def main():
articles = CategorizedPlaintextCorpusReader(corpusdir, '.*', cat_pattern = r'(.*)[/]')
feats = {}
trainfeats = []
testfeats = []
for cat in articles.categories():
wow = len([f for f in articles.fileids(cat)]) # such variable name
print "for category", cat, ":", wow
feats[cat] = [(word_feats(articles.words(fileids = [f])), cat) for f in articles.fileids(cat)]
cutoff = wow - hold_back(wow)
trainfeats.append(feats[cat][:cutoff])
testfeats.append(feats[cat][cutoff:])
train = [item for sublist in trainfeats for item in sublist]
test = [item for sublist in testfeats for item in sublist]
print 'train on %d instances, test on %d instances' % (len(train), len(test))
classifier = NaiveBayesClassifier.train(train)
print 'accuracy:', nltk.classify.util.accuracy(classifier, test)
classifier.show_most_informative_features() # I don't understand the output for more than 2 categories :(
# load with:
# import pickle
# f = open('my_classifier.pickle')
# classifier = pickle.load(f)
# f.close()
with open('../data/classifier.pickle', 'wb') as f:
pickle.dump(classifier, f)
'test_7.txt': 'Market Opinion'
}
art_i = []
class_i = []
#Conversion of Train Data into Single Input File
corpus_root = 'Train_set'
newcorpus = CategorizedPlaintextCorpusReader(corpus_root,
r'.*\.txt',
cat_pattern=r'(\w+)/*')
myfile = open('Input_Article_Data.csv', 'wb')
wr = csv.writer(myfile, quoting=csv.QUOTE_ALL, lineterminator="\n")
for category in newcorpus.categories():
for fileid in newcorpus.fileids(category):
#print fileid,category
data1 = (newcorpus.raw(fileid).encode('utf-8')).replace(",", " ")
data_list = [data1, category]
wr.writerow(data_list)
myfile.close()
#Reading of Train Data as Lists
with open('Input_Article_Data.csv', 'r') as f:
for line in f.readlines():
l, name = line.strip().split(',')
l = (re.sub('[^A-Za-z0-9.]+', ' ', l)).lower()
# l=porter_stemmer.stem(l) #Reduces Accuracy From 50% To 37%
if (name != "Category"):
art_i.append([l])
loc = '/Users/rmoura/nltk_data/corpora/rai/textoSimples/'
corpus1 = PlaintextCorpusReader(loc, '.*\.txt')
print(corpus1.fileids())
print(corpus1.sents())
print(corpus1.words())
# Corpus texto etiquetado
from nltk.corpus.reader.tagged import TaggedCorpusReader
loc = '/Users/rmoura/nltk_data/corpora/rai/textoEtiquetas/'
corpus2 = TaggedCorpusReader(loc, '.*\.txt')
print(corpus2.fileids())
print(corpus2.words())
print("Palavras etiquetadas: ", corpus2.tagged_words())
print(corpus2.tagged_words('003.txt'))
print("Sentencas diretas:")
for s in corpus2.sents():
print(' '.join(s))
from nltk.corpus.reader import CategorizedPlaintextCorpusReader
loc = '/Users/rmoura/nltk_data/corpora/rai/textoCategorias/'
corpus3 = CategorizedPlaintextCorpusReader(loc, '.*\.txt', cat_file="categorias.txt")
print(corpus3.fileids())
print(corpus3.categories())
print(corpus3.words(categories='brasnam'))
# Definicao de stopwords
stopwords = nltk.corpus.stopwords.words('portuguese')
fd = nltk.FreqDist(w.lower() for w in corpus3.words())
fd1 = nltk.FreqDist(w.lower() for w in corpus3.words()
if w.isalpha() and w not in stopwords)
from nltk.corpus.reader import CategorizedPlaintextCorpusReader
import nltk
d = nltk.data.find('corpora/cookbook')
reader = CategorizedPlaintextCorpusReader(d, r'movie_.*\.txt', cat_pattern=r'movie_(\w+)\.txt')
print(reader.categories())
print(reader.fileids(categories='neg'))
print(reader.fileids(categories='pos'))
# from nltk.corpus import brown
# print(brown.categories())
tweet = remove_links(tweet)
tweet = remove_users(tweet)
tweet = remove_numbers(tweet)
tweet = remove_hashtags(tweet)
tweet = [term for term in tweet.split(" ") if term not in stop_words]
if tweet:
if counter < 5:
prob_test_tweets[label].append((" ".join(tweet), original))
counter += 1
else:
normalized_tweets.append((" ".join(tweet), label))
return normalized_tweets[:
1600] # Barack Obama has more tweets, so I'm making it even
tweets_with_labels = normalize_tweets(reader.fileids(categories="BarackObama"),
0) + normalize_tweets(
reader.fileids(categories="NASA"), 1)
tweets = [tweet[0] for tweet in tweets_with_labels]
labels = [tweet[1] for tweet in tweets_with_labels]
tweets_train, tweets_test, labels_train, labels_test = train_test_split(
tweets, labels, test_size=0.1, random_state=12)
vectorizer = TfidfVectorizer()
tweets_train = vectorizer.fit_transform(tweets_train)
nb = MultinomialNB()
nb.fit(tweets_train, labels_train)
tweets_test = vectorizer.transform(tweets_test)
hashtag_free = remove_hashtags(number_free)
twitter_words = [
term.lower() for term in tweet_tokenizer.tokenize(hashtag_free)
if term.lower() not in stop_words
]
twitter_words_with_hashtags = [
term.lower() for term in tweet_tokenizer.tokenize(number_free)
if term.lower() not in stop_words
]
return twitter_words, twitter_words_with_hashtags
corpus_tokens = []
for category in reader.categories():
for file in reader.fileids(categories=category):
without_hashtags, with_hashtags = tokenize_tweets(file)
# c
fdist_category = nltk.FreqDist(without_hashtags)
print("Most common words in", category, ":",
fdist_category.most_common(10))
# d
hashtags = [word for word in with_hashtags if word.startswith("#")]
fdist_category_hashtag = nltk.FreqDist(hashtags)
print("Most common hashtags in", category, ":",
fdist_category_hashtag.most_common(10))
corpus_tokens += without_hashtags
if remove_stopwords:
sw = set(nltk.corpus.stopwords.words("english"))
words = [w for w in words if not w in sw]
if stem:
porter = nltk.PorterStemmer()
words = [porter.stem(w) for w in words]
return words
documents = [((fileid, category), preprocess(my_corpus.words(fileid),
to_lowercase = True, remove_punctuation = True, remove_digits = True,
remove_odd_chars = True, remove_stopwords=True, stem = False)) \
for category in my_corpus.categories() \
for fileid in my_corpus.fileids(category)]
def dummy_fun(doc):
return doc
bow_gen = sklearn.feature_extraction.text.CountVectorizer(
analyzer='word',
tokenizer=dummy_fun,
preprocessor=dummy_fun,
token_pattern=None,
ngram_range=(1, 2),
min_df = 150, # changed from 100
max_df = 0.85)
for f in os.listdir( path ) :
if not os.path.isfile( path ) :
if not f == ".DS_Store" :
dirList.append(f)
return dirList
###############################################
###############################################
#################
# TRAINING DATA #
#################
train_reader = CategorizedPlaintextCorpusReader('./training_data', r'.*\_.*\.txt', cat_pattern=r'.*\_(\w+)\.txt')
train_documents = [(list(train_reader.words(fileid)), category)
for category in train_reader.categories()
for fileid in train_reader.fileids(category)]
random.shuffle(train_documents)
#print train_documents
train_documents_clean = []
for i in train_documents :
cat = i[1]
#print cat
newList = []
for word in i[0] :
#print j
clean_word = word.encode('ascii', 'ignore').decode('ascii').encode('ascii', 'ignore')
newList.append(clean_word)
newTup = (newList, cat)
train_documents_clean.append(newTup)
#print train_documents_clean
# words = map(lambda word: word, word_tokenize(text));
# words = [word for word in words
# if word not in cachedStopWords]
# tokens =(list(map(lambda token: PorterStemmer().stem(token),
# words)));
# p = re.compile('[a-zA-Z]+');
# filtered_tokens = list(filter(lambda token:
# p.match(token) and len(token)>=min_length, tokens));
#
# return filtered_tokens
#Preparing a Tuple List of the Corpus Data based on
#Words In the corpus file and correspoindg category
data = [(list(tokenize(' '.join(reader.words(fileid)))), category)
for category in reader.categories()
for fileid in reader.fileids(category)]
#First preparing a train data set based on pre-identified features
featureListTrain = [
('Natural Language Processing', 'General'), ('Text Retrieval', 'General'),
('Text Access', 'General'), ('Information Retrieval', 'General'),
('NLP', 'General'), ('Content Analysis', 'General'),
('Vector', 'IR Models & Implementations'),
('Length', 'IR Models & Implementations'),
('Indexing', 'IR Models & Implementations'),
('Statistical', 'IR Models & Implementations'),
('Evaluation', 'IR Models- Evaluation,Ranking & Feedback'),
('Feedback', 'IR Models- Evaluation,Ranking & Feedback'),
('Ranking', 'IR Models- Evaluation,Ranking & Feedback'),
('Recommender', 'IR Models- Evaluation,Ranking & Feedback'),
def process_plaintext(dir_path):
reader = CategorizedPlaintextCorpusReader(dir_path,
r'.*\.txt',
cat_pattern=r'.+_.+_(.*)\.txt')
facilitator_files = reader.fileids(categories='facilitator')
participant_files = reader.fileids(categories='participant')
print facilitator_files, participant_files
#print reader.categories()
#print len(reader.words())
#print len(reader.sents())
fac_words = [word for word in reader.words(facilitator_files)]
par_words = [word for word in reader.words(participant_files)]
fac_words = edit_tokens(fac_words)
par_words = edit_tokens(par_words)
speakers = ([(word, 'facilitator')
for word in reader.words(facilitator_files)] +
[(word, 'participant')
for word in reader.words(participant_files)])
features = get_features(speakers)
size = int(len(features) * 0.3)
nb_train = features[size:]
nb_test = features[:size]
classifier = nltk.NaiveBayesClassifier.train(nb_train)
print "Classifier labels:", classifier.labels()
print classifier.show_most_informative_features()
print "Clasify test:", nltk.classify.accuracy(classifier, nb_test)
#print classifier.classify(get_features(["Yolo", "bag", "sp"], False))
#random.shuffle(speakers)
three_quarters = int(len(speakers) * 0.75)
train = speakers[:three_quarters]
test = speakers[three_quarters:]
est = lambda fdist, bins: nltk.probability.LaplaceProbDist(fdist)
un_lm = NgramModel(1, train, estimator=est)
bi_lm = NgramModel(2, train, estimator=est)
tr_lm = NgramModel(3, train, estimator=est)
qu_lm = NgramModel(4, train, estimator=est)
pe_lm = NgramModel(5, train, estimator=est)
print un_lm
print bi_lm
print tr_lm
print qu_lm
print pe_lm
print "1 gram Perplexity:", un_lm.perplexity(test)
print "2 gram Perplexity:", bi_lm.perplexity(test)
print "3 gram Perplexity:", tr_lm.perplexity(test)
print "4 gram Perplexity:", qu_lm.perplexity(test)
print "5 gram Perplexity:", pe_lm.perplexity(test)
print bi_lm.generate(10, ["uh", "sp"])
fd_fac = nltk.FreqDist(fac_words)
vocab_fac = fd_fac.keys()
fd_par = nltk.FreqDist(par_words)
vocab_par = fd_par.keys()
print "Fac Vocab: ", len(vocab_fac)
print "Fac Tokens: ", len(fac_words)
print vocab_fac[:20]
print "Par Vocab: ", len(vocab_par)
print "Par Tokens: ", len(par_words)
print vocab_par[:20]
fd_par.plot(50)
def process_plaintext(dir_path):
reader = CategorizedPlaintextCorpusReader(dir_path,
r'.*\.txt', cat_pattern=r'.+_.+_(.*)\.txt')
facilitator_files = reader.fileids(categories='facilitator')
participant_files = reader.fileids(categories='participant')
print facilitator_files, participant_files
#print reader.categories()
#print len(reader.words())
#print len(reader.sents())
fac_words = [word for word in reader.words(facilitator_files)]
par_words = [word for word in reader.words(participant_files)]
fac_words = edit_tokens(fac_words)
par_words = edit_tokens(par_words)
speakers = (
[(word, 'facilitator') for word in reader.words(facilitator_files)] +
[(word, 'participant') for word in reader.words(participant_files)]
)
features = get_features(speakers)
size = int(len(features) * 0.3)
nb_train = features[size:]
nb_test = features[:size]
classifier = nltk.NaiveBayesClassifier.train(nb_train)
print "Classifier labels:", classifier.labels()
print classifier.show_most_informative_features()
print "Clasify test:", nltk.classify.accuracy(classifier, nb_test)
#print classifier.classify(get_features(["Yolo", "bag", "sp"], False))
#random.shuffle(speakers)
three_quarters = int(len(speakers) * 0.75)
train = speakers[:three_quarters]
test = speakers[three_quarters:]
est = lambda fdist, bins: nltk.probability.LaplaceProbDist(fdist)
un_lm = NgramModel(1, train, estimator=est)
bi_lm = NgramModel(2, train, estimator=est)
tr_lm = NgramModel(3, train, estimator=est)
qu_lm = NgramModel(4, train, estimator=est)
pe_lm = NgramModel(5, train, estimator=est)
print un_lm
print bi_lm
print tr_lm
print qu_lm
print pe_lm
print "1 gram Perplexity:", un_lm.perplexity(test)
print "2 gram Perplexity:", bi_lm.perplexity(test)
print "3 gram Perplexity:", tr_lm.perplexity(test)
print "4 gram Perplexity:", qu_lm.perplexity(test)
print "5 gram Perplexity:", pe_lm.perplexity(test)
print bi_lm.generate(10, ["uh", "sp"])
fd_fac = nltk.FreqDist(fac_words)
vocab_fac = fd_fac.keys()
fd_par = nltk.FreqDist(par_words)
vocab_par = fd_par.keys()
print "Fac Vocab: " , len(vocab_fac)
print "Fac Tokens: " , len(fac_words)
print vocab_fac[:20]
print "Par Vocab: " , len(vocab_par)
print "Par Tokens: " , len(par_words)
print vocab_par[:20]
fd_par.plot(50)
if __name__ == '__main__':
#set up path to data
data_folder_name = sys.argv[1]
data_path = os.path.join(os.getcwd(), '', data_folder_name)
#make article object to read in files
article = CategorizedPlaintextCorpusReader(data_path,
r'.*\.*\.txt',
cat_pattern=r'(\w+).*\.txt')
#make list of all articles with labels based on what folder the file is in
all_articles = []
for category in article.categories():
for fileid in article.fileids(category):
#lowercases words and takes out stopwords
process = list(
w.lower() for w in list(article.words(fileid))
if w.isalpha() and w not in stopwords.words('english'))
entry = [process, category]
all_articles.append(entry)
random.shuffle(all_articles)
#make bigrams for every article
word_bigrams = [(nltk.bigrams(all_articles[i][0]))
for i in range(len(all_articles))]
#create frequency distribution for all words and select top 2000 for features
all_words = nltk.FreqDist(article.words())
########## CATEGORIZED CORPUS READER ###############
from nltk.corpus import brown
print brown.categories()
print brown.tagged_sents(categories=['news'])
from nltk.corpus.reader import CategorizedPlaintextCorpusReader as CPCR
root="C:\\Users\\Matrix\\AppData\\Roaming\\nltk_data\\corpora\\cookbook\\"
#Using cat_pattern
reader=CPCR(root
,r'movie_.*\.txt'
,cat_pattern=r'movie_(\w+)\.txt')
print reader.categories()
print reader.fileids(categories=['neg'])
print reader.fileids(categories=['pos'])
#Using cat_map: a dictionary mapping a ""fileid arg"" to a ""list of category labels""
reader=CPCR(root
,r'movie_.*\.txt'
,cat_map={'movie_pos.txt':['pos'],'movie_neg.txt':['neg']})
print reader.categories()
#Using cat file: it is a file containing mapping of fileid to category i.e. cats.txt
#for more details refer brown corpus folder.
#Using Wordnet Lemmatizer
wordnet_lemmatizer = WordNetLemmatizer()
all_words = nltk.FreqDist(word for word in reader.words())
top_words = list(all_words)[:100]
print(top_words)
def word_feats(words):
return {word: True for word in words if word in top_words}
#def word_feats(words):
#return dict([(wordnet_lemmatizer.lemmatize(word), True) for word in words])
# Generate all the files based on ThreatType.
IdentityThreat = reader.fileids('IdentityThreat')
InsiderThreat = reader.fileids('InsiderThreat')
Malware = reader.fileids('Malware')
# Identify the words in the datasets as based on ThreatType.
IdentityThreatfeats = [(word_feats(reader.words(fileids=[f])),
'IdentityThreat') for f in IdentityThreat]
InsiderThreatfeats = [(word_feats(reader.words(fileids=[f])), 'InsiderThreat')
for f in InsiderThreat]
Malwarefeats = [(word_feats(reader.words(fileids=[f])), 'Malware')
for f in Malware]
#print (IdentityThreatfeats)
IDcutoff = len(IdentityThreatfeats)
ITcutoff = len(InsiderThreatfeats)
Malcutoff = len(Malwarefeats)
print(IDcutoff, ITcutoff, Malcutoff)
def fetch_news(dir):
base = 'http://newsrss.bbc.co.uk/rss/newsonline_uk_edition/{}/rss.xml'
for category in ['world', 'technology']:
rss = fp.parse(base.format(category))
for i, entry in enumerate(rss.entries):
fname = '{0}_bbc_{1}.txt'.format(i, category)
fname = os.path.join(dir, fname)
if not dl.conf.file_exists(fname):
store_txt(entry.link, fname, entry.title)
if __name__ == "__main__":
dir = os.path.join(dl.data.get_data_dir(), 'bbc_news_corpus')
if not os.path.exists(dir):
os.mkdir(dir)
fetch_news(dir)
reader = CategorizedPlaintextCorpusReader(dir,
r'.*bbc.*\.txt',
cat_pattern=r'.*bbc_(\w+)\.txt')
printer = dl.log_api.Printer(nelems=3)
printer.print('Categories', reader.categories())
printer.print('World fileids', reader.fileids(categories=['world']))
printer.print('Technology fileids',
reader.fileids(categories=['technology']))
data_folder = './data'
encoding = 'UTF8'
language = 'italian'
wordTok = RegexpTokenizer(
r'(\w+|@\w+|<3|(\:\-?\))|(\:\-?\()|(\;\-?\))|((\:|(X|x))\-?(D|d)))')
sentTok = LineTokenizer()
reader = CategorizedPlaintextCorpusReader(data_folder,
r'SENTIPOLC-.*\.txt',
cat_pattern=r'SENTIPOLC-(\w+)\.txt',
encoding=encoding,
word_tokenizer=wordTok,
sent_tokenizer=sentTok)
pos_tweets = reader.sents(reader.fileids('pos'))
neg_tweets = reader.sents(reader.fileids('neg'))
# Inspection
rndP = random.randrange(len(pos_tweets))
rndN = random.randrange(len(neg_tweets))
print 'Pos:\n', pos_tweets[rndP:rndP + 3], '\nNeg:\n', neg_tweets[rndN:rndN +
3], '\n'
# All lowercase
pos_tweets = Proc.lowerize(pos_tweets)
neg_tweets = Proc.lowerize(neg_tweets)
# Removing digits
pos_tweets = Proc.remove_digits(pos_tweets)
neg_tweets = Proc.remove_digits(neg_tweets)
import nltk, random, string
from nltk.corpus.reader import CategorizedPlaintextCorpusReader
from nltk.corpus import stopwords
reader = CategorizedPlaintextCorpusReader('./', r'.*\.txt', cat_pattern=r'(\w+)/*')
print reader.categories()
print reader.fileids()
documents = [(list(reader.words(fileid)), category)
for category in reader.categories()
for fileid in reader.fileids(category)]
random.shuffle(documents)
# Remove stopwords & punc from content
table = string.maketrans("","")
stopwords = nltk.corpus.stopwords.words('english')
filtered_words = [w for w in reader.words() if not w in stopwords]
filtered_words_nopunc = [w for w in filtered_words if not w in string.punctuation]
all_words = nltk.FreqDist(w.lower() for w in filtered_words_nopunc)
print all_words
word_features = all_words.keys()[:2000]
def document_features(document):
document_words = set(document)
features = {}
class PolarityDataReader(object):
"""
PolarityDataReader:
Reader for POS/NEG Categorized Sentiword data
uses:
nltk.corpus.reader.CategorizedPlaintextCorpusReader
usage:
dataReader = PolarityDataReader([rootLocation],[readerObject])
dataReader.getDocuments()
dataReader.setTerms([No:ofTerms])
featuresets = dataReader.getTermDocMatrix()
"""
def __init__(self, rootLocation=config.POLARITY_DATASET, reader=None):
super(PolarityDataReader, self).__init__()
if reader == None:
self.reader = Reader(rootLocation,
r'.*/.*',
cat_pattern=r'(.*)/.*')
else:
self.reader = reader
self.setStopWords()
self.documents = None
self.terms = None
def getDocuments(self):
if not self.documents:
self.documents = [(list(self.reader.words(fileid)), category)
for category in self.reader.categories()
for fileid in self.reader.fileids(category)]
return self.documents
def setStopWords(self, fileLocation=config.STOP_WORDS_FILE):
stopfile = open(fileLocation, 'r')
self.stopwords = stopfile.read().split()
def removeStopWords(self, wordList):
""" Remove common words which have no search value """
return [word for word in wordList if word not in self.stopwords]
def setTerms(self, size=2000, featureSelection='PD', removeStopWords=True):
if featureSelection == 'PD':
self.__setTermsPD__(size)
print "Feature Selection : PD :done "
elif featureSelection == 'CHI_SQUARE':
self.__setTermsCHISQUARE__(size)
print "Feature Selection : CHI_SQUARE :done "
else:
"""
geting most frequent Words
"""
all_words = [w.lower() for w in self.reader.words()]
if removeStopWords:
all_words = self.removeStopWords(all_words)
all_words = FreqDist(w for w in all_words)
self.terms = all_words.keys()[:size]
print "Feature Selection: frequent Words :done "
def documentFeatures(self, document, sentiwordnet=False):
document_words = set(document)
features = {}
if sentiwordnet:
pass
#TODO
else:
for word in self.terms:
features[word] = (word in document_words)
return features
def getTermDocMatrix(self):
return [(self.documentFeatures(document), category)
for (document, category) in self.documents]
def __setTermsPD__(self, size):
"""
score=|(posDF-negDF)|/(posDF+negDF)
"""
posWord = {}
negWord = {}
for word in self.reader.words(categories=['pos']):
inc(posWord, word.lower())
for word in self.reader.words(categories=['neg']):
inc(negWord, word.lower())
wordScores = {}
for word in self.reader.words():
try:
posScore = posWord[word]
except KeyError, e:
posScore = 0
try:
negScore = negWord[word]
except KeyError, e:
negScore = 0
totalScore = posScore + negScore
if totalScore <= 10: # min total count
wordScores[word] = 0.1
else:
wordScore[word] = abs(posScore - negScore) / totalScore
cat_pattern=r'(\w+)/*')
from textblob.classifiers import NaiveBayesClassifier
random.seed(1)
train = [
('Identity', 'IdentityThreat'),
('identity', 'IdentityThreat'),
('identities', 'IdentityThreat'),
('identity loss', 'IdentityThreat'),
('insider', 'InsiderThreat'),
('Malware', 'Malware'),
]
# Categorized corpora Reader collect the respective words based on ThreatType
ThreatTypes = [(list(reader.words(fileid)), category)
for category in reader.categories()
for fileid in reader.fileids(category)]
random.shuffle(ThreatTypes)
print(reader.categories())
new_train = ThreatTypes
print(new_train)
#Naive Bayes classifiers assume that the value of a particular feature is independent of the value of
#any other feature, given the class variable.
cl = NaiveBayesClassifier(train)
#update the classifier with training keywords from Categorized corpora
cl.update(new_train)
inputpath = nltk.data.find('corpora/abc/threatdescp.txt')
f = open(inputpath, encoding='latin2')
outputpath = nltk.data.find('corpora/abc/ResultNB.txt')
ResultFile = open(outputpath, 'w', encoding='latin2')
for line in f:
line = BeautifulSoup(line.strip()).text
#From 1491 of cookbook
#This is how we would load in the customized corpus
from nltk.corpus.reader import CategorizedPlaintextCorpusReader
#reader = CategorizedPlaintextCorpusReader('.',r'movie_.*\.txt', cat_pattern=r'movie_(\w+)\.txt')
#reader = CategorizedPlaintextCorpusReader('.',r'movie_.*\.txt', cat_map={'movie_pos.txt':['pos'],'movie_next.txt':['neg']})
reader = CategorizedPlaintextCorpusReader('./nltk_data/custom_corpora/',r'content_.*\.txt', cat_map={'content_good.txt':['good'],'content_bad.txt':['bad']})
reader.categories()
#['neg','pos']
reader.fileids(categories=['good'])
#['movie_neg.txt']
reader.fileids(categories=['bad'])
#['movie_pos.txt']
#location 3442
#extract features from the corpus
def bag_of_words(words):
return dict([(word, True) for word in words])
def bag_of_words_not_in_set(words, badwords):
return bag_of_words(set(words) - set(badwords))
from nltk.corpus import stopwords
def bag_of_non_stopwords(words, stopfile='english'):
badwords = stopwords.words(stopfile)
return bag_of_words_not_in_set(words, badwords)
from nltk.collocations import BigramCollocationFinder
from nltk.metrics import BigramAssocMeasures
{
"category": cat, "doc": doc,
"tot_words": tot_words, "avg_char": avg_char,
"sentences": sentences, "avg_word": avg_word,
"most_common": common[0][0], "most_common_freq": common[0][1]
}
)
def clean_string(text):
clean_text = text.lower()
clean_text = re.sub('[^0-9a-zA-Z //]+', '', clean_text)
return clean_text.strip()
#create document properties
corpus = CategorizedPlaintextCorpusReader(
'C:/Users/gavin_000/Python/texts',
r'.*\.txt',
cat_pattern=r'(\w+)/*'
)
stop = stopwords.words('english')
results = pd.DataFrame()
for category in corpus.categories():
for document in corpus.fileids(category):
doc_properties = create_document_properties(category, document)
results = results.append(doc_properties, ignore_index=True)
print results
from nltk.stem import SnowballStemmer
from processor import Processor as Proc
data_folder = './data'
encoding = 'UTF8'
language = 'italian'
wordTok = RegexpTokenizer(r'(\w+|@\w+|<3|(\:\-?\))|(\:\-?\()|(\;\-?\))|((\:|(X|x))\-?(D|d)))')
sentTok = LineTokenizer()
reader = CategorizedPlaintextCorpusReader(data_folder, r'SENTIPOLC-.*\.txt',
cat_pattern=r'SENTIPOLC-(\w+)\.txt',
encoding=encoding,
word_tokenizer=wordTok,
sent_tokenizer=sentTok)
pos_tweets = reader.sents(reader.fileids('pos'))
neg_tweets = reader.sents(reader.fileids('neg'))
# Inspection
rndP = random.randrange(len(pos_tweets))
rndN = random.randrange(len(neg_tweets))
print 'Pos:\n', pos_tweets[rndP:rndP+3], '\nNeg:\n', neg_tweets[rndN:rndN+3], '\n'
# All lowercase
pos_tweets = Proc.lowerize(pos_tweets)
neg_tweets = Proc.lowerize(neg_tweets)
# Removing digits
pos_tweets = Proc.remove_digits(pos_tweets)
neg_tweets = Proc.remove_digits(neg_tweets)
from nltk.corpus.reader import CategorizedPlaintextCorpusReader
from nltk.tokenize.casual import TweetTokenizer
from normalization import normalizeTwitterWordsWithExtraFeatures, normalizeTwitterWordsWithNegationHandle
import pickle, nltk
tweetTokenizer = TweetTokenizer(reduce_len=True, preserve_case=True, strip_handles=False)
corpus = CategorizedPlaintextCorpusReader('corpus/2-step/polar', r'(\w+)-tweet[0-9]+\.txt', cat_pattern=r'(\w+)-tweet[0-9]+\.txt', word_tokenizer=tweetTokenizer)
normalizationFunction = normalizeTwitterWordsWithNegationHandle
wordsTaggedToCategory = []
i = 1
for category in corpus.categories():
for fileid in corpus.fileids(category):
words = corpus.words(fileids=[fileid])
normalizedWords = normalizationFunction(words)
extraNormalizedWords = normalizeTwitterWordsWithExtraFeatures(words)
wordsTagged = nltk.pos_tag(normalizedWords)
wordsTaggedToCategory += [(wordsTagged, category)]
print(i)
i += 1
with open("wordsTaggedToCategory-polar", 'wb') as fileout:
pickle.dump(wordsTaggedToCategory, fileout)
class PolarityDataReader(object):
"""
PolarityDataReader:
Reader for POS/NEG Categorized Sentiword data
uses:
nltk.corpus.reader.CategorizedPlaintextCorpusReader
usage:
dataReader = PolarityDataReader([rootLocation],[readerObject])
dataReader.getDocuments()
dataReader.setTerms([No:ofTerms])
featuresets = dataReader.getTermDocMatrix()
"""
def __init__(self, rootLocation = config.POLARITY_DATASET,reader=None):
super(PolarityDataReader, self).__init__()
if reader == None:
self.reader = Reader(rootLocation,r'.*/.*', cat_pattern=r'(.*)/.*')
else:
self.reader = reader
self.setStopWords()
self.documents = None;
self.terms = None;
def getDocuments(self):
if not self.documents:
self.documents = [(list(self.reader.words(fileid)), category)
for category in self.reader.categories()
for fileid in self.reader.fileids(category)]
return self.documents;
def setStopWords(self,fileLocation = config.STOP_WORDS_FILE):
stopfile = open(fileLocation, 'r')
self.stopwords = stopfile.read().split()
def removeStopWords(self,wordList):
""" Remove common words which have no search value """
return [word for word in wordList if word not in self.stopwords]
def setTerms(self,size=2000,featureSelection='PD',removeStopWords=True):
if featureSelection == 'PD':
self.__setTermsPD__(size)
print "Feature Selection : PD :done "
elif featureSelection == 'CHI_SQUARE':
self.__setTermsCHISQUARE__(size)
print "Feature Selection : CHI_SQUARE :done "
elif featureSelection == 'SWNSS':
self.__setTermsSWNSS__(size)
print "Feature Selection : SWNPD :done "
else:
"""
geting most frequent Words
"""
all_words = [w.lower() for w in self.reader.words()];
if removeStopWords:
all_words = self.removeStopWords(all_words);
all_words = FreqDist(w for w in all_words)
self.terms = all_words.keys()[:size]
print "Feature Selection: frequent Words :done "
def documentFeatures(self,document,sentiwordnet=False):
document_words = set(document)
features = {}
if sentiwordnet:
pass
#TODO
else :
for word in self.terms:
features[word] = (word in document_words)
return features
def getTermDocMatrix(self):
return [(self.documentFeatures(document), category)
for (document,category) in self.documents]
def __setTermsPD__(self,size):
"""
score=|(posDF-negDF)|/(posDF+negDF)
"""
posWord = {};
negWord = {};
for word in self.reader.words(categories = ['pos']):
inc(posWord,word.lower());
for word in self.reader.words(categories = ['neg']):
inc(negWord,word.lower());
wordScores = {}
for word in self.reader.words():
try:
posScore = posWord[word]
except KeyError, e:
posScore = 0
try:
negScore = negWord[word]
except KeyError, e:
negScore = 0
totalScore = posScore + negScore
if totalScore <= 10 : # min total count
wordScores[word] = 0.1
else :
wordScores[word] = abs(posScore-negScore)/totalScore
#removeStopWords does no affect accurcy
termScore = sorted(wordScores.items(),key=lambda(w,s):s,reverse=True)[:size]
self.terms = [w for (w,s) in termScore];
print(generate_model(cfd, word))
def generate_model(cfdist, word, num=15):
for i in range(num):
print(word, end=' ')
word = cfdist[word].max()
# 1. Construir Corpus texto categorizado
locPT = 'ch02/ES'
corpusPT = CategorizedPlaintextCorpusReader(locPT,
'.*\.txt',
cat_file="cat.txt")
print(corpusPT.fileids())
print(corpusPT.categories())
print(corpusPT.words(categories='ciencia'))
#print(corpusPT.raw())
vocab = set(w.lower() for w in corpusPT.words())
print('Tamanho Vocabulario:', len(vocab))
corpusCom = corpusPT.raw()
corpusComList = corpusCom.split()
print('Tamanho Total de palabras:', len(corpusComList))
# 2. Calcular medidas estadisticas simples
'''
Medidas: Tamanho médio das palavras, Tamanho médio das sentenças e Número de vezes que cada
item do vocabulário aparece no texto em média (escore de diversidade léxica)
'''
file=open('model_file.txt', 'w')
file.write("Feature words\tCategory\tProb(given_word|category)\n")
for word, cat in Feature_Set.keys():
file.write(str(word))
file.write("\t\t")
file.write((str(cat)))
file.write("\t\t")
file.write(str(Feature_Set[word,cat]))
file.write("\n")
file.close()
Classification_Accuracy=0
for file in Testing_Corpus.fileids():
pos_prob=1
neg_prob=1
real_category=Testing_Corpus.categories([file])
for word, cat in Feature_Set:
if word in Testing_Corpus.words([file]):
if cat=="pos":
pos_prob=Feature_Set[word, cat]*float(pos_prob)*10000
else:
neg_prob=Feature_Set[word, cat]*float(neg_prob)*10000
if float(pos_prob)>=float(neg_prob):
derived_category="['pos']"
else:
derived_category="['neg']"
import nltk, random, string, os
from nltk.collocations import *
from nltk.corpus.reader import CategorizedPlaintextCorpusReader
from nltk.corpus import stopwords
bigram_measures = nltk.collocations.BigramAssocMeasures()
#print reader.categories()
for name in os.listdir("."):
if os.path.isdir(name):
reader = CategorizedPlaintextCorpusReader(name, r'.*\.txt', cat_pattern=r'(\w+)/*')
# reader = CategorizedPlaintextCorpusReader(name, r'./raw_reviews/\.txt', cat_pattern=r'(\w+)/*')
print reader.fileids()
table = string.maketrans("","")
stopwords = nltk.corpus.stopwords.words('english')
filtered_words = [w for w in reader.words() if not w in stopwords]
filtered_words_nopunc = [w for w in filtered_words if not w in string.punctuation]
#all_words = nltk.FreqDist(w.lower() for w in filtered_words_nopunc)
finder = BigramCollocationFinder.from_words(filtered_words_nopunc)
#scored = finder.score_ngrams(bigram_measures.raw_freq)
#a = sorted(bigram for bigram, score in scored)
finder.apply_freq_filter(3)
a = finder.nbest(bigram_measures.pmi, 5)
#b = finder.score_ngrams(bigram_measures.pmi)
print a
data = get_data()
print(len(data))
evrth, maindict = tags_assignment(data)
# Save new final dictionary as well as the mapping for categories-numbers
listingssss = json.dumps(evrth)
with open("FinalCleanJuly1.json", "w") as f:
f.write(listingssss)
dictionaries = json.dumps(maindict)
with open("CorpusCatMapJuly1.json", "w") as f:
f.write(dictionaries)
#### This is IMPORTANT - CHOOSE ! ##### default is key2
#### Choose the label you want to have for naming!
### two options:
### 1) key1 with format: docID + _(i) where i numerated number of category e.g. -doc-_cr14021.txt
### 2) key2 with format country name + year + _(i) e.g. Albania2015_1.txt
### if you want to change--> line 90: "key2: taglist" to key1
### line 121: filename=evrth[i]['key2'] to key1
create_corpus(evrth)
#### Check if working
reader = CategorizedPlaintextCorpusReader('corpusCategory/',
r'\w+\d+_.*\.txt',
cat_map=maindict)
print(reader.categories()) #print all categories in a list
print(reader.fileids(categories=['Fiscal'])) #check docIDs in fiscal category
#Good reference - https://www.packtpub.com/books/content/python-text-processing-nltk-20-creating-custom-corpora
#They have options for creating chunked (by words, sentences, paragraphs and even customized paragraphs) corpora, tagged corpora etc
import nltk.classify.util, nltk.metrics
from nltk.metrics import *
from nltk.classify import NaiveBayesClassifier
from nltk.corpus import stopwords
from nltk.collocations import BigramCollocationFinder
from nltk.metrics import BigramAssocMeasures
from nltk.probability import FreqDist, ConditionalFreqDist
#Creating Corpus using WordListCorpusReader
from nltk.corpus.reader import CategorizedPlaintextCorpusReader
imdb_reviews = CategorizedPlaintextCorpusReader(
'D://USF//Independent Research Project//Dataset//Movie Review Dataset Pos Neg//aclImdb//train//negpos',
r'.*\.txt',
cat_pattern=r'(\w+)/*')
len(imdb_reviews.fileids())
def evaluate_classifier(featx):
negids = imdb_reviews.fileids('neg')
posids = imdb_reviews.fileids('pos')
negfeats = [(featx(imdb_reviews.words(fileids=[f])), 'neg')
for f in negids]
posfeats = [(featx(imdb_reviews.words(fileids=[f])), 'pos')
for f in posids]
negcutoff = len(negfeats) * 3 / 4
poscutoff = len(posfeats) * 3 / 4
trainfeats = negfeats[:negcutoff] + posfeats[:poscutoff]
count_pos += 1
elif row['rating_overall'] in ("1", "2", "3", "4", "5") and count_neg < 15000:
output = open('airline_review\\neg\\' + \
filename + '.txt', 'w')
output.write(row['reviewcontent'])
output.close()
count_neg += 1
os.chdir("E:/Documents/GSU/Python Development/Unstructured Data/Team Project/machine_learning_text_analysis")
reader = CategorizedPlaintextCorpusReader('./airline_review', r'.*\.txt',
cat_pattern = r'(\w+)/*') # file name format
# Positive reviews file ids
pos_ids = reader.fileids('pos')
# Negative reviews file ids
neg_ids = reader.fileids('neg')
'''Generating word feature list'''
def word_feats(words):
return dict([(word, True) for word in words])
'''Building positive and negative feature lists. Each
item is the positive/negative word features for a review file'''
pos_feat = [(word_feats(reader.words(fileids = f)), 'pos')
for f in pos_ids]
neg_feat = [(word_feats(reader.words(fileids = f)), 'neg')
for f in neg_ids]
