This repository has been archived by the owner. It is now read-only.
Switch branches/tags
Nothing to show
Find file Copy path
Fetching contributors…
Cannot retrieve contributors at this time
173 lines (150 sloc) 6.25 KB
# -*- coding: utf-8 -*-
from __future__ import absolute_import
import os
import random
from collections import defaultdict
import pickle
import logging
from textblob.base import BaseTagger
from textblob.tokenizers import WordTokenizer, SentenceTokenizer
from textblob.exceptions import MissingCorpusError
from textblob_aptagger._perceptron import AveragedPerceptron
PICKLE = "trontagger-0.1.0.pickle"
class PerceptronTagger(BaseTagger):
'''Greedy Averaged Perceptron tagger, as implemented by Matthew Honnibal.
See more implementation details here:
:param load: Load the pickled model upon instantiation.
START = ['-START-', '-START2-']
END = ['-END-', '-END2-']
AP_MODEL_LOC = os.path.join(os.path.dirname(__file__), PICKLE)
def __init__(self, load=True):
self.model = AveragedPerceptron()
self.tagdict = {}
self.classes = set()
if load:
def tag(self, corpus, tokenize=True):
'''Tags a string `corpus`.'''
# Assume untokenized corpus has \n between sentences and ' ' between words
s_split = SentenceTokenizer().tokenize if tokenize else lambda t: t.split('\n')
w_split = WordTokenizer().tokenize if tokenize else lambda s: s.split()
def split_sents(corpus):
for s in s_split(corpus):
yield w_split(s)
prev, prev2 = self.START
tokens = []
for words in split_sents(corpus):
context = self.START + [self._normalize(w) for w in words] + self.END
for i, word in enumerate(words):
tag = self.tagdict.get(word)
if not tag:
features = self._get_features(i, word, context, prev, prev2)
tag = self.model.predict(features)
tokens.append((word, tag))
prev2 = prev
prev = tag
return tokens
def train(self, sentences, save_loc=None, nr_iter=5):
'''Train a model from sentences, and save it at ``save_loc``. ``nr_iter``
controls the number of Perceptron training iterations.
:param sentences: A list of (words, tags) tuples.
:param save_loc: If not ``None``, saves a pickled model in this location.
:param nr_iter: Number of training iterations.
self.model.classes = self.classes
prev, prev2 = self.START
for iter_ in range(nr_iter):
c = 0
n = 0
for words, tags in sentences:
context = self.START + [self._normalize(w) for w in words] \
+ self.END
for i, word in enumerate(words):
guess = self.tagdict.get(word)
if not guess:
feats = self._get_features(i, word, context, prev, prev2)
guess = self.model.predict(feats)
self.model.update(tags[i], guess, feats)
prev2 = prev
prev = guess
c += guess == tags[i]
n += 1
random.shuffle(sentences)"Iter {0}: {1}/{2}={3}".format(iter_, c, n, _pc(c, n)))
# Pickle as a binary file
if save_loc is not None:
pickle.dump((self.model.weights, self.tagdict, self.classes),
open(save_loc, 'wb'), -1)
return None
def load(self, loc):
'''Load a pickled model.'''
w_td_c = pickle.load(open(loc, 'rb'))
except IOError:
msg = ("Missing trontagger.pickle file.")
raise MissingCorpusError(msg)
self.model.weights, self.tagdict, self.classes = w_td_c
self.model.classes = self.classes
return None
def _normalize(self, word):
'''Normalization used in pre-processing.
- All words are lower cased
- Digits in the range 1800-2100 are represented as !YEAR;
- Other digits are represented as !DIGITS
:rtype: str
if '-' in word and word[0] != '-':
return '!HYPHEN'
elif word.isdigit() and len(word) == 4:
return '!YEAR'
elif word[0].isdigit():
return '!DIGITS'
return word.lower()
def _get_features(self, i, word, context, prev, prev2):
'''Map tokens into a feature representation, implemented as a
{hashable: float} dict. If the features change, a new model must be
def add(name, *args):
features[' '.join((name,) + tuple(args))] += 1
i += len(self.START)
features = defaultdict(int)
# It's useful to have a constant feature, which acts sort of like a prior
add('i suffix', word[-3:])
add('i pref1', word[0])
add('i-1 tag', prev)
add('i-2 tag', prev2)
add('i tag+i-2 tag', prev, prev2)
add('i word', context[i])
add('i-1 tag+i word', prev, context[i])
add('i-1 word', context[i-1])
add('i-1 suffix', context[i-1][-3:])
add('i-2 word', context[i-2])
add('i+1 word', context[i+1])
add('i+1 suffix', context[i+1][-3:])
add('i+2 word', context[i+2])
return features
def _make_tagdict(self, sentences):
'''Make a tag dictionary for single-tag words.'''
counts = defaultdict(lambda: defaultdict(int))
for words, tags in sentences:
for word, tag in zip(words, tags):
counts[word][tag] += 1
freq_thresh = 20
ambiguity_thresh = 0.97
for word, tag_freqs in counts.items():
tag, mode = max(tag_freqs.items(), key=lambda item: item[1])
n = sum(tag_freqs.values())
# Don't add rare words to the tag dictionary
# Only add quite unambiguous words
if n >= freq_thresh and (float(mode) / n) >= ambiguity_thresh:
self.tagdict[word] = tag
def _pc(n, d):
return (float(n) / d) * 100