upgini 1.2.113a3974.dev2__py3-none-any.whl → 1.2.114a1__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.
- upgini/__about__.py +1 -1
- upgini/dataset.py +3 -1
- upgini/features_enricher.py +462 -136
- upgini/metadata.py +1 -0
- upgini/metrics.py +6 -2
- upgini/resource_bundle/strings.properties +4 -1
- upgini/sampler/base.py +3 -1
- upgini/sampler/random_under_sampler.py +18 -8
- upgini/utils/deduplicate_utils.py +43 -7
- upgini/utils/feature_info.py +5 -0
- upgini/utils/psi.py +294 -0
- {upgini-1.2.113a3974.dev2.dist-info → upgini-1.2.114a1.dist-info}/METADATA +31 -17
- {upgini-1.2.113a3974.dev2.dist-info → upgini-1.2.114a1.dist-info}/RECORD +15 -14
- {upgini-1.2.113a3974.dev2.dist-info → upgini-1.2.114a1.dist-info}/WHEEL +1 -1
- {upgini-1.2.113a3974.dev2.dist-info → upgini-1.2.114a1.dist-info}/licenses/LICENSE +0 -0
upgini/__about__.py
CHANGED
@@ -1 +1 @@
|
|
1
|
-
__version__ = "1.2.
|
1
|
+
__version__ = "1.2.114a1"
|
upgini/dataset.py
CHANGED
@@ -343,7 +343,9 @@ class Dataset:
|
|
343
343
|
if col in mandatory_columns:
|
344
344
|
self.data["valid_mandatory"] = self.data["valid_mandatory"] & self.data[f"{col}_is_valid"]
|
345
345
|
|
346
|
-
|
346
|
+
# Use stable pandas API across versions: Series.unique keeps order
|
347
|
+
# and collapses multiple NaNs into a single NaN
|
348
|
+
invalid_values = self.data.loc[self.data[f"{col}_is_valid"] == 0, col].unique().tolist()[:5]
|
347
349
|
valid_share = self.data[f"{col}_is_valid"].sum() / nrows
|
348
350
|
original_col_name = self.columns_renaming[col]
|
349
351
|
validation_stats[original_col_name] = {}
|