笔记 - 线性回归：tensorflow原生实现线性回归梯度下降参数更新过程

手动实现线性回归梯度计算公式

"""
X：m×n矩阵 -- m行样本n个维度
error： 列向量
"""
gradients = 1/m * tf.matmul(tf.transpose(X), error)

---

• 基于sklearn fetch_california_housing 数据集

import tensorflow as tf
import numpy as np
from sklearn.datasets import fetch_california_housing
from sklearn.preprocessing import StandardScaler


n_epochs = 36500
learning_rate = 0.001
# sklearn_learn.datasets 数据保存的地址
housing = fetch_california_housing(data_home="../data/scikit_learn_data", download_if_missing=True)
scaler = StandardScaler().fit(housing_data_plus_bias)
scaled_housing_data_plus_bias = scaler.transform(housing_data_plus_bias)

X = tf.constant(scaled_housing_data_plus_bias, dtype=tf.float32, name='X')
y = tf.constant(housing.target.reshape(-1, 1), dtype=tf.float32, name='y')

# random_uniform函数创建图里一个节点包含随机数值，给定它的形状和取值范围，就像numpy里面rand()函数
theta = tf.Variable(tf.random_uniform([n + 1, 1], -1.0, 1.0), name='theta')

y_pred = tf.matmul(X, theta, name="predictions")
error = y_pred - y
rmse = tf.sqrt(tf.reduce_mean(tf.square(error), name="rmse"))
# 梯度的公式：(y_pred - y) * xj
gradients = 2/m * tf.matmul(tf.transpose(X), error)
# 赋值函数对于BGD来说就是 theta_new = theta - (learning_rate * gradients)
training_op = tf.assign(theta, theta - learning_rate * gradients)

init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)

    for epoch in range(n_epochs):
        if epoch % 100 == 0:
            print("Epoch", epoch, "RMSE = ", rmse.eval())
        sess.run(training_op)

    best_theta = theta.eval()
    print(best_theta)