def RMSerror(trainingFileName, testFileName):
"""Returns the RMS error of predictions made from the training file
compared to the test file.
Keyword arguments:
trainingFileName -- partial set of user data
testFileName -- remainder of user data
"""
try:
trainingFile = open(trainingFileName, 'r')
testFile = open(testFileName, 'r')
except IOError:
print 'Cannot open training/test files.'
sys.exit()
users, numUsers, numMovies = part1.getUserData(trainingFile)
part1.setPearsons(numUsers, users)
rmse = 0.0
testRatings = map(part1.dataPattern.findall, testFile.readlines())
n = len(testRatings)
for rating in testRatings:
userID = int(rating[0])
movieID = int(rating[1])
rating = float(rating[2])
rmse += pow(rating - part2.getPrediction(users, userID, movieID), 2)
return math.sqrt(rmse/n)
def part2Wrapper(dataFileName, simFileName):
"""Reads a u.data like file and a similarities file in the format
used by module part1. Returns a list of User objects which reflect
the two input files.
Keyword arguments:
dataFileName -- input file, like u.data
simFileName -- similarities file, part1 module format
"""
try:
simFile = open(simFileName, 'r')
except IOError:
print 'Cannot open similarities file: ' + simFileName + '\n'
sys.exit()
try:
uData = open(dataFileName, 'r')
except IOError:
print 'Cannot open user file: ' + dataFileName + '\n'
sys.exit()
simLines = simFile.readlines()
IDs = map(idPat.findall, simLines)
PCCs = map(pearsonPat.findall, simLines)
users, numUsers, numMovies = part1.getUserData(uData)
setPearsonsMan(numUsers, users, IDs, PCCs)
simFile.close()
uData.close()
return users
def part4Wrapper(dataFileName, recFileName):
"""Combines functionality from part4 module. Takes a data file
such as u.data and outputs the top three recommendations to
recFileName.
Keyword arguments:
dataFileName -- file name, format is u.data
recFileName -- writes here
"""
try:
userData = open(dataFileName, "r")
recFile = open(recFileName, "w")
except IOError:
print "Cannot use given filenames: " + str(dataFileName) + " " + str(recFileName)
sys.exit()
users, numUsers, numMovies = part1.getUserData(userData)
part1.setPearsons(numUsers, users)
topRecs = getTopRecommendations(users, numMovies)
writeRecommendations(users, recFile)
userData.close()
recFile.close()