本文整理汇总了Python中EditModel.EditModel类的典型用法代码示例。如果您正苦于以下问题:Python EditModel类的具体用法?Python EditModel怎么用?Python EditModel使用的例子?那么, 这里精选的类代码示例或许可以为您提供帮助。
在下文中一共展示了EditModel类的5个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: scan_edits
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')
示例2: output
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
示例3: __init__
def __init__(self, lm, corpus):
"""initializes the language model."""
self.languageModel = lm
self.editModel = EditModel('../data/count_1edit.txt', corpus)
示例4: __init__
def __init__(self, lm, corpus):
self.languageModel = lm
self.editModel = EditModel('../data/count_1edit.txt', corpus)
示例5: __init__
def __init__(self, models, lm, corpus, classModel=None):
"""initializes the language model."""
self.classModel = classModel
self.languageModels = models
self.languageModelFunction = lm
self.editModel = EditModel('./data/count_1edit.txt', corpus)