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=['naiveBayes', 'mostFrequent' , 'decisionTree' ] , default='mostFrequent' )
parser.add_option('-d', '--data', help=default('Dataset to use'), choices=['car', 'ionosphere' , 'wine' ], default='car')
parser.add_option( '-m' , '--metric' , help = default( 'Division metric' ) , choices = [ 'gini' , 'error' , 'entropy' ] , default = 'error' )
parser.add_option( '-x' , '--maxdepth' , help = default( 'Maximum depth of the tree learned' ) , default = 200 )
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( options.data == "car" ) : ''
elif( options.data =="ionosphere" ) : ''
elif( options.data =="wine" ) : ''
else:
print "Unknown dataset" , options.data
print USAGE_STRING
sys.exit( 2 )
legalLabels = [ 0 , 1 ]
metric = None
if( options.classifier == "decisionTree" or options.classifier == "dt" ) :
classifier = decisionTree.DecisionTreeClassifier( legalLabels )
if options.metric == 'gini' :
metric = metrics.gini
elif options.metric == 'error' :
metric = metrics.error
elif options.metric == 'entropy' :
metric = metrics.entropy
else :
print "Unknown metric:", options.metric
print USAGE_STRING
sys.exit(2)
elif( options.classifier == "mostFrequent" or options.classifier == "mf" ) :
classifier = mostFrequent.MostFrequentClassifier( legalLabels )
else:
print "Unknown classifier:", options.classifier
print USAGE_STRING
sys.exit(2)
args['classifier'] = classifier
args[ 'metric' ] = metric
args[ 'maxdepth' ] = options.maxdepth
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 runClassifier():
"""
Harness code for running different classifiers on the face or digit data.
This is the main function for classification, and is designed
to be invoked from the command line (outside the Python interpreter).
Usage:
> python dataClassifier.py
OR
> python dataClassifier.py <data> <classifierName>
OR
> python dataClassifier.py <data> <classifierName> <featureFunction>
OR
> python dataClassifier.py <data> <classifierName> <featureFunction> <numTrainingExamples>
OR
> python dataClassifier.py <data> <classifierName> <featureFunction> <numTrainingExamples> <odds class1 class2>
For example:
> python dataClassifier.py digits naivebayes basic 1000
would run the naive Bayes classifier on 1000 training examples using the
basicFeatureExtractor function, and then test the classifier on the test data.
"""
print "Doing classification"
print "--------------------"
# Assign default values for arguments if they are not provided.
if (len(sys.argv) == 1):
print "No data specified; using digits."
sys.argv.append("digits")
if (len(sys.argv) == 2):
print "No classifier specified; using default."
sys.argv.append("mostfrequent")
if (len(sys.argv) == 3):
print "No feature extraction function specified; using default."
sys.argv.append("basic")
if (len(sys.argv) == 4):
print "No training set size specified; using default."
sys.argv.append("100")
if (len(sys.argv) == 5):
print "Not doing odds ratio computation."
sys.argv.append("noodds")
# Set up variables according to the command line input.
print "data:\t\t" + sys.argv[1]
print "classifier:\t\t" + sys.argv[2]
print "feature extractor:\t" + sys.argv[3]
print "training set size:\t" + sys.argv[4]
if ((sys.argv[1] == "digits") & (sys.argv[3] == "basic")):
featureFunction = basicFeatureExtractorDigit
elif ((sys.argv[1] == "faces") & (sys.argv[3] == "basic")):
featureFunction = basicFeatureExtractorFace
elif ((sys.argv[1] == "digits") & (sys.argv[3] == "enhanced")):
featureFunction = enhancedFeatureExtractorDigit
elif ((sys.argv[1] == "faces") & (sys.argv[3] == "enhanced")):
featureFunction = enhancedFeatureExtractorFace
else:
print "Unknown feature function:", sys.argv[2]
return
if (sys.argv[1] == "digits"): # if digits detect
legalLabels = range(10)
else: # if face detect
legalLabels = range(2)
if (sys.argv[2] == "mostfrequent"):
classifier = mostFrequent.MostFrequentClassifier(legalLabels)
elif (sys.argv[2] == "naivebayes"):
classifier = naiveBayes.NaiveBayesClassifier(legalLabels)
elif (sys.argv[2] == "perceptron"):
classifier = perceptron.PerceptronClassifier(legalLabels)
else:
print "Unknown classifier:", sys.argv[2]
return
# Load data
numTraining = int(sys.argv[4])
if (sys.argv[1] == "faces"):
rawTrainingData = samples.loadDataFile("facedata/facedatatrain",
numTraining, FACE_DATUM_WIDTH,
FACE_DATUM_HEIGHT)
trainingLabels = samples.loadLabelsFile("facedata/facedatatrainlabels",
numTraining)
rawValidationData = samples.loadDataFile("facedata/facedatatrain",
TEST_SET_SIZE,
FACE_DATUM_WIDTH,
FACE_DATUM_HEIGHT)
validationLabels = samples.loadLabelsFile(
"facedata/facedatatrainlabels", TEST_SET_SIZE)
rawTestData = samples.loadDataFile("facedata/facedatatest",
TEST_SET_SIZE, FACE_DATUM_WIDTH,
FACE_DATUM_HEIGHT)
testLabels = samples.loadLabelsFile("facedata/facedatatestlabels",
TEST_SET_SIZE)
else:
rawTrainingData = samples.loadDataFile("digitdata/trainingimages",
numTraining, DIGIT_DATUM_WIDTH,
DIGIT_DATUM_HEIGHT)
trainingLabels = samples.loadLabelsFile("digitdata/traininglabels",
numTraining)
rawValidationData = samples.loadDataFile("digitdata/validationimages",
TEST_SET_SIZE,
DIGIT_DATUM_WIDTH,
DIGIT_DATUM_HEIGHT)
validationLabels = samples.loadLabelsFile("digitdata/validationlabels",
TEST_SET_SIZE)
rawTestData = samples.loadDataFile("digitdata/testimages",
TEST_SET_SIZE, DIGIT_DATUM_WIDTH,
DIGIT_DATUM_HEIGHT)
testLabels = samples.loadLabelsFile("digitdata/testlabels",
TEST_SET_SIZE)
# Extract features
print "Extracting features..."
trainingData = map(featureFunction, rawTrainingData)
validationData = map(featureFunction, rawValidationData)
testData = map(featureFunction, rawTestData)
# Conduct training and testing
print "Training..."
classifier.train(trainingData, trainingLabels, validationData,
validationLabels)
print "Validating..."
guesses = classifier.classify(validationData)
correct = [
guesses[i] == validationLabels[i] for i in range(len(validationLabels))
].count(True)
print str(correct), ("correct out of " + str(len(validationLabels)) +
" (%.1f%%).") % (100.0 * correct /
len(validationLabels))
print "Testing..."
guesses = classifier.classify(testData)
correct = [guesses[i] == testLabels[i]
for i in range(len(testLabels))].count(True)
print str(correct), ("correct out of " + str(len(testLabels)) +
" (%.1f%%).") % (100.0 * correct / len(testLabels))
util.pause()
analysis(classifier, guesses, testLabels, rawTestData)
# do odds ratio computation if specified at command line
if ((sys.argv[5] == "odds") & (len(sys.argv) == 8)):
features_class1, features_class2, features_odds = classifier.findHighOddsFeatures(
int(sys.argv[6]), int(sys.argv[7]))
if (sys.argv[1] == "faces"):
printImage(features_class1, FACE_DATUM_WIDTH, FACE_DATUM_HEIGHT)
printImage(features_class2, FACE_DATUM_WIDTH, FACE_DATUM_HEIGHT)
printImage(features_odds, FACE_DATUM_WIDTH, FACE_DATUM_HEIGHT)
else:
printImage(features_class1, DIGIT_DATUM_WIDTH, DIGIT_DATUM_HEIGHT)
printImage(features_class2, DIGIT_DATUM_WIDTH, DIGIT_DATUM_HEIGHT)
printImage(features_odds, DIGIT_DATUM_WIDTH, DIGIT_DATUM_HEIGHT)
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', 'GDA'],
default='mostFrequent')
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=450,
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 "training set size:\t" + str(options.training)
if (options.data == "digits"):
printImage = ImagePrinter(DIGIT_DATUM_WIDTH,
DIGIT_DATUM_HEIGHT).printImage
featureFunction = basicFeatureExtractorDigit
elif (options.data == "faces"):
printImage = ImagePrinter(FACE_DATUM_WIDTH,
FACE_DATUM_HEIGHT).printImage
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.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 == "GDA"):
classifier = gaussianDiscriminantAnalysis.GaussianDiscriminantAnalysisClassifier(
legalLabels, "GDA")
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=['mostFrequent', 'perceptron', 'mlp', 'svm'],
default='mostFrequent')
parser.add_option('-t',
'--training',
help=default('The size of the training set'),
default=TRAINING_SET_SIZE,
type="int")
parser.add_option('-w',
'--weights',
help=default('Whether to print weights'),
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")
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 "training set size:\t" + str(options.training)
printImage = ImagePrinter(DIGIT_DATUM_WIDTH, DIGIT_DATUM_HEIGHT).printImage
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.classifier == "mostFrequent"):
classifier = mostFrequent.MostFrequentClassifier(legalLabels)
elif (options.classifier == "mlp"):
classifier = mlp.MLPClassifier(legalLabels, options.iterations)
elif (options.classifier == "perceptron"):
classifier = perceptron.PerceptronClassifier(legalLabels,
options.iterations)
elif (options.classifier == "svm"):
classifier = svm.SVMClassifier(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=[
'mostFrequent', 'nb', 'naiveBayes',
'nearestNeighbors', 'perceptron', 'mira',
'minicontest'
],
default='mostFrequent')
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',
'--k_number_of_neighbors',
help=default("Number of neighbors to search (For nearestNeighbors)"),
default=3,
type="int")
parser.add_option(
'-x',
'--specialMode',
help=default(
"Trains in increments of random 10% of data and displays results"),
default=False,
action="store_true")
parser.add_option('-y',
'--analysis',
help=default("Shows which data is wrongly predicted"),
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("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 not options.specialMode:
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
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.k_number_of_neighbors <= 0:
print(
"Please provide a positive number for neighbors (you provided: %f)"
% options.k_number_of_neighbors)
print(USAGE_STRING)
sys.exit(2)
if options.classifier == "mostFrequent":
classifier = mostFrequent.MostFrequentClassifier(legalLabels)
elif options.classifier == "nearestNeighbors":
classifier = nearestNeighbors.NNClassifier(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":
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")
elif options.classifier == 'minicontest':
import minicontest
classifier = minicontest.contestClassifier(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('-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=['mostFrequent', 'naiveBayes', 'perceptron', 'knn'],
default='mostFrequent')
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 == "mostFrequent":
classifier = mostFrequent.MostFrequentClassifier(legalLabels)
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.
"""
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
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",
"perceptron",
],
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)
print("using enhanced features?:\t" + str(options.features))
print("training set size:\t" + str(options.training))
if options.data == "digits":
printImage = ImagePrinter(
DIGIT_DATUM_WIDTH, DIGIT_DATUM_HEIGHT
).printImage
featureFunction = basicFeatureExtractorDigit
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 = list(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 == "perceptron":
if options.data != "pacman":
classifier = perceptron.PerceptronClassifier(
legalLabels, options.iterations
)
else:
classifier = perceptron_pacman.PerceptronClassifierPacman(
legalLabels, options.iterations
)
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
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':
