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 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')
