def main(): data = random(1000) i = 0 for i in range(0,(len(data) - wSize + 1)): digest = TDigest() digest.batch_update(data[i:i+wSize]) results.append([i+1,digest.percentile(15)]) i += 1 print(results)
def get_footer_stats(self):
try:
self.check_progress = False
try:
avg_ms = sum(self.ms_list) / len(self.ms_list)
except ZeroDivisionError:
# 捕获全部检测失败的情况。
avg_ms = 0
# 打印百分比分布信息 percentile
if sys.modules.get("tdigest"):
digest = TDigest()
for item in self.ms_list:
digest.update(item)
p50 = digest.percentile(50)
p90 = digest.percentile(90)
p99 = digest.percentile(99)
percentile_string = "\tp50: %.2f p90: %.2f p99: %.2f" % (
p50, p90, p99)
else:
percentile_string = ""
footer = "\rtotal: %d success: %d failure: %d s_rate: %.2f f_rate: %.2f avg_ms: %.2f ms" % (
self.check_count, self.check_success_count,
self.check_failure_count,
self.check_success_count / self.check_count,
self.check_failure_count / self.check_count, avg_ms)
#print(footer + percentile_string, file=sys.stderr, flush=True)
print(footer + percentile_string, flush=True)
if self.check_success_count / self.check_count == 0:
# 如果一个都没有成功，则返回状态码 1.
exit(1)
elif self.check_success_count / self.check_count < 1:
# 返回成功率的整数状态码
exit(trunc(self.check_success_count / self.check_count * 100))
else:
# 全部成功，退出状态码 0。
#exit(0)
pass
except Exception:
# 指定 Exception 不捕获 exit 退出异常动作。
pass
class DigestMachine(DistMachine):
def __init__(self):
super().__init__()
self.digest = TDigest()
def update(self, value, dt=None, **kwargs):
self.digest.update(value)
def inv_cdf(self, p):
return self.digest.percentile(100. * p)
class Digest:
def __init__(self):
self.digest = TDigest()
self.digest.update(0)
self._count = 0
self.lock = asyncio.Lock()
def add(self, v):
self.digest.update(v)
self._count += 1
def percentile(self, v):
return self.digest.percentile(v)
def count(self):
return self._count
class IngestionThread(threading.Thread):
def __init__(self, threadId, args, dimensionMetrics, dimensionEvents,
highUtilizationHosts, lowUtilizationHosts, event):
threading.Thread.__init__(self)
self.threadId = threadId
self.args = args
self.dimensionMetrics = dimensionMetrics
self.dimensionEvents = dimensionEvents
self.client = tswrite.createWriteClient(region=args.region,
profile=args.profile,
endpoint=args.endpoint)
self.databaseName = args.databaseName
self.tableName = args.tableName
self.numMetrics = len(dimensionMetrics)
self.numEvents = len(dimensionEvents)
self.digest = TDigest(
) ## Use the t-digest to compute the streaming percentiles
self.count = 0
self.success = 0
self.sum = 0.0
self.variance = float('nan')
self.highUtilizationHosts = highUtilizationHosts
self.lowUtilizationHosts = lowUtilizationHosts
self.sigInt = False
self.event = event
self.recordsWritten = 0
def run(self):
global seriesId
global timestamp
global lock
idx = 0
mean = 0.0
squared = 0.0
addReqId = self.args.addReqId
addReqIdAsDim = addReqId and self.args.addReqIdAsDim
addReqIdAsMeasure = addReqId and not self.args.addReqIdAsDim
writeRecordsBatch = list()
recordsToWrite = list()
while True:
with lock:
if self.sigInt == True or sigInt == True or self.event.is_set(
):
print("Thread {} exiting.".format(self.threadId))
break
seriesId += 1
if seriesId >= self.numMetrics + self.numEvents:
## Wrapping around, so move to new timestamp.
seriesId = 0
newTimestamp = timestamp + self.args.intervalMillis
currentTime = getCurrentTimestampMillis()
## Check if the timestamps are falling behind
if newTimestamp < currentTime - 0.05 * self.args.intervalMillis:
print(
"Can't keep up ingestion to the desired inter-event interval. Expected interval: {} ms. Actual: {} ms. Consider increasing concurrency or processes."
.format(self.args.intervalMillis,
currentTime - timestamp))
## Move time forward.
timestamp = getTimestampMillis()
else:
timestamp = newTimestamp
## Check if we are ingesting too fast, then slow down.
if timestamp > currentTime - 1000:
## Slow down
sleepTimeSecs = int(
(timestamp - currentTime) / 1000)
print("Thread {} sleeping for {} secs".format(
self.threadId, sleepTimeSecs))
time.sleep(sleepTimeSecs)
now = datetime.datetime.now()
print(
"Resetting to first series from thread: [{}] at time {}. Timestamp set to: {}."
.format(self.threadId,
now.strftime("%Y-%m-%d %H:%M:%S"), timestamp))
localSeriesId = seriesId
localTimestamp = timestamp
if localSeriesId < self.numMetrics:
dimensions = model.createDimensionsEntry(
self.dimensionMetrics[localSeriesId],
addReqId=addReqIdAsDim)
records = model.createRandomMetrics(localSeriesId,
dimensions,
localTimestamp,
"MILLISECONDS",
self.highUtilizationHosts,
self.lowUtilizationHosts,
wide=self.args.wide,
addReqId=addReqIdAsMeasure)
else:
dimensions = model.createDimensionsEntry(
self.dimensionEvents[localSeriesId - self.numMetrics],
addReqId=addReqIdAsDim)
records = model.createRandomEvent(dimensions,
localTimestamp,
"MILLISECONDS",
wide=self.args.wide,
addReqId=addReqIdAsMeasure)
if self.args.batchWrites:
if len(writeRecordsBatch) + len(
records) <= self.args.batchSize:
writeRecordsBatch.extend(records)
## Generate more data, unless we're wrapping around, at which point, drain any pending records.
if localSeriesId < self.numMetrics + self.numEvents:
continue
else:
## transfer a subset of values from the records produced into the batch
spaceRemaining = self.args.batchSize - len(
writeRecordsBatch)
assert (spaceRemaining < len(records))
## Transfer 0 - spaceRemaining - 1 to be written with this batch, and spaceRemaining - end in the next batch
## If spaceRemaining is 0, then just write what we have accumulated so far
if spaceRemaining > 0:
writeRecordsBatch.extend(records[0:spaceRemaining])
## The batch is full, now we issue the write record request.
recordsToWrite.clear()
recordsToWrite.extend(writeRecordsBatch)
writeRecordsBatch.clear()
writeRecordsBatch.extend(records[spaceRemaining:])
else:
recordsToWrite.clear()
recordsToWrite.extend(records)
idx += 1
start = timer()
try:
writeResult = tswrite.writeRecords(self.client,
self.databaseName,
self.tableName,
recordsToWrite)
self.recordsWritten += len(recordsToWrite)
self.success += 1
except Exception as e:
print(e)
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type,
exc_value,
exc_traceback,
limit=2,
file=sys.stdout)
requestId = "RequestId: {}".format(
e.response['ResponseMetadata']['RequestId'])
print(requestId)
print(json.dumps(dimensions, indent=2))
print(json.dumps(records, indent=2))
continue
finally:
self.count += 1
end = timer()
cur = end - start
self.digest.update(cur)
self.sum += cur
## Computing the streaming M^2 (squared distance from mean)
delta = cur - mean
mean += delta / self.count
squared += delta * (cur - mean)
if self.count > 1:
self.variance = float(squared / (self.count - 1))
requestId = writeResult['ResponseMetadata']['RequestId']
if idx % 1000 == 0:
now = datetime.datetime.now()
print(
"{}. {}. {}. Last RequestId: {}. Avg={:,}, Stddev={:,}, 50thPerc={:,}, 90thPerc={:,}, 99thPerc={:,}. Records written: {}"
.format(self.threadId, idx,
now.strftime("%Y-%m-%d %H:%M:%S"), requestId,
round(self.sum / self.count, 3),
round(math.sqrt(self.variance), 3),
round(self.digest.percentile(50), 3),
round(self.digest.percentile(90), 3),
round(self.digest.percentile(99), 3),
self.recordsWritten))
def interrupt(self):
print("Interrupting thread: ", self.threadId)
self.sigInt = True
def ingestRecordsMultiProc(dimensionsMetrics, dimensionsEvents, args):
## Register sigint handler
signal.signal(signal.SIGINT, signalHandlerMultiProc)
numHosts = len(dimensionsMetrics)
remainder = numHosts % args.processes
startId = 0
ingestionStart = timer()
for processId in range(1, args.processes + 1):
endId = startId + int(
numHosts / args.processes) + (1 if remainder > 0 else 0)
if endId > numHosts:
print(
"Number of processes more than number of hosts, skipping process creation"
)
break
print("Starting process {} with host ranges: [{}, {}]".format(
processId, startId, endId - 1))
## Select a subset of hosts
dimensionsMetricsLocal = dimensionsMetrics[startId:endId]
dimensionsMetricsSet = set()
for dim in dimensionsMetricsLocal:
dimensionsMetricsSet.add(
(dim.region, dim.cell, dim.silo, dim.availability_zone,
dim.microservice_name, dim.instance_name))
dimensionsEventsLocal = list()
## Select the dimension events for the hosts selected above.
for dim in dimensionsEvents:
host = (dim.region, dim.cell, dim.silo, dim.availability_zone,
dim.microservice_name, dim.instance_name)
if host in dimensionsMetricsSet:
dimensionsEventsLocal.append(dim)
print(
"Starting process {} with host ranges: [{}, {}]. Metrics: {}. Events: {}"
.format(processId, startId, endId - 1, len(dimensionsMetricsLocal),
len(dimensionsEventsLocal)))
lowUtilizationHosts, highUtilizationHosts = initializeHighAndLowUtilizationHosts(
len(dimensionsMetricsLocal))
parentConn, childConn = multiprocessing.Pipe()
manager = multiprocessing.Manager()
event = manager.Event()
process = MultiProcessIngestWorker(
processId, args, dimensionsMetricsLocal, dimensionsEventsLocal,
highUtilizationHosts, lowUtilizationHosts, childConn, event)
process.start()
processes.append((process, parentConn, event))
remainder -= 1
startId = endId
success = 0
count = 0
recordsWritten = 0
totalLatency = 0.0
aggregatedDigests = TDigest()
pooledVariance = 0.0
for p, conn, event in processes:
output = conn.recv()
p.join()
if output == None:
continue
success += output.success
## Pool the variance.
if count == 0:
pooledVariance = output.variance
else:
pooledVariance = ((count - 1) * pooledVariance +
(output.count - 1) * output.variance) / (
(count - 1) + (output.count - 1))
count += output.count
recordsWritten += output.records
aggregatedDigests += output.digest
totalLatency += output.sum
print(
"[OVERALL] Total={:,}, Success={:,}, Avg={:,}, Stddev={:,}, 50thPerc={:,}, 90thPerc={:,}, 99thPerc={:,}. Records written: {}"
.format(count, success, round(totalLatency / count, 3),
round(math.sqrt(pooledVariance), 3),
round(aggregatedDigests.percentile(50), 3),
round(aggregatedDigests.percentile(90), 3),
round(aggregatedDigests.percentile(99), 3), recordsWritten))
ingestionEnd = timer()
print("Total time to ingest: {:,} seconds. TPS: {:,}, Records/sec: {:,}".
format(round(ingestionEnd - ingestionStart, 2),
round(count / (ingestionEnd - ingestionStart), 2),
round(recordsWritten / (ingestionEnd - ingestionStart), 2)))
def run(self):
global lock
global seriesId
global timestamp
with lock:
## Randomly pick a series ID to start for this process.
seriesId = random.randint(
0,
len(self.dimensionEvents) + len(self.dimensionMetrics) - 1)
timestamp = getTimestampMillis()
print("Process {} using start series ID: {}".format(
self.processId, seriesId))
## Register sigint handler
signal.signal(signal.SIGINT, signalHandler)
overallSummary = None
ingestionStart = timer()
try:
for threadId in range(self.args.concurrency):
threadIdStr = "{}-{}".format(self.processId, threadId + 1)
print("Starting ThreadId: {}".format(threadIdStr))
thread = IngestionThread(threadIdStr, self.args,
self.dimensionMetrics,
self.dimensionEvents,
self.highUtilizationHosts,
self.lowUtilizationHosts, self.event)
thread.start()
self.threads.append(thread)
success = 0
count = 0
recordsWritten = 0
totalLatency = 0.0
aggregatedDigests = TDigest()
pooledVariance = 0.0
for t in self.threads:
t.join()
success += t.success
## Pool the variance.
if count == 0:
pooledVariance = t.variance
else:
pooledVariance = ((count - 1) * pooledVariance +
(t.count - 1) * t.variance) / (
(count - 1) + (t.count - 1))
count += t.count
recordsWritten += t.recordsWritten
aggregatedDigests += t.digest
totalLatency += t.sum
print(
"[Process: {}] Total={:,}, Success={:,}, Avg={:,}, Stddev={:,}, 50thPerc={:,}, 90thPerc={:,}, 99thPerc={:,}. Records written: {}"
.format(self.processId, count, success,
round(totalLatency / count, 3),
round(math.sqrt(pooledVariance), 3),
round(aggregatedDigests.percentile(50), 3),
round(aggregatedDigests.percentile(90), 3),
round(aggregatedDigests.percentile(99), 3),
recordsWritten))
overallSummary = IngestionSummaryStats(aggregatedDigests, count,
success, totalLatency,
pooledVariance,
recordsWritten)
ingestionEnd = timer()
print("Total time to ingest: {:,} seconds".format(
round(ingestionEnd - ingestionStart, 2)))
finally:
self.conn.send(overallSummary)
digest = TDigest()
wallet = simWallet()
wallet.print_wallet()
initial_value = wallet.estimate_total()
print('Initial wallet value is {} BTC.'.format(initial_value), flush=True)
while True:
current_price = wallet.update_price()
digest.update(current_price)
digest_value = digest.percentile(15)
print('\n\nCurrent BNB/BTC price is {}. Digest value is {}'.format(
current_price, digest_value),
flush=True)
if current_price > 1.1 * digest_value:
wallet.buy_bnb(1)
if current_price < 0.9 * digest_value:
wallet.sell_bnb(1)
percent = int(wallet.estimate_total() / initial_value * 100)
print('\nCurrent wallet value is {}% of initial'.format(percent),
flush=True)
import json
start_pos = 0
with open(fn, 'r') as f:
while True:
try:
obj = json.load(f)
yield obj
return
except json.JSONDecodeError as e:
f.seek(start_pos)
json_str = f.read(e.pos)
obj = json.loads(json_str)
start_pos += e.pos
yield obj
final_digest = TDigest()
json_object = stream_read_json('./metric-result-no-presumed-revenue.json')
for num, json_list in enumerate(json_object):
num_list = pyjq.all('.[] | .metric', json_list)
digest = TDigest()
digest.batch_update(num_list)
print(digest.percentile(50))
final_digest = final_digest + digest
print('final: ' + str(final_digest.percentile(25)))
print('final: ' + str(final_digest.percentile(50)))
print('final: ' + str(final_digest.percentile(75)))
print('final: ' + str(final_digest.percentile(90)))
class Percentiles(DataFrameModule):
parameters = [('percentiles', object, [0.25, 0.5, 0.75]),
('history', np.dtype(int), 3)]
def __init__(self, column, percentiles=None, **kwds):
if not column:
raise ProgressiveError('Need a column name')
self._add_slots(kwds,'input_descriptors',
[SlotDescriptor('df', type=pd.DataFrame)])
super(Percentiles, self).__init__(dataframe_slot='percentiles', **kwds)
self._column = column
self.default_step_size = 1000
self.tdigest = TDigest()
if percentiles is None:
percentiles = np.array([0.25, 0.5, 0.75])
else:
# get them all to be in [0, 1]
percentiles = np.asarray(percentiles)
if (percentiles > 1).any():
percentiles = percentiles / 100.0
msg = ("percentiles should all be in the interval [0, 1]. "
"Try {0} instead.")
raise ValueError(msg.format(list(percentiles)))
if (percentiles != 0.5).all(): # median isn't included
lh = percentiles[percentiles < .5]
uh = percentiles[percentiles > .5]
percentiles = np.hstack([lh, 0.5, uh])
self._percentiles = percentiles
self.schema = [(_pretty_name(x), np.dtype(float), np.nan) for x in self._percentiles]
self.schema.append(DataFrameModule.UPDATE_COLUMN_DESC)
self._df = create_dataframe(self.schema)
def is_ready(self):
if self.get_input_slot('df').has_created():
return True
return super(Percentiles, self).is_ready()
def run_step(self,run_number,step_size,howlong):
dfslot = self.get_input_slot('df')
dfslot.update(run_number)
if dfslot.has_updated() or dfslot.has_deleted():
dfslot.reset()
dfslot.update(run_number)
self.tdigest = TDigest() # reset
indices = dfslot.next_created(step_size)
steps = indices_len(indices)
if steps == 0:
return self._return_run_step(self.state_blocked, steps_run=steps)
input_df = dfslot.data()
with dfslot.lock:
x = self.filter_columns(input_df, fix_loc(indices))
self.tdigest.batch_update(x)
df = self._df
values = []
for p in self._percentiles:
values.append(self.tdigest.percentile(p*100))
values.append(run_number)
with self.lock:
df.loc[run_number] = values
if len(df) > self.params.history:
self._df = df.loc[df.index[-self.params.history:]]
return self._return_run_step(dfslot.next_state(),
steps_run=steps, reads=steps, updates=len(self._df))
def column_summary(series, column_props, delta=0.01):
"""Summarise a numeric column.
Parameters
----------
series : pd.Series
Numeric column.
column_props : TODO
TODO
delta : float
TODO
Returns
-------
TODO
"""
col = series.name
if not column_props[col]["numeric"] or column_props[col]["notnulls"] == 0:
# Series is not numeric or is all NaNs.
return None
logger.debug("column_summary - " + col)
# select non-nulls from column
data = series.dropna()
colresult = {}
for m in ["mean", "min", "max", "std", "sum"]:
val = getattr(data, m)()
if type(val) is np.int64:
colresult[m] = int(val)
else:
colresult[m] = val
colresult["n"] = column_props[col]["notnulls"]
percentiles = [0.1, 1, 10, 25, 50, 75, 90, 99, 99.9]
colresult["percentiles"] = {
perc: np.nanpercentile(series, perc)
for perc in percentiles
}
colresult["median"] = colresult["percentiles"][50]
colresult["iqr"] = (colresult["percentiles"][75] -
colresult["percentiles"][25])
# Compute the t-digest.
logger.debug("column_summary - {} - creating TDigest...".format(col))
digest = TDigest(delta)
digest.batch_update(data)
logger.debug("column_summary - {} - testing log trans...".format(col))
try:
colresult["logtrans"] = bool(_test_logtrans(digest))
except Exception as e:
# Hard to pinpoint problems with the logtrans TDigest.
logger.warning("test_logtrans has failed for column `{}`: {}".format(
col, e))
colresult["logtrans"] = False
if colresult["logtrans"]:
logdigest = TDigest()
for c in digest.C.values():
logdigest.update(np.log(c.mean), c.count)
colresult["logtrans_mean"] = _tdigest_mean(logdigest)
colresult["logtrans_std"] = _tdigest_std(logdigest)
colresult["logtrans_IQR"] = logdigest.percentile(
75) - logdigest.percentile(25)
logger.debug("column_summary - {} - should {}be log-transformed".format(
col, "NOT " if not colresult["logtrans"] else ""))
# Compress and store the t-digest.
digest.delta = delta
digest.compress()
colresult["tdigest"] = [(c.mean, c.count) for c in digest.C.values()]
# Compute histogram
logger.debug("column_summary - {} - computing histogram...".format(col))
if column_props[col]["is_categorical"]:
# Compute frequency table and store as histogram
counts, edges = _compute_histogram_from_frequencies(data)
else:
if colresult["logtrans"]:
counts, log_edges = np.histogram(np.log10(data),
density=False,
bins="fd")
edges = 10**log_edges
else:
counts, edges = np.histogram(data, density=False, bins="fd")
colresult["histogram"] = {
"counts": counts.tolist(),
"bin_edges": edges.tolist(),
}
# Compute KDE
logger.debug("column_summary - {} - computing KDE...".format(col))
bw = _bw_scott(colresult, colresult["n"], colresult["logtrans"], 1)
logger.debug("column_summary - {} - KDE bw: {:.4g}".format(col, bw))
if column_props[col]["is_categorical"]:
kde_x, kde_y = np.zeros(1), np.zeros(1)
else:
coord_range = colresult["min"], colresult["max"]
kde_x, kde_y = _compute_smoothed_histogram(
data, bw, coord_range, logtrans=colresult["logtrans"])
colresult["kde"] = {"x": kde_x.tolist(), "y": kde_y.tolist()}
return {col: colresult, "_columns": [col]}
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
class Percentiles(TableModule):
parameters = [
("percentiles", np.dtype(np.object_), [0.25, 0.5, 0.75]),
("history", np.dtype(int), 3),
]
inputs = [SlotDescriptor("table", type=Table)]
def __init__(self,
column: str,
percentiles: Optional[Union[List[float],
np.ndarray[Any, Any]]] = None,
**kwds: Any) -> None:
if not column:
raise ProgressiveError("Need a column name")
super(Percentiles, self).__init__(**kwds)
self._columns = [column]
self.default_step_size = 1000
self.tdigest = TDigest()
if percentiles is None:
percentiles = np.array([0.25, 0.5, 0.75])
else:
# get them all to be in [0, 1]
percentiles = np.asarray(percentiles)
if (percentiles > 1).any(): # type: ignore
percentiles = percentiles / 100.0
msg = ("percentiles should all be in the interval [0, 1]. "
"Try {0} instead.")
raise ValueError(msg.format(list(percentiles)))
if (percentiles != 0.5).all(): # median isn't included
lh = percentiles[percentiles < 0.5]
uh = percentiles[percentiles > 0.5]
percentiles = np.hstack([lh, 0.5, uh])
self._percentiles = percentiles
self._pername: List[str] = [_pretty_name(x) for x in self._percentiles]
dshape = "{" + ",".join(["%s: real" % n for n in self._pername]) + "}"
self.result = Table(self.generate_table_name("percentiles"),
dshape=dshape,
create=True)
def is_ready(self) -> bool:
slot = self.get_input_slot("table")
if slot is not None and slot.created.any():
return True
return super(Percentiles, self).is_ready()
def reset(self) -> None:
self.tdigest = TDigest()
@process_slot("table", reset_cb="reset")
@run_if_any
def run_step(self, run_number: int, step_size: int,
howlong: float) -> ReturnRunStep:
assert self.context
with self.context as ctx:
dfslot = ctx.table
indices = dfslot.created.next(length=step_size)
steps = indices_len(indices)
if steps == 0:
return self._return_run_step(self.state_blocked,
steps_run=steps)
input_df = dfslot.data()
x = self.filter_columns(input_df, fix_loc(indices))
self.tdigest.batch_update(x[0])
df = self.table
values = {}
for n, p in zip(self._pername, self._percentiles):
values[n] = self.tdigest.percentile(p * 100)
df.add(values)
# with self.lock:
# df.loc[run_number] = values
# if len(df) > self.params.history:
# self._df = df.loc[df.index[-self.params.history:]]
return self._return_run_step(self.next_state(dfslot),
steps_run=steps)
class IngestionThread(threading.Thread):
def __init__(self, threadId, args, dimensionMetrics, dimensionEvents,
highUtilizationHosts, lowUtilizationHosts, event):
threading.Thread.__init__(self)
self.threadId = threadId
self.args = args
self.dimensionMetrics = dimensionMetrics
self.dimensionEvents = dimensionEvents
self.client = tswrite.createWriteClient(args.endpoint,
profile=args.profile)
self.databaseName = args.databaseName
self.tableName = args.tableName
self.numMetrics = len(dimensionMetrics)
self.numEvents = len(dimensionEvents)
self.digest = TDigest(
) ## Use the t-digest to compute the streaming percentiles
self.count = 0
self.success = 0
self.sum = 0.0
self.variance = float('nan')
self.highUtilizationHosts = highUtilizationHosts
self.lowUtilizationHosts = lowUtilizationHosts
self.sigInt = False
self.event = event
def run(self):
global seriesId
global timestamp
global lock
idx = 0
mean = 0.0
squared = 0.0
while True:
with lock:
if self.sigInt == True or sigInt == True or self.event.is_set(
):
print("Thread {} exiting.".format(self.threadId))
break
seriesId += 1
if seriesId >= self.numMetrics + self.numEvents:
## Wrapping around, so move to new timestamp.
seriesId = 0
newTimestamp = timestamp + self.args.intervalMillis
currentTime = getCurrentTimestampMillis()
## Check if the timestamps are falling behind
if newTimestamp < currentTime - 0.05 * self.args.intervalMillis:
print(
"Can't keep up ingestion to the desired inter-event interval. Expected interval: {} ms. Actual: {} ms. Consider increasing concurrency or processes."
.format(self.args.intervalMillis,
currentTime - timestamp))
## Move time forward.
timestamp = getTimestampMillis()
else:
timestamp = newTimestamp
## Check if we are ingesting too fast, then slow down.
if timestamp > currentTime - 1000:
## Slow down
sleepTimeSecs = int(
(timestamp - currentTime) / 1000)
print("Thread {} sleeping for {} secs".format(
self.threadId, sleepTimeSecs))
time.sleep(sleepTimeSecs)
now = datetime.datetime.now()
print(
"Resetting to first series from thread: [{}] at time {}. Timestamp set to: {}."
.format(self.threadId,
now.strftime("%Y-%m-%d %H:%M:%S"), timestamp))
localSeriesId = seriesId
localTimestamp = timestamp
if localSeriesId < self.numMetrics:
commonAttributes = model.createWriteRecordCommonAttributes(
self.dimensionMetrics[localSeriesId])
records = model.createRandomMetrics(seriesId, localTimestamp,
"MILLISECONDS",
self.highUtilizationHosts,
self.lowUtilizationHosts)
else:
commonAttributes = model.createWriteRecordCommonAttributes(
self.dimensionEvents[localSeriesId - self.numMetrics])
records = model.createRandomEvent(localTimestamp,
"MILLISECONDS")
idx += 1
start = timer()
try:
writeResult = tswrite.writeRecords(self.client,
self.databaseName,
self.tableName,
commonAttributes, records)
self.success += 1
except Exception as e:
print(e)
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type,
exc_value,
exc_traceback,
limit=2,
file=sys.stdout)
requestId = "RequestId: {}".format(
e.response['ResponseMetadata']['RequestId'])
print(requestId)
print(json.dumps(commonAttributes, indent=2))
print(json.dumps(records, indent=2))
continue
finally:
self.count += 1
end = timer()
cur = end - start
self.digest.update(cur)
self.sum += cur
## Computing the streaming M^2 (squared distance from mean)
delta = cur - mean
mean += delta / self.count
squared += delta * (cur - mean)
if self.count > 1:
self.variance = float(squared / (self.count - 1))
requestId = writeResult['ResponseMetadata']['RequestId']
if idx % 1000 == 0:
now = datetime.datetime.now()
print(
"{}. {}. {}. Last RequestId: {}. Avg={:,}, Stddev={:,}, 50thPerc={:,}, 90thPerc={:,}, 99thPerc={:,}"
.format(self.threadId, idx,
now.strftime("%Y-%m-%d %H:%M:%S"), requestId,
round(self.sum / self.count, 3),
round(math.sqrt(self.variance), 3),
round(self.digest.percentile(50), 3),
round(self.digest.percentile(90), 3),
round(self.digest.percentile(99), 3)))
def interrupt(self):
print("Interrupting thread: ", self.threadId)
self.sigInt = True
def column_summary(series, column_props, delta=0.01):
"""Summarise a numeric column.
Parameters
----------
series : pd.Series
Numeric column.
column_props : TODO
TODO
delta : float
TODO
Returns
-------
TODO
"""
col = series.name
if not column_props[col]['numeric'] or column_props[col]['notnulls'] == 0:
# Series is not numeric or is all NaNs.
return None
logger.debug('column_summary - ' + col)
# select non-nulls from column
data = series.dropna()
colresult = {}
for m in ['mean', 'min', 'max', 'std', 'sum']:
val = getattr(data, m)()
if type(val) is np.int64:
colresult[m] = int(val)
else:
colresult[m] = val
colresult['n'] = column_props[col]['notnulls']
percentiles = [0.1, 1, 10, 25, 50, 75, 90, 99, 99.9]
colresult['percentiles'] = {
perc: np.nanpercentile(series, perc)
for perc in percentiles
}
colresult['median'] = colresult['percentiles'][50]
colresult['iqr'] = (colresult['percentiles'][75] -
colresult['percentiles'][25])
# Compute the t-digest.
logger.debug('column_summary - {} - creating TDigest...'.format(col))
digest = TDigest(delta)
digest.batch_update(data)
logger.debug('column_summary - {} - testing log trans...'.format(col))
try:
colresult['logtrans'] = bool(_test_logtrans(digest))
except Exception as e:
# Hard to pinpoint problems with the logtrans TDigest.
logger.warning('test_logtrans has failed for column `{}`: {}'.format(
col, e))
colresult['logtrans'] = False
if colresult['logtrans']:
logdigest = TDigest()
for c in digest.C.values():
logdigest.update(np.log(c.mean), c.count)
colresult['logtrans_mean'] = _tdigest_mean(logdigest)
colresult['logtrans_std'] = _tdigest_std(logdigest)
colresult['logtrans_IQR'] = (logdigest.percentile(75) -
logdigest.percentile(25))
logger.debug('column_summary - {} - should {}be log-transformed'.format(
col, 'NOT ' if not colresult['logtrans'] else ''))
# Compress and store the t-digest.
digest.delta = delta
digest.compress()
colresult['tdigest'] = [(c.mean, c.count) for c in digest.C.values()]
# Compute histogram
logger.debug('column_summary - {} - computing histogram...'.format(col))
if column_props[col]['is_categorical']:
# Compute frequency table and store as histogram
counts, edges = _compute_histogram_from_frequencies(data)
else:
if colresult['logtrans']:
counts, log_edges = np.histogram(np.log10(data),
density=False,
bins='fd')
edges = 10**log_edges
else:
counts, edges = np.histogram(data, density=False, bins='fd')
colresult['histogram'] = {
'counts': counts.tolist(),
'bin_edges': edges.tolist()
}
# Compute KDE
logger.debug('column_summary - {} - computing KDE...'.format(col))
bw = _bw_scott(colresult, colresult['n'], colresult['logtrans'], 1)
logger.debug('column_summary - {} - KDE bw: {:.4g}'.format(col, bw))
if column_props[col]['is_categorical']:
kde_x, kde_y = np.zeros(1), np.zeros(1)
else:
coord_range = colresult['min'], colresult['max']
kde_x, kde_y = _compute_smoothed_histogram(
data, bw, coord_range, logtrans=colresult['logtrans'])
colresult['kde'] = {'x': kde_x.tolist(), 'y': kde_y.tolist()}
return {col: colresult, '_columns': [col]}
