Stats on bikes "hidden" moves in CaBi data

gistfile1.py

# "hidden" move - bike move started in bike station, different from the one where bike was actually left in previous trip

# 0 ['Duration', 'Start date', 'End date', 'Start station', 'End station', 'Bike#', 'Member Type']
# 1 ['0h 7min. 48sec.', '12/31/2011 23:55', '1/1/2012 0:03', '18th & M St NW (31221)', '10th & U St NW (31111)', 'W01319', 'Registered']

f=open ("2011-1st-quarter.csv")

tracking={}
member_types={}
total=0
mismatch=0

for i, line in enumerate(f):
	if i==0:
		#skip SCV headers
		continue
	
	total=total+1
		
	line=line.rstrip('\n')
	duration, start_date, end_date, start_station, end_station, bike, member_type = line.split(',')
	
	if member_type in member_types:
		member_types[member_type]=member_types[member_type]+1
	else:
		member_types[member_type]=1
	

	if bike in tracking:

		if tracking[bike]["start_station"]!=end_station:
			print bike
			print "new  ", tracking[bike]["start_date"], tracking[bike]["start_station"]
			print "old  " ,end_date, end_station
			print "------"
			#print bike, tracking[bike]["end_station"], start_station
			#print bike, {"duration":duration, "start_date":start_date, "end_date":end_date, "start_station":start_station, "end_station":end_station, "member_type":member_type}
			#print bike, tracking[bike]
			mismatch=mismatch+1
		tracking[bike]={"duration":duration, "start_date":start_date, "end_date":end_date, "start_station":start_station, "end_station":end_station, "member_type":member_type}
	else:
		tracking[bike]={"duration":duration, "start_date":start_date, "end_date":end_date, "start_station":start_station, "end_station":end_station, "member_type":member_type}
	#if bike=='W00746':
	#	print line
print total, mismatch, float(mismatch)/float(total)

print member_types