Permalink
Cannot retrieve contributors at this time
Name already in use
A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
BigData/BagOfWords.py
Go to fileThis commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
113 lines (102 sloc)
3.58 KB
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
from __future__ import division | |
import string | |
import numpy | |
import nltk | |
from TFIDF import tfidf, delta_tfidf | |
# "Adapting a technique of Das and Chen (2001), we added the tag NOT to every word between a negation word ('not', | |
# 'isn't', 'didn't', etc.) and the first punctuation mark following the negation word." | |
# They didn't provide a full list. | |
NEGATION_WORDS = ["not", "n't"] | |
PUNCTUATION = [".", "!", "?", ",", ";", '(', ')'] #TODO make this work with POS tags (._.) | |
POSITION_TAGS = ["_1Q", "_2H", "_3Q"] | |
ADJECTIVE_TAGS = ["JJ", "JJR", "JJS", "JJT"] | |
POSITION_THRESHOLDS = [0.25, 0.75, 1] | |
# ref_bag is used to calculate the total word count across all documents. | |
def make(words, ref_bag=None, gram_length=1, use_negation=False, use_presence=False, use_pos_tags=False, use_adj_only=False, use_position=False, normalize=False): | |
bag_of_words = {} | |
if use_negation: | |
do_negation = False | |
if use_pos_tags: | |
#tagged = nltk.pos_tag(words) | |
tagged = tagger.tag(words) # this is much much faster !!! | |
words = [string.join(t, "_") for t in tagged] | |
for i in range(len(words) - gram_length + 1): | |
n_gram = string.join(words[i:i+gram_length], "_") | |
if use_negation: | |
if (gram_length == 1): # Pang and Lee didn't do negation tagging for bigrams. | |
if n_gram in NEGATION_WORDS: | |
do_negation = True | |
elif n_gram in PUNCTUATION: | |
do_negation = False | |
if do_negation: | |
n_gram = "NOT_" + n_gram | |
if use_position: | |
for j in range(len(POSITION_TAGS)): | |
if i/len(words) < POSITION_THRESHOLDS[j]: | |
n_gram += POSITION_TAGS[j] | |
break | |
index = n_gram | |
if not (use_pos_tags and use_adj_only and (tagged[i][1] not in ADJECTIVE_TAGS)): | |
if (not use_presence) and bag_of_words.has_key(index): | |
bag_of_words[index] += 1 | |
else: | |
bag_of_words[index] = 1 | |
# Add it to the reference bag | |
if ref_bag != None: | |
if ref_bag.has_key(index): | |
ref_bag[index] += 1 | |
else: | |
ref_bag[index] = 1 | |
#length-normalize | |
if normalize: | |
length = 0 | |
for k in bag_of_words.keys(): | |
length += (bag_of_words[k]**2) | |
length **= 0.5 | |
for k in bag_of_words.keys(): | |
bag_of_words[k] = bag_of_words[k]/length | |
return bag_of_words | |
# document and document are lists of words (pre-tokenized with nltk.word_tokenize()) | |
def make_tfidf(document, documents): | |
bag = {} | |
factor = 0 | |
for term in set(document): | |
weight = tfidf(term, document, documents) | |
if (weight != 0): | |
bag[term] = weight | |
factor += weight**2 | |
factor **= 0.5 | |
for key in bag.keys(): | |
bag[key] /= factor | |
return bag | |
# As per Martineau and Finn (2009), create a bag of words using delta TFIDF as the feature value. | |
# Todo: Bigrams? | |
def make_delta_tfidf(document, positive_set, negative_set, pos_idfs, neg_idfs, ref_bag, use_pos_tags=False): | |
bag = {} | |
factor = 0 | |
for term in set(document): | |
weight = delta_tfidf(term, document, positive_set, negative_set, pos_idfs, neg_idfs) | |
if (weight != 0): | |
bag[term] = weight | |
factor += weight**2 | |
factor **= 0.5 | |
for key in bag.keys(): | |
bag[key] /= factor | |
# Add word counts to the reference bag | |
for term in document: | |
if ref_bag != None: | |
if ref_bag.has_key(term): | |
ref_bag[term] += 1 | |
else: | |
ref_bag[term] = 1 | |
return bag | |
def to_vector(bag, wordlist): | |
vec = [] | |
for word in wordlist: | |
if bag.has_key(word): | |
vec.append(bag[word]) | |
else: | |
vec.append(0) | |
return vec | |
#return numpy.array(vec).reshape(1,-1) | |
tagger = nltk.tag.perceptron.PerceptronTagger() |