logisticregression

 from numpy import *
 import random
 import time
 st = time.time()

 def loaddata(filename):
     fr = open(''.join([filename, '.txt'])).readlines()
     trainx = [[1] + map(float, line.split()[:-1]) for line in fr] # trainx = [[1,12.2,22.4],[1,22.3,31.2],...]
     trainy = [[float(line.split()[-1])] for line in fr] # trainy = [0,1,1,0,...]
     return trainx, trainy

 def sigmod(z):
     return 1.0 / (1 + exp(-z))

 def optimizaion(trainx, trainy):
     trainxmat = mat(trainx)
     m = len(trainx)
     # beta = [0,0,0]
     beta = ones((len(trainx[0]),1)) # array
     # maxiter
     M = 500
     """
     # error permid
     e =
     """
     """
     for i in xrange(M):
         #if error2sum > e:
         # z = betat.T * x = trainx (matricdoc)* beta = [beta.Tx1,beta.Tx2,...,beta.Txn]
         sigmodz = sigmod(trainxmat * beta)
         # [error_i = yi - sigmod(zi)]
         error = trainy - sigmodz
         # update beta
         beta += alpha * trainxmat.T * error
         print beta
         """
     # random gradascent
     for j in xrange(M):
         for i in xrange(m):
             # per span
             alpha = 0.01 + 4 / (1.0 + i +j)
             randid = random.randint(0, m - 1)
             sigmodz = sigmod(trainxmat[randid] * beta)
             error = trainy[randid] - sigmodz
             beta += alpha * trainxmat[randid].T * error
             #print beta

     return beta

 def logregress(testx, beta):
     if mat(testx) * beta > 0: return [1.0]
     else: return [0.0]

 def main():
     # step 1: loading data...
     print "step 1: loading data..."
     trainx, trainy = loaddata('horseColicTraining')
     testx, testy = loaddata('horseColicTest')
     """
     print 'trainx', trainx
     print 'trainy', trainy
     print 'testx', testx
     print 'testy', testy
     print 'testy[2]',testy[2]
     """

     # step 2: training...
     print "step 2: training..."
     beta = optimizaion(trainx, trainy)
     #print "beta = ",beta

     # step 3: testing...
     print "step 3: testing..."
     numTests = 10; errorSum = 0.0; l = len(testx)
     for j in xrange(numTests):
         errorcount = 0.0
         #print 'the total number is: ',l
         for i in xrange(l):
             if logregress(testx[i], beta) != testy[i]:
                 errorcount += 1
         #print "the number of error is: ", errorcount
         print "the error rate is: ", (errorcount / l)
         errorSum += (errorcount / l)
     print "after %d iterations the average error rate is: %f" %(numTests, errorSum/numTests)

 """
 trainx, trainy = loaddata('testSet')
 print trainy
 optimizaion(trainx, trainy)
 """

 main()

 print "cost time: ", (time.time() - st)

 """ lineregres
         # ssi = sigmod(zi) - sigmod(zi) ** 2
         ss = [sigmodzi - sigmodzi ** 2 for sigmodzi in sigmodz]
         # errssi = errori * ssi
         errss = map(lambda x, y: x * y, error, ss)
         # treri = errssi * trainxi(vector)
         trer = [errss[i] * array(trainx[i]) for i in xrange(m)]
         """