def it_should_search_test(self): vectorSpace = VectorSpace(self.documents) eq_(vectorSpace.search(["cat"]), [ 0.14487566959813258, 0.1223402602604157, 0.07795622058966725, 0.05586504042763477 ])
def run(data, queries, max_response=10): all_documents = [] for entry in data: all_documents.append(entry["raw_data"]) vector_space = VectorSpace(all_documents) #Search for cat indexed_result = {} result = vector_space.search([queries]) index = 0 for entry in result: indexed_result[index] = entry index += 1 sorted_resp = sorted(indexed_result.items(), key=operator.itemgetter(1), reverse=True) sorted_resp = sorted_resp[:int(max_response) + 1] response = {} rank = 1 for entry in sorted_resp: data_index = entry[0] response[rank] = data[data_index] rank += 1 return response
def it_should_search_test(self): vectorSpace = VectorSpace(self.documents) eq_( vectorSpace.search(["cat"]), [0.14487566959813258, 0.1223402602604157, 0.07795622058966725, 0.05586504042763477], )
def it_should_search_test(self): vector_space = VectorSpace(self.documents, transforms = []) eq_(vector_space.search(["cat"]), [1.0, 0.7071067811865475, 0.0])
posExamples = userQueriesAndClicks[item][i][1] negExamples = userQueriesAndClicks[item][i][1] return (list(posExamples), list(negExamples)) return ([], []) print "loaded queries and clicks" map = 0 counter = 0 for query in queries: #print "query is: " + query queryL = [] queryL.append(query) try: results = vector_space.search(queryL) except: results = [] if (len(results) != 0): print "query is: " + query #query terms found inside the matrix, sort the results retrievedDocs = zip(results, docIds) #sort them retrievedDocs = sorted(retrievedDocs) #print "documents retrieved for query " + query #print retrievedDocs (a, b) = getQueryResults(query, userQueriesAndClicks) if (a != [] and b != []): print "pos examples" print a
#print userQueriesAndClicks[item][i][2] posExamples = userQueriesAndClicks[item][i][1] negExamples = userQueriesAndClicks[item][i][1] return (list(posExamples), list(negExamples)) return ([],[]) print "loaded queries and clicks" map = 0 counter = 0 for query in queries: #print "query is: " + query queryL = [] queryL.append(query) try: results = vector_space.search(queryL) except: results = [] if (len(results) != 0): print "query is: " + query #query terms found inside the matrix, sort the results retrievedDocs = zip(results, docIds) #sort them retrievedDocs = sorted(retrievedDocs) #print "documents retrieved for query " + query #print retrievedDocs (a,b) = getQueryResults(query, userQueriesAndClicks) if (a != [] and b != []): print "pos examples" print a