def evaluate_function(query, index, filterproduct, termslist, topN = TOPN):
'''
'''
rank = index.filters_query(' '.join(termslist), filterproduct)
vetor_ganho_consulta = obter_vetor_ganho(rank, query)
ndcg_q = lepref_util.ndcg_unico(vetor_ganho_consulta, query.idcg, topN, chave = lambda e: e)
mean_ndcg_atual = lepref_util.ndcg_medio_unico(ndcg_q)
return (filterproduct, mean_ndcg_atual)
def evaluate(queries, index, topN = TOPN):
acumulador_ndcg = 0.0
for query in queries:
#rank = efetuar consulta
rank = index.simple_query(' '.join([term.word for term in query.term]))
##computados
#vetor_ganho_consulta = obter_vetor_ganho(rank, queries)
vetor_ganho_consulta = obter_vetor_ganho(rank, query)
#ndcg_q = lepref_util.ndcg_unico(vetor_ganho, query.idcg, topN, chave = lambda e: e[0])
if (len(query.idcg) != 40): #TODO remover
print(len(query.idcg), query.queryid)
ndcg_q = lepref_util.ndcg_unico(vetor_ganho_consulta, query.idcg, topN, chave = lambda e: e)
#query.mean_ndcg_atual = lepref_util.ndcg_medio_unico(ndcg_q)
query.mean_ndcg_atual = lepref_util.ndcg_medio_unico(ndcg_q)
#acumulador_ndcg += query.mean_ndcg_atual
acumulador_ndcg += query.mean_ndcg_atual
return acumulador_ndcg/len(queries)
def evaluate_filters(queries, index, dirresultname, topN = TOPN, qiini = None, fiini = None, qiend = None, fiend = None):
start_time = time.time()
mini_time = start_time
print(time.strftime("Start at: %a, %d %b %Y %H:%M:%S", time.localtime()))
# products = {}
results = []
countdict, totalqueries = count_execs(queries, qiini, fiini, qiend, fiend)
queriesdone = 0
miniqueriesdone = 0
seq = 1
try:
queries = queries[qiini:qiend+1]
#exceção necessária para validar a soma em queries = queries[qiini:qiend+1]
except TypeError as error:
if type(qiend) == type(None):
queries = queries[qiini:]
else:
raise(error)
#Configura posqiini para salvamento de relatório posteriormente
posqiini = 0
if type(qiini) == int:
posqiini = qiini
elif qiini == None:
qiini = 0
posfiini = 0
if type(fiini) == int:
posfiini = fiini
if fiini == None:
fiini = 0
for qi, query in enumerate(queries):
if NOSTOPWORDS:
termslist = remove_stopwords(query)
else:
termslist = [term.word for term in query.term]
#n_jobs = len(productslist)
n_jobs = len(filters) ** len(termslist)
productsresults = []
filteriterator = itertools.product(filters.keys(), repeat = len(termslist))
if qi == 0 and fiini:
if fiini < 0:
print('fiini não pode ser negativo')
print('fiini:', fiini)
sys.exit()
if fiini >= n_jobs:
print('O número inicial do filtro não pode ser maior ou igual a quantidade de filtros ')
print('fiini:', fiini)
print('Nfiltros:', n_jobs)
sys.exit()
filteriterator = itertools.islice(filteriterator, fiini, n_jobs)
if qi == len(queries)-1 and fiend != None:
if fiend < 0:
print('fiend não pode ser negativo')
print('fiend:', fiend)
sys.exit()
if fiend >= n_jobs:
print('O índice final de filtros não pode ser maior ou igual a quantidade de filtros ')
print('fiend:', fiend)
print('Nfiltros:', 3**len(termslist))
sys.exit()
if qi == 0:
filteriterator = itertools.islice(filteriterator, fiend + 1 - fiini)
else:
filteriterator = itertools.islice(filteriterator, fiend + 1)
# try:
# filteriterator = itertools.islice(filteriterator, fiend + 1 - fiini)
# except ValueError as error:
# print('qi', qi + qiini)
# print('fiend', fiend)
# print('fiini', fiini)
# print('fiend + 1 - fiini', fiend + 1 - fiini)
# raise(error)
for fi, filterproduct in enumerate(filteriterator):
#Evalue query
rank = index.filters_query(' '.join(termslist), filterproduct)
vetor_ganho_consulta = obter_vetor_ganho(rank, query)
ndcg_q = lepref_util.ndcg_unico(vetor_ganho_consulta, query.idcg, topN, chave = lambda e: e)
query.mean_ndcg_atual = lepref_util.ndcg_medio_unico(ndcg_q)
queriesdone += 1
miniqueriesdone += 1
#Process tracker
#(56%) 1541 of 5125 queries. Query 650 processing (34%) 14 of 59 filters...
#reset mini time
if time.time() - mini_time > 1:
print('\rExecs: %d/%d (%2.2f%%) Query: %d/%d (%2.2f%%) Processing %d/%d (%2.2f%%) %.1fq/s (%.1fq/s)' % (
queriesdone, totalqueries, (queriesdone)/totalqueries * 100,
(qi+1), len(queries), (qi+1)/len(queries) * 100,
fi+1, n_jobs, (fi+1)/n_jobs * 100,
(queriesdone) / (time.time() - start_time),
(miniqueriesdone) / (time.time() - mini_time)),
end = '')
mini_time = time.time()
miniqueriesdone = 0
#Add result to products results
# if qi == 0:
# productsresults.append((fi + fiini, query.mean_ndcg_atual))
# else:
# productsresults.append((fi, query.mean_ndcg_atual))
productsresults.append((filterproduct, query.mean_ndcg_atual))
# Implementar salvar arquivo
if queriesdone%EXECSTHRESHOLD == 0:
queryresult = (query.queryid, termslist, productsresults)
results.append(queryresult)
posqiend = qi + qiini
if qi == 0:
posfiend = fiini + fi
else:
posfiend = fi
#Save results
save_results(results, dirresultname, posqiini, posfiini, posqiend, posfiend, seq)
#Configura nova rodada de armazenamento
seq += 1
if fi+1 == n_jobs:
posqiini = qiini + qi + 1 # next query
posfiini = 0
else:
posqiini = qiini + qi # same query next filter
if qi == 0: # soma o inicio do intervalo na posição
if fiini == None:
posfiini = fi + 1
else:
posfiini = fiini + fi + 1
else:
posfiini = fi + 1
del(productsresults)
del(results)
productsresults = []
results = []
if productsresults:
#Add query results to final results
queryresult = (query.queryid, termslist, productsresults)
results.append(queryresult)
if results:
posqiend = qi + qiini
posfiend = fi + fiini
save_results(results, dirresultname, posqiini, posfiini, posqiend, posfiend, seq)
print('\rExecs: %d/%d (%2.2f%%) Query: %d/%d (%2.2f%%) Processing %d/%d (%2.2f%%) %.1fq/s' % (
queriesdone, totalqueries, (queriesdone)/totalqueries * 100,
(qi+1), len(queries), (qi+1)/len(queries) * 100,
fi+1, n_jobs, (fi+1)/n_jobs * 100,
(queriesdone) / (time.time() - start_time))
)
print(time.strftime("Ends at: %a, %d %b %Y %H:%M:%S", time.localtime()))
print("--- %s seconds ---" % (time.time() - start_time))
