Python samples.loadDataFile函数代码示例

def readDigitData(trainingSize=100, testSize=100):
    rootdata = "digitdata/"
    # loading digits data
    rawTrainingData = samples.loadDataFile(
        rootdata + "trainingimages", trainingSize, DIGIT_DATUM_WIDTH, DIGIT_DATUM_HEIGHT
    )
    trainingLabels = samples.loadLabelsFile(rootdata + "traininglabels", trainingSize)
    rawValidationData = samples.loadDataFile(
        rootdata + "validationimages", TEST_SET_SIZE, DIGIT_DATUM_WIDTH, DIGIT_DATUM_HEIGHT
    )
    validationLabels = samples.loadLabelsFile(rootdata + "validationlabels", TEST_SET_SIZE)
    rawTestData = samples.loadDataFile("digitdata/testimages", testSize, DIGIT_DATUM_WIDTH, DIGIT_DATUM_HEIGHT)
    testLabels = samples.loadLabelsFile("digitdata/testlabels", testSize)
    try:
        print "Extracting features..."
        featureFunction = dataClassifier.basicFeatureExtractorDigit
        trainingData = map(featureFunction, rawTrainingData)
        validationData = map(featureFunction, rawValidationData)
        testData = map(featureFunction, rawTestData)
    except:
        display("An exception was raised while extracting basic features: \n %s" % getExceptionTraceBack())
    return (
        trainingData,
        trainingLabels,
        validationData,
        validationLabels,
        rawTrainingData,
        rawValidationData,
        testData,
        testLabels,
        rawTestData,
    )

def get_neuron_training_data():
	training_data = samples.loadDataFile("digitdata/trainingimages", num_train_examples, 28, 28)
	training_labels = np.array(samples.loadLabelsFile("digitdata/traininglabels", num_train_examples))
	training_labels = training_labels == 3

	featurized_training_data = np.array(map(dcu.simple_image_featurization, training_data))
	return training_data, featurized_training_data, training_labels

def get_neuron_test_data():
	test_data = samples.loadDataFile("digitdata/testimages", 1000, 28,28)
	test_labels = np.array(samples.loadLabelsFile("digitdata/testlabels", 1000))
	test_labels = test_labels == 3	

	featurized_test_data = np.array(map(dcu.simple_image_featurization, test_data))
	return test_data, featurized_test_data, test_labels

def runClassifier(args, options):
  classifier = args['classifier']
  printImage = args['printImage']
  # Load data  
  numTraining = options.training
  numTest = options.test
  if(options.data=="faces"):
    print "loading face data set"
    rawTrainingData = samples.loadDataFile("facedata/facedatatrain",FACE_DATUM_WIDTH,FACE_DATUM_HEIGHT)
    trainingLabels = samples.loadLabelsFile("facedata/facedatatrainlabels")
    rawValidationData = samples.loadDataFile("facedata/facedatavalidation",FACE_DATUM_WIDTH,FACE_DATUM_HEIGHT)
    validationLabels = samples.loadLabelsFile("facedata/facedatavalidationlabels")
    rawTestData = samples.loadDataFile("facedata/facedatatest", FACE_DATUM_WIDTH,FACE_DATUM_HEIGHT)
    testLabels = samples.loadLabelsFile("facedata/facedatatestlabels")
    rawTrainingData,trainingLabels=randomSample(rawTrainingData,trainingLabels,numTraining)
    rawTestData,testLabels=randomSample(rawTestData,testLabels,numTest)
  else:
    print "loading digit data set"
    rawTrainingData = samples.loadDataFile("digitdata/trainingimages",DIGIT_DATUM_WIDTH,DIGIT_DATUM_HEIGHT)
    trainingLabels = samples.loadLabelsFile("digitdata/traininglabels")
    rawValidationData = samples.loadDataFile("digitdata/validationimages",DIGIT_DATUM_WIDTH,DIGIT_DATUM_HEIGHT)
    validationLabels = samples.loadLabelsFile("digitdata/validationlabels")
    rawTestData = samples.loadDataFile("digitdata/testimages",DIGIT_DATUM_WIDTH,DIGIT_DATUM_HEIGHT)
    testLabels = samples.loadLabelsFile("digitdata/testlabels")
    rawTrainingData, trainingLabels = randomSample(rawTrainingData, trainingLabels, numTraining)
    rawTestData, testLabels = randomSample(rawTestData, testLabels, numTest)
  print "Extracting features..."
  if (options.classifier == "linear_svm"):
        if (options.data == "faces"):
            featureFunction = HogFeatureFaceImg
        else:
            featureFunction=HogFeatureImgDigit
        trainingData = map(featureFunction, rawTrainingData)
        trainingData=np.array(trainingData).transpose()
        validationData=map(featureFunction, rawValidationData)
        validationData = np.array(validationData).transpose()
        testData=map(featureFunction, rawTestData)
        testData = np.array(testData).transpose()
  else:
      if (options.data == "faces"):
          featureFunction = enhancedFeatureExtractorFace
      else:
          featureFunction = enhancedFeatureExtractorDigit
      trainingData = map(featureFunction, rawTrainingData)
      validationData = map(featureFunction, rawValidationData)
      testData = map(featureFunction, rawTestData)
  print "Training..."
  start = timeit.default_timer()
  classifier.train(trainingData, trainingLabels, validationData, validationLabels)
  stop = timeit.default_timer()
  print  stop - start, " s"
  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))
  analysis(classifier, guesses, testLabels, testData, rawTestData, printImage)

def runClassifier(args, options):

  featureFunction = args['featureFunction']
  classifier = args['classifier']
  printImage = args['printImage']
      
  # Load data  
  numTraining = options.training

  if(options.data=="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))
  analysis(classifier, guesses, testLabels, testData, rawTestData, printImage)
  
  # do odds ratio computation if specified at command line
  if((options.odds) & (options.classifier != "mostFrequent")):
    label1, label2 = options.label1, options.label2
    features_odds = classifier.findHighOddsFeatures(label1,label2)
    if(options.classifier == "naiveBayes" or options.classifier == "nb"):
      string3 = "=== Features with highest odd ratio of label %d over label %d ===" % (label1, label2)
    else:
      string3 = "=== Features for which weight(label %d)-weight(label %d) is biggest ===" % (label1, label2)    
      
    print string3
    printImage(features_odds)

def runClassifier(args, options):

  featureFunction = args['featureFunction']
  classifier = args['classifier']
  printImage = args['printImage']
      
  # Load data  
  numTraining = options.training

  if(options.data=="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))
  analysis(classifier, guesses, testLabels, testData, rawTestData, printImage)

def runClassifier(args, options):
    featureFunction = args['featureFunction']
    classifier = args['classifier']
    printImage = args['printImage']
    
    # Load data
    numTraining = options.training
    numTest = options.test

    if(options.data=="pacman"):
        agentToClone = args.get('agentToClone', None)
        trainingData, validationData, testData = MAP_AGENT_TO_PATH_OF_SAVED_GAMES.get(agentToClone, (None, None, None))
        trainingData = trainingData or args.get('trainingData', False) or MAP_AGENT_TO_PATH_OF_SAVED_GAMES['ContestAgent'][0]
        validationData = validationData or args.get('validationData', False) or MAP_AGENT_TO_PATH_OF_SAVED_GAMES['ContestAgent'][1]
        testData = testData or MAP_AGENT_TO_PATH_OF_SAVED_GAMES['ContestAgent'][2]
        rawTrainingData, trainingLabels = samples.loadPacmanData(trainingData, numTraining)
        rawValidationData, validationLabels = samples.loadPacmanData(validationData, numTest)
        rawTestData, testLabels = samples.loadPacmanData(testData, numTest)
    else:
        rawTrainingData = samples.loadDataFile("digitdata/trainingimages", numTraining,DIGIT_DATUM_WIDTH,DIGIT_DATUM_HEIGHT)
        trainingLabels = samples.loadLabelsFile("digitdata/traininglabels", numTraining)
        rawValidationData = samples.loadDataFile("digitdata/validationimages", numTest,DIGIT_DATUM_WIDTH,DIGIT_DATUM_HEIGHT)
        validationLabels = samples.loadLabelsFile("digitdata/validationlabels", numTest)
        rawTestData = samples.loadDataFile("digitdata/testimages", numTest,DIGIT_DATUM_WIDTH,DIGIT_DATUM_HEIGHT)
        testLabels = samples.loadLabelsFile("digitdata/testlabels", numTest)


    # 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))
    analysis(classifier, guesses, testLabels, testData, rawTestData, printImage)

    # do odds ratio computation if specified at command line
    if((options.odds) & (options.classifier == "naiveBayes" or (options.classifier == "nb")) ):
        label1, label2 = options.label1, options.label2
        features_odds = classifier.findHighOddsFeatures(label1,label2)
        if(options.classifier == "naiveBayes" or options.classifier == "nb"):
            string3 = "=== Features with highest odd ratio of label %d over label %d ===" % (label1, label2)
        else:
            string3 = "=== Features for which weight(label %d)-weight(label %d) is biggest ===" % (label1, label2)

        print string3
        printImage(features_odds)

    if((options.weights) & (options.classifier == "perceptron")):
        for l in classifier.legalLabels:
            features_weights = classifier.findHighWeightFeatures(l)
            print ("=== Features with high weight for label %d ==="%l)
            printImage(features_weights)

import numpy as np

def writeLabeledData(prefix, labeled_data):
    datums, labels = zip(*labeled_data)

    with open(prefix + "images", 'w') as f:
        for datum in datums:
            f.write(str(datum) + "\n")
        f.close()

    with open(prefix + "labels", 'w') as f:
        for label in labels:
            f.write(str(label) + "\n")
        f.close()

rawTrainingData = samples.loadDataFile("digitdata/trainingimages", 5000,DIGIT_DATUM_WIDTH,DIGIT_DATUM_HEIGHT)
trainingLabels = samples.loadLabelsFile("digitdata/traininglabels", 5000)
rawValidationData = samples.loadDataFile("digitdata/validationimages", 1000,DIGIT_DATUM_WIDTH,DIGIT_DATUM_HEIGHT)
validationLabels = samples.loadLabelsFile("digitdata/validationlabels", 1000)
rawTestData = samples.loadDataFile("digitdata/testimages", 1000,DIGIT_DATUM_WIDTH,DIGIT_DATUM_HEIGHT)
testLabels = samples.loadLabelsFile("digitdata/testlabels", 1000)


all_data = rawTrainingData + rawValidationData + rawTestData
all_labels = trainingLabels + validationLabels + testLabels

labeled_data = zip(all_data, all_labels)

perm = np.random.permutation(len(labeled_data))

permuted_data = []

def runClassifier(args, options):

    featureFunction = args['featureFunction']
    classifier = args['classifier']
    printImage = args['printImage']

    # Load data    
    numTraining = options.training
    numTest = options.test

    if(options.data=="faces"):
        rawTrainingData = samples.loadDataFile("facedata/facedatatrain", numTraining,FACE_DATUM_WIDTH,FACE_DATUM_HEIGHT)
        trainingLabels = samples.loadLabelsFile("facedata/facedatatrainlabels", numTraining)
        rawValidationData = samples.loadDataFile("facedata/facedatatrain", numTest,FACE_DATUM_WIDTH,FACE_DATUM_HEIGHT)
        validationLabels = samples.loadLabelsFile("facedata/facedatatrainlabels", numTest)
        rawTestData = samples.loadDataFile("facedata/facedatatest", numTest,FACE_DATUM_WIDTH,FACE_DATUM_HEIGHT)
        testLabels = samples.loadLabelsFile("facedata/facedatatestlabels", numTest)
    else:
        rawTrainingData = samples.loadDataFile("digitdata/trainingimages", numTraining,DIGIT_DATUM_WIDTH,DIGIT_DATUM_HEIGHT)
        trainingLabels = samples.loadLabelsFile("digitdata/traininglabels", numTraining)
        rawValidationData = samples.loadDataFile("digitdata/validationimages", numTest,DIGIT_DATUM_WIDTH,DIGIT_DATUM_HEIGHT)
        validationLabels = samples.loadLabelsFile("digitdata/validationlabels", numTest)
        rawTestData = samples.loadDataFile("digitdata/testimages", numTest,DIGIT_DATUM_WIDTH,DIGIT_DATUM_HEIGHT)
        testLabels = samples.loadLabelsFile("digitdata/testlabels", numTest)


    # Extract features
    print "Extracting features..."
    trainingData = map(featureFunction, rawTrainingData)
    validationData = map(featureFunction, rawValidationData)
    testData = map(featureFunction, rawTestData)

    # Conduct training and testing
    print "Start training..."
    start = time.time()
    classifier.train(trainingData, trainingLabels, validationData, validationLabels)
    end = time.time() - start
    print "Traning time: " + str(end)
    print "Start validating..."
    guesses = classifier.classify(validationData)
    correct = [guesses[i] == validationLabels[i] for i in range(len(validationLabels))].count(True)
    print "Validation result: ", str(correct), ("correct out of " + str(len(validationLabels)) + " (%.1f%%).") % (100.0 * correct / len(validationLabels))
    print "Start testing..."
    guesses = classifier.classify(testData)
    correct = [guesses[i] == testLabels[i] for i in range(len(testLabels))].count(True)
    print "Testing result: ", str(correct), ("correct out of " + str(len(testLabels)) + " (%.1f%%).") % (100.0 * correct / len(testLabels))
    #analysis(classifier, guesses, testLabels, testData, rawTestData, printImage)

    # do odds ratio computation if specified at command line
    if((options.odds) & (options.classifier == NB) ):
        label1, label2 = options.label1, options.label2
        features_odds = classifier.findHighOddsFeatures(label1,label2)
        if(options.classifier == NB):
            string3 = "=== Features with highest odd ratio of label %d over label %d ===" % (label1, label2)
        else:
            string3 = "=== Features for which weight(label %d)-weight(label %d) is biggest ===" % (label1, label2)        

        print string3
        printImage(features_odds)

    if((options.weights) & (options.classifier == PT)):
        for l in classifier.legalLabels:
            features_weights = classifier.findHighWeightFeatures(l)
            print ("=== Features with high weight for label %d ==="%l)
            printImage(features_weights)

def runClassifier(args, options):

  featureFunction = args['featureFunction']
  classifier = args['classifier']
  printImage = args['printImage']
      
  # Load data  
  numTraining = options['train']

  if(options['data']=="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, testData, rawTestData, printImage)
  
  # do odds ratio computation if specified at command line
  if((options['odds']) & (options['classifier'] != "mostfrequent")):
    class1, class2 = options['class1'], options['class2']
    features_class1,features_class2,features_odds = classifier.findHighOddsFeatures(class1,class2)
    if(options['classifier'] == "naivebayes"):
      string1 = "=== Features with max P(F_i = 1 | class = %d) ===" % class1
      string2 = "=== Features with max P(F_i = 1 | class = %d) ===" % class2
      string3 = "=== Features with highest odd ratio of class %d over class %d ===" % (class1, class2)
    else:
      string1 = "=== Features with largest weight for class %d ===" % class1
      string2 = "=== Features with largest weight for class %d ===" % class2
      string3 = "=== Features with for which weight(class %d)-weight(class %d) is biggest ===" % (class1, class2)    
      
    print string1
    printImage(features_class1)
    print string2
    printImage(features_class2)
    print string3
    printImage(features_odds)

"""This file is in Beta and is not the real autograder."""

import data_classification_utils as dcu
import samples
import numpy as np

training_data = samples.loadDataFile("digitdata/trainingimages", 1, 28, 28)
features = dcu.simple_image_featurization(training_data[0])

expected = np.array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1., 1., 1., 1., 2., 2., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1., 1., 1., 1., 2., 2., 2., 2., 2., 2., 1., 2., 2., 2., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 2., 2., 2., 2., 2., 2., 2., 2., 2., 2., 1., 1., 1., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 2., 2., 2., 2., 2., 2., 2., 1., 2., 2., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1., 1., 2., 2., 2., 0., 0., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 2., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 2., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 2., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 2., 2., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 2., 2., 2., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1., 2., 2., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 2., 2., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 2., 2., 2., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1., 1., 2., 2., 2., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1., 2., 2., 2., 2., 2., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1., 2., 2., 2., 2., 2., 2., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1., 2., 2., 2., 2., 2., 2., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 2., 2., 2., 2., 2., 2., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 1., 2., 2., 2., 2., 2., 2., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 2., 2., 2., 2., 1., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.])
if not np.array_equal(features, expected):
	print("Error, featurization is incorrect. You reported: ")
	print(features)

def runClassifier(args, options):
  #print 'args: ', args
  #print 'options', options
  featureFunction = args['featureFunction']
  classifier = args['classifier']
  printImage = args['printImage']
      
  # Load data  
  numTraining = options.training
  numTest = options.test

  if(options.data=="faces"):
    rawTrainingData = samples.loadDataFile("facedata/facedatatrain", numTraining,FACE_DATUM_WIDTH,FACE_DATUM_HEIGHT)
    trainingLabels = samples.loadLabelsFile("facedata/facedatatrainlabels", numTraining)
    rawValidationData = samples.loadDataFile("facedata/facedatatrain", numTest,FACE_DATUM_WIDTH,FACE_DATUM_HEIGHT)
    validationLabels = samples.loadLabelsFile("facedata/facedatatrainlabels", numTest)
    rawTestData = samples.loadDataFile("facedata/facedatatest", numTest,FACE_DATUM_WIDTH,FACE_DATUM_HEIGHT)
    testLabels = samples.loadLabelsFile("facedata/facedatatestlabels", numTest)
  else:
    rawTrainingData = samples.loadDataFile("digitdata/trainingimages", numTraining,DIGIT_DATUM_WIDTH,DIGIT_DATUM_HEIGHT)
    trainingLabels = samples.loadLabelsFile("digitdata/traininglabels", numTraining)
    rawValidationData = samples.loadDataFile("digitdata/validationimages", numTest,DIGIT_DATUM_WIDTH,DIGIT_DATUM_HEIGHT)
    validationLabels = samples.loadLabelsFile("digitdata/validationlabels", numTest)
    rawTestData = samples.loadDataFile("digitdata/testimages", numTest,DIGIT_DATUM_WIDTH,DIGIT_DATUM_HEIGHT)
    testLabels = samples.loadLabelsFile("digitdata/testlabels", numTest)
    
  
  # Extract features
  #print "Extracting features..."
  #print '#######type of rawTrainingData is', rawTrainingData.__class__ # list of Datum
  #print '#######type of rawTrainingData[0] is', rawTrainingData[0].__class__ # Datum
  trainingData = map(featureFunction, rawTrainingData)
  #print '#######type of trainingData is', trainingData.__class__ # list of Counter
  #print '#######type of trainingData[0] is', trainingData[0].__class__ # Counter
  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))
  analysis(classifier, guesses, testLabels, testData, rawTestData, printImage)
  
  # do odds ratio computation if specified at command line
  if((options.odds) & (options.classifier == "naiveBayes" or (options.classifier == "nb")) ):
    label1, label2 = options.label1, options.label2
    features_odds = classifier.findHighOddsFeatures(label1,label2)
    if(options.classifier == "naiveBayes" or options.classifier == "nb"):
      string3 = "=== Features with highest odd ratio of label %d over label %d ===" % (label1, label2)
    else:
      string3 = "=== Features for which weight(label %d)-weight(label %d) is biggest ===" % (label1, label2)    
      
    print string3
    printImage(features_odds)

  if((options.weights) & (options.classifier == "perceptron")):
    for l in classifier.legalLabels:
      features_weights = classifier.findHighWeightFeatures(l)
      print ("=== Features with high weight for label %d ==="%l)
      printImage(features_weights)