def _metric_agg_series(
self,
query_compiler: "QueryCompiler",
agg: List,
numeric_only: Optional[bool] = None,
) -> pd.Series:
results = self._metric_aggs(query_compiler,
agg,
numeric_only=numeric_only)
if numeric_only:
return build_pd_series(results,
index=results.keys(),
dtype=np.float64)
else:
# If all results are float convert into float64
if all(isinstance(i, float) for i in results.values()):
dtype = np.float64
# If all results are int convert into int64
elif all(isinstance(i, int) for i in results.values()):
dtype = np.int64
# If single result is present consider that datatype instead of object
elif len(results) <= 1:
dtype = None
else:
dtype = "object"
return build_pd_series(results, index=results.keys(), dtype=dtype)
def test_empty_series_dtypes():
with warnings.catch_warnings(record=True) as w:
s = build_pd_series({})
assert s.dtype == EMPTY_SERIES_DTYPE
assert w == []
# Ensure that a passed-in dtype isn't ignore
# even if the result is empty.
with warnings.catch_warnings(record=True) as w:
s = build_pd_series({}, dtype=np.int32)
assert np.int32 != EMPTY_SERIES_DTYPE
assert s.dtype == np.int32
assert w == []
def count(self, query_compiler):
query_params, post_processing = self._resolve_tasks(query_compiler)
# Elasticsearch _count is very efficient and so used to return results here. This means that
# data frames that have restricted size or sort params will not return valid results
# (_count doesn't support size).
# Longer term we may fall back to pandas, but this may result in loading all index into memory.
if self._size(query_params, post_processing) is not None:
raise NotImplementedError(
f"Requesting count with additional query and processing parameters "
f"not supported {query_params} {post_processing}")
# Only return requested field_names
fields = query_compiler.get_field_names(include_scripted_fields=False)
counts = {}
for field in fields:
body = Query(query_params.query)
body.exists(field, must=True)
field_exists_count = query_compiler._client.count(
index=query_compiler._index_pattern,
body=body.to_count_body())["count"]
counts[field] = field_exists_count
return build_pd_series(data=counts, index=fields)
def _terms_aggs(
self, query_compiler: "QueryCompiler", func: str, es_size: int
) -> pd.Series:
"""
Parameters
----------
es_size: int, default None
Parameter used by Series.value_counts()
Returns
-------
pandas.Series
Series containing results of `func` applied to the field_name(s)
"""
query_params, post_processing = self._resolve_tasks(query_compiler)
size = self._size(query_params, post_processing)
if size is not None:
raise NotImplementedError(
f"Can not count field matches if size is set {size}"
)
# Get just aggregatable field_names
aggregatable_field_names = query_compiler._mappings.aggregatable_field_names()
body = Query(query_params.query)
for field in aggregatable_field_names.keys():
body.terms_aggs(field, func, field, es_size=es_size)
response = query_compiler._client.search(
index=query_compiler._index_pattern, size=0, body=body.to_search_body()
)
results = {}
for key in aggregatable_field_names.keys():
# key is aggregatable field, value is label
# e.g. key=category.keyword, value=category
for bucket in response["aggregations"][key]["buckets"]:
results[bucket["key"]] = bucket["doc_count"]
try:
# get first value in dict (key is .keyword)
name = list(aggregatable_field_names.values())[0]
except IndexError:
name = None
return build_pd_series(results, name=name)
def mad(self, query_compiler, numeric_only=True):
results = self._metric_aggs(query_compiler, ["mad"],
numeric_only=numeric_only)
return build_pd_series(results, index=results.keys())
def nunique(self, query_compiler):
results = self._metric_aggs(query_compiler, ["nunique"],
numeric_only=False)
return build_pd_series(results, index=results.keys())
