def main(): filename = "stars_data.csv" data = a.read_data(filename) data.pop(0) random.shuffle(data) frequency = a.frequency_word(data) data_neg = [x for x in data if int(x[6]) == 1] data_pos = [x for x in data if int(x[6]) == 5] matrix_pos = np.zeros((2000,2500)) matrix_neg = np.zeros((2000,2500)) matrix_pos = cluster.create_matrix(matrix_pos,data_pos,frequency) matrix_neg = cluster.create_matrix(matrix_neg,data_neg,frequency) kmeans_feature = cluster.kmeans_bin(data,matrix_pos,matrix_neg,frequency,50) smeans_feature = cluster.smeans_bin(data,matrix_pos,matrix_neg,frequency,50) origin_feature = a.create_binary_feature(data,frequency,6) sample_origin_feature = a.create_binary_feature(data,random.sample(frequency,100),6) combine_feature = combine(kmeans_feature,sample_origin_feature) print "Test1" test1(matrix_pos,matrix_neg) print "Test2" test2(kmeans_feature,smeans_feature) print "Test3" test3(origin_feature,kmeans_feature) print "Test4" test4(sample_origin_feature,kmeans_feature,combine_feature)
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 main():
#data preprocessing
filename = "stars_data.csv"
data = a.read_data(filename)
data.pop(0)
random.shuffle(data)
words = a.frequency_word(data)
features = a.create_binary_feature(data,words,6)
words.append("isPositive")
words.append("isNegative")
minsupport = 0.03
minconf = 3.81
L,support_count = apriori.frequentItemsetGeneration(features,words,minsupport)
print len(L[0]) + len(L[1]) + len(L[2])
rules = ruleG(L,support_count,minconf)
print len(rules)
rules = sorted(rules.items(),key=operator.itemgetter(1),reverse= True)
rules = [rules[i] for i in range(30)]
for rule in rules:
print rule
def main():
#data preprocessing
filename = "stars_data.csv"
data = a.read_data(filename)
data.pop(0)
random.shuffle(data)
words = a.frequency_word(data)
features = a.create_binary_feature(data,words,6)
words.append("isPositive")
words.append("isNegative")
minsupport = 0.03
minconf = 0.25
D = construct(features,words)
D = map(set, D)
t = []
t.append(frozenset(['friendly']))
t.append(frozenset(['isPositive']))
t.append(frozenset(['staff']))
t.append(frozenset(['favorite']))
q2(D,t)
'''