def test_parse_as_dataframe(self):
my_agg = Aggs(sample.EXPECTED_AGG_QUERY, mapping=MAPPING)
df = Aggregations(
data=sample.ES_AGG_RESPONSE,
aggs=my_agg,
index=None,
client=None,
query=None,
).serialize_as_dataframe()
self.assertIsInstance(df, pd.DataFrame)
self.assertEqual(set(df.index.names),
{"classification_type", "global_metrics.field.name"})
self.assertEqual(set(df.columns),
{"avg_f1_micro", "avg_nb_classes", "doc_count"})
self.assertEqual(
df.index.to_list(),
[
("multilabel", "ispracticecompatible"),
("multilabel", "gpc"),
("multilabel", "preservationmethods"),
("multiclass", "kind"),
("multiclass", "gpc"),
],
)
self.assertEqual(
df.to_dict(orient="rows"),
[
{
"avg_f1_micro": 0.72,
"avg_nb_classes": 18.71,
"doc_count": 128
},
{
"avg_f1_micro": 0.95,
"avg_nb_classes": 183.21,
"doc_count": 119
},
{
"avg_f1_micro": 0.8,
"avg_nb_classes": 9.97,
"doc_count": 76
},
{
"avg_f1_micro": 0.89,
"avg_nb_classes": 206.5,
"doc_count": 370
},
{
"avg_f1_micro": 0.93,
"avg_nb_classes": 211.12,
"doc_count": 198
},
],
)
def test_parse_as_dataframe(self):
my_agg = Aggs(sample.EXPECTED_AGG_QUERY, mappings=MAPPINGS)
df = Aggregations(data=sample.ES_AGG_RESPONSE,
_search=Search().aggs(my_agg)).to_dataframe(
grouped_by="global_metrics.field.name")
self.assertIsInstance(df, pd.DataFrame)
self.assertEqual(set(df.index.names),
{"classification_type", "global_metrics.field.name"})
self.assertEqual(set(df.columns),
{"avg_f1_micro", "avg_nb_classes", "doc_count"})
self.assertEqual(
df.to_dict(orient="index"),
{
("multiclass", "gpc"): {
"avg_f1_micro": 0.93,
"avg_nb_classes": 211.12,
"doc_count": 198,
},
("multiclass", "kind"): {
"avg_f1_micro": 0.89,
"avg_nb_classes": 206.5,
"doc_count": 370,
},
("multilabel", "ispracticecompatible"): {
"avg_f1_micro": 0.72,
"avg_nb_classes": 18.71,
"doc_count": 128,
},
("multilabel", "preservationmethods"): {
"avg_f1_micro": 0.8,
"avg_nb_classes": 9.97,
"doc_count": 76,
},
},
)