def test_pipeline(pipeline):
"""
Support function used to test a pipeline using the specified testSet
"""
if not isinstance(pipeline, Pipeline):
raise ValueError("pipeline must be an instance of Pipeline")
timer.start()
if not useConllFile:
labeled_featuresets = read_tweets_file(originalFile, pipeline).values()
else:
labeled_featuresets = read_conll_file(originalFile, conllFile,
pipeline).values()
validator = CrossValidator(labeled_featuresets)
print "Elapsed time for data set processing: %.0fs\n" % (timer.stop() /
1000)
# test the classifiers
for classifierName in classifiers:
timer.start()
print "- %s " % classifierName,
print "accuracy: %f" % validator.validate(classifiers[classifierName],
numOfBins)[0]
print " Elapsed time: %.0fs\n" % (timer.stop() / 1000)
def test_pipeline(pipeline):
"""
Support function used to test a pipeline using the specified testSet
"""
if not isinstance(pipeline, Pipeline):
raise ValueError("pipeline must be an instance of Pipeline")
timer.start()
if not useConllFile:
labeled_featuresets = read_tweets_file(originalFile, pipeline).values()
else:
labeled_featuresets = read_conll_file(originalFile, conllFile, pipeline).values()
validator = CrossValidator(labeled_featuresets)
print "Elapsed time for data set processing: %.0fs\n" % (timer.stop()/1000)
# test the classifiers
for classifierName in classifiers:
timer.start()
print "- %s " % classifierName,
print "accuracy: %f" % validator.validate(classifiers[classifierName], numOfBins)[0]
print " Elapsed time: %.0fs\n" % (timer.stop()/1000)
from adapter.tagRemover import TagRemover
tagrm = TagRemover()
postfilters.append(tagrm)
print " TagRemover."
print "]"
print ""
print ""
pipeline = Pipeline(tokenizer, tagger, prefilters, postfilters)
file = ["tweeti-b", "tweeti-b.dev"]
if not args.n:
# Load standard tweet file
trainingfile = map(lambda path: args.datasetpath + path + ".tsv", file)
labeled_featuresets = read_tweets_file(trainingfile, pipeline).values()
else:
# If the not adapter filter has to be used, the program has to load the *.conll files instead
# the conll files must be in the same dataset path specified by the user.
trainingfile = map(lambda path: args.datasetpath + path + ".tsv", file)
conllfile = map(lambda path: args.datasetpath + path + ".conll", file)
labeled_featuresets = read_conll_file(trainingfile, conllfile,
pipeline).values()
if not args.predict:
############ Cross Validation
validator = CrossValidator(labeled_featuresets)
timer.start()
(acc, conf_matr, prec, recall,
f_measure) = validator.validate(classifier, args.v)
print "Accuracy: %f" % acc
# classifier from classifier.shortTextClassifier import ShortTextClassifier classifier = ShortTextClassifier( ) # file paths originalFile = map(lambda path: get_project_dir() + "resources/tweeti/" + path + ".tsv", ["tweeti-b", "tweeti-b.dev"]) testingFile = map(lambda path: get_project_dir() + "resources/tweeti/" + path + ".tsv", ["twitter-test-input-B"]) # initialize the pipeline used to transform the tweets tokenizer = POSTokenizer() tagger = POSTagger() pipeline = Pipeline( tokenizer, tagger, [], [] ) # read the training file labeled_featuresets = read_tweets_file( originalFile, pipeline ).values( ) # training classifier.train( labeled_featuresets ) # read the test file labeled_featuresets_test = read_tweets_file( testingFile, pipeline ) for key in labeled_featuresets_test: labeled_featuresets_test[key] = labeled_featuresets_test[key][0] # classification labeled_featuresets_test = classifier.classify_dict( labeled_featuresets_test ) # output generation output = open( get_project_dir() + "resources/twitter-test-input-B.out", 'w') for key, label in labeled_featuresets_test.iteritems():
from adapter.tagRemover import TagRemover tagrm = TagRemover() postfilters.append(tagrm) print " TagRemover." print "]" print "" print "" pipeline = Pipeline( tokenizer, tagger, prefilters, postfilters ) file = ["tweeti-b", "tweeti-b.dev"] if not args.n: # Load standard tweet file trainingfile = map(lambda path: args.datasetpath + path + ".tsv", file) labeled_featuresets = read_tweets_file(trainingfile, pipeline).values() else: # If the not adapter filter has to be used, the program has to load the *.conll files instead # the conll files must be in the same dataset path specified by the user. trainingfile = map(lambda path: args.datasetpath + path + ".tsv", file) conllfile = map(lambda path: args.datasetpath + path + ".conll", file) labeled_featuresets = read_conll_file(trainingfile, conllfile,pipeline).values() if not args.predict: ############ Cross Validation validator = CrossValidator(labeled_featuresets) timer.start() (acc, conf_matr, prec, recall, f_measure) = validator.validate(classifier, args.v) print "Accuracy: %f" % acc print "Confusion Matrix:" for prec_label in conf_matr:
# file paths
originalFile = map(
lambda path: get_project_dir() + "resources/tweeti/" + path + ".tsv",
["tweeti-b", "tweeti-b.dev"])
testingFile = map(
lambda path: get_project_dir() + "resources/tweeti/" + path + ".tsv",
["twitter-test-input-B"])
# initialize the pipeline used to transform the tweets
tokenizer = POSTokenizer()
tagger = POSTagger()
pipeline = Pipeline(tokenizer, tagger, [], [])
# read the training file
labeled_featuresets = read_tweets_file(originalFile, pipeline).values()
# training
classifier.train(labeled_featuresets)
# read the test file
labeled_featuresets_test = read_tweets_file(testingFile, pipeline)
for key in labeled_featuresets_test:
labeled_featuresets_test[key] = labeled_featuresets_test[key][0]
# classification
labeled_featuresets_test = classifier.classify_dict(labeled_featuresets_test)
# output generation
output = open(get_project_dir() + "resources/twitter-test-input-B.out", 'w')
for key, label in labeled_featuresets_test.iteritems():
