机器学习/深度学习入门：python实现逻辑回归(二分类)
代价函数总是NaN的问题已解决
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2018/4/3 19:37
# @Author : HJH
# @Site :
# @File : logistics.py
# @Software: PyCharm
from numpy import *
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_breast_cancer
class log(object):
def __init__(self):
self.W=None
def sigmoid(self,X):
# longfloat防止溢出,但是并没有什么用
return longfloat(1.0 / (1.0 + exp(-X)))
def loss(self,X_train,y_train):
m,n=X_train.shape
h=self.sigmoid(X_train.dot(self.W))
# print(h)
# print((h-y).shape)
#此处的loss是矩阵类型,为了便于画图将其中的数取出
loss=(y_train.T.dot(np.log(h))+(1-y_train).T.dot(np.log(1-h)))/-m
loss=loss[0,0]
dW=X_train.T.dot((h - y_train)) / m
# print(dW.shape, '-----------')
return loss,dW
def train(self,X_train,y_train,learn_rate=0.0005,iters=10000):
m,n=X_train.shape
# print(m,n)
self.W=np.random.rand(n,1)
loss_list = []
for i in range(iters):
loss,dW=self.loss(X_train,y_train)
self.W-=learn_rate*dW
loss_list.append(loss)
if i % 500 == 0:
print('iters = %d,loss = %f' % (i, loss))
return loss_list
def predict(self, X_test):
m=X_test.shape[0]
X_test = np.hstack((X_test, mat(np.ones((m, 1)))))
y_pred_list=[]
for xx in X_test:
y_pred = self.sigmoid(xx.dot(self.W))
# y_pred_list.append(y_pred[0,0])
if y_pred>=0.5:
y_pred_list.append(1)
else:
y_pred_list.append(0)
return y_pred_list
#从文件中加载数据：特征X，标签label
def loadDataSet():
digits=load_breast_cancer()
norm_digits=autoNorm(digits.data)
X_train = norm_digits[:-10,:]
m= X_train.shape[0]
#print(m,n)
y_total = digits.target.reshape(569,1)
#print(y_total.shape)
y_train=y_total[:-10,:]
#print(m,n)
#print(X)
X_train = np.hstack((X_train,mat(np.ones((559,1)))))
# print(X)
#print(y.shape)
X_test=norm_digits[-10:,:]
X_test=X_test
y_test = y_total[-10:, :]
return X_train,y_train,X_test,y_test#将数据归一化(解决代价函数NaN)
def autoNorm(X):
minVals=X.min(0)
maxVals=X.max(0)
ranges=maxVals-minVals
normDataSet=zeros(shape(X))
m=X.shape[0]
normDataSet=X-tile(minVals,(m,1))#在行方向重复minVals m次和列方向上重复minVals 1次
normDataSet=normDataSet/tile(ranges,(m,1))
return normDataSet
def plot(loss_list,log):
fig = plt.figure()
digits = load_breast_cancer()
norm_digits = autoNorm(digits.data)
x_index = 0
y_index = 1
colors = ['blue', 'red']
plt.subplot(211)
for label, color in zip(range(len(digits.target_names)), colors):
plt.scatter(norm_digits[digits.target == label, x_index],
norm_digits[digits.target == label, y_index],
label=digits.target_names[label],
c=color)
plt.xlabel(digits.feature_names[x_index])
plt.ylabel(digits.feature_names[y_index])
plt.legend(loc='upper left')
plt.subplot(212)
plt.plot(loss_list, color='blue')
plt.xlabel('epochs')
plt.ylabel('errors')
plt.show()
if __name__ == '__main__':
X_train,y_train,X_test,y_test=loadDataSet()
l=log()
loss_list=l.train(X_train,y_train)
print(l.predict(X_test))
for i in loss_list:
print(i)
plot(loss_list,l)
网上的做法：
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2018/4/4 11:07
# @Author : HJH
# @Site :
# @File : temp.py
# @Software: PyCharm
from numpy import *
filename='./testSet.txt' #文件目录
def loadDataSet(): #读取数据（这里只有两个特征）
dataMat = []
labelMat = []
fr = open(filename)
for line in fr.readlines():
lineArr = line.strip().split()
dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])]) #前面的1，表示方程的常量。比如两个特征X1,X2，共需要三个参数，W1+W2*X1+W3*X2
labelMat.append(int(lineArr[2]))
return dataMat,labelMat
def sigmoid(inX): #sigmoid函数
return 1.0/(1+exp(-inX))
def gradAscent(dataMat, labelMat): #梯度上升求最优参数
dataMatrix=mat(dataMat) #将读取的数据转换为矩阵
classLabels=mat(labelMat).transpose() #将读取的数据转换为矩阵
m,n = shape(dataMatrix)
alpha = 0.001 #设置梯度的阀值，该值越大梯度上升幅度越大
maxCycles = 500 #设置迭代的次数，一般看实际数据进行设定，有些可能200次就够了
weights = ones((n,1)) #设置初始的参数，并都赋默认值为1。注意这里权重以矩阵形式表示三个参数。
for k in range(maxCycles):
h = sigmoid(dataMatrix*weights)
error = (classLabels - h) #求导后差值
weights = weights + alpha * dataMatrix.transpose()* error #迭代更新权重
return weights
def stocGradAscent0(dataMat, labelMat): #随机梯度上升，当数据量比较大时，每次迭代都选择全量数据进行计算，计算量会非常大。所以采用每次迭代中一次只选择其中的一行数据进行更新权重。
dataMatrix=mat(dataMat)
classLabels=labelMat
m,n=shape(dataMatrix)
alpha=0.01
maxCycles = 500
weights=ones((n,1))
for k in range(maxCycles):
for i in range(m): #遍历计算每一行
h = sigmoid(sum(dataMatrix[i] * weights))
error = classLabels[i] - h
weights = weights + alpha * error * dataMatrix[i].transpose()
return weights
def stocGradAscent1(dataMat, labelMat): #改进版随机梯度上升，在每次迭代中随机选择样本来更新权重，并且随迭代次数增加，权重变化越小。
dataMatrix=mat(dataMat)
classLabels=labelMat
m,n=shape(dataMatrix)
weights=ones((n,1))
maxCycles=500
for j in range(maxCycles): #迭代
dataIndex=[i for i in range(m)]
for i in range(m): #随机遍历每一行
alpha=4/(1+j+i)+0.0001 #随迭代次数增加，权重变化越小。
randIndex=int(random.uniform(0,len(dataIndex))) #随机抽样
h=sigmoid(sum(dataMatrix[randIndex]*weights))
error=classLabels[randIndex]-h
weights=weights+alpha*error*dataMatrix[randIndex].transpose()
del(dataIndex[randIndex]) #去除已经抽取的样本
return weights
def plotBestFit(weights): #画出最终分类的图
import matplotlib.pyplot as plt
dataMat,labelMat=loadDataSet()
dataArr = array(dataMat)
n = shape(dataArr)[0]
xcord1 = []; ycord1 = []
xcord2 = []; ycord2 = []
for i in range(n):
if int(labelMat[i])== 1:
xcord1.append(dataArr[i,1])
ycord1.append(dataArr[i,2])
else:
xcord2.append(dataArr[i,1])
ycord2.append(dataArr[i,2])
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(xcord1, ycord1, s=30, c='red', marker='s')
ax.scatter(xcord2, ycord2, s=30, c='green')
x = arange(-3.0, 3.0, 0.1)
y = (-weights[0]-weights[1]*x)/weights[2]
ax.plot(x, y)
plt.xlabel('X1')
plt.ylabel('X2')
plt.show()
if __name__=='__main__':
dataMat, labelMat = loadDataSet()
weights = gradAscent(dataMat, labelMat).getA()
plotBestFit(weights)test.txt数据集：
-0.017612 14.053064 0
-1.395634 4.662541 1
-0.752157 6.538620 0
-1.322371 7.152853 0
0.423363 11.054677 0
0.406704 7.067335 1
0.667394 12.741452 0
-2.460150 6.866805 1
0.569411 9.548755 0
-0.026632 10.427743 0
0.850433 6.920334 1
1.347183 13.175500 0
1.176813 3.167020 1
-1.781871 9.097953 0
-0.566606 5.749003 1
0.931635 1.589505 1
-0.024205 6.151823 1
-0.036453 2.690988 1
-0.196949 0.444165 1
1.014459 5.754399 1
1.985298 3.230619 1
-1.693453 -0.557540 1
-0.576525 11.778922 0
-0.346811 -1.678730 1
-2.124484 2.672471 1
1.217916 9.597015 0
-0.733928 9.098687 0
-3.642001 -1.618087 1
0.315985 3.523953 1
1.416614 9.619232 0
-0.386323 3.989286 1
0.556921 8.294984 1
1.224863 11.587360 0
-1.347803 -2.406051 1
1.196604 4.951851 1
0.275221 9.543647 0
0.470575 9.332488 0
-1.889567 9.542662 0
-1.527893 12.150579 0
-1.185247 11.309318 0
-0.445678 3.297303 1
1.042222 6.105155 1
-0.618787 10.320986 0
1.152083 0.548467 1
0.828534 2.676045 1
-1.237728 10.549033 0
-0.683565 -2.166125 1
0.229456 5.921938 1
-0.959885 11.555336 0
0.492911 10.993324 0
0.184992 8.721488 0
-0.355715 10.325976 0
-0.397822 8.058397 0
0.824839 13.730343 0
1.507278 5.027866 1
0.099671 6.835839 1
-0.344008 10.717485 0
1.785928 7.718645 1
-0.918801 11.560217 0
-0.364009 4.747300 1
-0.841722 4.119083 1
0.490426 1.960539 1
-0.007194 9.075792 0
0.356107 12.447863 0
0.342578 12.281162 0
-0.810823 -1.466018 1
2.530777 6.476801 1
1.296683 11.607559 0
0.475487 12.040035 0
-0.783277 11.009725 0
0.074798 11.023650 0
-1.337472 0.468339 1
-0.102781 13.763651 0
-0.147324 2.874846 1
0.518389 9.887035 0
1.015399 7.571882 0
-1.658086 -0.027255 1
1.319944 2.171228 1
2.056216 5.019981 1
-0.851633 4.375691 1
-1.510047 6.061992 0
-1.076637 -3.181888 1
1.821096 10.283990 0
3.010150 8.401766 1
-1.099458 1.688274 1
-0.834872 -1.733869 1
-0.846637 3.849075 1
1.400102 12.628781 0
1.752842 5.468166 1
0.078557 0.059736 1
0.089392 -0.715300 1
1.825662 12.693808 0
0.197445 9.744638 0
0.126117 0.922311 1
-0.679797 1.220530 1
0.677983 2.556666 1
0.761349 10.693862 0
-2.168791 0.143632 1
1.388610 9.341997 0
0.317029 14.739025 0