梯度下降求解逻辑回归

创建Python Project

#建立一个逻辑回归模型来预测一个学生是否被大学录取，假设你是一个大学系的管理员，
#你想根据两次考试的结果来决定每个申请人的录取机会。你有以前的申请人的历史数据，
#你可以用它作为逻辑回归的训练集。对于每一个培训例子，你有两个考试的申请人的分数
#和录取决定。为了做到这一点，我们将建立一个分类模型，根据考试成绩估计入学概率。

数据准备

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import os
path = 'data' + os.sep + 'LogiReg_data.txt'
pdData = pd.read_csv(path, header=None, names=['Exam1','Exam2','Admitted'])
pdData.head()
positive = pdData[pdData['Admitted'] == 1]
negative = pdData[pdData['Admitted'] == 0]
fig, ax = plt.subplots(figsize=(10,5))
ax.scatter(positive['Exam1'],positive['Exam2'], s=30, c='b', marker='o',label='Admitted')
ax.scatter(negative['Exam1'],negative['Exam2'], s=30, c='b', marker='x',label='Not Admitted')
ax.legend()
ax.set_xlabel('Exam 1 Score')
ax.set_ylabel('Exam 2 Score')

sigmoid：映射到概率的函数

model：返回预测结果值

gradient：计算每个参数的梯度方向

descent：进行参数更新

accuracy：计算精度

def sigmoid(z):
    return 1 / (1 + np.exp(-z))
nums  = np.arange(-10,10,step=1)
fig, ax = plt.subplots(figsize=(12,4))
ax.plot(nums, sigmoid(nums),'r')
def model(X, theta):
    return sigmoid(np.dot(X, theta.T))
pdData.insert(0, 'Ones', 1)
orig_data = pdData.as_matrix()
cols = orig_data.shape[1]
X = orig_data[:,0:cols-1]
y = orig_data[:,cols-1:cols]
theta = np.zeros([1,3])

损失函数

def cost(X, y, theta):
    left = np.multiply(-y, np.log(model(X, theta)))
    right = np.multiply(1 - y, np.log(1 - model(X, theta)))
    return np.sum(left - right) / (len(X))
cost(X, y, theta)

计算梯度

def gradient(X, y, theta):
    grad = np.zeros(theta.shape)
    error = (model(X, theta) - y).ravel()
    for j in range(len(theta.ravel())):
        term = np.multiply(error,X[:,j])
        grad[0, j] = np.sum(term) / len(X)
    return grad

Gradient descent

STOP_ITER = 0
STOP_COST = 1
STOP_GRAD = 2
def stopCriterion(type,value,threshold):
    #设定三种不同的停止策略
    if type == STOP_ITER:          return value > threshold
    elif type == STOP_COST:        return abs(value[-1]-value[-2]) <threshold
    elif type == STOP_GRAD:        return np.linalg.norm(value) < threshold
import numpy.random
def shuffleData(data):
    np.random.shuffle(data)
    cols = data.shape[1]
    X = data[:,0: cols-1]
    y = data[:,cols-1: ]
    return X, y
import time
def descent(data,theta,batchSize,stopType,thresh,alpha):
    init_time = time.time()
    i = 0
    k = 0
    X, y = shuffleData(data)
    grad = np.zeros(theta.shape)
    costs = [cost(X, y, theta)]
    while True:
        grad = gradient(X[k:k+batchSize], y[k:k+batchSize], theta)
        k += batchSize
        if k >= n:
            k = 0
            X, y = shuffleData(data)
        theta = theta - alpha * grad
        costs.append(cost(X, y, theta))
        i += 1
        if stopType == STOP_ITER:      value = i
        elif stopType == STOP_COST:      value = costs
        elif stopType == STOP_GRAD:      value = grad
        if stopCriterion(stopType,value,thresh): break
    return theta, i-1, costs, grad, time.time() - init_time
def runExpe(data, theta, batchSize, stopType, thresh, alpha):
    theta, iter, costs, grad, dur = descent(data, theta, batchSize, stopType, thresh, alpha)
    name = "Original" if (data[:,1]>2).sum() > 1 else "Scaled"
    name += " data - learning rate: {} - ".format(alpha)
    if batchSize==n: strDescType = "Gradient"
    elif batchSize==1:  strDescType = "Stochastic"
    else: strDescType = "Mini-batch ({})".format(batchSize)
    name += strDescType + " descent - Stop: "
    if stopType == STOP_ITER: strStop = "{} iterations".format(thresh)
    elif stopType == STOP_COST: strStop = "costs change < {}".format(thresh)
    else: strStop = "gradient norm < {}".format(thresh)
    name += strStop
    print ("***{}\nTheta: {} - Iter: {} - Last cost: {:03.2f} - Duration: {:03.2f}s".format(
        name, theta, iter, costs[-1], dur))
    fig, ax = plt.subplots(figsize=(12,4))
    ax.plot(np.arange(len(costs)), costs, 'r')
    ax.set_xlabel('Iterations')
    ax.set_ylabel('Cost')
    ax.set_title(name.upper() + ' - Error vs. Iteration')
    return theta

选择的梯度下降方法是基于所有样本的

n = 100

设定迭代次数

runExpe(orig_data, theta, n, STOP_ITER, thresh=5000, alpha=0.000001)

根据损失值停止

runExpe(orig_data, theta, n, STOP_COST, thresh=0.000001, alpha=0.001)

根据梯度变化停止

runExpe(orig_data, theta, n, STOP_GRAD, thresh=0.05, alpha=0.001)
plt.show()