def output(self, partId, ch_aux):
"""Uses the student code to compute the output for test cases."""
trainCorpus = HolbrookCorpus('../data/holbrook-tagged-train.dat')
if partId in [1, 2]:
editModel = EditModel('../data/count_1edit.txt', trainCorpus)
return json.dumps([[(e.editedWord, e.rule())
for e in editModel.edits(line.strip())]
for line in ch_aux.split("\n")])
else:
testCorpus = HolbrookCorpus()
testCorpus.slurpString(ch_aux)
lm = None
if partId in [3, 4]:
lm = LaplaceUnigramLanguageModel(trainCorpus)
elif partId in [5, 6]:
lm = LaplaceBigramLanguageModel(trainCorpus)
elif partId in [7, 8]:
lm = StupidBackoffLanguageModel(trainCorpus)
elif partId in [9, 10]:
lm = CustomLanguageModel(trainCorpus)
else:
print 'Unknown partId: " + partId'
return None
speller = SpellCorrect(lm, trainCorpus)
output = speller.correctCorpus(testCorpus)
# put in the part ID as well
output = '[["%d"],%s' % (partId, output[1:])
return output
def scan_edits(edits_file):
print >> sys.stderr, "Processing " + edits_file
editmodel = EditModel('')
edit_probs = Counter()
edits1 = read_edit1s(edits_file)
print >> sys.stderr, "Counting"
for error, correct in edits1:
count_chars(correct)
v, edit_types = editmodel.get_edits(correct, error)
edit_types = set(edit_types)
edit_types = [each for each in edit_types if each[0] != editmodel.nc]
edit_probs.update(edit_types)
num_char_unigrams = len(char_counts)
print >> sys.stderr, "Normalizing"
norm_edit_probs = {}
for kind, str in edit_probs.keys():
if kind == editmodel.dl:
norm_edit_probs[(kind, str)] = (edit_probs[(kind, str)] + 1.0) / (
get_char_bigram_count(str) + num_char_unigrams + 1)
elif kind == editmodel.ins:
norm_edit_probs[(kind, str)] = (edit_probs[(kind, str)] + 1.0) / (
get_char_unigram_count(str[0]) + num_char_unigrams + 1)
elif kind == editmodel.sub:
#If this is a substitution, reverse the characters because of bug in get_edits
norm_edit_probs[(
kind, str[::-1])] = (edit_probs[(kind, str)] + 1.0) / (
get_char_unigram_count(str[0]) + num_char_unigrams + 1)
elif kind == editmodel.trs:
norm_edit_probs[(kind, str)] = (edit_probs[(kind, str)] + 1.0) / (
get_char_bigram_count(str) + num_char_unigrams + 1)
print >> sys.stderr, "Writing to file - edits_model"
serialize_data(norm_edit_probs, 'edit_model')
serialize_data(dict(char_counts), 'char_unigram_model')
serialize_data(dict(char_bigram_counts), 'char_bigram_model')
def __init__(self, lm, corpus):
self.languageModel = lm
self.editModel = EditModel('data/count_1edit.txt', corpus)
def __init__(self, lm, corpus):
"""initializes the language model."""
self.languageModel = lm
self.editModel = EditModel('../data/count_1edit.txt', corpus)
return result, max
if __name__ == '__main__':
if len(sys.argv) < 4:
print "Usage: python corrector.py <dev | test> <uniform | empirical> <queries file>"
exit(0)
queries_file = sys.argv[3]
queries, gold, google = read_query_data(queries_file)
kind_of_editmodel = sys.argv[2]
#Read in unigram and bigram probs
print >> sys.stderr, "Loading language model"
languagemodel = LanguageModel('unigram_model','bigram_model')
print >> sys.stderr, "Loading edit model"
editmodel = EditModel(kind_of_editmodel,languagemodel)
languagemodel.init_edit_model(editmodel)
print >> sys.stderr,"Loading spell correct"
spell_corrector = SpellCorrect(languagemodel, editmodel)
answers = []
qc = 0
for eachquery in queries:
answer = spell_corrector.spell_correct_query(eachquery)
print answer
print >> sys.stderr, "%d" % (qc)
qc+=1
answers.append(answer)
#Accuracy evaluation
wrong = 0
correct = 0
for i in range(len(answers)):
def __init__(self, lm, corpus):
self.lm = lm
self.editModel = EditModel("./data/count_1edit.txt", corpus)
