upgini 1.2.9a3__tar.gz → 1.2.9a99__tar.gz

{upgini-1.2.9a3 → upgini-1.2.9a99}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.9a3
+Version: 1.2.9a99
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -28,6 +28,7 @@ Requires-Dist: fastparquet>=0.8.1
 Requires-Dist: ipywidgets>=8.1.0
 Requires-Dist: jarowinkler>=2.0.0
 Requires-Dist: levenshtein>=0.25.1
+Requires-Dist: lightgbm>=3.3.2
 Requires-Dist: numpy<=1.26.4,>=1.19.0
 Requires-Dist: pandas<3.0.0,>=1.1.0
 Requires-Dist: pydantic<3.0.0,>1.0.0

{upgini-1.2.9a3 → upgini-1.2.9a99}/pyproject.toml

@@ -38,7 +38,7 @@ dependencies = [
     "catboost>=1.0.3",
     "fastparquet>=0.8.1",
     "ipywidgets>=8.1.0",
-
+    "lightgbm>=3.3.2",
     "numpy>=1.19.0,<=1.26.4",
     "pandas>=1.1.0,<3.0.0",
     "pydantic>1.0.0,<3.0.0",

upgini-1.2.9a99/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.9a99"

{upgini-1.2.9a3 → upgini-1.2.9a99}/src/upgini/features_enricher.py

@@ -2531,7 +2531,7 @@ class FeaturesEnricher(TransformerMixin):
         features_columns = [c for c in df.columns if c not in non_feature_columns]
 
         features_to_drop = FeaturesValidator(self.logger).validate(
-            df, features_columns, self.generate_features, columns_renaming, self.warning_counter
+            df, features_columns, self.generate_features, self.warning_counter
         )
         self.fit_dropped_features.update(features_to_drop)
         df = df.drop(columns=features_to_drop)
@@ -2657,7 +2657,7 @@ class FeaturesEnricher(TransformerMixin):
             and len(self._search_task.unused_features_for_generation) > 0
         ):
             unused_features_for_generation = [
-                columns_renaming.get(col) or col for col in self._search_task.unused_features_for_generation
+                dataset.columns_renaming.get(col) or col for col in self._search_task.unused_features_for_generation
             ]
             msg = self.bundle.get("features_not_generated").format(unused_features_for_generation)
             self.logger.warning(msg)

{upgini-1.2.9a3 → upgini-1.2.9a99}/src/upgini/metrics.py

@@ -10,6 +10,7 @@ import catboost
 import numpy as np
 import pandas as pd
 from catboost import CatBoostClassifier, CatBoostRegressor
+from lightgbm import LGBMClassifier, LGBMRegressor
 from numpy import log1p
 from pandas.api.types import is_numeric_dtype
 from sklearn.metrics import check_scoring, get_scorer, make_scorer, roc_auc_score
@@ -405,7 +406,6 @@ class EstimatorWrapper:
                 estimator = CatBoostWrapper(**kwargs)
             else:
                 try:
-                    from lightgbm import LGBMClassifier, LGBMRegressor
                     if isinstance(estimator, (LGBMClassifier, LGBMRegressor)):
                         estimator = LightGBMWrapper(**kwargs)
                     else:
@@ -486,7 +486,7 @@ class CatBoostWrapper(EstimatorWrapper):
 
         # Find rest categorical features
         self.cat_features = _get_cat_features(x, self.text_features, embedding_features)
-        # x = fill_na_cat_features(x, self.cat_features)
+        x = fill_na_cat_features(x, self.cat_features)  # Was commented
         unique_cat_features = []
         for name in self.cat_features:
             # Remove constant categorical features
@@ -536,7 +536,7 @@ class CatBoostWrapper(EstimatorWrapper):
             x, emb_columns = self.group_embeddings(x)
             params["embedding_features"] = emb_columns
         if self.cat_features:
-            # x = fill_na_cat_features(x, self.cat_features)
+            x = fill_na_cat_features(x, self.cat_features)  # Was commented
             params["cat_features"] = self.cat_features
 
         return x, y, params

{upgini-1.2.9a3 → upgini-1.2.9a99}/src/upgini/utils/features_validator.py

@@ -1,6 +1,6 @@
 import logging
 from logging import Logger
-from typing import Dict, List, Optional
+from typing import List, Optional
 
 import pandas as pd
 from pandas.api.types import is_integer_dtype, is_object_dtype, is_string_dtype
@@ -22,7 +22,6 @@ class FeaturesValidator:
         df: pd.DataFrame,
         features: List[str],
         features_for_generate: Optional[List[str]],
-        columns_renaming: Dict[str, str],
         warning_counter: WarningCounter,
     ) -> List[str]:
         # one_hot_encoded_features = []
@@ -64,7 +63,7 @@ class FeaturesValidator:
 
         high_cardinality_features = self.find_high_cardinality(df[features])
         if features_for_generate:
-            high_cardinality_features = [f for f in high_cardinality_features if columns_renaming[f] not in features_for_generate]
+            high_cardinality_features = [f for f in high_cardinality_features if f not in features_for_generate]
         if high_cardinality_features:
             msg = bundle.get("high_cardinality_features").format(high_cardinality_features)
             print(msg)

upgini-1.2.9a3/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.9a3"