upgini 1.2.9a3__py3-none-any.whl → 1.2.9a99__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.9a3"
+__version__ = "1.2.9a99"

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/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/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.dist-info → upgini-1.2.9a99.dist-info}/METADATA

@@ -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.dist-info → upgini-1.2.9a99.dist-info}/RECORD

@@ -1,13 +1,13 @@
-upgini/__about__.py,sha256=r3QIbFOSJMAs6ONA-HrOMmqgGlWw7zq9CfF__Tf43EE,24
+upgini/__about__.py,sha256=GPfVcGLNLsPn7GOGxyUAePD4tmtosYALOutsKNehkhs,25
 upgini/__init__.py,sha256=M64LwQTBa-5Jz24Zm2h8rWwlKQQ1J8nP7gGgIciS0WU,589
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=olZ-OHSfBNoBSCo7R5t7uCLukI2nO7afpx_A-HCiJLk,31067
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=cnNZ5e_uyU5f3cHumeeVBI1PZFn3DKcuTNBz0XRCEDU,188144
+upgini/features_enricher.py,sha256=J5-bn07iaJSXVN8COeu2RbDqZ4NTPd1L27HePaNh52o,188134
 upgini/http.py,sha256=21asexflvavydzCOONJDGQBtQanCElrbnqLXakJ9Cu8,42880
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=osmzdNESeh7yP3BZday6N9Q3eaIHfzhhRM1d6NSgcf0,11223
-upgini/metrics.py,sha256=AYVvcqSqO_UWwFIby0gcqSDNLiIoy6EU3pa8aUBUQ4k,30946
+upgini/metrics.py,sha256=d4r20WhuYxsdSwDXU0M0Ny40K3QBuQuckOOvOlat48Y,30956
 upgini/search_task.py,sha256=qxUxAD-bed-FpZYmTB_4orW7YJsW_O6a1TcgnZIRFr4,17307
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=ddSKUK_-eGJB3NgrqOMoWJU-OxQ253WsNLp8aqJkaIM,1389
@@ -47,7 +47,7 @@ upgini/utils/deduplicate_utils.py,sha256=Zvs7zW4QzaERQmJNPrTVf2ZTVBkBLOycFCzyMwt
 upgini/utils/display_utils.py,sha256=A2ouB5eiZ-Kyt9ykYxkLQwyoRPrdYeJymwNTiajtFXs,10990
 upgini/utils/email_utils.py,sha256=j0Ug1R_0AnCg1Y92zIZ4XMwvKo3G5_pcOlBN1OH_gZs,5191
 upgini/utils/fallback_progress_bar.py,sha256=PDaKb8dYpVZaWMroNcOHsTc3pSjgi9mOm0--cOFTwJ0,1074
-upgini/utils/features_validator.py,sha256=Vu-zQ-QoxDG0tQfkqQy_il9dQDkyiZadKBpr6izKAe0,3373
+upgini/utils/features_validator.py,sha256=PgKNt5dyqfErTvjtRNNUS9g7GFqHBtAtnsfA-V5UO1A,3307
 upgini/utils/format.py,sha256=Yv5cvvSs2bOLUzzNu96Pu33VMDNbabio92QepUj41jU,243
 upgini/utils/ip_utils.py,sha256=Q6vb7Sr5Khx3Sq3eENjW2qCXKej_S5jZbneH6zEOkzQ,5171
 upgini/utils/phone_utils.py,sha256=IrbztLuOJBiePqqxllfABWfYlfAjYevPhXKipl95wUI,10432
@@ -57,7 +57,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=BVtDmrmFMKerSUWaNOIEdzsYHIFiODdpnWbE50QDPDc,7864
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.2.9a3.dist-info/METADATA,sha256=bpMUUAhh6v9AbRs2WD7Ns4PGK2kR61jPm8ITvr8-pwE,48578
-upgini-1.2.9a3.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.9a3.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.9a3.dist-info/RECORD,,
+upgini-1.2.9a99.dist-info/METADATA,sha256=YA-Hrmg8rsT_cDBcvN1hRbHHsfYUXtYtbKaGNc40X5M,48610
+upgini-1.2.9a99.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.9a99.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.9a99.dist-info/RECORD,,