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 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_get_doc_by_id(self):
mx = Matrix()
for i,s in enumerate(['hello', 'how are you', 'fine thank you']):
mx.add_doc( doc_id = str(i),
doc_class='Email',
doc_terms= s.split(),
do_padding=True,
frequency=True)
doc1_id = mx.docs.index('1')
self.assertEqual(mx.docs[doc1_id]['id'], '1')
def test_get_doc_by_id(self):
mx = Matrix()
for i, s in enumerate(['hello', 'how are you', 'fine thank you']):
mx.add_doc(doc_id=str(i),
doc_class='Email',
doc_terms=s.split(),
do_padding=True,
frequency=True)
doc1_id = mx.docs.index('1')
self.assertEqual(mx.docs[doc1_id]['id'], '1')
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 test_white_and_black_lists(self):
doc_terms = ['this', 'is', 'a', 'new', 'test']
white_list = ['test']
black_list = ['this', 'is', 'a']
mx = Matrix(whitelist=white_list, blacklist=black_list)
mx.add_doc( doc_id = 'doc1',
doc_class='TestClass',
doc_terms= doc_terms,
do_padding=True,
frequency=True)
returned_terms = mx.vocabulary()
expected_terms = ['test']
self.assertItemsEqual(returned_terms, expected_terms)
def test_white_and_black_lists(self):
doc_terms = ['this', 'is', 'a', 'new', 'test']
white_list = ['test']
black_list = ['this', 'is', 'a']
mx = Matrix(whitelist=white_list, blacklist=black_list)
mx.add_doc(doc_id='doc1',
doc_class='TestClass',
doc_terms=doc_terms,
do_padding=True,
frequency=True)
returned_terms = mx.vocabulary()
expected_terms = ['test']
self.assertItemsEqual(returned_terms, expected_terms)
def test_meta_data(self):
mx = Matrix()
for i, s in enumerate(['hello', 'world']):
mx.add_doc(doc_id=str(i),
doc_class='Email',
doc_terms=s.split(),
do_padding=True,
frequency=True,
meta_data={
'original_text': s,
'original_text_len': len(s)
})
self.assertEqual(mx.docs[1]['original_text'], 'world')
self.assertEqual(mx.docs[1]['original_text_len'], 5)
def test_meta_data(self):
mx = Matrix()
for i,s in enumerate(['hello', 'world']):
mx.add_doc( doc_id = str(i),
doc_class='Email',
doc_terms= s.split(),
do_padding=True,
frequency=True,
meta_data={
'original_text': s,
'original_text_len': len(s)
})
self.assertEqual(mx.docs[1]['original_text'], 'world')
self.assertEqual(mx.docs[1]['original_text_len'], 5)
def test_docs_unique_ids(self):
mx = Matrix()
for i,s in enumerate(['hello', 'how are you', 'fine thank you']):
mx.add_doc( doc_id = str(i),
doc_class='Email',
doc_terms= s.split(),
do_padding=True,
frequency=True)
mx.add_doc(doc_id = '1',
doc_class='Email',
doc_terms= 'goodbye'.split(),
do_padding=True,
frequency=True,
unique_ids=True)
self.assertEqual(len(mx), 3)
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
class TestMatrix(unittest.TestCase):
def setUp(self):
self.m = Matrix()
def test_add_doc(self):
# Try without frequency
self.assertEqual(len(self.m),0)
doc1_terms = ['buy', 'now', 'or', 'buy', 'later']
self.m.add_doc( doc_id = 'file_spam.txt',
doc_class='Spam',
doc_terms= doc1_terms,
frequency=False)
self.assertEqual(self.m.terms, ['buy', 'now', 'or', 'later'])
self.assertEqual(self.m.docs[0]['terms'], [1,1,1,1])
# Now try with frequency
doc2_terms = ['buy', 'today', 'or', 'buy', 'later']
self.m.add_doc( doc_id = 'file_spam.txt',
doc_class='Spam',
doc_terms= doc2_terms,
frequency=True)
self.assertEqual(self.m.terms, ['buy', 'now', 'or', 'later', 'today'])
self.assertEqual(self.m.docs[1]['terms'], [2,0,1,1,1])
# Now let's see if padding is working
doc2_terms = ['buy', 'now']
self.m.add_doc( doc_id = 'file_spam.txt',
doc_class='Ham',
doc_terms= doc2_terms,
frequency=True,
do_padding=True)
print self.m.terms, self.m.docs[0]['terms']
self.assertEqual(len(self.m.terms), len(self.m.docs[0]['terms']))
self.assertEqual(len(self.m),3)
self.assertEqual('buy' in self.m, True)
self.assertEqual('shopping' in self.m, False)
class TestMatrix(unittest.TestCase):
def setUp(self):
self.m = Matrix()
def test_add_doc(self):
# Try without frequency
self.assertEqual(len(self.m), 0)
doc1_terms = ['buy', 'now', 'or', 'buy', 'later']
self.m.add_doc(doc_id='file_spam.txt',
doc_class='Spam',
doc_terms=doc1_terms,
frequency=False)
self.assertEqual(self.m.terms, ['buy', 'now', 'or', 'later'])
self.assertEqual(self.m.docs[0]['terms'], [1, 1, 1, 1])
# Now try with frequency
doc2_terms = ['buy', 'today', 'or', 'buy', 'later']
self.m.add_doc(doc_id='file_spam.txt',
doc_class='Spam',
doc_terms=doc2_terms,
frequency=True)
self.assertEqual(self.m.terms, ['buy', 'now', 'or', 'later', 'today'])
self.assertEqual(self.m.docs[1]['terms'], [2, 0, 1, 1, 1])
# Now let's see if padding is working
doc2_terms = ['buy', 'now']
self.m.add_doc(doc_id='file_spam.txt',
doc_class='Ham',
doc_terms=doc2_terms,
frequency=True,
do_padding=True)
#print self.m.terms, self.m.docs[0]['terms']
self.assertEqual(len(self.m.terms), len(self.m.docs[0]['terms']))
self.assertEqual(len(self.m), 3)
self.assertEqual('buy' in self.m, True)
self.assertEqual('shopping' in self.m, False)
def test_docs_unique_ids(self):
mx = Matrix()
for i, s in enumerate(['hello', 'how are you', 'fine thank you']):
mx.add_doc(doc_id=str(i),
doc_class='Email',
doc_terms=s.split(),
do_padding=True,
frequency=True)
mx.add_doc(doc_id='1',
doc_class='Email',
doc_terms='goodbye'.split(),
do_padding=True,
frequency=True,
unique_ids=True)
self.assertEqual(len(mx), 3)
class TestMatrix(TestCase):
def setUp(self):
self.m = Matrix()
def test_add_doc(self):
# Try without frequency
self.assertEqual(len(self.m),0)
doc1_terms = ['buy', 'now', 'or', 'buy', 'later']
self.m.add_doc( doc_id = 'file_spam.txt',
doc_class='Spam',
doc_terms= doc1_terms,
frequency=False)
self.assertEqual(self.m.terms, ['buy', 'now', 'or', 'later'])
self.assertEqual(self.m.docs[0]['terms'], [1,1,1,1])
# Now try with frequency
doc2_terms = ['buy', 'today', 'or', 'buy', 'later']
self.m.add_doc( doc_id = 'file_spam.txt',
doc_class='Spam',
doc_terms= doc2_terms,
frequency=True)
self.assertEqual(self.m.terms, ['buy', 'now', 'or', 'later', 'today'])
self.assertEqual(self.m.docs[1]['terms'], [2,0,1,1,1])
# Now let's see if padding is working
doc2_terms = ['buy', 'now']
self.m.add_doc( doc_id = 'file_spam.txt',
doc_class='Ham',
doc_terms= doc2_terms,
frequency=True,
do_padding=True)
#print self.m.terms, self.m.docs[0]['terms']
self.assertEqual(len(self.m.terms), len(self.m.docs[0]['terms']))
self.assertEqual(len(self.m),3)
self.assertEqual('buy' in self.m, True)
self.assertEqual('shopping' in self.m, False)
def test_add_doc_empty(self):
doc1_terms = []
with self.assertRaises(ValueError):
self.m.add_doc( doc_id = 'doc1',
doc_class='Spam',
doc_terms= doc1_terms)
def test_meta_data(self):
mx = Matrix()
for i,s in enumerate(['hello', 'world']):
mx.add_doc( doc_id = str(i),
doc_class='Email',
doc_terms= s.split(),
do_padding=True,
frequency=True,
meta_data={
'original_text': s,
'original_text_len': len(s)
})
self.assertEqual(mx.docs[1]['original_text'], 'world')
self.assertEqual(mx.docs[1]['original_text_len'], 5)
def test_docs_unique_ids(self):
mx = Matrix()
for i,s in enumerate(['hello', 'how are you', 'fine thank you']):
mx.add_doc( doc_id = str(i),
doc_class='Email',
doc_terms= s.split(),
do_padding=True,
frequency=True)
mx.add_doc(doc_id = '1',
doc_class='Email',
doc_terms= 'goodbye'.split(),
do_padding=True,
frequency=True,
unique_ids=True)
self.assertEqual(len(mx), 3)
def test_get_doc_by_id(self):
mx = Matrix()
for i,s in enumerate(['hello', 'how are you', 'fine thank you']):
mx.add_doc( doc_id = str(i),
doc_class='Email',
doc_terms= s.split(),
do_padding=True,
frequency=True)
doc1_id = mx.docs.index('1')
self.assertEqual(mx.docs[doc1_id]['id'], '1')
def test_query_alignment(self):
doc1_terms = ['buy', 'now', 'or', 'buy', 'later']
self.m.add_doc( doc_id = 'file_spam.txt',
doc_class='Spam',
doc_terms= doc1_terms,
frequency=False)
q_vector = self.m.query_to_vector(['best', 'buy'], frequency=False)
self.assertEqual(q_vector, [1,0,0,0])
def test_tf_idf(self):
doc1_terms = ['new', 'york', 'times']
self.m.add_doc( doc_id = 'doc1',
doc_class='Spam',
doc_terms= doc1_terms,
do_padding=True,
frequency=True)
doc2_terms = ['new', 'york', 'post']
self.m.add_doc( doc_id = 'doc2',
doc_class='Spam',
doc_terms= doc2_terms,
do_padding=True,
frequency=True)
doc3_terms = ['los', 'angeles', 'times']
self.m.add_doc( doc_id = 'doc3',
doc_class='Spam',
doc_terms= doc3_terms,
do_padding=True,
frequency=True)
self.m.tf_idf(log_base=2)
doc1_tfidf_retval = self.m.docs[0]['terms']
doc1_tfidf_retval = [round(item, 3) for item in doc1_tfidf_retval]
doc1_tfidf_expval = [0.585, 0.585, 0.585, 0, 0, 0]
self.assertEqual(doc1_tfidf_retval, doc1_tfidf_expval)
def test_white_and_black_lists(self):
doc_terms = ['this', 'is', 'a', 'new', 'test']
white_list = ['test']
black_list = ['this', 'is', 'a']
mx = Matrix(whitelist=white_list, blacklist=black_list)
mx.add_doc( doc_id = 'doc1',
doc_class='TestClass',
doc_terms= doc_terms,
do_padding=True,
frequency=True)
returned_terms = mx.vocabulary()
expected_terms = ['test']
self.assertItemsEqual(returned_terms, expected_terms)
def setUp(self):
self.m = Matrix()
# 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 setUp(self):
self.m = Matrix()
class TestMatrix(TestCase):
def setUp(self):
self.m = Matrix()
def test_add_doc(self):
# Try without frequency
self.assertEqual(len(self.m), 0)
doc1_terms = ['buy', 'now', 'or', 'buy', 'later']
self.m.add_doc(doc_id='file_spam.txt',
doc_class='Spam',
doc_terms=doc1_terms,
frequency=False)
self.assertEqual(self.m.terms, ['buy', 'now', 'or', 'later'])
self.assertEqual(self.m.docs[0]['terms'], [1, 1, 1, 1])
# Now try with frequency
doc2_terms = ['buy', 'today', 'or', 'buy', 'later']
self.m.add_doc(doc_id='file_spam.txt',
doc_class='Spam',
doc_terms=doc2_terms,
frequency=True)
self.assertEqual(self.m.terms, ['buy', 'now', 'or', 'later', 'today'])
self.assertEqual(self.m.docs[1]['terms'], [2, 0, 1, 1, 1])
# Now let's see if padding is working
doc2_terms = ['buy', 'now']
self.m.add_doc(doc_id='file_spam.txt',
doc_class='Ham',
doc_terms=doc2_terms,
frequency=True,
do_padding=True)
#print self.m.terms, self.m.docs[0]['terms']
self.assertEqual(len(self.m.terms), len(self.m.docs[0]['terms']))
self.assertEqual(len(self.m), 3)
self.assertEqual('buy' in self.m, True)
self.assertEqual('shopping' in self.m, False)
def test_add_doc_empty(self):
doc1_terms = []
with self.assertRaises(ValueError):
self.m.add_doc(doc_id='doc1',
doc_class='Spam',
doc_terms=doc1_terms)
def test_meta_data(self):
mx = Matrix()
for i, s in enumerate(['hello', 'world']):
mx.add_doc(doc_id=str(i),
doc_class='Email',
doc_terms=s.split(),
do_padding=True,
frequency=True,
meta_data={
'original_text': s,
'original_text_len': len(s)
})
self.assertEqual(mx.docs[1]['original_text'], 'world')
self.assertEqual(mx.docs[1]['original_text_len'], 5)
def test_docs_unique_ids(self):
mx = Matrix()
for i, s in enumerate(['hello', 'how are you', 'fine thank you']):
mx.add_doc(doc_id=str(i),
doc_class='Email',
doc_terms=s.split(),
do_padding=True,
frequency=True)
mx.add_doc(doc_id='1',
doc_class='Email',
doc_terms='goodbye'.split(),
do_padding=True,
frequency=True,
unique_ids=True)
self.assertEqual(len(mx), 3)
def test_get_doc_by_id(self):
mx = Matrix()
for i, s in enumerate(['hello', 'how are you', 'fine thank you']):
mx.add_doc(doc_id=str(i),
doc_class='Email',
doc_terms=s.split(),
do_padding=True,
frequency=True)
doc1_id = mx.docs.index('1')
self.assertEqual(mx.docs[doc1_id]['id'], '1')
def test_query_alignment(self):
doc1_terms = ['buy', 'now', 'or', 'buy', 'later']
self.m.add_doc(doc_id='file_spam.txt',
doc_class='Spam',
doc_terms=doc1_terms,
frequency=False)
q_vector = self.m.query_to_vector(['best', 'buy'], frequency=False)
self.assertEqual(q_vector, [1, 0, 0, 0])
def test_tf_idf(self):
doc1_terms = ['new', 'york', 'times']
self.m.add_doc(doc_id='doc1',
doc_class='Spam',
doc_terms=doc1_terms,
do_padding=True,
frequency=True)
doc2_terms = ['new', 'york', 'post']
self.m.add_doc(doc_id='doc2',
doc_class='Spam',
doc_terms=doc2_terms,
do_padding=True,
frequency=True)
doc3_terms = ['los', 'angeles', 'times']
self.m.add_doc(doc_id='doc3',
doc_class='Spam',
doc_terms=doc3_terms,
do_padding=True,
frequency=True)
self.m.tf_idf(log_base=2)
doc1_tfidf_retval = self.m.docs[0]['terms']
doc1_tfidf_retval = [round(item, 3) for item in doc1_tfidf_retval]
doc1_tfidf_expval = [0.585, 0.585, 0.585, 0, 0, 0]
self.assertEqual(doc1_tfidf_retval, doc1_tfidf_expval)
def test_white_and_black_lists(self):
doc_terms = ['this', 'is', 'a', 'new', 'test']
white_list = ['test']
black_list = ['this', 'is', 'a']
mx = Matrix(whitelist=white_list, blacklist=black_list)
mx.add_doc(doc_id='doc1',
doc_class='TestClass',
doc_terms=doc_terms,
do_padding=True,
frequency=True)
returned_terms = mx.vocabulary()
expected_terms = ['test']
self.assertItemsEqual(returned_terms, expected_terms)
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 __init__(self):
self._mx = Matrix()
self._prep = Preprocessor(pattern='\W+', lower=True, stem=True)
