Created
February 23, 2016 13:06
-
-
Save mrvege/43e67e5677d043cb39f2 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# encoding: utf-8 | |
from numpy import * | |
import matplotlib.pyplot as plt | |
def logistic(wTx): | |
return 1.0/(1.0 + exp(-wTx)) | |
def file2matrix(filename,delimiter): | |
recordlist = [] | |
fp = open(filename,"rb") | |
content = fp.read() | |
fp.close() | |
rowlist = content.splitlines() | |
# 逐行遍历 并将结果按分隔符分割为行向量 | |
recordlist=[map(eval, row.split(delimiter)) for row in rowlist if row.strip()] | |
# 返回转换后的矩阵形式 | |
return mat(recordlist) | |
def buildMat(dataSet): | |
m,n=shape(dataSet) | |
dataMat = zeros((m,n)) | |
dataMat[:,0] = 1 | |
dataMat[:,1:] = dataSet[:,:-1] | |
return dataMat | |
def load_data(): | |
filename = "testSet.txt" | |
Input = file2matrix(filename, delimiter='\t') | |
label = Input[:,-1] | |
return Input, label | |
def logistic_regression_bgd(Input, label): | |
num_samples, num_features = shape(Input) | |
dataMat = buildMat(Input) | |
alpha = 0.001 | |
steps = 500 | |
weights = ones((num_features, 1)) | |
for iteration in range(steps): | |
output = logistic(dataMat * mat(weights)) | |
error = label - output | |
weights = weights + alpha*dataMat.T*error | |
print weights | |
return weights | |
def logistic_regression_sgd(Input, label): | |
num_samples, num_features = shape(Input) | |
dataMat = buildMat(Input) | |
alpha = 0.001 | |
steps = 500 | |
weights = ones(num_features) | |
for iteration in range(steps): | |
dataIndex = range(num_samples) | |
for i in range(num_samples): | |
randIndex = random.randint(0, len(dataIndex)) | |
output = logistic(sum(dataMat[randIndex]*weights.T)) | |
error = label[randIndex] - output | |
weights = weights + alpha*error*dataMat[randIndex] | |
del(dataIndex[randIndex]) | |
print weights | |
return weights | |
def logistic_regression_nsgd(Input, label): | |
num_samples, num_features = shape(Input) | |
dataMat = buildMat(Input) | |
# alpha = 0.001 | |
steps = 500 | |
weights = ones(num_features) | |
for iteration in range(steps): | |
dataIndex = range(num_samples) | |
for i in range(num_samples): | |
alpha = 1.0/(1.0+i+iteration) + 0.0001 | |
randIndex = random.randint(0, len(dataIndex)) | |
output = logistic(sum(dataMat[randIndex]*weights.T)) | |
error = label[randIndex] - output | |
weights = weights + alpha*error*dataMat[randIndex] | |
del(dataIndex[randIndex]) | |
print weights | |
return weights | |
if __name__ == '__main__': | |
Input, label = load_data() | |
weights = logistic_regression_bgd(Input, label) | |
weights_2 = logistic_regression_sgd(Input, label) | |
weights_3 = logistic_regression_nsgd(Input, label) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment