Last active
August 29, 2015 14:00
-
-
Save alep/11297967 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import nltk | |
from collections import namedtuple | |
from sklearn.linear_model import LogisticRegression | |
from sklearn.feature_extraction import FeatureHasher | |
Data = namedtuple('Data', [ | |
'word_i_minus_2', | |
'tag_i_minus_2', | |
'word_i_minus_1', | |
'tag_i_minus_1', | |
'word', | |
'tag', | |
'word_i_plus_1', | |
'word_i_plus_2', | |
]) | |
class LRTagger(object): | |
def preprocess_train(self, tagged_sentence): | |
for ngram in nltk.util.ngrams( | |
tagged_sentence, 5, pad_symbol=("__none__", "__none__"), | |
pad_left=True, pad_right=True): | |
wt_m2, wt_m1, wt, wt_p1, wt_p2 = ngram | |
if wt != ("__none__", "__none__"): | |
yield Data( | |
tag_i_minus_2=str(wt_m2[1]), | |
word_i_minus_2=str(wt_m2[0]), | |
tag_i_minus_1=str(wt_m1[1]), | |
word_i_minus_1=str(wt_m1[0]), | |
word=str(wt[0]), | |
tag=str(wt[1]), | |
word_i_plus_1=str(wt_p1[0]), | |
word_i_plus_2=str(wt_p2[0]),) | |
def preprocess_test(self, tagged_sentence): | |
for ngram in nltk.util.ngrams( | |
tagged_sentence, 5, pad_symbol="__none__", | |
pad_left=True, pad_right=True): | |
w_m2, w_m1, w, w_p1, w_p2 = ngram | |
if w != "__none__": | |
yield Data( | |
tag_i_minus_2="__none__", | |
word_i_minus_2=w_m2, | |
tag_i_minus_1="__none__", | |
word_i_minus_1=w_m1, | |
word=w, | |
tag="__none__", | |
word_i_plus_1=w_p1, | |
word_i_plus_2=w_p2,) | |
def feat(self, data): | |
features = [ | |
lambda data: data.tag_i_minus_1, | |
lambda data: "%s %s" % (data.tag_i_minus_2, data.tag_i_minus_1), | |
lambda data: data.word_i_minus_1, | |
lambda data: data.word_i_minus_2, | |
lambda data: data.word_i_plus_1, | |
lambda data: data.word_i_plus_2, | |
lambda data: data.word, | |
lambda data: (any(digit in data.word for digit in '1234567890') | |
and '__hasnum__' or '__nonum__'), | |
lambda data: '-' in data.word and '__hyphen__' or '__nohyphen__', | |
lambda data: (any(map(lambda x: x.isupper, data.word)) | |
and '__upper__' or '__noupper__'), | |
lambda data: data.word[:2], | |
lambda data: data.word[-2:], | |
lambda data: data.word[:3], | |
lambda data: data.word[-3:], | |
lambda data: data.word[:4], | |
lambda data: data.word[-4:], | |
] | |
for f in features: | |
yield f(data) | |
def transform(self, train): | |
for sent in train: | |
for feature in self.preprocess_train(sent): | |
yield feature | |
def finder(self, test): | |
# Must explore using search, where the option would | |
# be using the history or not. | |
tag_i_minus_1 = "__none__" | |
tag_i_minus_2 = "__none__" | |
for sample in test: | |
sample = sample._replace( | |
tag_i_minus_1=tag_i_minus_1, | |
tag_i_minus_2=tag_i_minus_2) | |
hashed_sample = self.hasher.transform( | |
[self.feat(sample)]) | |
predicted_tag = self.model.predict(hashed_sample) | |
tag_i_minus_2 = tag_i_minus_1 | |
tag_i_minus_1 = str(predicted_tag[0]) | |
yield sample.word, str(predicted_tag[0]) | |
def __init__(self, train): | |
self.hasher = FeatureHasher(input_type='string') | |
self.train = list(self.transform(train)) | |
X = self.hasher.transform(self.feat(d) for d in self.train) | |
y = map(lambda d: d.tag, self.train) | |
self.model = LogisticRegression() | |
self.model.fit(X, y) | |
def tag(self, words): | |
return list(self.finder(self.preprocess_test(words))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment