def question3():
tagger = CRFTagger(feature_func=feature_func)
tagger.train(train_sentences, 'model.crf.tagger')
print(tagger.evaluate(test_sentences))
return
def run_crf(trainfile, testfile, model_file=None):
maxlen = 100
sents_train, tags_train, unique_words_train, unique_tags_train = \
P.retrieve_sentences_tags(trainfile, maxlen=maxlen)
sents_test, tags_test, unique_word_test, unique_tags_test = \
P.retrieve_sentences_tags(testfile, maxlen=maxlen, allowedtags=unique_tags_train)
train_data = []
for n, st in enumerate(sents_train):
s = []
for m, _ in enumerate(st):
s.append((unicode(sents_train[n][m], "utf-8")
, unicode(tags_train[n][m], "utf-8")))
train_data.append(s)
crf = CRFTagger()
if model_file is None:
crf.train(train_data, model_file='data/crf.mdl')
else:
crf.set_model_file(model_file)
test_data = []
for n, st in enumerate(sents_test):
s = []
for m, _ in enumerate(st):
s.append((unicode(sents_test[n][m], "utf-8")
, unicode(tags_test[n][m], "utf-8")))
test_data.append(s)
print(crf.evaluate(test_data))
def cltk_pos_cv(full_training_set, local_dir_rel, counter):
local_dir = os.path.expanduser(local_dir_rel)
stdout_old = sys.stdout
sys.stdout = open(os.path.join(local_dir, 'test_%d.out'%counter), 'w')
# read POS corpora
print("local_dir", local_dir)
train_reader = TaggedCorpusReader(local_dir, 'train_%d.pos'%counter)
train_sents = train_reader.tagged_sents()
test_reader = TaggedCorpusReader(local_dir, 'test_%d.pos'%counter)
test_sents = test_reader.tagged_sents()
print('Loop #' + str(counter))
sys.stdout.flush()
# make crf tagger
crf_tagger = CRFTagger()
crf_tagger.train(train_sents, 'model.crf.tagger')
#crf_tagger = UnigramTagger(train_sents)
# evaluate crf tagger
crf_accuracy = None
crf_accuracy = crf_tagger.evaluate(test_sents)
print('crf:', crf_accuracy)
sys.stdout = stdout_old
def cltk_pos_cv(full_training_set, local_dir_rel, counter):
local_dir = os.path.expanduser(local_dir_rel)
stdout_old = sys.stdout
sys.stdout = open(os.path.join(local_dir, 'test_%d.out' % counter), 'w')
# read POS corpora
print("local_dir", local_dir)
train_reader = TaggedCorpusReader(local_dir, 'train_%d.pos' % counter)
train_sents = train_reader.tagged_sents()
test_reader = TaggedCorpusReader(local_dir, 'test_%d.pos' % counter)
test_sents = test_reader.tagged_sents()
print('Loop #' + str(counter))
sys.stdout.flush()
# make crf tagger
crf_tagger = CRFTagger()
crf_tagger.train(train_sents, 'model.crf.tagger')
#crf_tagger = UnigramTagger(train_sents)
# evaluate crf tagger
crf_accuracy = None
crf_accuracy = crf_tagger.evaluate(test_sents)
print('crf:', crf_accuracy)
sys.stdout = stdout_old
def question3():
tagger = CRFTagger(feature_func=feature_func)
tagger.train(train_sentences, 'model_windows_size_1.crf.tagger')
#tagger = CRFTagger(feature_func=feature_func)
#tagger.set_model_file('model_windows_size_1.crf.tagger')
print(tagger.evaluate(test_sentences))
return
def main():
import pickle
from nltk.tag import CRFTagger
infolist = pickle.load(open('infolist.pickle', 'rb'))
ct = CRFTagger()
train_data = [[(x, z)
for [x, y, z] in infolist[:round(0.9 * len(infolist))]]]
ct.train(train_data, 'model.crf.tagger')
ners = ct.tag_sents(
[[x for [x, y, z] in infolist[round(0.9 * len(infolist)):]]])
print(ners)
gold_sentences = [[(x, z)
for [x, y, z] in infolist[round(0.9 * len(infolist)):]]]
ct.evaluate(gold_sentences)
print(ct.evaluate(gold_sentences))
def crf_tag():
news_text = brown.tagged_sents(categories='news')
train_sents = news_text[:3230]
test_sents = news_text[3230:4600]
ct = CRFTagger()
tagger = ct.train(train_sents, 'model.crf.tagger')
test = ct.evaluate(test_sents)
print test
sent3 = "Narendra Modi won Lok Sabha election with massive majority after long years".decode(
'utf-8')
sent_w = sent3.lower().split()
print sent_w
tag = ct.tag(sent_w)
print "The Tag Is:", tag
def ontweetdata():
tweetinfolist = pickle.load(open('tweetinfolist.pickle',
'rb')) #data from tweets
counter = 0
for item in tweetinfolist:
if item[1] == "O":
counter = counter + 1
print("BASELINE: ", (counter) / len(tweetinfolist))
ct = CRFTagger()
train_data = [[
(x.lower(), y.lower())
for [x, y] in tweetinfolist[round(0.9 * len(tweetinfolist)):]
]]
ct.set_model_file('model.crf.tagger')
ct.train(train_data, 'model.crf.tagger')
gold_sentences = [[
(x.lower(), y.lower())
for [x, y] in tweetinfolist[:round(0.9 * len(tweetinfolist))]
]]
print(ct.evaluate(gold_sentences))
def oninfolist():
"""NU DOEN: KIJK NAAR FORMAT VAN GEGEVEN INFORMATIE OP INTERNET IN VOORBEELD, CHECK ALLE LIJSTEN DIE IK GEMAAKT HEB OF ZE OVEREENKOMEN MET DE VORM"""
#SEE: http://www.nltk.org/_modules/nltk/tag/crf.html
infolist = pickle.load(open('sentencelist.pickle', 'rb'))
limit = round(len(infolist) * 0.4)
train_data = infolist[0:limit]
#print("train_data = ", train_data[0:10])
ct = CRFTagger()
#print(infolist[0:10])
realsentences = []
realsentence = ""
"""
for sentence in infolist[limit:]:
for (word,nertag) in sentence:
realsentence = realsentence +" "+ word
realsentences.append(realsentence)
realsentence = ""
pickle.dump(realsentences,open("realsentences.pickle","wb"))
print("pickle-bestand gemaakt")
"""
realsentences = pickle.load(open("realsentences.pickle", "rb"))
print("REALSENTENCES:", realsentences[0:10])
splitsentences = [] #[['dog','is','good'],['cat','eat','meat']]
for r in realsentences:
splitsentence = r.split()
splitsentences.append(splitsentence)
#print("train_data:", infolist[0:10])
#print("sentences for tag_sents:", splitsentences[0:10])
ct.tag_sents(splitsentences[limit:])
gold_sentences = infolist[limit:]
print("GOLD SENTENCES:", infolist[10:20])
print(ct.evaluate(gold_sentences))
from nltk.tag import CRFTagger
ct = CRFTagger()
train_data = [[('Universiteit', 'Noun'), ('is', 'Verb'), ('een', 'Det'),
('goed', 'Adj'), ('goede', 'Adj'), ('plek', 'Noun'),
('hond', 'Noun'), ('eet', 'Verb'), ('vlees', 'Noun')]]
ct.train(train_data, 'model.crf.tagger')
ct.tag_sents([['hond', 'is', 'goed'], ['kat', 'eet', 'vlees']])
gold_sentences = [[('hond', 'Noun'), ('is', 'Verb'), ('goed', 'Adj')],
[('kat', 'Noun'), ('eet', 'Verb'), ('vlees', 'Noun')]]
ct.evaluate(gold_sentences)
ct = CRFTagger()
ct.set_model_file('model.crf.tagger')
print(ct.evaluate(gold_sentences))
class DataAdapter(object):
def __init__(self, data=[]):
self.tagger = CRFTagger()
self.tagger.set_model_file('model.crf.tagger')
if data.count(True) > 0:
self.data_tagging, self.data_testing = self.for_tagging_testing(
data)
# print('TAGGING', self.data_tagging)
# print('TESTING', self.data_testing)
def tokenize_tag(self, text):
text = text.replace('\r', ' | ').replace('\n', ' | ')
tokens = word_tokenize(text, preserve_line=True)
labels = []
for label in self.tag(tokens):
labels.append(label[1])
return tokens, labels
def for_tagging_testing(self, data):
# self.data = data
array_tagging = []
array_testing = []
for d in data:
all_tags = []
all_test = []
for index, t in enumerate(d['text']):
one_tag = [t, d['label'][index]]
all_test.append(one_tag)
all_tags.append(t)
array_tagging.append(all_tags)
array_testing.append(all_test)
# print(all_tags)
return array_tagging, array_testing
def for_testing(self, data):
# self.data = data
array = []
# print('TEST', data.count())
for d in data:
all_tags = []
for index, t in enumerate(d['text']):
# one_tag = [t, (d['label'][index] if is_ascii(d['label'][index]) else 'O')]
one_tag = [t, d['label'][index]]
all_tags.append(one_tag)
array.append(all_tags)
# print(all_tags)
return array
def for_tagging(self, data):
# self.data = data
array = []
for d in data:
all_tags = []
for t in d['text']:
all_tags.append(t)
array.append(all_tags)
# print(all_tags)
return array
def tag_sents(self):
if self.data_tagging is not None:
return self.tagger.tag_sents(self.data_tagging)
else:
return 'NoData'
def tag(self, data):
return self.tagger.tag(data)
def evaluate(self):
if self.data_testing is not None:
return self.tagger.evaluate(self.data_testing)
else:
return 'NoData'
def train(self, data):
data = self.for_testing(data)
self.tagger.train(data, 'model.crf.tagger')
print('ACCURACY:', self.tagger.evaluate(data))
from nltk.corpus import treebank
from nltk.tag import tnt, CRFTagger
# split training data from test data
train_data = treebank.tagged_sents()[:3000]
test_data = treebank.tagged_sents()[3000:]
# train a trigram N tagger (TnT)
tnt_pos_tagger = tnt.TnT()
tnt_pos_tagger.train(train_data)
print tnt_pos_tagger.evaluate(test_data)
# train a CRF tagger
crf_tagger = CRFTagger()
crf_tagger.train(train_data,
'~/Documents/NLP/NLP/crf_model.txt')
print crf_tagger.evaluate(test_data)
# -*- coding: utf-8 -*-
from nltk.tag import CRFTagger
import re
import codecs
def get_data():
with codecs.open('th_pud-ud-test.conllu', 'r',encoding='utf8') as f:
lines = f.read()
return re.split("#(.*)+[\r\n]#(.*)+[\r\n]",lines)
data=get_data()
i=0
data_all=[]
while i<len(data):
data_list=[]
for r in re.split('\n',data[i]):
t=[x for x in re.split('\t',r) if x!='']
if t!=[]:
data_list.append((t[1],t[3]))
data_all.append(data_list)
i+=1
train_data=[x for x in data_all if x!=[]]
ct = CRFTagger()
ct.set_model_file('model.crf.tagger')
print(ct.evaluate(train_data))
# In[ ]:
tagger = BigramTagger(train_reducido[:1000])
tagger.evaluate(test_reducido[:1000])
entrenar_bill(tagger,"BigramTagger")
# In[ ]:
ct = CRFTagger()
ct.train(train_reducido[:1000],'model.crf.tagger')
evaluacion = ct.evaluate(test_reducido[:1000])
xlabels.append("CRF Tagger")
accuracys.append(evaluacion)
# In[ ]:
tagger = PerceptronTagger(load=False)
tagger.train(train_reducido[:1000])
evaluacion = tagger.evaluate(test_reducido[:1000])
xlabels.append("Perceptron Tagger")
accuracys.append(evaluacion)
# In[ ]:
language = page.find('language').text.decode('utf8')
pos = page.find('pos_tags').text.decode('utf8')
splitText = text.split(" ")[1:-1]
posText = pos.split(" ")[1:-1]
for i in range(len(splitText)):
l.append((splitText[i], posText[i]))
data.append(l)
count = count + 1
shuffle(data)
print len(data)
# Divide data into train and test sets
eightyPercent = count * 0.9
training_set = data[0:int(eightyPercent)]
test_set = data[int(eightyPercent):]
print training_set
# Train
ct = CRFTagger()
train_data = training_set
ct.train(train_data, 'model.crf.tagger')
# Accuracy
gold_sentences = test_set
print ct.evaluate(gold_sentences)
print "Give a sentence..."
# Test
test_sent = raw_input()
test_sent = test_sent.encode('utf-8').decode('utf-8').split(' ')
# print test_sent
print ct.tag_sents([test_sent])
print "\nReading training corpus...."
ListOfSentences_Training = corpusRead(Training_Data)
print "Reading test corpus...."
ListOfSentences_Test = corpusRead(Test_Data)
#CRF Training
ct = CRFTagger()
print "CRF Training starts..."
ct.train(ListOfSentences_Training,'model.crf.tagger')
print "CRF Training is done."
print "Testing starts"
print "Accuracy of CRF is = ",ct.evaluate(ListOfSentences_Test) * 100
#Tagging by CRF Tagger
ch = 'y'
while (ch != 'n'):
text = raw_input("Enter the text to be tagged : \n")
text = converter(text)
print ct.tag_sents(text)
print "\nDo you want to continue ?"
ch = raw_input()
#HMM Training
print "HMM Training using HiddenMarkovModelTrainer() starts.."
from nltk.tag import CRFTagger from nltk.corpus import brown tagged_sents = brown.tagged_sents() train = tagged_sents[:50000] test = tagged_sents[50000:] crf = CRFTagger() crf.train(train, 'crf_tagger.model') a = crf.evaluate(test) print a
def cltk_pos_cv(full_training_set, local_dir_rel):
print("full_training_set", full_training_set)
crf_accuracies = []
with open(full_training_set) as f:
training_set_string = f.read()
pos_set = training_set_string.split('\n\n') # mk into a list
sentence_count = len(pos_set) # 3473
tenth = math.ceil(int(sentence_count) / int(10))
random.seed(0)
random.shuffle(pos_set)
def chunks(l, n):
"""Yield successive n-sized chunks from l.
http://stackoverflow.com/a/312464
"""
for i in range(0, len(l), n):
yield l[i:i+n]
# a list of 10 lists
ten_parts = list(chunks(pos_set, tenth)) # a list of 10 lists with ~347 sentences each
#for counter in list(range(10)):
for counter, part in list(enumerate(ten_parts)):
# map test list to part of given loop
test_set = ten_parts[counter] # or: test_set = part
# filter out this loop's test index
training_set_lists = [x for x in ten_parts if x is not ten_parts[counter]]
# next concatenate the list together into 1 file ( http://stackoverflow.com/a/952952 )
training_set = [item for sublist in training_set_lists for item in sublist]
# save shuffled tests to file (as NLTK trainers expect)
#local_dir_rel = '~/cltk_data/user_data'
local_dir = os.path.expanduser(local_dir_rel)
if not os.path.isdir(local_dir):
os.makedirs(local_dir)
test_path = os.path.join(local_dir, 'test.pos')
with open(test_path, 'w') as f:
f.write('\n\n'.join(test_set))
train_path = os.path.join(local_dir, 'train.pos')
with open(train_path, 'w') as f:
f.write('\n\n'.join(training_set))
# read POS corpora
print("local_dir", local_dir)
train_reader = TaggedCorpusReader(local_dir, 'train.pos')
train_sents = train_reader.tagged_sents()
test_reader = TaggedCorpusReader(local_dir, 'test.pos')
test_sents = test_reader.tagged_sents()
print('Loop #' + str(counter))
# make crf tagger
crf_tagger = CRFTagger()
crf_tagger.train(train_sents, 'model.crf.tagger')
# evaluate crf tagger
crf_accuracy = None
crf_accuracy = crf_tagger.evaluate(test_sents)
crf_accuracies.append(crf_accuracy)
print('crf:', crf_accuracy)
#if counter> 0: break
final_accuracies_list = []
mean_accuracy_crf = mean(crf_accuracies)
standard_deviation_crf = stdev(crf_accuracies)
uni = {'crf': {'mean': mean_accuracy_crf, 'sd': standard_deviation_crf}}
final_accuracies_list.append(uni)
final_dict = {}
for x in final_accuracies_list:
final_dict.update(x)
return final_dict
line=f.readline()
f.close()
res = ct.tag_sents(test_sentences)
tagged_result = []
tagged_actual = []
for i in range(len(res)):
for j in range(len(res[i])):
tagged_result.append(res[i][j][1])
tagged_actual.append(test_actual[i][j][1])
print res[0]
print test_actual[0]
#print tagged_result[0]
#print tagged_actual[0]
gold_sentences=test_actual
accuracy = ct.evaluate(gold_sentences)
print "accuracy:"+str(accuracy)
#recall = nltk.metrics.scores.recall(test_actual,res)
precision = precision_score(tagged_actual,tagged_result)
print "precision:"+str(precision)
recall = recall_score(tagged_actual,tagged_result)
print "recall:"+str(recall)
f1 = f1_score(tagged_actual,tagged_result)
print "F1_score:"+str(f1)
def onsentencelist():
ct = CRFTagger()
"""sentencelist contains nertaged sentences"""
sentencelist = pickle.load(open('sentencelist.pickle','rb'))
"""training size as percentage"""
trainingsize = 0.9
""" calculate where to split data """
limit = round(trainingsize*len(sentencelist))
"""wordsentencelist contains the same sentences not ner-tagged"""
wordsentencelist = pickle.load(open("wordsentencelist.pickle","rb"))
"""train the data / choose one of the 2 blocks """
#train_data = sentencelist[:limit]
#ct.train(train_data,'model.crf.tagger')
ct.set_model_file('tweetmodel.crf.tagger')
"""Test data and evaluate"""
test_data = wordsentencelist[limit:]
ct.tag_sents(test_data) # tagging sentences
gold_sentences = sentencelist[limit:]
print("\nAccuracy:", ct.evaluate(gold_sentences))
""" TURN TRAINED TAGGED LIST AND TEST LIST INTO ONE LIST CONTAINING
ONLY THE TRUE AND PREDTAGS"""
pred_nerlist = []
for sentence in wordsentencelist[:limit]:
for (word,nertag) in ct.tag(sentence):
#pred_nerlist.append((word,nertag))
pred_nerlist.append(nertag.lower())
true_nerlist = []
#ct_true = gold_sentences
for sentence in sentencelist[:limit]:
for (word,nertag) in sentence:
#true_nerlist.append((word,nertag))
true_nerlist.append(nertag.lower())
""" Print baseline """
#print("\nBaseline = 0.9048987094135446 (everything tagged O)")
""""Print F-score and confusion matrix """
#print(len(pred_nerlist))
#print(len(true_nerlist))
""""Print F-score and confusion matrix """
print("\nF-score (micro):", f1_score(true_nerlist, pred_nerlist, average='micro') )
print("\nF-score (macro):", f1_score(true_nerlist, pred_nerlist, average='macro') )
print("\nF-score (weigthed):", f1_score(true_nerlist, pred_nerlist, average='weighted') )
print("\nF-score (None):", f1_score(true_nerlist, pred_nerlist, average=None, labels=["o","b-per","i-per","b-loc","i-loc","b-org","i-org","b-misc","i-misc"]))
print("\nConfusion matrix:\n")
for item in ["O","B-per","I-per","B-loc","I-loc","B-org","I-org","B-misc","I-misc"]: print(" ",item,end="")
print("\n",confusion_matrix(true_nerlist, pred_nerlist,labels = ["o","b-per","i-per","b-loc","i-loc","b-org","i-org","b-misc","i-misc"]))
train_data.append(lists_e)
print('Training the CRF++ model started')
ct.train(train_data,
'model.crf.tagger') # training the crf model using the training set
print('Training the CRF++ model completed')
test_number_lines = 0
print('Reading Unseen Data')
for lines in test_set:
test_number_lines = test_number_lines + 1
print('Processing file', test_number_lines)
xx = (lines.split())
test_data.append(xx)
tagged_sent = ct.tag_sents(test_data) # tagging the the unseen data
for tag_set in tagged_sent:
tagged_text.write(str(tag_set))
tagged_text.write('\n')
tagged_text.close()
print('Tagging the Unseen data Completed')
for vz in gold_line:
vz = "[" + vz + "]"
gold_list = ast.literal_eval(vz)
gold_data.append(gold_list)
print('The Total Accuracy of the System is:' + str(ct.evaluate(gold_data)))