Created
December 4, 2013 22:27
-
-
Save young001/7796746 to your computer and use it in GitHub Desktop.
test
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
data = file("test_train") | |
relevance_file = file("train_relevance","w") | |
def dwell_to_relevance(time): | |
if time < 50: | |
return 0 | |
elif 50 <= time <=399: | |
return 1 | |
else: | |
return 2 | |
session_data_list = [] | |
session_type_list = [] | |
session_timepassed_list = [] | |
session_relevance_list = [] | |
for line in data: | |
#print "lline",line.split()[1] | |
if line.split()[1] == "M": | |
if session_type_list: | |
print session_type_list | |
session_length = len(session_type_list) | |
max_index = session_length-1 | |
for index,item in enumerate(session_type_list): | |
if index == max_index: | |
if item == "C": | |
session_relevance_list.append(2) | |
continue | |
else: | |
session_relevance_list.append(0) | |
continue | |
if item == "Q" or item == "M": | |
session_relevance_list.append(0) | |
elif item == "C": | |
dwell_time = int(session_timepassed_list[index+1]) - int(session_timepassed_list[index]) | |
relevance = dwell_to_relevance(dwell_time) | |
session_relevance_list.append(relevance) | |
print session_relevance_list | |
#print len(session_relevance_list) | |
#print len(session_data_list) | |
for index1,line in enumerate(session_data_list): | |
#print index1 | |
#print session_relevance_list[1] | |
#print session_relevance_list[index1] | |
if session_relevance_list[index1]: | |
line = line + "\t" + str(session_relevance_list[index1]) + "\n" | |
else: | |
line = line | |
relevance_file.write(line) | |
session_data_list = [] | |
session_type_list = [] | |
session_timepassed_list = [] | |
session_relevance_list = [] | |
session_data_list = [] | |
session_type_list = [] | |
session_timepassed_list = [] | |
session_relevance_list = [] | |
sessionid = line.split()[0] | |
line_type = line.split()[1] | |
session_data_list.append(line) | |
session_type_list.append(line_type) | |
session_timepassed_list.append(0) | |
else: | |
line_type = line.split()[2] | |
timepassed = int(line.split()[1]) | |
session_data_list.append(line) | |
session_type_list.append(line_type) | |
session_timepassed_list.append(timepassed) | |
#basetime = line.split()[1] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment