from numpy import *
from pandas import read_csv
import matplotlib.pyplot as plt
from scipy.sparse import bsr_matrix
from preProcess import preProcess
from loadSparseData import loadSparseData
from PA import PA
fname1 = 'pu1'
fname2 = 'pu2'
fname3 = 'pu3'
fname4 = 'pua'
X1, Y1 = loadSparseData(fname1)
X2, Y2 = loadSparseData(fname2)
X3, Y3 = loadSparseData(fname3)
X4, Y4 = loadSparseData(fname4)
print 'preProcess X'
X1 = preProcess(X1)
X2 = preProcess(X2)
X3 = preProcess(X3)
X4 = preProcess(X4)
print 'start COML'
def update_CM(i, X, Y, w, u):
x_t = X[i]
f_t = dot(w, x_t)
loss_w = max(0, 1 - Y[i] * f_t)
if loss_w == 0:
tau = 0
idx = ID_list[j][i]
if Y_list[j][idx] * (alf * ft_list[j] +
beta * fut_list[j]) < 0:
errcount_list[j] += 1
misrate_list[j].append(errcount_list[j] / float(count_list[j]))
return misrate_list, w_list, u
# load data
fname1 = 'tfidf_pu1'
fname2 = 'tfidf_pu2'
fname3 = 'tfidf_pu3'
fname4 = 'tfidf_pua'
sampleNum = -1
X1, Y1 = loadSparseData(fname1, sampleNum)
X2, Y2 = loadSparseData(fname2, sampleNum)
X3, Y3 = loadSparseData(fname3, sampleNum)
X4, Y4 = loadSparseData(fname4, sampleNum)
# preProcess data
print 'preProcess X'
X1 = mmPreProcess(X1)
X2 = mmPreProcess(X2)
X3 = mmPreProcess(X3)
X4 = mmPreProcess(X4)
# X1 = stdPreProcess(X1)
# X2 = stdPreProcess(X2)
# X3 = stdPreProcess(X3)
# X4 = stdPreProcess(X4)
if i < len_list[j]:
idx = ID_list[j][i]
if Y_list[j][idx] * (alf * ft_list[j] + beta * fut_list[j]) < 0:
errcount_list[j] +=1
misrate_list[j].append(errcount_list[j]/float(count_list[j]))
return misrate_list, w_list, u
# load data
fname1 = 'tfidf_pu1'
fname2 = 'tfidf_pu2'
fname3 = 'tfidf_pu3'
fname4 = 'tfidf_pua'
sampleNum = -1
X1, Y1 = loadSparseData(fname1, sampleNum)
X2, Y2 = loadSparseData(fname2, sampleNum)
X3, Y3 = loadSparseData(fname3, sampleNum)
X4, Y4 = loadSparseData(fname4, sampleNum)
# preProcess data
print 'preProcess X'
X1 = mmPreProcess(X1)
X2 = mmPreProcess(X2)
X3 = mmPreProcess(X3)
X4 = mmPreProcess(X4)
# X1 = stdPreProcess(X1)
# X2 = stdPreProcess(X2)
# X3 = stdPreProcess(X3)
# X4 = stdPreProcess(X4)