def populate_measurements(self, specs):
start = before_now(minutes=5)
for spec in specs:
spec = HistogramSpec(*spec)
for field, count in spec.fields:
if not is_measurement(field):
continue
measurement = get_measurement_name(field)
for i in range(count):
data = deepcopy(self.data)
data["timestamp"] = iso_format(start)
data["start_timestamp"] = iso_format(start - timedelta(seconds=i))
value = random.random() * (spec.end - spec.start) + spec.start
data["transaction"] = "/measurement/{}/value/{}".format(measurement, value)
data["measurements"] = {measurement: {"value": value}}
self.store_event(data, self.project.id)
def histogram_query(
fields,
user_query,
params,
num_buckets,
precision=0,
min_value=None,
max_value=None,
data_filter=None,
referrer=None,
):
"""
API for generating histograms for numeric columns.
A multihistogram is possible only if the columns are all measurements.
The resulting histograms will have their bins aligned.
:param [str] fields: The list of fields for which you want to generate histograms for.
:param str user_query: Filter query string to create conditions from.
:param {str: str} params: Filtering parameters with start, end, project_id, environment
:param int num_buckets: The number of buckets the histogram should contain.
:param int precision: The number of decimal places to preserve, default 0.
:param float min_value: The minimum value allowed to be in the histogram.
If left unspecified, it is queried using `user_query` and `params`.
:param float max_value: The maximum value allowed to be in the histogram.
If left unspecified, it is queried using `user_query` and `params`.
:param str data_filter: Indicate the filter strategy to be applied to the data.
"""
multiplier = int(10**precision)
if max_value is not None:
# We want the specified max_value to be exclusive, and the queried max_value
# to be inclusive. So we adjust the specified max_value using the multiplier.
max_value -= 0.1 / multiplier
min_value, max_value = find_histogram_min_max(fields, min_value, max_value,
user_query, params,
data_filter)
key_column = None
conditions = []
if len(fields) > 1:
key_column = "array_join(measurements_key)"
key_alias = get_function_alias(key_column)
measurements = []
for f in fields:
measurement = get_measurement_name(f)
if measurement is None:
raise InvalidSearchQuery(
u"multihistogram expected all measurements, received: {}".
format(f))
measurements.append(measurement)
conditions.append([key_alias, "IN", measurements])
histogram_params = find_histogram_params(num_buckets, min_value, max_value,
multiplier)
histogram_column = get_histogram_column(fields, key_column,
histogram_params)
histogram_alias = get_function_alias(histogram_column)
if min_value is None or max_value is None:
return normalize_histogram_results(fields, key_column,
histogram_params, {"data": []})
# make sure to bound the bins to get the desired range of results
if min_value is not None:
min_bin = histogram_params.start_offset
conditions.append([histogram_alias, ">=", min_bin])
if max_value is not None:
max_bin = histogram_params.start_offset + histogram_params.bucket_size * num_buckets
conditions.append([histogram_alias, "<=", max_bin])
columns = [] if key_column is None else [key_column]
results = query(
selected_columns=columns + [histogram_column, "count()"],
conditions=conditions,
query=user_query,
params=params,
orderby=[histogram_alias],
limit=len(fields) * num_buckets,
referrer=referrer,
auto_fields=True,
use_aggregate_conditions=True,
functions_acl=["array_join", "histogram"],
)
return normalize_histogram_results(fields, key_column, histogram_params,
results)
