def test_stemmer_lower(self):
p = Preprocessor(lower=True, stem=True)
stemmed = p.stemmer('Running')
if my_nltk:
self.assertEqual(stemmed, 'run')
else:
self.assertTrue(False, 'NLTK is not installed')
def __validateResponse(self, response, queryTerms):
from bs4 import BeautifulSoup
if response.status_code == 200:
soup = BeautifulSoup(response.text)
from irlib.preprocessor import Preprocessor
from irlib.matrix import Matrix
from irlib.metrics import Metrics
prep = Preprocessor()
mx = Matrix()
metric = Metrics()
terms = prep.ngram_tokenizer(text=soup.get_text())
mx.add_doc(doc_id=response.url,
doc_terms=terms,
frequency=True,
do_padding=True)
cnt = Counter()
for word in terms:
cnt[word] += 1
table = Texttable()
table.set_cols_align(["l", "l"])
table.set_cols_valign(["m", "m"])
table.set_cols_width([40, 55])
rows = [["Term", "Frequency"]]
for word in sorted(cnt, key=cnt.get, reverse=True):
if word.lower() in queryTerms.lower().split():
rows.append([word, cnt[word]])
table.add_rows(rows)
print table.draw() + "\n"
else:
print "[-] Response for %s is %s " % (response.url,
response.status_code)
def __validateResponse(self, response, queryTerms):
from bs4 import BeautifulSoup
if response.status_code == 200:
soup = BeautifulSoup(response.text)
from irlib.preprocessor import Preprocessor
from irlib.matrix import Matrix
from irlib.metrics import Metrics
prep = Preprocessor()
mx = Matrix()
metric = Metrics()
terms = prep.ngram_tokenizer(text=soup.get_text())
mx.add_doc( doc_id=response.url,doc_terms=terms,frequency=True,do_padding=True)
cnt = Counter()
for word in terms:
cnt[word] += 1
table = Texttable()
table.set_cols_align(["l", "l"])
table.set_cols_valign(["m", "m"])
table.set_cols_width([40,55])
rows = [["Term", "Frequency"]]
for word in sorted(cnt, key=cnt.get, reverse=True):
if word.lower() in queryTerms.lower().split():
rows.append([word, cnt[word]])
table.add_rows(rows)
print table.draw() + "\n"
else:
print "[-] Response for %s is %s " %(response.url, response.status_code)
def validateResponse(self, response, queryTerms):
from bs4 import BeautifulSoup
if response.status_code == 200:
soup = BeautifulSoup(response.text)
from irlib.preprocessor import Preprocessor
from irlib.matrix import Matrix
from irlib.metrics import Metrics
prep = Preprocessor()
mx = Matrix()
metric = Metrics()
terms = prep.ngram_tokenizer(text=soup.get_text())
mx.add_doc( doc_id=response.url,doc_terms=terms,frequency=True,do_padding=True)
'''for doc in mx.docs:
distance = metric.euclid_vectors(doc['terms'], q_vector)
print distance
'''
cnt = Counter()
for word in terms:
cnt[word] += 1
tableTerms = PrettyTable(["Term", "Frequency"])
for word in sorted(cnt, key=cnt.get, reverse=True):
if word.encode('ascii').lower() in queryTerms.encode('ascii').lower().split():
tableTerms.add_row([word, cnt[word]])
print tableTerms
else:
print "[-] Response for %s is %s " %(response.url, response.status_code)
def test_stemmer_lower(self):
p = Preprocessor(lower=True, stem=True)
stemmed = p.stemmer('Running')
if my_nltk:
self.assertEqual(stemmed,'run')
else:
self.assertTrue(False,'NLTK is not installed')
def validateResponse(self, response, queryTerms):
from bs4 import BeautifulSoup
if response.status_code == 200:
soup = BeautifulSoup(response.text)
from irlib.preprocessor import Preprocessor
from irlib.matrix import Matrix
from irlib.metrics import Metrics
prep = Preprocessor()
mx = Matrix()
metric = Metrics()
terms = prep.ngram_tokenizer(text=soup.get_text())
mx.add_doc(doc_id=response.url,
doc_terms=terms,
frequency=True,
do_padding=True)
'''for doc in mx.docs:
distance = metric.euclid_vectors(doc['terms'], q_vector)
print distance
'''
cnt = Counter()
for word in terms:
cnt[word] += 1
tableTerms = PrettyTable(["Term", "Frequency"])
for word in sorted(cnt, key=cnt.get, reverse=True):
if word.encode('ascii').lower() in queryTerms.encode(
'ascii').lower().split():
tableTerms.add_row([word, cnt[word]])
print tableTerms
else:
print "[-] Response for %s is %s " % (response.url,
response.status_code)
def test_is_link(self):
is_it = Preprocessor.is_link('hello world')
self.assertEqual(is_it, False)
is_it = Preprocessor.is_link('http://www.yahoo.com')
self.assertEqual(is_it, True)
is_it = Preprocessor.is_link('https://www.yahoo.com')
self.assertEqual(is_it, True)
is_it = Preprocessor.is_link('www.yahoo.com')
self.assertEqual(is_it, True)
def test_is_link(self):
is_it = Preprocessor.is_link('hello world')
self.assertEqual(is_it, False)
is_it = Preprocessor.is_link('http://www.yahoo.com')
self.assertEqual(is_it, True)
is_it = Preprocessor.is_link('https://www.yahoo.com')
self.assertEqual(is_it, True)
is_it = Preprocessor.is_link('www.yahoo.com')
self.assertEqual(is_it, True)
class QA:
def __init__(self):
self.file_name = 'qa.txt'
self.qa_list = {}
self.qa_id = 0
self.prep = Preprocessor()
self.mx = Matrix()
self.metric = Metrics()
def randomize(self, a):
for i in range(len(a)):
a[i] = random.randint(0,1)
def readfile(self):
fd = open(self.file_name,'r')
for line in fd.readlines():
line = line.strip().lower().split(':')
if len(line) != 2:
continue
elif line[0] == 'q':
q_line = ' '.join(line[1:])
self.qa_id += 1
self.qa_list[self.qa_id] = {'q': q_line, 'a': ''}
terms = self.prep.ngram_tokenizer(text=q_line)
self.mx.add_doc(doc_id=self.qa_id, doc_terms=terms,
frequency=True, do_padding=True)
elif line[0] == 'a':
a_line = ' '.join(line[1:])
self.qa_list[self.qa_id]['a'] = a_line
#print 'Number of read questions and answers:', len(self.mx.docs)
#print 'Number of read terms', len(self.mx.terms)
def ask(self, q=''):
q_id = 0
q_distance = 99999
terms = self.prep.ngram_tokenizer(text=q)
q_vector = self.mx.query_to_vector(terms, frequency=False)
if sum(q_vector) == 0:
self.randomize(q_vector)
for doc in self.mx.docs:
distance = self.metric.euclid_vectors(doc['terms'], q_vector)
if distance < q_distance:
q_distance = distance
q_id = doc['id']
print 'Tarek:', self.qa_list[q_id]['a']
def __init__(self):
self.file_name = 'qa.txt'
self.qa_list = {}
self.qa_id = 0
self.prep = Preprocessor()
self.mx = Matrix()
self.metric = Metrics()
def readfiles(fold_path='all-folds/fold1/'):
prep = Preprocessor()
mx = Matrix()
files = os.listdir(fold_path)
for filename in files:
fd = open('%s/%s' % (fold_path, filename), 'r')
file_data = fd.read()
terms = prep.ngram_tokenizer(text=file_data)
mx.add_doc(doc_id=filename, doc_terms=terms,
frequency=True, do_padding=True)
print 'Number of read documents:', len(mx.docs)
print 'Number of read terms', len(mx.terms)
#print mx.terms[0:5], mx.terms[-5:-1]
print mx.terms
print mx.docs
def readfiles(fold_path='all-folds/fold1/'):
prep = Preprocessor()
mx = Matrix()
files = os.listdir(fold_path)
for filename in files:
fd = open('%s/%s' % (fold_path, filename), 'r')
file_data = fd.read()
terms = prep.ngram_tokenizer(text=file_data)
mx.add_doc(doc_id=filename,
doc_terms=terms,
frequency=True,
do_padding=True)
print 'Number of read documents:', len(mx.docs)
print 'Number of read terms', len(mx.terms)
#print mx.terms[0:5], mx.terms[-5:-1]
print mx.terms
print mx.docs
def main():
# Load configuration from file
config = Configuration(config_file='/home/huma/Downloads/irlib-0.1.1/irlib/classify.conf')
try:
config.load_configuration()
config_data = config.get_configuration()
except:
print("Error loading configuration file.")
print("Classifier aborting.")
raise
# config.display_configuration()
print(config)
# sys.exit()
myfolds = config.get_folds()
correctness = 0
# Preporcessor: tokenizer, stemmer, etc.
prep_lower = config_data['lower']
prep_stem = config_data['stem']
prep_pos = config_data['pos']
prep_ngram = config_data['ngram']
prep = Preprocessor(pattern='\W+', lower=prep_lower, stem=prep_stem, pos=prep_pos, ngram=prep_ngram)
for myfold in myfolds:
ev = Evaluation(config=config, fold=myfold)
if config_data['classifier'] == 'rocchio':
ml = Rocchio(verbose=VERBOSE, fold=myfold, config=config, ev=ev)
elif config_data['classifier'] == 'knn':
ml = KNN(verbose=VERBOSE, fold=myfold, config=config, ev=ev)
else:
ml = NaiveBayes(verbose=VERBOSE, fold=myfold, config=config, ev=ev)
training(config, myfold, ml, prep)
ml.do_padding()
ml.calculate_training_data()
# r.display_idx()
ml.diagnose()
testing(config, myfold, ml, ev, prep)
k = config_data['k']
results = ev.calculate(review_spam=True, k=k)
print('Accuracy for fold %d: %s' % (myfold, results))
correctness += results
print("Average accuracy for all folds:", correctness / len(myfolds))
def test_term2ch(self):
p = Preprocessor()
charlist = p.term2ch('help')
self.assertEqual(charlist, ['h', 'e', 'l', 'p'])
def test_tokenizer_lower(self):
p = Preprocessor(lower=True, stem=False)
tokens = p.tokenizer('This is IRLib')
self.assertEqual(tokens, ['this', 'is', 'irlib'])
# Load the three modules:
from irlib.preprocessor import Preprocessor
from irlib.matrix import Matrix
from irlib.metrics import Metrics
import difflib
# Create instances for their classes:
prep = Preprocessor()
mx = Matrix()
metric = Metrics()
q_vector = []
def generateMatrix():
fd = open('./content_transfer_data/roto-sent-data.train-ONLYTAGS.src', 'r')
count = 1
for line in fd.readlines():
terms = line.split(' ')
terms = [x.strip() for x in terms]
mx.add_doc(doc_id=str(count),
doc_terms=terms,
frequency=True,
do_padding=True)
count += 1
if count % 1000 == 0:
print count
mx.dump('IRmatrix.train.src.csv', delimiter='\t', header=True)
def __init__(self):
self._mx = Matrix()
self._prep = Preprocessor(pattern='\W+', lower=True, stem=True)
class Search:
def __init__(self):
self._mx = Matrix()
self._prep = Preprocessor(pattern='\W+', lower=True, stem=True)
def readfiles(self, fold_path='all-folds/fold1/'):
ruta = os.path.split(sys.argv[0])
abs = os.path.join(ruta[0], fold_path)
files = os.listdir(abs)
for filename in files:
abs_arch = os.path.join(abs, filename)
fd = open(abs_arch, 'r')
file_data = fd.read()
self.createMX(filename, file_data)
print 'Number of read documents:', len(self._mx.docs)
print 'Number of read terms', len(self._mx.terms)
#print mx.terms[0:5], mx.terms[-5:-1]
'''print mx.terms
for doc in mx.docs:
print doc'''
self.saveMX(self._mx)
print 'proceso culminado'
def saveMX(self, mx):
ruta = os.path.split(sys.argv[0])
abs = os.path.join(ruta[0], "db/matrix.mx")
filemx = open(abs, 'w')
serializer = Pickler(filemx)
serializer.dump(mx)
print 'matrix salvada'
def createMX(self, file_id, file_data, lenguaje = 'english'):
stop = stopwords.words(lenguaje)
file = file_data.split(" ")
content = [w for w in file if w.lower() not in stop]
data = content.__str__()
terms = self._prep.ngram_tokenizer(text=data)
if len(terms) > 0:
self._mx.add_doc(doc_id=file_id, doc_terms=terms,
frequency=True, do_padding=True)
def search(self):
ruta = os.path.split(sys.argv[0])
abs = os.path.join(ruta[0], "db/matrix.mx")
filemx = open(abs, 'r')
serializer = Unpickler(filemx)
self._mx = serializer.load()
cadena = sys.argv
del cadena[0]
del cadena[0]
cade = cadena.__str__()
cade = cade.lower()
cad = self._prep.ngram_tokenizer(text=cade)
resultado = list()
for doc in self._mx.docs:
vector = list()
for q in cad:
if q in self._mx.terms:
pos = self._mx.terms.index(q)
vector.append(doc['terms'][pos])
resultado.append((doc['id'],vector))
resultado.sort(lambda a,b: self.__Deuclidiana(a[1]) - self.__Deuclidiana(b[1]), reverse = True)
print resultado
def __Deuclidiana(self, vector):
dist = 0
for v in vector:
dist+=v**2
return dist.__int__()
def main(self):
#self.readfiles()
self.search()
def test_3gram_tokenizer(self):
p = Preprocessor(lower=False, stem=False, ngram=3)
returned_tokens = p.ngram_tokenizer('how do you do?')
expected_tokens = ['how do you', 'do you do']
self.assertEqual(returned_tokens, expected_tokens)
def test_3gram_tokenizer(self):
p = Preprocessor(lower=False, stem=False, ngram=3)
returned_tokens = p.ngram_tokenizer('how do you do?')
expected_tokens = ['how do you', 'do you do']
self.assertEqual(returned_tokens, expected_tokens)
def test_tokenizer_lower(self):
p = Preprocessor(lower=True, stem=False)
tokens = p.tokenizer('This is IRLib')
self.assertEqual(tokens,['this','is','irlib'])
def test_is_mention(self):
is_it = Preprocessor.is_mention('@twitter')
self.assertEqual(is_it, True)
is_it = Preprocessor.is_mention('#twitter')
self.assertEqual(is_it, False)
def test_term2ch(self):
p = Preprocessor()
charlist = p.term2ch('help')
self.assertEqual(charlist, ['h', 'e', 'l', 'p'])
def test_is_hashtag(self):
is_it = Preprocessor.is_hashtag('@twitter')
self.assertEqual(is_it, False)
is_it = Preprocessor.is_hashtag('#twitter')
self.assertEqual(is_it, True)
def test_is_hashtag(self):
is_it = Preprocessor.is_hashtag('@twitter')
self.assertEqual(is_it, False)
is_it = Preprocessor.is_hashtag('#twitter')
self.assertEqual(is_it, True)
def test_is_mention(self):
is_it = Preprocessor.is_mention('@twitter')
self.assertEqual(is_it, True)
is_it = Preprocessor.is_mention('#twitter')
self.assertEqual(is_it, False)
