upgini 1.2.23__py3-none-any.whl → 1.2.24__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.23"
+__version__ = "1.2.24"

upgini/metrics.py

@@ -273,6 +273,9 @@ class EstimatorWrapper:
         else:
             x, y = self._remove_empty_target_rows(x, y)
 
+        # Make order of columns idempotent
+        x = x[sorted(x.columns)]
+
         self.logger.info(f"After preparing data columns: {x.columns.to_list()}")
         return x, y, groups
 
@@ -434,7 +437,8 @@ class EstimatorWrapper:
                                 f"Client cat_feature `{cat_feature}` not found in x columns: {x.columns.to_list()}"
                             )
                     estimator_copy.set_params(
-                        cat_features=[x.columns.get_loc(cat_feature) for cat_feature in cat_features]
+                        # cat_features=[x.columns.get_loc(cat_feature) for cat_feature in cat_features]
+                        cat_features=cat_features
                     )
                 estimator = CatBoostWrapper(**kwargs)
             else:

upgini/resource_bundle/strings.properties

@@ -171,7 +171,7 @@ dataset_invalid_column_type=Unsupported data type of column {}: {}
 dataset_invalid_filter=Unknown field in filter_features. Should be {'min_importance', 'max_psi', 'max_count', 'selected_features'}.
 dataset_too_big_file=Too big size of dataframe X for processing. Please reduce number of rows or columns
 dataset_transform_diff_fit=You try to enrich dataset that column names are different from the train dataset column names that you used on the fit stage. Please make the column names the same as in the train dataset and restart.
-binary_small_dataset=The least populated class in Target contains less than 1000 rows.\nSmall numbers of observations may negatively affect the number of selected features and quality of your ML model.\nUpgini recommends you increase the number of observations in the least populated class.
+binary_small_dataset=The least populated class in Target contains less than 1000 rows.\nSmall numbers of observations may negatively affect the number of selected features and quality of your ML model.\nUpgini recommends you increase the number of observations in the least populated class.\n
 all_search_keys_invalid=All search keys are invalid
 all_emails_invalid=All values in column {} are invalid emails    # Metrics validation
 metrics_msle_negative_target=Mean Squared Logarithmic Error cannot be used when y contain negative values

upgini/utils/deduplicate_utils.py

@@ -24,7 +24,7 @@ def remove_fintech_duplicates(
     date_format: Optional[str] = None,
     logger: Optional[Logger] = None,
     bundle: ResourceBundle = None,
-) -> tuple[pd.DataFrame, Optional[List[str]]]:
+) -> Tuple[pd.DataFrame, Optional[List[str]]]:
     # Initial checks for target type and date column
     bundle = bundle or get_custom_bundle()
     if logger is None:
@@ -60,7 +60,7 @@ def remove_fintech_duplicates(
 
     warning_messages = []
 
-    def process_df(segment_df: pd.DataFrame, eval_index=0) -> tuple[pd.DataFrame, Optional[str]]:
+    def process_df(segment_df: pd.DataFrame, eval_index=0) -> Tuple[pd.DataFrame, Optional[str]]:
         """Process a subset of the dataset to remove duplicates based on personal keys."""
         # Fast check for duplicates based on personal keys
         if not segment_df[personal_cols].duplicated().any():

{upgini-1.2.23.dist-info → upgini-1.2.24.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.23
+Version: 1.2.24
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/

{upgini-1.2.23.dist-info → upgini-1.2.24.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=y_Ev8AcJxzZe4ZJWlW3Wsver97OJUqU1nFSDqHzKBDw,23
+upgini/__about__.py,sha256=rRcFnLqwG22zZ399qswskAE5L_if50hEsd_TKzGcrZ4,23
 upgini/__init__.py,sha256=M64LwQTBa-5Jz24Zm2h8rWwlKQQ1J8nP7gGgIciS0WU,589
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=iPFiMJtk4HF1ytw9wCQr8H9RfoOKj_TIo8XYZKWgcMc,31331
@@ -7,7 +7,7 @@ upgini/features_enricher.py,sha256=rctS3kRWwTJmU5X203t7sUZ_B40XYVBPeXy_0hPw2Ec,1
 upgini/http.py,sha256=21asexflvavydzCOONJDGQBtQanCElrbnqLXakJ9Cu8,42880
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=osmzdNESeh7yP3BZday6N9Q3eaIHfzhhRM1d6NSgcf0,11223
-upgini/metrics.py,sha256=10Cg_6cqIOsZyz2tO4GGbCxiBH7lGb35Vh-pR6IUzLg,34459
+upgini/metrics.py,sha256=PoY1fq6XYAHNzn-rmnwRQZjCoVYP5bJNmKhR0ST2Txk,34588
 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=h1GViOWzULy5vf6M4dpTJuIk-4V38UCrTY1sb9yLa5I,1594
@@ -30,7 +30,7 @@ upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
 upgini/normalizer/normalize_utils.py,sha256=Ft2MwSgVoBilXAORAOYAuwPD79GOLfwn4qQE3IUFzzg,7218
 upgini/resource_bundle/__init__.py,sha256=S5F2G47pnJd2LDpmFsjDqEwiKkP8Hm-hcseDbMka6Ko,8345
 upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
-upgini/resource_bundle/strings.properties,sha256=wxdxH13ncXjRion__GCM_ecllCDjGqOhOxZ41beFslg,26665
+upgini/resource_bundle/strings.properties,sha256=ikL5KvPcJz9fGyVK-xOvvo6LyRfeOey8xXjoq5nnWqU,26667
 upgini/resource_bundle/strings_widget.properties,sha256=gOdqvZWntP2LCza_tyVk1_yRYcG4c04K9sQOAVhF_gw,1577
 upgini/sampler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/sampler/base.py,sha256=7GpjYqjOp58vYcJLiX__1R5wjUlyQbxvHJ2klFnup_M,6389
@@ -43,7 +43,7 @@ upgini/utils/country_utils.py,sha256=lY-eXWwFVegdVENFttbvLcgGDjFO17Sex8hd2PyJaRk
 upgini/utils/custom_loss_utils.py,sha256=kieNZYBYZm5ZGBltF1F_jOSF4ea6C29rYuCyiDcqVNY,3857
 upgini/utils/cv_utils.py,sha256=w6FQb9nO8BWDx88EF83NpjPLarK4eR4ia0Wg0kLBJC4,3525
 upgini/utils/datetime_utils.py,sha256=a8X4jX2y3-6E7ZNZIG5z61qfzCvsvaNEjR1Bi5KUqfM,11279
-upgini/utils/deduplicate_utils.py,sha256=kINO1KoH8kPRA3JSYogzv4jaUP1Ceguv5etBPtLcsSw,8855
+upgini/utils/deduplicate_utils.py,sha256=SMZx9IKIhWI5HqXepfKiQb3uDJrogQZtG6jcWuMo5Z4,8855
 upgini/utils/display_utils.py,sha256=NGhki1aGMsS8OeI69eLXEpmS_s41k8ojKHQxacJaXiU,11493
 upgini/utils/email_utils.py,sha256=j0Ug1R_0AnCg1Y92zIZ4XMwvKo3G5_pcOlBN1OH_gZs,5191
 upgini/utils/fallback_progress_bar.py,sha256=PDaKb8dYpVZaWMroNcOHsTc3pSjgi9mOm0--cOFTwJ0,1074
@@ -57,7 +57,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=qHzZRmICFbLNCrmVqGkaBcjm91L2ERRZMppci36acV4,10085
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.23.dist-info/METADATA,sha256=DGV0FR8F9_7casA5R9U3b22oSUhXuZeX0RfNGnMgnQ8,48578
-upgini-1.2.23.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.23.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.23.dist-info/RECORD,,
+upgini-1.2.24.dist-info/METADATA,sha256=eRRiMIY75gP4H4Y20_D9dmut5jCgx_siV-TrG_VA_qg,48578
+upgini-1.2.24.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.24.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.24.dist-info/RECORD,,