def generate_benchmark_commands(total_benchmark_commands, bench_fname, all_fname, indexname, docs, stop_words,
use_numeric_range_searchs, ts_digest, p_writes):
total_benchmark_reads = 0
total_benchmark_writes = 0
all_csvfile = open(all_fname, 'a', newline='')
bench_csvfile = open(bench_fname, 'w', newline='')
all_csv_writer = csv.writer(all_csvfile, delimiter=',', quoting=csv.QUOTE_ALL)
bench_csv_writer = csv.writer(bench_csvfile, delimiter=',', quoting=csv.QUOTE_ALL)
progress = tqdm(unit="docs", total=total_benchmark_commands)
total_docs = len(docs)
## timestamp related
timestamps_pdist = generate_lognormal_dist(total_benchmark_commands)
min_ts = ts_digest.percentile(0.0)
max_ts = ts_digest.percentile(100.0)
query_range_digest = TDigest()
generated_commands = 0
while generated_commands < total_benchmark_commands:
query_ts_pdist = timestamps_pdist[generated_commands]
percentile = (1.0 - query_ts_pdist) * 100.0
query_min_ts = ts_digest.percentile(percentile)
random_doc_pos = random.randint(0, total_docs - 1)
doc = docs[random_doc_pos]
# decide read or write
p_cmd = random.random()
if p_cmd < p_writes:
## WRITE
total_benchmark_writes = total_benchmark_writes + 1
generated_row, doc_size = use_case_to_cmd(use_ftadd, doc["title"], doc["text"], doc["comment"],
doc["username"],
doc["timestamp"],
generated_commands)
else:
## READ
total_benchmark_reads = total_benchmark_reads + 1
words, totalW = getQueryWords(doc, stop_words, 2)
choice = random.choices(["simple-1word-query", "2word-union-query", "2word-intersection-query"])[0]
generated_row = None
numeric_range_str = ""
if use_numeric_range_searchs:
numeric_range_str = "@timestamp:[{} {}] ".format(query_min_ts, max_ts)
query_range_digest.update(int(max_ts - query_min_ts))
if choice == "simple-1word-query" and len(words) >= 1:
generated_row = generate_ft_search_row(indexname, "simple-1word-query",
"{}{}".format(numeric_range_str, words[0]))
elif choice == "2word-union-query" and len(words) >= 2:
generated_row = generate_ft_search_row(indexname, "2word-union-query",
"{}{} {}".format(numeric_range_str, words[0], words[1]))
elif choice == "2word-intersection-query" and len(words) >= 2:
generated_row = generate_ft_search_row(indexname, "2word-intersection-query",
"{}{}|{}".format(numeric_range_str, words[0], words[1]))
if generated_row != None:
# all_csv_writer.writerow(generated_row)
# bench_csv_writer.writerow(generated_row)
progress.update()
generated_commands = generated_commands + 1
progress.close()
bench_csvfile.close()
all_csvfile.close()
# print()
xx = []
yy = []
p90 = query_range_digest.percentile(90.0)
dataset_percent = ts_digest.cdf(p90)
print("90% of the read queries target at max {} percent o keyspace".format(dataset_percent))
print("100% of the read queries target at max {} percent o keyspace".format(ts_digest.cdf(max_ts - min_ts)))
for centroid in query_range_digest.centroids_to_list():
ts_m = centroid["m"]
xx.append(ts_m)
yy.append(query_range_digest.cdf(ts_m))
plt.scatter(xx, yy)
plt.title('EnWiki pages Query time range')
plt.xlabel('Query time range')
plt.ylabel('cdf')
plt.xscale('log')
plt.show()
return total_benchmark_reads, total_benchmark_writes
plt.hist(docs_sizes, bins=bins, alpha=0.5)
plt.title('EnWiki pages document size frequency. Avg document size: {} Bytes'.format(int(np.average(docs_sizes))))
plt.xlabel('Document Size in Bytes')
plt.ylabel('count')
plt.xscale('log')
plt.show()
xx = []
yy = []
for centroid in ts_digest.centroids_to_list():
# print(centroid)
ts_m = centroid["m"]
xx.append(ts_m)
yy.append(ts_digest.cdf(ts_m))
plt.scatter(xx, yy)
plt.title('EnWiki pages timestamp range')
plt.xlabel('timestamp')
plt.ylabel('cdf')
# plt.xscale('log')
plt.show()
progress.close()
all_csvfile.close()
setup_csvfile.close()
print("-- generating {} full text search commands -- ".format(total_benchmark_commands))
print("\t saving to {} and {}".format(bench_fname, all_fname))
total_benchmark_reads, total_benchmark_writes = generate_benchmark_commands(total_benchmark_commands, bench_fname,
