def predict(knownFileLocation,unknownFileLocation):
#Create readable csv objects from the given file locations
passengerDataFile = csv.reader(open(unknownFileLocation, 'r'))
knownPassengerDataFile = csv.reader(open(knownFileLocation,'r'))
#Grab the header from the given files
unknownHeader = next(passengerDataFile)
unknown_passenger_data=[]
knownHeader = next(knownPassengerDataFile)
known_passenger_data=[]
myList = PassengerList(unknown_passenger_data)
knownList = PassengerList(known_passenger_data)
#Fill each passenger list with passengers that have the attributes given from the csv files
for row in passengerDataFile:
newPassenger = Passenger(row[0],row[1],row[2],row[3],row[4],row[5],row[6],row[7],row[8],row[9],row[10])
myList.add(newPassenger)
#For known passengers, we can also set their survival attribute
for row in knownPassengerDataFile:
newPassenger = Passenger(row[0],row[2],row[3],row[4],row[5],row[6],row[7],row[8],row[9],row[10],row[11])
newPassenger.setSurvived(row[1])
knownList.add(newPassenger)
#Gather the statistics on both data sets involving their survival rate after we predict on the unknown set using the known set
statsLists = PredictiveAnalyzer.train(knownList,myList)
#Write the predicted survival information to the prediction csv file
kaggleSubmissionFile = open("TitanicPredictions.csv", "w",newline='')
open_file_object = csv.writer(kaggleSubmissionFile)
open_file_object.writerow(["Survived","PassengerID"])
for passenger in myList:
open_file_object.writerow([passenger.getSurvived(),passenger.getID()])
kaggleSubmissionFile.close()
#Return the statistiscs for output in our gui
return statsLists
def predict(knownFileDirectory,unknownFileDirectory):
passengerDataFile = csv.reader(open('passengerNoSurvivedData.csv', 'r'))
knownPassengerDataFile = csv.reader(open('passengerSurvivedData.csv','r'))
header = next(passengerDataFile)
passenger_data=[]
knownHeader = next(knownPassengerDataFile)
known_passenger_data=[]
myList = PassengerList(passenger_data)
knownList = PassengerList(known_passenger_data)
for row in passengerDataFile:
newPassenger = Passenger(row[0],row[1],row[2],row[3],row[4],row[5],row[6],row[7],row[8],row[9],row[10])
myList.add(newPassenger)
for row in knownPassengerDataFile:
newPassenger = Passenger(row[0],row[2],row[3],row[4],row[5],row[6],row[7],row[8],row[9],row[10],row[11])
newPassenger.setSurvived(row[1])
knownList.add(newPassenger)
PredictiveAnalyzer.train(knownList,myList)
kaggleSubmissionFile = open("TitanicPredictions.csv", "w",newline='')
open_file_object = csv.writer(kaggleSubmissionFile)
open_file_object.writerow(["Survived","PassengerID"])
for passenger in myList:
#print(passenger.getID())
#print(passenger.getSurvived())
open_file_object.writerow([passenger.getSurvived(),passenger.getID()])
kaggleSubmissionFile.close()
