upgini 1.2.9__tar.gz → 1.2.9a2__tar.gz

{upgini-1.2.9 → upgini-1.2.9a2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.9
+Version: 1.2.9a2
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -28,7 +28,6 @@ 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-1.2.9 → upgini-1.2.9a2}/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-1.2.9a2/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.9a2"

{upgini-1.2.9 → upgini-1.2.9a2}/src/upgini/__init__.py

@@ -1,7 +1,7 @@
 import os
 
-from upgini.features_enricher import FeaturesEnricher  # noqa: F401
-from upgini.metadata import SearchKey, CVType, RuntimeParameters, ModelTaskType  # noqa: F401
+# from upgini.features_enricher import FeaturesEnricher  # noqa: F401
+# from upgini.metadata import SearchKey, CVType, RuntimeParameters, ModelTaskType  # noqa: F401
 # from .lazy_import import LazyImport
 
 os.environ["SETUPTOOLS_USE_DISTUTILS"] = "stdlib"

{upgini-1.2.9 → upgini-1.2.9a2}/src/upgini/features_enricher.py

@@ -1103,7 +1103,7 @@ class FeaturesEnricher(TransformerMixin):
                             else:
                                 eval_uplift = None
 
-                            # effective_eval_set = eval_set if eval_set is not None else self.eval_set
+                            effective_eval_set = eval_set if eval_set is not None else self.eval_set
                             eval_metrics = {
                                 self.bundle.get("quality_metrics_segment_header"): self.bundle.get(
                                     "quality_metrics_eval_segment"
@@ -1369,7 +1369,6 @@ class FeaturesEnricher(TransformerMixin):
                 + [DateTimeSearchKeyConverter.DATETIME_COL, SYSTEM_RECORD_ID, ENTITY_SYSTEM_RECORD_ID]
             )
         ]
-        self.logger.info(f"Client features column on prepare data for metrics: {client_features}")
 
         filtered_enriched_features = self.__filtered_enriched_features(
             importance_threshold,
@@ -1436,19 +1435,31 @@ class FeaturesEnricher(TransformerMixin):
                 )
 
         fitting_eval_set_dict = {}
-        fitting_x_columns = fitting_X.columns.to_list()
-        self.logger.info(f"Final list of fitting X columns: {fitting_x_columns}")
-        fitting_enriched_x_columns = fitting_enriched_X.columns.to_list()
-        self.logger.info(f"Final list of fitting enriched X columns: {fitting_enriched_x_columns}")
         for idx, eval_tuple in eval_set_sampled_dict.items():
             eval_X_sampled, enriched_eval_X, eval_y_sampled = eval_tuple
             eval_X_sorted, eval_y_sorted = self._sort_by_system_record_id(eval_X_sampled, eval_y_sampled, self.cv)
             enriched_eval_X_sorted, enriched_eval_y_sorted = self._sort_by_system_record_id(
                 enriched_eval_X, eval_y_sampled, self.cv
             )
-            fitting_eval_X = eval_X_sorted[fitting_x_columns].copy()
-            fitting_enriched_eval_X = enriched_eval_X_sorted[fitting_enriched_x_columns].copy()
-
+            fitting_eval_X = eval_X_sorted[client_features].copy()
+            fitting_enriched_eval_X = enriched_eval_X_sorted[
+                client_features + existing_filtered_enriched_features
+            ].copy()
+
+            # # Drop high cardinality features in eval set
+            if len(columns_with_high_cardinality) > 0:
+                fitting_eval_X = fitting_eval_X.drop(columns=columns_with_high_cardinality, errors="ignore")
+                fitting_enriched_eval_X = fitting_enriched_eval_X.drop(
+                    columns=columns_with_high_cardinality, errors="ignore"
+                )
+            # Drop constant features in eval_set
+            if len(constant_columns) > 0:
+                fitting_eval_X = fitting_eval_X.drop(columns=constant_columns, errors="ignore")
+                fitting_enriched_eval_X = fitting_enriched_eval_X.drop(columns=constant_columns, errors="ignore")
+            # Drop datetime features in eval_set
+            if len(datetime_features) > 0:
+                fitting_eval_X = fitting_eval_X.drop(columns=datetime_features, errors="ignore")
+                fitting_enriched_eval_X = fitting_enriched_eval_X.drop(columns=datetime_features, errors="ignore")
             # Convert bool to string in eval_set
             if len(bool_columns) > 0:
                 fitting_eval_X[col] = fitting_eval_X[col].astype(str)
@@ -1669,7 +1680,6 @@ class FeaturesEnricher(TransformerMixin):
         X_sampled = enriched_Xy[x_columns].copy()
         y_sampled = enriched_Xy[TARGET].copy()
         enriched_X = enriched_Xy.drop(columns=[TARGET, EVAL_SET_INDEX], errors="ignore")
-        enriched_X_columns = enriched_X.columns.to_list()
 
         self.logger.info(f"Shape of enriched_X: {enriched_X.shape}")
         self.logger.info(f"Shape of X after sampling: {X_sampled.shape}")
@@ -1684,7 +1694,7 @@ class FeaturesEnricher(TransformerMixin):
             for idx in range(len(eval_set)):
                 eval_X_sampled = enriched_eval_sets[idx + 1][x_columns].copy()
                 eval_y_sampled = enriched_eval_sets[idx + 1][TARGET].copy()
-                enriched_eval_X = enriched_eval_sets[idx + 1][enriched_X_columns].copy()
+                enriched_eval_X = enriched_eval_sets[idx + 1].drop(columns=[TARGET, EVAL_SET_INDEX])
                 eval_set_sampled_dict[idx] = (eval_X_sampled, enriched_eval_X, eval_y_sampled)
 
         self.__cached_sampled_datasets = (
@@ -1763,13 +1773,12 @@ class FeaturesEnricher(TransformerMixin):
             X_sampled = enriched_Xy[x_columns].copy()
             y_sampled = enriched_Xy[TARGET].copy()
             enriched_X = enriched_Xy.drop(columns=[TARGET, EVAL_SET_INDEX])
-            enriched_X_columns = enriched_X.columns.tolist()
 
             for idx in range(len(eval_set)):
                 enriched_eval_xy = enriched_df.query(f"{EVAL_SET_INDEX} == {idx + 1}")
                 eval_x_sampled = enriched_eval_xy[x_columns].copy()
                 eval_y_sampled = enriched_eval_xy[TARGET].copy()
-                enriched_eval_x = enriched_eval_xy[enriched_X_columns].copy()
+                enriched_eval_x = enriched_eval_xy.drop(columns=[TARGET, EVAL_SET_INDEX])
                 eval_set_sampled_dict[idx] = (eval_x_sampled, enriched_eval_x, eval_y_sampled)
         else:
             self.logger.info("Transform without eval_set")

{upgini-1.2.9 → upgini-1.2.9a2}/src/upgini/metrics.py

@@ -10,7 +10,6 @@ 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
@@ -254,7 +253,6 @@ class EstimatorWrapper:
     def _prepare_data(
         self, x: pd.DataFrame, y: pd.Series, groups: Optional[np.ndarray] = None
     ) -> Tuple[pd.DataFrame, np.ndarray, np.ndarray]:
-        self.logger.info(f"Before preparing data columns: {x.columns.to_list()}")
         for c in x.columns:
             if is_numeric_dtype(x[c]):
                 x[c] = x[c].astype(float)
@@ -273,7 +271,6 @@ class EstimatorWrapper:
         else:
             x, y = self._remove_empty_target_rows(x, y)
 
-        self.logger.info(f"After preparing data columns: {x.columns.to_list()}")
         return x, y, groups
 
     def _remove_empty_target_rows(self, x: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, pd.Series]:
@@ -408,6 +405,7 @@ class EstimatorWrapper:
                 estimator = CatBoostWrapper(**kwargs)
             else:
                 try:
+                    from lightgbm import LGBMClassifier, LGBMRegressor
                     if isinstance(estimator, (LGBMClassifier, LGBMRegressor)):
                         estimator = LightGBMWrapper(**kwargs)
                     else:
@@ -495,9 +493,7 @@ class CatBoostWrapper(EstimatorWrapper):
             if x[name].nunique() > 1:
                 unique_cat_features.append(name)
             else:
-                self.logger.info(f"Drop column {name} on preparing data for fit")
                 x = x.drop(columns=name)
-                self.exclude_features.append(name)
         self.cat_features = unique_cat_features
         if (
             hasattr(self.estimator, "get_param")

{upgini-1.2.9 → upgini-1.2.9a2}/src/upgini/utils/features_validator.py

@@ -87,4 +87,4 @@ class FeaturesValidator:
 
     @staticmethod
     def find_constant_features(df: pd.DataFrame) -> List[str]:
-        return [i for i in df if df[i].nunique() <= 1]
+        return [i for i in df if df[i].nunique() == 1]

upgini-1.2.9/src/upgini/__about__.py

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