#数据分析与机器学习笔记# 逻辑回归与梯度下降的实现

逻辑回归与梯度下降
（来自于视频学习）

目标：建立分类器（求解出三个参数O1,O2,O3）
设定阈值，根据阈值判断结果

要完成的模块
1、sigmoid：映射到函数的概率

2、model：返回预测结果值

3、cost：根据参数计算损失函数

4、gradient：计算每个参数的梯度方向

5、descent:进行参数更新
6、accuracy：计算精度

代码实现：

1、必备模块

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

2、读取数据：

path = 'data'+os.sep+'LogiReg_data.txt'
pdData = pd.read_csv(path, header = None, names = ['Exam 1', 'Exam 2','Admitted'])
#print(pdData.head())
#print(pdData.shape)

#指定正负
positive = pdData[pdData['Admitted']==1]
negative = pdData[pdData['Admitted']==0]

#画图
fig, ax = plt.subplots(figsize=(10,5)) #指定画图域的大小
ax.scatter(positive['Exam 1'], positive['Exam 2'], s=30, c='b', marker='o', label='Admitted')
ax.scatter(negative['Exam 1'], negative['Exam 2'], s=30, c='r', marker='x', label='Not Admitted')
ax.legend()
ax.set_xlabel('Exam 1 Score')
ax.set_ylabel('Exam 2 Score')
#plt.show()

3、构造数据

pdData.insert(0,'ones',1) #插入一列1
#设置X为训练数据，Y为目标值
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])
print(theta)
print(X[:5])
print(X.shape, Y.shape, theta.shape)

4、定义sigmoid 模块

def sigmoid(z):
    return 1/(1+np.exp(-z))
#simoid函数画图展示
# nums = np.arange(-10,10,step = 1)
# fig, ax = plt.subplots(figsize=(12,4))
# ax.plot(nums, sigmoid(nums),'r')
# plt.show()

5、定义模型

def model(X, theta):
    return sigmoid(np.dot(X,theta.T))  #np.dot矩阵的乘法，X与参数矩阵相乘

6、定义损失函数

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

7、定义梯度

def gradient(X,Y,theta):
    grad = np.zeros(theta.shape)
    error = (model(X,theta)-Y).ravel()
    for j in range(len(theta.ravel())):#d对所有O求偏导
        term = np.multiply(error, X[:,j])
        grad[0, j] = np.sum(term)/len(X)
    return grad

8、梯度下降停止策略

STOP_ITER = 0 #迭代次数
STOP_COST = 1 #损失函数
STOP_GRAD = 2 #梯度
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

9、数据随机打乱

import numpy.random
#洗牌
def shuffleData(data):
    np.random.shuffle(data)
    cols = data.shape[1]
    X = data[:, 0:cols-1]
    y = data[:, cols-1:]
    return X, y

10、梯度下降求解

import time
def descent(data, theta, batchSize, stopType, thresh, alpha):
    # 梯度下降求解
    init_time = time.time()
    i = 0  # 迭代次数
    k = 0  # batch
    X, y = shuffleData(data)
    grad = np.zeros(theta.shape)  # 计算的梯度
    costs = [cost(X, y, theta)]  # 损失值

    while True:
        grad = gradient(X[k:k + batchSize], y[k:k + batchSize], theta)
        k += batchSize  # 取batch数量个数据
        if k >= n:
            k = 0
            X, y = shuffleData(data)  # 重新洗牌
        theta = theta - alpha * grad  # 参数更新
        costs.append(cost(X, y, theta))  # 计算新的损失
        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

11、定义功能性函数

def runExpe(data, theta, batchSize, stopType, thresh, alpha):
    #import pdb; pdb.set_trace();
    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')
    plt.show()
    return theta

12、求精度

#选择的梯度下降方法是基于所有样本的
n=100
runExpe(orig_data, theta, n, STOP_ITER, thresh=5000, alpha=0.000001)
#将数据值转变为类别值
#设定阈值
def predict(X, theta):
    return [1 if x >= 0.5 else 0 for x in model(X, theta)]

scaled_X,y = shuffleData(orig_data)
predictions = predict(scaled_X, theta)

correct = [1 if ((a == 1 and b == 1) or (a == 0 and b == 0)) else 0 for (a, b) in zip(predictions, y)]
accuracy = (sum(map(int, correct)) % len(correct))
print ('accuracy = {0}%'.format(accuracy))

accuracy = 60%

提高精度的策略：
增加迭代次数，
降低学习率，
数据预处理，
选用不同的梯度下降策略，
等