def test_custom_feat_avg_perceptron():
# w, tr_acc, dv_acc = avg_perceptron.trainAvgPerceptron(10,tr_all,features.yourFeatures,alltags)
# confusion = tagger_base.evalTagger(lambda words,alltags : tagger_base.classifierTagger(words,features.yourFeatures,w,alltags),'classifier')
confusion = scorer.getConfusion(constants.DEV_FILE, 'avg_perceptron_custom.response')
expected_acc = 0.810
actual_acc = scorer.accuracy(confusion)
ok_ (expected_acc < actual_acc, msg="NOT_IN_RANGE Expected:%f, Actual:%f" %(expected_acc, actual_acc))
def test_custom_str_perceptron():
# w,tr_acc,dv_acc = str_perceptron.trainAvgStructPerceptron(10,tr_all,features.yourHMMFeatures,alltags)
# confusion = tagger_base.evalTagger(lambda words,alltags : viterbi.viterbiTagger(words,features.yourHMMFeatures,w,alltags)[0],'custom_str_classifier')
confusion = scorer.getConfusion(DEV_FILE, 'str_avg_perceptron_custom.response')
expected_acc = 0.810
actual_acc = scorer.accuracy(confusion)
ok_ (expected_acc < actual_acc, msg="NOT_IN_RANGE Expected:%f, Actual:%f" %(expected_acc, actual_acc))
def test_str_perceptron():
# w,tr_acc,dv_acc = str_perceptron.trainAvgStructPerceptron(10,tr_all,features.wordTransFeatures,alltags)
# confusion = tagger_base.evalTagger(lambda words,alltags : viterbi.viterbiTagger(words,features.wordTransFeatures,w,alltags)[0],'str_classifier')
confusion = scorer.getConfusion(DEV_FILE, 'str_avg_perceptron.response')
expected_acc = 0.749
actual_acc = scorer.accuracy(confusion)
ok_(expected_acc < actual_acc,
msg="NOT_IN_RANGE Expected:%f, Actual:%f" % (expected_acc, actual_acc))
def test_avg_perceptron():
# w, tr_acc, dv_acc = avg_perceptron.trainAvgPerceptron(10,tr_all,features.wordCharFeatures,alltags)
# confusion = tagger_base.evalTagger(lambda words,alltags : tagger_base.classifierTagger(words,features.wordCharFeatures,w,alltags),'classifier')
confusion = scorer.getConfusion(constants.DEV_FILE,
'avg_perceptron.response')
expected_acc = 0.740
actual_acc = scorer.accuracy(confusion)
ok_(expected_acc < actual_acc,
msg="NOT_IN_RANGE Expected:%f, Actual:%f" % (expected_acc, actual_acc))
def evalTagger(tagger,outfilename,testfile=DEV_FILE):
alltags = set()
for i,(words, tags) in enumerate(preproc.conllSeqGenerator(TRAIN_FILE)):
for tag in tags:
alltags.add(tag)
with open(outfilename,'w') as outfile:
for words,_ in preproc.conllSeqGenerator(testfile):
pred_tags = tagger(words,alltags)
for tag in pred_tags:
print >>outfile, tag
print >>outfile, ""
return scorer.getConfusion(testfile,outfilename) #run the scorer on the prediction file
def evalTagger(tagger,outfilename,testfile=DEV_FILE):
alltags = set()
for i,(words, tags) in enumerate(preproc.conllSeqGenerator(TRAIN_FILE)):
for tag in tags:
alltags.add(tag)
with open(outfilename,'w') as outfile:
for words,_ in preproc.conllSeqGenerator(testfile):
pred_tags = tagger(words,alltags)
for tag in pred_tags:
print >>outfile, tag
print >>outfile, ""
return scorer.getConfusion(testfile,outfilename) #run the scorer on the prediction file
def evalTagger(tagger,outfilename,testfile=DEV_FILE):
"""Calculate confusion_matrix for a given tagger
Parameters:
tagger -- Function mapping (words, possible_tags) to an optimal
sequence of tags for the words
outfilename -- Filename to write tagger predictions to
testfile -- (optional) Filename containing true labels
Returns:
confusion_matrix -- dict of occurences of (true_label, pred_label)
"""
alltags = set()
for i,(words, tags) in enumerate(preproc.conllSeqGenerator(TRAIN_FILE)):
for tag in tags:
alltags.add(tag)
with open(outfilename,'w') as outfile:
for words,_ in preproc.conllSeqGenerator(testfile):
pred_tags = tagger(words,alltags)
for tag in pred_tags:
print >>outfile, tag
print >>outfile, ""
return scorer.getConfusion(testfile,outfilename) #run the scorer on the prediction file
def evalTagger(tagger, outfilename, testfile=DEV_FILE):
"""Calculate confusion_matrix for a given tagger
Parameters:
tagger -- Function mapping (words, possible_tags) to an optimal
sequence of tags for the words
outfilename -- Filename to write tagger predictions to
testfile -- (optional) Filename containing true labels
Returns:
confusion_matrix -- dict of occurences of (true_label, pred_label)
"""
alltags = set()
for i, (words, tags) in enumerate(preproc.conllSeqGenerator(TRAIN_FILE)):
for tag in tags:
alltags.add(tag)
with open(outfilename, 'w') as outfile:
for words, _ in preproc.conllSeqGenerator(testfile):
pred_tags = tagger(words, alltags)
for tag in pred_tags:
print >> outfile, tag
print >> outfile, ""
return scorer.getConfusion(
testfile, outfilename) #run the scorer on the prediction file
