#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @File : 自實現(xiàn)一個線性回歸.py
# @Author: 趙路倉
# @Date : 2020/4/12
# @Desc :
# @Contact : 398333404@qq.com
import os

import tensorflow as tf


def linear_regression():
  """
  自實現(xiàn)一個線性回歸
  :return:
  """
  # 命名空間
  with tf.variable_scope("prepared_data"):
    # 準(zhǔn)備數(shù)據(jù)
    x = tf.random_normal(shape=[100, 1], name="Feature")
    y_true = tf.matmul(x, [[0.08]]) + 0.7
    # x = tf.constant([[1.0], [2.0], [3.0]])
    # y_true = tf.constant([[0.78], [0.86], [0.94]])

  with tf.variable_scope("create_model"):
    # 2.構(gòu)造函數(shù)
    # 定義模型變量參數(shù)
    weights = tf.Variable(initial_value=tf.random_normal(shape=[1, 1], name="Weights"))
    bias = tf.Variable(initial_value=tf.random_normal(shape=[1, 1], name="Bias"))
    y_predit = tf.matmul(x, weights) + bias

  with tf.variable_scope("loss_function"):
    # 3.構(gòu)造損失函數(shù)
    error = tf.reduce_mean(tf.square(y_predit - y_true))

  with tf.variable_scope("optimizer"):
    # 4.優(yōu)化損失
    optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(error)

  # 收集變量
  tf.summary.scalar("error", error)
  tf.summary.histogram("weights", weights)
  tf.summary.histogram("bias", bias)

  # 合并變量
  merged = tf.summary.merge_all()

  # 創(chuàng)建saver對象
  saver = tf.train.Saver()

  # 顯式的初始化變量
  init = tf.global_variables_initializer()

  # 開啟會話
  with tf.Session() as sess:
    # 初始化變量
    sess.run(init)

    # 創(chuàng)建事件文件
    file_writer = tf.summary.FileWriter("E:/tmp/linear", graph=sess.graph)

    # print(x.eval())
    # print(y_true.eval())
    # 查看初始化變量模型參數(shù)之后的值
    print("訓(xùn)練前模型參數(shù)為:權(quán)重%f,偏置%f" % (weights.eval(), bias.eval()))

    # 開始訓(xùn)練
    for i in range(1000):
      sess.run(optimizer)
      print("第%d次參數(shù)為：權(quán)重%f,偏置%f,損失%f" % (i + 1, weights.eval(), bias.eval(), error.eval()))

      # 運行合并變量操作
      summary = sess.run(merged)
      # 將每次迭代后的變量寫入事件
      file_writer.add_summary(summary, i)

      # 保存模型
      if i == 999:
        saver.save(sess, "./tmp/model/my_linear.ckpt")

    # # 加載模型
    # if os.path.exists("./tmp/model/checkpoint"):
    #   saver.restore(sess, "./tmp/model/my_linear.ckpt")

    print("參數(shù)為：權(quán)重%f,偏置%f,損失%f" % (weights.eval(), bias.eval(), error.eval()))
    pre = [[0.5]]
    prediction = tf.matmul(pre, weights) + bias
    sess.run(prediction)
    print(prediction.eval())

  return None


if __name__ == "__main__":
  linear_regression()