def readCommand( argv ):
"Processes the command used to run from the command line."
from optparse import OptionParser
parser = OptionParser(USAGE_STRING)
parser.add_option('-c', '--classifier', help=default('The type of classifier'), choices=['1vr', '1v1', 'mira'], default='1vr')
parser.add_option('-t', '--training', help=default('The size of the training set'), default=TRAIN_SET_SIZE, type="int")
parser.add_option('-f', '--features', help=default('Whether to use enhanced features'), default=False, action="store_true")
parser.add_option('-a', '--autotune', help=default("Whether to automatically tune hyperparameters"), default=False, action="store_true")
parser.add_option('-i', '--iterations', help=default("Maximum iterations to run training"), default=3, type="int")
parser.add_option('-s', '--test', help=default("Amount of test data to use"), default=TEST_SET_SIZE, type="int")
parser.add_option('-v', '--validate', help=default("Whether to validate when training (for graphs)"), default=False, action="store_true")
parser.add_option('-d', '--dataset', help=default("Specifies the data set to use"), choices=['d1', 'd2'], default='d1')
parser.add_option('-k', '--classes', help=default("Specifies the number of classes"), default=10, type="int")
options, otherjunk = parser.parse_args(argv)
if len(otherjunk) != 0: raise Exception('Command line input not understood: ' + str(otherjunk))
args = {}
# Set up variables according to the command line input.
print "Doing classification"
print "--------------------"
print "classifier:\t\t" + options.classifier
print "using enhanced features?:\t" + str(options.features)
print "training set size:\t" + str(options.training)
if (options.features):
featureFunction = enhancedFeatureExtractorDigit
else:
featureFunction = basicFeatureExtractorDigit
legalLabels = range(options.classes)
if options.training <= 0:
print "Training set size should be a positive integer (you provided: %d)" % options.training
print USAGE_STRING
sys.exit(2)
if(options.classifier == "1vr"):
classifier = perceptron1vr.Perceptron1vrClassifier(legalLabels,options.iterations)
elif(options.classifier == "1v1"):
classifier = perceptron1v1.Perceptron1v1Classifier(legalLabels, options.iterations)
elif(options.classifier == 'mira'):
classifier = mira.MiraClassifier(legalLabels, options.iterations)
else:
print "Unknown classifier:", options.classifier
print USAGE_STRING
sys.exit(2)
args['classifier'] = classifier
args['featureFunction'] = featureFunction
return args, options
def readCommand(argv):
"Processes the command used to run from the command line."
from optparse import OptionParser
parser = OptionParser(USAGE_STRING)
parser.add_option('-c',
'--classifier',
help=default('The type of classifier'),
choices=[
'mostFrequent', 'nb', 'naiveBayes', 'perceptron',
'mira', 'minicontest'
],
default='mostFrequent')
parser.add_option('-d',
'--data',
help=default('Dataset to use'),
choices=['digits', 'faces', 'pacman'],
default='digits')
parser.add_option('-t',
'--training',
help=default('The size of the training set'),
default=100,
type="int")
parser.add_option('-f',
'--features',
help=default('Whether to use enhanced features'),
default=False,
action="store_true")
parser.add_option('-o',
'--odds',
help=default('Whether to compute odds ratios'),
default=False,
action="store_true")
parser.add_option('-1',
'--label1',
help=default("First label in an odds ratio comparison"),
default=0,
type="int")
parser.add_option('-2',
'--label2',
help=default("Second label in an odds ratio comparison"),
default=1,
type="int")
parser.add_option('-w',
'--weights',
help=default('Whether to print weights'),
default=False,
action="store_true")
parser.add_option(
'-k',
'--smoothing',
help=default("Smoothing parameter (ignored when using --autotune)"),
type="float",
default=2.0)
parser.add_option(
'-a',
'--autotune',
help=default("Whether to automatically tune hyperparameters"),
default=False,
action="store_true")
parser.add_option('-i',
'--iterations',
help=default("Maximum iterations to run training"),
default=3,
type="int")
parser.add_option('-s',
'--test',
help=default("Amount of test data to use"),
default=TEST_SET_SIZE,
type="int")
parser.add_option('-g',
'--agentToClone',
help=default("Pacman agent to copy"),
default=None,
type="str")
options, otherjunk = parser.parse_args(argv)
if len(otherjunk) != 0:
raise Exception('Command line input not understood: ' + str(otherjunk))
args = {}
# Set up variables according to the command line input.
print "Doing classification"
print "--------------------"
print "data:\t\t" + options.data
print "classifier:\t\t" + options.classifier
if not options.classifier == 'minicontest':
print "using enhanced features?:\t" + str(options.features)
else:
print "using minicontest feature extractor"
print "training set size:\t" + str(options.training)
if (options.data == "digits"):
printImage = ImagePrinter(DIGIT_DATUM_WIDTH,
DIGIT_DATUM_HEIGHT).printImage
if (options.features):
featureFunction = enhancedFeatureExtractorDigit
else:
featureFunction = basicFeatureExtractorDigit
if (options.classifier == 'minicontest'):
featureFunction = contestFeatureExtractorDigit
elif (options.data == "faces"):
printImage = ImagePrinter(FACE_DATUM_WIDTH,
FACE_DATUM_HEIGHT).printImage
if (options.features):
featureFunction = enhancedFeatureExtractorFace
else:
featureFunction = basicFeatureExtractorFace
elif (options.data == "pacman"):
printImage = None
if (options.features):
featureFunction = enhancedFeatureExtractorPacman
else:
featureFunction = basicFeatureExtractorPacman
else:
print "Unknown dataset", options.data
print USAGE_STRING
sys.exit(2)
if (options.data == "digits"):
legalLabels = range(10)
else:
legalLabels = ['Stop', 'West', 'East', 'North', 'South']
if options.training <= 0:
print "Training set size should be a positive integer (you provided: %d)" % options.training
print USAGE_STRING
sys.exit(2)
if options.smoothing <= 0:
print "Please provide a positive number for smoothing (you provided: %f)" % options.smoothing
print USAGE_STRING
sys.exit(2)
if options.odds:
if options.label1 not in legalLabels or options.label2 not in legalLabels:
print "Didn't provide a legal labels for the odds ratio: (%d,%d)" % (
options.label1, options.label2)
print USAGE_STRING
sys.exit(2)
if (options.classifier == "mostFrequent"):
classifier = mostFrequent.MostFrequentClassifier(legalLabels)
elif (options.classifier == "naiveBayes" or options.classifier == "nb"):
classifier = naiveBayes.NaiveBayesClassifier(legalLabels)
classifier.setSmoothing(options.smoothing)
if (options.autotune):
print "using automatic tuning for naivebayes"
classifier.automaticTuning = True
else:
print "using smoothing parameter k=%f for naivebayes" % options.smoothing
elif (options.classifier == "perceptron"):
if options.data != 'pacman':
classifier = perceptron.PerceptronClassifier(
legalLabels, options.iterations)
else:
classifier = perceptron_pacman.PerceptronClassifierPacman(
legalLabels, options.iterations)
elif (options.classifier == "mira"):
if options.data != 'pacman':
classifier = mira.MiraClassifier(legalLabels, options.iterations)
if (options.autotune):
print "using automatic tuning for MIRA"
classifier.automaticTuning = True
else:
print "using default C=0.001 for MIRA"
elif (options.classifier == 'minicontest'):
import minicontest
classifier = minicontest.contestClassifier(legalLabels)
else:
print "Unknown classifier:", options.classifier
print USAGE_STRING
sys.exit(2)
args['agentToClone'] = options.agentToClone
args['classifier'] = classifier
args['featureFunction'] = featureFunction
args['printImage'] = printImage
return args, options
def readCommand( argv ):
"Processes the command used to run from the command line."
from optparse import OptionParser
parser = OptionParser(USAGE_STRING)
parser.add_option('-c', '--classifier', help=default('The type of classifier'), choices=['mostFrequent', 'nb', 'naiveBayes', 'perceptron','mira'], default='perceptron')
parser.add_option('-d', '--data', help=default('Dataset to use'), choices=['digits', 'faces'], default='digits')
parser.add_option('-t', '--training', help=default('The size of the training set'), default=100, type="int")
parser.add_option('-f', '--features', help=default('Whether to use enhanced features'), default=False, action="store_true")
parser.add_option('-o', '--odds', help=default('Whether to compute odds ratios'), default=False, action="store_true")
parser.add_option('-1', '--label1', help=default("First label in an odds ratio comparison"), default=0, type="int")
parser.add_option('-2', '--label2', help=default("Second label in an odds ratio comparison"), default=1, type="int")
parser.add_option('-w', '--weights', help=default('Whether to print weights'), default=False, action="store_true")
parser.add_option('-k', '--smoothing', help=default("Smoothing parameter (ignored when using --autotune)"), type="float", default=2.0)
parser.add_option('-a', '--autotune', help=default("Whether to automatically tune hyperparameters"), default=False, action="store_true")
parser.add_option('-i', '--iterations', help=default("Maximum iterations to run training"), default=3, type="int")
parser.add_option('-s', '--test', help=default("Amount of test data to use"), default=TEST_SET_SIZE, type="int")
parser.add_option('-n', '--analysis', help=default("Shows which data is wrongly predicted"), default=True, action="store_true")
parser.add_option('-r', '--random', help=default("Trains the data set using random data and calculates averages for percent accuracy and standard deviation"), default=True, action="store_true")
options, otherjunk = parser.parse_args(argv)
if len(otherjunk) != 0: raise Exception('Command line input not understood: ' + str(otherjunk))
args = {}
# Set up variables according to the command line input.
print ("Doing classification")
print ("--------------------")
print ("Data:\t\t" + options.data)
print ("Classifier:\t\t" + options.classifier)
print ("Using enhanced features?:\t" + str(options.features))
if not options.random:
print ("Training set size:\t" + str(options.training))
if(options.data=="digits"):
printImage = ImagePrinter(DIGIT_DATUM_WIDTH, DIGIT_DATUM_HEIGHT).printImage
if (options.features):
featureFunction = enhancedFeatureExtractorDigit
else:
featureFunction = basicFeatureExtractorDigit
elif(options.data=="faces"):
printImage = ImagePrinter(FACE_DATUM_WIDTH, FACE_DATUM_HEIGHT).printImage
if (options.features):
featureFunction = enhancedFeatureExtractorFace
else:
featureFunction = basicFeatureExtractorFace
else:
print ("Unknown dataset", options.data)
print (USAGE_STRING)
sys.exit(2)
if(options.data=="digits"):
legalLabels = range(10)
else:
legalLabels = range(2)
if options.training <= 0:
print ("Training set size should be a positive integer (you provided: %d)" % options.training)
print (USAGE_STRING)
sys.exit(2)
if options.smoothing <= 0:
print ("Please provide a positive number for smoothing (you provided: %f)" % options.smoothing)
print (USAGE_STRING)
sys.exit(2)
if options.odds:
if options.label1 not in legalLabels or options.label2 not in legalLabels:
print ("Didn't provide a legal labels for the odds ratio: (%d,%d)" % (options.label1, options.label2))
print (USAGE_STRING)
sys.exit(2)
if(options.classifier == "naiveBayes" or options.classifier == "nb"):
classifier = naiveBayes.NaiveBayesClassifier(legalLabels)
classifier.setSmoothing(options.smoothing)
if (options.autotune):
print ("Using automatic tuning for naivebayes")
classifier.automaticTuning = True
else:
print ("Using smoothing parameter k=%f for naivebayes" % options.smoothing)
elif(options.classifier == "perceptron"):
classifier = perceptron.PerceptronClassifier(legalLabels,options.iterations)
elif(options.classifier == "mira"):
classifier = mira.MiraClassifier(legalLabels, options.iterations)
if (options.autotune):
print ("Using automatic tuning for MIRA")
classifier.automaticTuning = True
else:
print ("Using default C=0.001 for MIRA")
else:
print ("Unknown classifier:", options.classifier)
print (USAGE_STRING)
sys.exit(2)
args['classifier'] = classifier
args['featureFunction'] = featureFunction
args['printImage'] = printImage
return args, options
def readCommand(argv):
"""Processes the command used to run from the command line."""
from optparse import OptionParser
parser = OptionParser(USAGE_STRING)
parser.add_option(
'-r',
'--run',
help=default('automatically runs training and test cycle for 5 times'),
default=False,
action='store_true')
parser.add_option('-c',
'--classifier',
help=default('The type of classifier'),
choices=['perceptron', 'naiveBayes', 'mira'],
default='naiveBayes')
parser.add_option('-d',
'--data',
help=default('Dataset to use'),
choices=['digits', 'faces'],
default='digits')
parser.add_option('-t',
'--training',
help=default('The ratio of the training set to use'),
default=1.0,
type="float")
parser.add_option('-f',
'--features',
help=default('Whether to use enhanced features'),
default=False,
action="store_true")
parser.add_option('-o',
'--odds',
help=default('Whether to compute odds ratios'),
default=False,
action="store_true")
parser.add_option('-1',
'--label1',
help=default("First label in an odds ratio comparison"),
default=0,
type="int")
parser.add_option('-2',
'--label2',
help=default("Second label in an odds ratio comparison"),
default=1,
type="int")
parser.add_option(
'-k',
'--smoothing',
help=default("Smoothing parameter (ignored when using --autotune)"),
type="float",
default=2.0)
parser.add_option(
'-a',
'--autotune',
help=default("Whether to automatically tune hyperparameters"),
default=False,
action="store_true")
parser.add_option('-i',
'--iterations',
help=default("Maximum iterations to run training"),
default=3,
type="int")
options, otherjunk = parser.parse_args(argv)
if len(otherjunk) != 0:
raise Exception('Command line input not understood: ' + str(otherjunk))
args = {}
# Set up variables according to the command line input.
print("Doing classification")
print("--------------------")
print("data:\t\t" + options.data)
print("classifier:\t\t" + options.classifier)
print("using enhanced features?:\t" + str(options.features))
if options.data == "digits":
printImage = ImagePrinter(DIGIT_DATUM_WIDTH,
DIGIT_DATUM_HEIGHT).printImage
if options.features:
featureFunction = enhancedFeatureExtractorDigit
else:
featureFunction = basicFeatureExtractorDigit
elif options.data == "faces":
printImage = ImagePrinter(FACE_DATUM_WIDTH,
FACE_DATUM_HEIGHT).printImage
if options.features:
featureFunction = enhancedFeatureExtractorFace
else:
featureFunction = basicFeatureExtractorFace
else:
print("Unknown dataset", options.data)
print(USAGE_STRING)
sys.exit(2)
if options.data == "digits":
legalLabels = range(10)
else:
legalLabels = range(2)
if options.training <= 0:
print(
"Training set size should be a positive integer (you provided: %d)"
% options.training)
print(USAGE_STRING)
sys.exit(2)
if options.smoothing <= 0:
print(
"Please provide a positive number for smoothing (you provided: %f)"
% options.smoothing)
print(USAGE_STRING)
sys.exit(2)
if options.odds:
if options.label1 not in legalLabels or options.label2 not in legalLabels:
print("Didn't provide a legal labels for the odds ratio: (%d,%d)" %
(options.label1, options.label2))
print(USAGE_STRING)
sys.exit(2)
if options.classifier == "mira":
classifier = mira.MiraClassifier(legalLabels, options.iterations)
elif options.classifier == "naiveBayes":
classifier = naiveBayes.NaiveBayesClassifier(legalLabels)
classifier.setSmoothing(options.smoothing)
if options.autotune:
print
"using automatic tuning for naivebayes"
classifier.automaticTuning = True
else:
print("using smoothing parameter k=%f for naivebayes" %
options.smoothing)
elif options.classifier == "perceptron":
classifier = perceptron.PerceptronClassifier(legalLabels,
options.iterations)
elif options.classifier == "knn":
classifier = knn.KNN(legalLabels)
else:
print("Unknown classifier:", options.classifier)
print(USAGE_STRING)
sys.exit(2)
args['classifier'] = classifier
args['featureFunction'] = featureFunction
args['printImage'] = printImage
return args, options
def readCommand( argv ):
"Processes the command used to run from the command line."
from optparse import OptionParser
parser = OptionParser(USAGE_STRING)
parser.add_option('-c', '--classifier', help=default('The type of classifier'), choices=['perceptron', 'mira'], default='perceptron')
parser.add_option('-t', '--training', help=default('The size of the training set'), default=1000, type="int")
parser.add_option('-f', '--features', help=default('Whether to use enhanced features'), default=False, action="store_true")
parser.add_option('-k', '--smoothing', help=default("Smoothing parameter (ignored when using --autotune)"), type="float", default=2.0)
parser.add_option('-a', '--autotune', help=default("Whether to automatically tune hyperparameters"), default=False, action="store_true")
parser.add_option('-i', '--iterations', help=default("Maximum iterations to run training"), default=3, type="int")
parser.add_option('-s', '--test', help=default("Amount of test data to use"), default=TEST_SET_SIZE, type="int")
parser.add_option('-v', '--validate', help=default("Whether to validate when training (for graphs)"), default=False, action="store_true")
options, otherjunk = parser.parse_args(argv)
if len(otherjunk) != 0: raise Exception('Command line input not understood: ' + str(otherjunk))
args = {}
# Set up variables according to the command line input.
print "Doing classification"
print "--------------------"
print "classifier:\t\t" + options.classifier
print "using enhanced features?:\t" + str(options.features)
print "training set size:\t" + str(options.training)
printImage = ImagePrinter(DIGIT_DATUM_WIDTH, DIGIT_DATUM_HEIGHT).printImage
if (options.features):
featureFunction = enhancedFeatureExtractorDigit
else:
featureFunction = basicFeatureExtractorDigit
legalLabels = range(10)
if options.training <= 0:
print "Training set size should be a positive integer (you provided: %d)" % options.training
print USAGE_STRING
sys.exit(2)
if options.smoothing <= 0:
print "Please provide a positive number for smoothing (you provided: %f)" % options.smoothing
print USAGE_STRING
sys.exit(2)
if(options.classifier == "perceptron"):
classifier = perceptron.PerceptronClassifier(legalLabels,options.iterations)
elif(options.classifier == "mira"):
classifier = mira.MiraClassifier(legalLabels, options.iterations)
if (options.autotune):
print "using automatic tuning for MIRA"
classifier.automaticTuning = True
else:
print "using default C=0.001 for MIRA"
else:
print "Unknown classifier:", options.classifier
print USAGE_STRING
sys.exit(2)
args['classifier'] = classifier
args['featureFunction'] = featureFunction
args['printImage'] = printImage
return args, options
def readCommand( argv ):
"""
Processes the command used to run from the command line.
"""
import getopt
# Set default options
options = {'classifier': 'mostfrequent',
'data': 'digits',
'enhancedFeatures': False,
'train': 100,
'odds': False,
'class1': 1,
'class2': 0,
'smoothing': 1,
'automaticTuning' : False,
'maxIterations': 3}
args = {} # This dictionary will hold the objects used by the main method
# Read input from the command line
commands = ['help',
'classifer=',
'data=',
'train=',
'enhancedFeatures',
'odds',
'class1=',
'class2=',
'smoothing=',
'automaticTuning'
'maxIterations=']
try:
opts = getopt.getopt( argv, "hc:d:t:fo1:2:k:ai:", commands )
except getopt.GetoptError:
print USAGE_STRING
sys.exit( 2 )
for option, value in opts[0]:
if option in ['--help', '-h']:
print USAGE_STRING
sys.exit( 0 )
if option in ['--classifier', '-c']:
options['classifier'] = value
if option in ['--data', '-d']:
options['data'] = value
if option in ['--train', '-t']:
options['train'] = int(value)
if option in ['--enhancedFeatures', '-f']:
options['enhancedFeatures'] = True
if option in ['--odds', '-o']:
options['odds'] = True
if option in ['--class1', '-1']:
options['class1'] = int(value)
if option in ['--class2', '-2']:
options['class2'] = int(value)
if option in ['--smoothing', '-k']:
options['smoothing'] = float( value )
if option in ['--automaticTuning', '-a']:
options['automaticTuning'] = True
if option in ['--maxIterations', '-i']:
options['maxIterations'] = int(value)
# Set up variables according to the command line input.
print "Doing classification"
print "--------------------"
print "data:\t\t" + options['data']
print "classifier:\t\t" + options['classifier']
print "using enhanced features?:\t" + str(options['enhancedFeatures'])
print "training set size:\t" + str(options['train'])
if(options['data']=="digits"):
printImage = ImagePrinter(DIGIT_DATUM_WIDTH, DIGIT_DATUM_HEIGHT).printImage
if (options['enhancedFeatures']):
featureFunction = enhancedFeatureExtractorDigit
else:
featureFunction = basicFeatureExtractorDigit
elif(options['data']=="faces"):
printImage = ImagePrinter(FACE_DATUM_WIDTH, FACE_DATUM_HEIGHT).printImage
if (options['enhancedFeatures']):
featureFunction = enhancedFeatureExtractorFace
else:
featureFunction = basicFeatureExtractorFace
else:
print "Unknown dataset", options['data']
print USAGE_STRING
sys.exit(2)
if(options['data']=="digits"):
legalLabels = range(10)
else:
legalLabels = range(2)
if options['train'] <= 0:
print "Training set size should be a positive integer (you provided: %d)" % options['train']
print USAGE_STRING
sys.exit(2)
if options['smoothing'] <= 0:
print "Please provide a positive number for smoothing (you provided: %f)" % options['smoothing']
print USAGE_STRING
sys.exit(2)
if options['odds']:
for className in ['class1','class2']:
if options[className] not in legalLabels:
print "Didn't provide a legal labels for the odds ratio for %s" % className
print USAGE_STRING
sys.exit(2)
if(options['classifier'] == "mostfrequent"):
classifier = mostFrequent.MostFrequentClassifier(legalLabels)
elif(options['classifier'] == "naivebayes"):
classifier = naiveBayes.NaiveBayesClassifier(legalLabels)
classifier.setSmoothing(options['smoothing'])
if (options['automaticTuning']):
print "using automatic tuning for naivebayes"
classifier.automaticTuning = True
else:
print "using smoothing parameter k=%f for naivebayes" % options['smoothing']
elif(options['classifier'] == "perceptron"):
classifier = perceptron.PerceptronClassifier(legalLabels,options['maxIterations'])
elif(options['classifier'] == "mira"):
classifier = mira.MiraClassifier(legalLabels, options['maxIterations'])
if (options['automaticTuning']):
print "using automatic tuning for MIRA"
classifier.automaticTuning = True
else:
print "using default C=0.001 for MIRA"
else:
print "Unknown classifier:", options['classifier']
print USAGE_STRING
sys.exit(2)
args['classifier'] = classifier
args['featureFunction'] = featureFunction
args['printImage'] = printImage
return args, options
elif(options.classifier == "naiveBayes" or options.classifier == "nb"):
classifier = naiveBayes.NaiveBayesClassifier(legalLabels)
classifier.setSmoothing(options.smoothing)
if (options.autotune):
print "using automatic tuning for naivebayes"
classifier.automaticTuning = True
else:
print "using smoothing parameter k=%f for naivebayes" % options.smoothing
elif(options.classifier == "perceptron"):
if options.data != 'pacman':
classifier = perceptron.PerceptronClassifier(legalLabels,options.iterations)
else:
classifier = perceptron_pacman.PerceptronClassifierPacman(legalLabels,options.iterations)
elif(options.classifier == "mira"):
if options.data != 'pacman':
classifier = mira.MiraClassifier(legalLabels, options.iterations)
if (options.autotune):
print "using automatic tuning for MIRA"
classifier.automaticTuning = True
else:
print "using default C=0.001 for MIRA"
elif(options.classifier == 'minicontest'):
import minicontest
classifier = minicontest.contestClassifier(legalLabels)
else:
print "Unknown classifier:", options.classifier
print USAGE_STRING
sys.exit(2)
args['agentToClone'] = options.agentToClone