import process as pr
import time
start_time = time.time()
DP = pr.Data_Process()
DP.read_data(detail=True)
DP.data_frequency(idf=True)
data_time = time.time() - start_time
hour, minute, second = pr.time_process(data_time)
print 'data process time: ' + str(hour) + "h " + str(minute) + "m " + str(
second) + "s "
K_range = range(1, 11)
err_prob = []
false_pos = []
false_neg = []
from sklearn import neighbors
total_email = float(len(DP.test_email_class))
for K in K_range:
start_time = time.time()
clf = neighbors.KNeighborsClassifier(K)
clf.fit(DP.train_bag_words_transformed, DP.train_email_class)
fit_time = time.time() - start_time
hour, minute, second = pr.time_process(fit_time)
__author__ = 'liangshengzhang'
import process as pr
import numpy as np
import time
start_time = time.time()
chr1 = pr.Data(1)
chr1.read()
read_time = time.time() - start_time
hour, minute, second = pr.time_process(read_time)
print '\n'
print 'Loading time: ' + str(hour) + "h " + str(minute) + "m " + str(
second) + "s "
start_time = time.time()
chr1.data_extract(strand_binary=True, pos_normalize=True)
from sklearn import preprocessing
imputer = preprocessing.Imputer(copy=False)
imputer.fit_transform(chr1.train_beta)
process_time = time.time() - start_time
hour, minute, second = pr.time_process(process_time)
print '\n'
__author__ = 'liangshengzhang'
import process as pr
import numpy as np
import time
from math import log, exp
start_time = time.time()
chr1 = pr.Data(1)
chr1.read(detail=True)
read_time = time.time() - start_time
hour, minute, second = pr.time_process(read_time)
print '\n'
print 'Loading time: ' + str(hour) + "h " + str(minute) + "m " + str(
second) + "s "
start_time = time.time()
chr1.data_extract(strand_binary=True, pos_normalize=True)
start_time = time.time()
from sklearn import preprocessing
imputer = preprocessing.Imputer(copy=False)
imputer.fit_transform(chr1.train_beta)
process_time = time.time() - start_time