二、回归问题

最新推荐文章于 2023-11-12 16:31:26 发布

原创最新推荐文章于 2023-11-12 16:31:26 发布 · 373 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#python #机器学习 #深度学习 #人工智能

深度学习专栏收录该内容

12 篇文章

订阅专栏

本文主要探讨了TensorFlow2在回归问题中的应用，包括数据生成和线性回归的实现，是作者的学习笔记，旨在方便未来复习。

二、回归问题

内容参考来自https://github.com/dragen1860/Deep-Learning-with-TensorFlow-book开源书籍《TensorFlow2深度学习》，这只是我做的简单的学习笔记，方便以后复习。

1. 数据生成

import numpy as np
import pandas as pd

# y = wx + b
data = []
X = []
Y = []
for i in range(100):
    x = np.random.uniform(3., 12.)
    # mean=0, std=0.1
    eps = np.random.normal(0., 0.1)
    y = 1.477 * x + 0.089 + eps
    X.append(x)
    Y.append(y)
    data.append([x, y])
data = np.array(data)
print(data.shape, data)

dataFrame = pd.DataFrame({'x': X, 'y': Y})
dataFrame.to_csv("data_jyz.csv", index=False, sep=',', header=None)

2.线性回归

import numpy as np
import matplotlib.pyplot as plt


def compute_error_for_line_given_points(b, w, points):
    totalError = 0
    for i in range(0, len(points)):
        x = points[i, 0]
        y = points[i, 1]
        # computer mean-squared-error
        totalError += (y - (w * x + b)) ** 2
    # average loss for each point
    return totalError / float(len(points))


def step_gradient(b_current, w_current, points, learningRate):
    b_gradient = 0
    w_gradient = 0
    N = float(len(points))
    for i in range(0, len(points)):
        x = points[i, 0]
        y = points[i, 1]
        # grad_b = 2(wx+b-y)
        b_gradient += (2 / N) * ((w_current * x + b_current) - y)
        # grad_w = 2(wx+b-y)*x
        w_gradient += (2 / N) * x * ((w_current * x + b_current) - y)
    # update w'
    new_b = b_current - (learningRate * b_gradient)
    new_w = w_current - (learningRate * w_gradient)
    return [new_b, new_w]


def gradient_descent_runner(points, starting_b, starting_w, learning_rate, num_iterations):
    b = starting_b
    w = starting_w
    # update for several times
    for i in range(num_iterations):
        b, w = step_gradient(b, w, np.array(points), learning_rate)
    return [b, w]


def showCharts(points, w, b):
    points = np.array(points)
    plt.scatter(points[:, 0], points[:, 1])
    x_ = np.random.uniform(0, 80, 100)
    y_ = w * x_ + b
    plt.plot(x_, y_)
    plt.show()


def run():
    points = np.genfromtxt("data.csv", delimiter=",")
    learning_rate = 0.0001
    initial_b = 0  # initial y-intercept guess
    initial_w = 0  # initial slope guess
    num_iterations = 1000
    print("Starting gradient descent at b = {0}, w = {1}, error = {2}".format(initial_b, initial_w,
                                                                              compute_error_for_line_given_points(
                                                                                  initial_b, initial_w, points)))
    print("Running...")
    [b, w] = gradient_descent_runner(points, initial_b, initial_w, learning_rate, num_iterations)
    print("After {0} iterations b = {1}, w = {2}, error = {3}".
          format(num_iterations, b, w,
                 compute_error_for_line_given_points(b, w, points))
          )
    showCharts(points, w, b)


if __name__ == '__main__':
    run()