def main(args):
#take argument
trainfile = args[1]
testfile = args[2]
classlabel = int(args[3])
printWord = int(args[4])
#set train file an dtest file
train = a.read_data(trainfile)
test = a.read_data(testfile)
#get top 2000 frequency
fre = a.frequency(train)
#if yes, print Words
if (printWord == 1):
a.printTopwords(fre)
#create binary feature for boss data
train = a.create_binary_feature(train,fre,classlabel)
test = a.create_binary_feature(test,fre,classlabel)
#get probability table based on train data
prob_table,pYes,pNo = a.train_nbc(train)
#use probability table for testing,and return result
result = a.test_nbc(prob_table,test,pYes,pNo)
#get test class label
classlabel = [x[-1] for x in test]
#use zero one difference figure out result
diff = a.zero_onr_loss(result,classlabel)
print "ZERO-ONE-LOSS {0}".format(diff)
def crossValidation(data):
X = kfold(data, 10)
for tss in [100, 250, 500, 1000, 2000]:
print "tss = ", tss
loss = list()
for i in range(10):
test_set = X[i]
# take rest of data
train_data = list()
for j in range(10):
if j != i:
train_data += X[j]
train_set = random.sample(train_data, tss)
train, pYes, pNo = nbc.train_nbc(train_set)
result = nbc.test_nbc(train, test_set, pYes, pNo)
label = [x[-1] for x in test_set]
diff = nbc.zero_one_loss(result, label)
loss.append(diff)
print loss
print "mean: ", numpy.mean(loss)
print "std error: ", standard_error(loss, 10)