def GetZipData():
'''
Reads zipCodes.csv into memory, returns it as a dict.
'''
parser = ParseCSV(dataFile)
return parser.getLabelledData()
def GetZipsBorough():
parser = ParseCSV(boroughsFile)
(fields, data) = parser.getRawData()
zipBoroughs = {}
for idx in xrange(len(data[0])):
zipCode = data[0][idx]
borough = data[1][idx]
if zipCode not in zipBoroughs:
zipBoroughs[zipCode] = borough
return zipBoroughs
def GetZipIncidentsFromFile():
'''
returns a dict of
{ (Zip Code):incidents }
'''
parser = ParseCSV(incidentFile, (1, 2))
(fields, data) = parser.getRawData()
# Not all of the zip codes and counts are well-formed.
# Using this regex to try and only find numbers in them.
numberParser = re.compile(r'[^\d.]+')
zipsDict = {}
for i in xrange(len(data[0])):
zipCode = data[0][i]
zipCount = numberParser.sub('', data[1][i]) # I'm not actually sure if this is a count. It looks like it might be, but there's no description anywhere.
# I am likewise going to assume that any entry (aka a blank one) is just "1".
if zipCount is '':
zipCount = 1
if zipCode is '':
continue
# It seems like there are a bunch of errors in the formatting
# This is attemptin gto deal with that noise
elif len(zipCode) > 5 and zipCode[0:5].isdigit():
zipCode = zipCode[0:5]
elif len(zipCode) > 5 and zipCode.isdigit():
print zipCode
continue
try:
if zipCode in zipsDict:
zipsDict[zipCode] += int(zipCount)
else:
zipsDict[zipCode] = int(zipCount)
except ValueError:
print "Value Error occured for ZipCode", zipCode, " and count", zipCount
return zipsDict
