L2))

optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss)

loss_list = []
with tf.Session() as sess:
    init = tf.global_variables_initializer()
    sess.run(init)
    for epoch in range(train_epochs):
        loss_sum = 0.0
        for xs, ys in zip(x_data, y_data):
            xs = xs.reshape(1, 12)
            ys = ys.reshape(1, 1)

            _, loss_f = sess.run([optimizer, loss], feed_dict={x:xs, y:ys})
            loss_sum = loss_sum + loss_f

            xvalue, yvalue = shuffle(x_data, y_data)   #打乱数据的顺序
            b0temp = b.eval(session=sess)
            w0temp = w.eval(session=sess)
            loss_average = loss_sum/len(y_data)
            loss_list.append(loss_average)
            plt.plot(loss_list)
            #print('epoch', epoch+1, 'loss=', loss_average, 'b=', b0temp, 'w', w0temp)
    n = np.random.randint(506)
    print(n)
    x_test = x_data[n]

    x_test = x_test.reshape(1, 12)
    predict = sess.run(L2, feed_dict={x: x_test})
    print('预测值 %f' % predict)
    target = y_data[n]
    print('标签值 %f' % target)