def mapSpelling(self, inputLine):
words = inputLine.split(",")
airportCodes = ["atl", "pek", "lhr", "ord", "hnd", "lax", "cdg", "dfw", "fra", "hkg",
"den", "dxb", "cgk", "ams", "mad", "bkk", "jfk", "sin", "can", "las", "pvg", "sfo", "phx",
"iah", "clt", "mia", "muc", "kul", "fco", "ist"]
if words[2] in airportCodes and words[3] in airportCodes:
return KVPair(words[0] + "," + words[1], words[2] + "," + words[3] + "," + words[4] + "," + words[5])
else:
print(":: ERROR: Airport not found, removed from dataset: " + inputLine)
def redCalcFlightInfo(self, kvPairs):
#kvPair.value column headers:
# [0] = Passenger ID (XXXnnnnXXn)
# [1] = Dept. airport code (XXX)
# [2] = Arr. airport code (XXX)
# [3] = Arr. airport code Departure time GMT (n [10] (This is using unix epoch time))
# [4] = Total Flight time (mins) (n [1..4])
retVal = ""
# Split the first KVPair's value
words = kvPairs[0].value.split(",")
# Add airport codes to return value
retVal += words[1]
retVal += "," + words[2]
# Add departure time to return value
timestamp = datetime.fromtimestamp(int(words[3]))
hms = str(timestamp).split(" ")
retVal += "," + hms[1]
# Add flight duration to the return value
secs = int(words[4]) * 60
mins, seconds = divmod(secs, 60)
hours, minutes = divmod(mins, 60)
retVal += "," + (str(hours) + ":" + str(minutes) + ":" + str(seconds))
# Add arrival time to the return value
arrivalTime = timestamp + timedelta(
hours=hours, minutes=minutes, seconds=seconds)
hms = str(arrivalTime).split(" ")
retVal += "," + hms[1]
# Add passenger IDs to return value
passengers = ""
for pair in kvPairs:
values = pair.value.split(",")
passengers += (";" + values[0])
retVal += "," + passengers
return KVPair(kvPairs[0].key, retVal)
def redCalcFlightDistance(self, kvPairs):
#kvPair.key column headers:
# [0] = Passenger ID
# [1] = Flight ID
#kvPair.value column headers:
# [0] = Dept. airport code (XXX)
# [1] = Arr. airport code (XXX)
# Open the airport information file and split it on new line
airports = open("./inputFiles/Top30_airports_LatLong.csv")
if not airports:
print(":: Error, could not open airport info file")
airportInfo = airports.read()
airportInfo = airportInfo.split("\n")
# Split the first KVPair's value
kvPairValues = kvPairs[0].value.split(",")
# Find the latitude and longitude of the airpots in use and calculate the distance between them
deptLat = ""
deptLong = ""
arrLat = ""
arrLong = ""
for line in airportInfo[:-1]:
info = line.split(",")
if kvPairValues[0] in info[1].lower():
# print(":: Found departure airport!")
deptLat = float(info[2])
deptLong = float(info[3])
if kvPairValues[1] in info[1].lower():
# print(":: Found destinartion airport!")
arrLat = float(info[2])
arrLong = float(info[3])
if len(kvPairs) > 1:
for pairs in kvPairs:
print(pairs.key)
print(pairs.value)
distance = haversine(deptLat, deptLong, arrLat, arrLong)
return KVPair(kvPairs[0].key, str(round(distance)))
def run(self):
# Read the file, if there's a line then change everything in that line to
# lowercase, and split on new line character, then run the mapper function on each of those lines
# and set that array of mapped lines to the variable 'mapped'
# Mapped will now be an array of arrays where each sub array is the result from mapping each line
if not self.mapper:
print(":: No mapper function set")
return 0
else:
inFile = open(self.inputFile)
if not inFile:
print(":: File could not be opened")
# else:
# print(":: File opened successfully")
mapped = [ self.mapper(self, line) for line in inFile.read().lower().split("\n") if line ]
# print(":: Found " + str(len(mapped)) + " lines")
output = []
for pair in mapped:
# print(type(pair))
if str(type(pair)) == "<class 'KVPair.KVPair'>":
output.append(KVPair(pair.key, pair.value))
# else:
# print(":: Not of class KVPair")
return output
def mapMakePairs(self, inputLine):
inputLine = inputLine.split(",")
return KVPair(inputLine[0], inputLine[1])
def mapPassengerToFlight(self, inputLine):
words = inputLine.split(",")
return KVPair(words[1], words[0])
def redCountPassengers(self, kvPairs):
cnt = 0
for pairs in kvPairs:
cnt += 1
return KVPair(kvPairs[0].key, str(cnt))
def mapReOrder(self, inputLine):
words = inputLine.split(",")
return KVPair(
words[1],
str(words[0] + "," + words[2] + "," + words[3] + "," + words[4] + "," +
words[5]))
def mapDistaces(self, inputLine):
words = inputLine.split(",")
return KVPair(words[1], words[2])
def redCountFlights(self, kvPairs):
val = 0
for pairs in kvPairs:
val += int(pairs.value)
return KVPair(kvPairs[0].key, str(val))
def redWrite(self, kvPairs):
return KVPair(kvPairs[0].key, kvPairs[0].value)
def redTotalPassengerDistance(self, kvPairs):
distance = 0
for pairs in kvPairs:
distance += int(pairs.value)
return KVPair(kvPairs[0].key, str(distance))
def redDistances(self, kvPairs):
return KVPair(kvPairs[0].key, kvPairs[0].value)
def mapTotalPassengerDistance(self, inputLine):
words = inputLine.split(",")
return KVPair(words[0], words[2])
def redUnusedAirports(self, kvPairs):
return KVPair(kvPairs[0].key, "0")
def redUsedAirports(self, kvPairs):
flightCodes = [pair.value for pair in kvPairs]
# print(":: Found " + str(len(set(flightCodes))) + " from " + kvPairs[0].key)
return KVPair(kvPairs[0].key, str(len(set(flightCodes))))
def mapDuplicates(self, inputLine):
if stripErrors(inputLine):
inputLine = inputLine.split(",")
return KVPair(inputLine[0] + "," + inputLine[1], inputLine[2] + "," + inputLine[3] + "," + inputLine[4] + "," + inputLine[5])
else:
print(":: ERROR: Input line not propely formed, removed from dataset: " + inputLine)
def mapUnusedAirports(self, inputLine):
inputLine = inputLine.split(",")
return KVPair(inputLine[1], "0")
def mapCalcFlightDistances(self, inputLine):
words = inputLine.split(",")
return KVPair(str(words[0] + "," + words[1]),
str(words[2] + "," + words[3]))