def _lauch_engine(self):
# Create boolean or vectorial search engine
if self.config['Research_engine']['type'] == 'vectorial':
research_engine = Vectorial_search(
reverse_index=self.reverse_index,
similarity=self.config['Vectorial_search']['similarity'],
)
query_processor = Process_query('sources/common_words',
'vectorial')
elif self.config['Research_engine']['type'] == 'boolean':
research_engine = Boolean_search(
reverse_index=self.reverse_index,
p_norm=self.config['Boolean_search']['p_norm'],
default_similarity=self.config['Boolean_search']
['default_similarity'])
query_processor = Process_query('sources/common_words', 'boolean')
elif self.config['Research_engine']['type'] == 'probabilistic':
research_engine = Probabilistic_search(
reverse_index=self.reverse_index,
rsv_relevant_method=self.config['Probabilistic_search']
['rsv_relevant_method'])
query_processor = Process_query('sources/common_words',
'probabilistic')
else:
raise ValueError('Unsupported research engine type!')
max_results_number = self.config['Research_engine'][
'max_results_number']
while 1:
query = raw_input('Enter your query: ')
t0 = time.time()
results = research_engine.do_search(
query_processor.format_query(query))
print len(results), 'results in', time.time() - t0, 'seconds'
if max_results_number > 0 and len(results) > max_results_number:
results = results[:max_results_number]
print 'printing only the first', max_results_number, 'results: \n'
print 'document id \t score'
print '-----------------------------'
for (document_id, score) in results:
print document_id, '\t\t', score
def _lauch_engine(self):
# Create boolean or vectorial search engine
if self.config['Research_engine']['type'] == 'vectorial':
research_engine = Vectorial_search(
reverse_index=self.reverse_index,
similarity=self.config['Vectorial_search']['similarity'],
)
query_processor = Process_query('sources/common_words', 'vectorial')
elif self.config['Research_engine']['type'] == 'boolean':
research_engine = Boolean_search(
reverse_index=self.reverse_index,
p_norm=self.config['Boolean_search']['p_norm'],
default_similarity=self.config['Boolean_search']['default_similarity']
)
query_processor = Process_query('sources/common_words', 'boolean')
elif self.config['Research_engine']['type'] == 'probabilistic':
research_engine = Probabilistic_search(
reverse_index=self.reverse_index,
rsv_relevant_method=self.config['Probabilistic_search']['rsv_relevant_method']
)
query_processor = Process_query('sources/common_words', 'probabilistic')
else:
raise ValueError('Unsupported research engine type!')
max_results_number = self.config['Research_engine']['max_results_number']
while 1:
query = raw_input('Enter your query: ')
t0 = time.time()
results = research_engine.do_search(query_processor.format_query(query))
print len(results), 'results in', time.time()-t0, 'seconds'
if max_results_number > 0 and len(results) > max_results_number:
results = results[:max_results_number]
print 'printing only the first', max_results_number, 'results: \n'
print 'document id \t score'
print '-----------------------------'
for (document_id, score) in results:
print document_id, '\t\t', score
def run_testing(self):
print 'Launching tests!'
print 'Loading documents...',
reverse_index_builder = Reverse_index_builder(
ponderation_method=self.config['Reverse_index']['ponderation'],
index_type=self.config['Reverse_index']['index_type'],
save_folder_path=self.config['Reverse_index']['save_folder_path']
)
reverse_index = reverse_index_builder.create_reverse_index('sources/cacm.all', 'sources/common_words')
print ' Done'
print 'Loading test data...',
# {query: [answer1, answer2...]}
self.query_answer = self._parse_queries_answers(self.queries_filename, self.answers_filename)
print ' Done'
print 'Initializing variables...',
time_parsing_queries = 0.
time_doing_researches = 0.
precision = []
recall = []
r_measure = []
f_measure = []
average_precision = []
if self.config['Research_engine']['type'] == 'vectorial':
search_engine = Vectorial_search(reverse_index, self.similarity_method)
elif self.config['Research_engine']['type'] == 'boolean':
search_engine = Boolean_search(reverse_index, self.p_norm, self.default_similarity)
elif self.config['Research_engine']['type'] == 'probabilistic':
search_engine = Probabilistic_search(reverse_index, self.rsv_relevant_method)
query_processor = Process_query(stop_list_filename='sources/cacm.all', format_type=self.config['Research_engine']['type'])
print ' Done'
t0 = time.time()
print 'Let\'s get to it! (this may take 5-10 seconds)'
for query in self.query_answer:
expected_answers = self.query_answer[query]
t_init = time.time()
processed_query = query_processor.format_query(query)
t_parse = time.time()
time_parsing_queries += t_parse - t_init
answers_with_score = search_engine.do_search(processed_query)
answers = map(lambda (x, y): x, answers_with_score)
t_query = time.time()
time_doing_researches += t_query - t_parse
precision.append(self._compute_precision(answers, expected_answers))
recall.append(self._compute_recall(answers, expected_answers))
r_measure.append(self._compute_r_measure(answers, expected_answers))
f_measure.append(self._compute_f_measure(precision[-1], recall[-1]))
average_precision.append(self._compute_average_precision(answers, expected_answers))
number_of_tests = float(len(self.query_answer))
print 'Number of queries tested:', int(number_of_tests), 'in', round(time.time() - t0, 2), 'seconds'
print 'Average time spent on query processing:', time_parsing_queries / number_of_tests, 'seconds',
print ', doing the research:', time_doing_researches / number_of_tests, 'seconds'
print 'Average time spent on a query (total):', (time_doing_researches + time_parsing_queries) / number_of_tests, 'seconds'
print """
###################################
# PERFORMANCE MEASURES #
###################################"""
print 'Max Precision:', max(precision), 'average:', reduce(lambda x, y: x + y, precision) / float(len(precision))
print 'Max Recall:', max(recall), 'average:', reduce(lambda x, y: x + y, recall) / float(len(recall))
print 'Max F-measure', max(f_measure), 'average:', reduce(lambda x, y: x + y, f_measure) / float(len(f_measure))
print 'Min E-measure', 1 - max(f_measure), 'average:', 1 - reduce(lambda x, y: (x + y), f_measure) / float(len(f_measure))
print 'Max R-measure', max(r_measure), 'average:', reduce(lambda x, y: x + y, r_measure) / float(len(r_measure))
print 'Mean Average Precision (MAP)', reduce(lambda x, y: x + y, average_precision) / float(len(average_precision))