def output(partId, ch_aux):
"""Uses the student code to compute the output for test cases."""
print '== Running your code ...'
featureFactory = FeatureFactory()
# read the train and test data
trainData = featureFactory.readData("../data/train")
testData = featureFactory.readTestData(ch_aux)
# add the features
trainDataWithFeatures = featureFactory.setFeaturesTrain(trainData)
testDataWithFeatures = featureFactory.setFeaturesTest(testData)
# write the updated data into JSON files
featureFactory.writeData(trainDataWithFeatures, "trainWithFeaturesSubmit")
featureFactory.writeData(testDataWithFeatures, "testWithFeaturesSubmit")
# run MEMM
output = Popen([
'java', '-cp', 'classes', '-Xmx1G', 'MEMM',
'trainWithFeaturesSubmit.json', 'testWithFeaturesSubmit.json',
'-submit'
],
stdout=PIPE).communicate()[0]
# print output[:100]
os.remove('trainWithFeaturesSubmit.json')
os.remove('testWithFeaturesSubmit.json')
print '== Finished running your code'
return output
def main(argv):
if len(argv) < 2:
print 'USAGE: python NER.py trainFile testFile'
exit(0)
printOp = ''
if len(argv) > 2:
printOp = '-print'
featureFactory = FeatureFactory()
# read the train and test data
trainData = featureFactory.readData(argv[0])
testData = featureFactory.readData(argv[1])
# add the features
trainDataWithFeatures = featureFactory.setFeaturesTrain(trainData)
testDataWithFeatures = featureFactory.setFeaturesTest(testData)
# write the updated data into JSON files
featureFactory.writeData(trainDataWithFeatures, 'trainWithFeatures')
featureFactory.writeData(testDataWithFeatures, 'testWithFeatures')
# run MEMM
output = Popen([
'java', '-cp', '../java/classes', '-Xmx2G', 'MEMM',
'trainWithFeatures.json', 'testWithFeatures.json', printOp
],
stdout=PIPE).communicate()[0]
# java -cp classes -Xmx1G MEMM trainWithFeatures.json testWithFeatures.json
# java -cp ../java/classes -Xmx1G MEMM trainWithFeatures.json testWithFeatures.json
print output
def main():
print 'USAGE: python NER.py trainFile testFile'
featureFactory = FeatureFactory()
# read the train and test data
trainData = featureFactory.readData("../data/train")
testData = featureFactory.readData("../data/dev")
# add the features
trainDataWithFeatures = featureFactory.setFeaturesTrain(trainData);
testDataWithFeatures = featureFactory.setFeaturesTest(testData);
# write the updated data into JSON files
featureFactory.writeData(trainDataWithFeatures, 'trainWithFeatures');
featureFactory.writeData(testDataWithFeatures, 'testWithFeatures');
# run MEMM
output = Popen(['java','-cp', 'classes', '-Xmx1G' ,'MEMM'
,'trainWithFeatures.json', 'testWithFeatures.json', '-print'],
stdout=PIPE).communicate()[0]
print output
def main(argv):
# defaults
if len(argv) == 0:
argv.append("../data/train")
argv.append("../data/dev")
elif len(argv) < 2:
print 'USAGE: python NER.py trainFile testFile'
exit(0)
# Set this to -print to print
printOp = ''
if len(argv) > 2:
printOp = '-print'
featureFactory = FeatureFactory()
# read the train and test data
trainData = featureFactory.readData(argv[0])
testData = featureFactory.readData(argv[1])
# add the features
trainDataWithFeatures = featureFactory.setFeaturesTrain(trainData)
testDataWithFeatures = featureFactory.setFeaturesTest(testData)
# write the updated data into JSON files
featureFactory.writeData(trainDataWithFeatures, 'trainWithFeatures')
featureFactory.writeData(testDataWithFeatures, 'testWithFeatures')
# run MEMM
output = Popen([
'java', '-cp', 'classes', '-Xmx2G', 'MEMM', 'trainWithFeatures.json',
'testWithFeatures.json', printOp
],
stdout=PIPE).communicate()[0]
print output
#write past feature name to file
with open('last', 'w') as f:
f.write(feature)
if feature == '1':
fe = features.FEATURE
elif feature == '2':
fe = features.FEATURE2
elif feature == '3':
fe = features.FEATURE3
elif feature == 'stress':
fe = features.STRESSTEST
#options for cluster:
k = raw_input('Number of clusters (k): ') or 'auto'
if k != 'auto':
k = int(k)
t = int(raw_input('Number of iterations: ') or 1)
weightlist = raw_input('enter weight vector, or auto: ') or '1 0 0'
if weightlist == 'auto':
w = 'auto'
else:
w = weightlist.split(" ")
w = map(float, w)
euclidean = raw_input('Use Euclidean distance? [Y/N]: ') or 'N'
if euclidean == 'Y' or euclidean == 'y': euclid = True
FeatureFactory = FeatureFactory(44100, fe, mp3list, k, t, run_before,
euclid)
test_cluster(w, auto)
