upgini 1.2.23__tar.gz → 1.2.24a2__tar.gz

{upgini-1.2.23 → upgini-1.2.24a2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.23
+Version: 1.2.24a2
 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-1.2.24a2/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.24a2"

{upgini-1.2.23 → upgini-1.2.24a2}/src/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
 

{upgini-1.2.23 → upgini-1.2.24a2}/src/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-1.2.23 → upgini-1.2.24a2}/src/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/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.23"