def transform_to_fixed_size_buckets(percentages_histogram,
expected_buckets=200):
"""
Returns for given histogram to a normalized histogram in term of buckets.
:param percentages_histogram: Histogram as returned per middleware in format
:param expected_buckets: Number of buckets expected in the histogram
:return: Histogram which has 100µs buckets between [0, expected_buckets/10 - 0.1] ms
"""
result = {}
# Default initialize the result-dictionary to our needs
for i in range(expected_buckets):
result[StdLib.get_rounded_double(i / 10)] = 0.0
sum_beyond_range = 0
# Fill in the observed values to the dictionary
for item in percentages_histogram:
if item >= expected_buckets / 10:
# Accumulate anything above X milliseconds
sum_beyond_range += percentages_histogram.get(item)
continue
index = StdLib.get_rounded_double(item)
result[index] = percentages_histogram.get(item)
last_bucket = StdLib.get_rounded_double((expected_buckets - 1) / 10)
result[last_bucket] += sum_beyond_range
return result
def transform_to_fixed_size_buckets(percentages_histogram,
expected_buckets=200):
"""
Returns for given histogram to a normalized histogram in term of buckets.
:param percentages_histogram: Histogram as returned per memtier in format
:param expected_buckets: Number of buckets expected in the histogram
:return: Histogram which has 100µs buckets between [0, expected_buckets/10 - 0.1] ms
"""
result = {}
# Default initialize the result-dictionary to our needs
for i in range(expected_buckets):
result[StdLib.get_rounded_double(i / 10)] = 0.0
sum_below_range = 0
sum_beyond_range = 0
current_below = 0
# Fill in the observed values to the dictionary
for item in percentages_histogram:
if item >= expected_buckets / 10:
# Accumulate anything above X milliseconds
sum_beyond_range += percentages_histogram.get(item)
continue
if item <= 1:
if int(item * 10) - int(current_below * 10) > 0.99:
if not current_below == 0.0:
index = StdLib.get_rounded_double(
int(current_below * 10) / 10)
result[index] = sum_below_range
sum_below_range = percentages_histogram.get(item)
current_below = item
if item == 1:
current_below = 0
sum_below_range = 0
index = StdLib.get_rounded_double(item)
result[index] = percentages_histogram.get(item)
else:
sum_below_range += percentages_histogram.get(item)
continue
# Try to expand buckets and divide respective percentages evenly -> uniform distribution inside buckets
bucket_count = int(
math.pow(10,
math.ceil(math.log10(item + 0.1)) - 1))
bucket_value = StdLib.safe_div(percentages_histogram.get(item),
bucket_count)
for i in range(bucket_count):
index = StdLib.get_rounded_double(item + i / 10)
result[index] = bucket_value
last_bucket = StdLib.get_rounded_double((expected_buckets - 1) / 10)
result[last_bucket] += sum_beyond_range
return result