upgini 1.2.113a5__py3-none-any.whl → 1.2.113a3974.dev2__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (15) hide show
  1. upgini/__about__.py +1 -1
  2. upgini/autofe/date.py +8 -2
  3. upgini/features_enricher.py +125 -438
  4. upgini/metadata.py +0 -1
  5. upgini/metrics.py +1 -4
  6. upgini/resource_bundle/strings.properties +1 -4
  7. upgini/sampler/base.py +1 -3
  8. upgini/sampler/random_under_sampler.py +8 -18
  9. upgini/utils/deduplicate_utils.py +7 -43
  10. upgini/utils/feature_info.py +0 -5
  11. {upgini-1.2.113a5.dist-info → upgini-1.2.113a3974.dev2.dist-info}/METADATA +1 -1
  12. {upgini-1.2.113a5.dist-info → upgini-1.2.113a3974.dev2.dist-info}/RECORD +14 -15
  13. {upgini-1.2.113a5.dist-info → upgini-1.2.113a3974.dev2.dist-info}/WHEEL +1 -1
  14. upgini/utils/psi.py +0 -294
  15. {upgini-1.2.113a5.dist-info → upgini-1.2.113a3974.dev2.dist-info}/licenses/LICENSE +0 -0
upgini/__about__.py CHANGED
@@ -1 +1 @@
1
- __version__ = "1.2.113a5"
1
+ __version__ = "1.2.113a3974.dev2"
upgini/autofe/date.py CHANGED
@@ -244,7 +244,8 @@ class DateListDiffBounded(DateListDiff, ParametrizedOperator):
244
244
 
245
245
  class DatePercentileBase(PandasOperator, abc.ABC):
246
246
  is_binary: bool = True
247
- output_type: Optional[str] = "float"
247
+ is_categorical: bool = True
248
+ output_type: Optional[str] = "category"
248
249
 
249
250
  date_unit: Optional[str] = None
250
251
 
@@ -254,7 +255,12 @@ class DatePercentileBase(PandasOperator, abc.ABC):
254
255
 
255
256
  bounds = self._get_bounds(left)
256
257
 
257
- return right.index.to_series().apply(lambda i: self._perc(right[i], bounds[i]))
258
+ return (
259
+ right.index.to_series()
260
+ .apply(lambda i: self._perc(right[i], bounds[i]))
261
+ .astype(pd.Int64Dtype())
262
+ .astype("category")
263
+ )
258
264
 
259
265
  @abc.abstractmethod
260
266
  def _get_bounds(self, date_col: pd.Series) -> pd.Series: