def add_doc(self, doc_id = '', doc_class='', doc_terms=[], do_padding = False):
my_doc_terms = SuperList()
for term in doc_terms:
self.terms.unique_append(term)
my_doc_terms.insert_after_padding(self.terms.index(term))
self.matrix.append({'id': doc_id, 'class': doc_class, 'terms': my_doc_terms})
if do_padding:
self.do_padding()
def add_query(self, query_id = '', query_class='n/a', query_terms=[]):
my_query_terms = SuperList()
my_query_terms.do_padding(new_len=len(self.terms), padding_data=0)
new_terms_count = 0
for term in query_terms:
try:
my_query_terms.insert_after_padding(self.terms.index(term))
except:
# Term not obtaied in traing phase
new_terms_count += 1
self.queries.append({'id': query_id, 'class': query_class, 'terms': my_query_terms, 'new_terms_count': new_terms_count})
def add_query(self, query_id = '', query_class='n/a', query_terms=[]):
my_query_terms = SuperList()
my_query_terms.do_padding(new_len=len(self.terms), padding_data=0)
for term in query_terms:
try:
my_query_terms.insert_after_padding(self.terms.index(term))
except:
# Term not obtaied in traing phase, ignore it
pass
# Calling add_vectors to convert my_query_terms to log_tf values
self.add_vectors(a=my_query_terms, log_tf_a = True)
self.queries.append({'id': query_id, 'class': query_class, 'terms': my_query_terms})
