upgini 1.2.167a4220.dev12__tar.gz → 1.2.167a4220.dev14__tar.gz

{upgini-1.2.167a4220.dev12 → upgini-1.2.167a4220.dev14}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: upgini
-Version: 1.2.167a4220.dev12
+Version: 1.2.167a4220.dev14
 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-1.2.167a4220.dev14/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.167.a4220.dev14"

{upgini-1.2.167a4220.dev12 → upgini-1.2.167a4220.dev14}/src/upgini/features_enricher.py

@@ -100,7 +100,6 @@ from upgini.utils.deduplicate_utils import (
     remove_fintech_duplicates,
 )
 from upgini.report.assemble import (
-    _fold_model_nodes,
     _generated_feature_names,
     _parse_generated_feature,
     assemble_report_data,
@@ -2514,39 +2513,6 @@ class FeaturesEnricher(TransformerMixin):
             return False
         return bool(aliases & self._column_name_aliases(list(ensemble_names), renaming))
 
-    def _match_autofe_node_meta(
-        self,
-        autofe_feature: Feature,
-        features_meta: list[FeaturesMetadataV2],
-        used_names: set[str],
-    ) -> FeaturesMetadataV2 | None:
-        name = autofe_feature.get_display_name(shorten=True, unhash=True, cache=False)
-        matched = self._match_autofe_meta_by_names({name} if name else set(), features_meta, used_names)
-        if matched is not None or not name:
-            return matched
-        # Fold formulas omit display_index; FeaturesMetadata still uses the ordinary
-        # get_display_name() with that index. Recover only the remainder after the
-        # Feature-computed base name, then verify with get_display_name().
-        prefix = name + "_"
-        previous = autofe_feature.display_index
-        try:
-            for meta in features_meta or []:
-                if meta.name in used_names or not meta.name.startswith(prefix):
-                    continue
-                index = meta.name[len(prefix) :]
-                if not index:
-                    continue
-                if (
-                    autofe_feature.set_display_index(index).get_display_name(
-                        shorten=True, unhash=True, cache=False
-                    )
-                    == meta.name
-                ):
-                    return meta
-        finally:
-            autofe_feature.set_display_index(previous)
-        return None
-
     @staticmethod
     def _match_autofe_meta_by_names(
         names: set[str],
@@ -6070,31 +6036,6 @@ if response.status_code == 200:
                     self.logger.exception(f"Failed to parse AutoFE formula: {m.formula}")
                     continue
 
-                fold_autofe = [
-                    child
-                    for fold in _fold_model_nodes(autofe_feature)
-                    for child in fold.children
-                    if isinstance(child, Feature)
-                    and (not child.op.is_vector or isinstance(child.op, TimeSeriesBase))
-                ]
-                if fold_autofe:
-                    hashed_to_orig = {hashed: orig for orig, hashed in orig_to_hashed.items()}
-                    for node in fold_autofe:
-                        is_ts = isinstance(node.op, TimeSeriesBase)
-                        source_names = [
-                            hashed
-                            for hashed in node.get_columns()
-                            if not is_ts or hashed_to_orig.get(hashed, hashed) not in self.fit_search_keys
-                        ]
-                        self._add_autofe_description(
-                            descriptions,
-                            used_names,
-                            self._match_autofe_node_meta(node, features_meta, used_names),
-                            source_names,
-                            node.get_all_operand_names(),
-                        )
-                    continue
-
                 is_ts = isinstance(autofe_feature.op, TimeSeriesBase)
                 if autofe_feature.op.is_vector and not is_ts:
                     continue

{upgini-1.2.167a4220.dev12 → upgini-1.2.167a4220.dev14}/src/upgini/utils/deduplicate_utils.py

@@ -17,6 +17,15 @@ from upgini.resource_bundle import ResourceBundle, get_custom_bundle
 from upgini.utils.datetime_utils import DateTimeConverter
 from upgini.utils.target_utils import define_task
 
+_INDEX_SAMPLE = 3
+
+
+def _format_index_sample(indexes) -> str:
+    values = list(indexes)
+    if len(values) <= _INDEX_SAMPLE:
+        return str(values)
+    return str(values[:_INDEX_SAMPLE])[:-1] + ", ...]"
+
 
 def remove_fintech_duplicates(
     df: pd.DataFrame,
@@ -117,11 +126,11 @@ def remove_fintech_duplicates(
             perc = len(rows_to_remove) * 100 / len(segment_df)
             if eval_index == 0:
                 msg = bundle.get("dataset_train_diff_target_duplicates_fintech").format(
-                    perc, len(rows_to_remove), rows_to_remove.index.to_list()
+                    perc, len(rows_to_remove), _format_index_sample(rows_to_remove.index)
                 )
             else:
                 msg = bundle.get("dataset_eval_diff_target_duplicates_fintech").format(
-                    perc, len(rows_to_remove), eval_index, rows_to_remove.index.to_list()
+                    perc, len(rows_to_remove), eval_index, _format_index_sample(rows_to_remove.index)
                 )
             return segment_df[~segment_df.index.isin(rows_to_remove.index)], msg
         return segment_df, None
@@ -227,7 +236,7 @@ def clean_full_duplicates(
 
         marked_duplicates = df_for_dedup.duplicated(subset=unique_columns, keep=False)
         if marked_duplicates.sum() > 0:
-            dups_indices = df_for_dedup[marked_duplicates].index.to_list()[:100]
+            dups_indices = _format_index_sample(df_for_dedup[marked_duplicates].index)
             nrows_after_tgt_dedup = len(df_for_dedup.drop_duplicates(subset=unique_columns, keep=False))
             num_dup_rows = len(df_for_dedup) - nrows_after_tgt_dedup
             share_tgt_dedup = 100 * num_dup_rows / len(df_for_dedup)
@@ -240,7 +249,7 @@ def clean_full_duplicates(
             df = pd.concat([df_for_dedup, oot_df], ignore_index=False)
             marked_duplicates = df.duplicated(subset=unique_columns, keep=False)
             if marked_duplicates.sum() > 0:
-                dups_indices = df[marked_duplicates].index.to_list()[:100]
+                dups_indices = _format_index_sample(df[marked_duplicates].index)
                 nrows_after_tgt_dedup = len(df.drop_duplicates(subset=unique_columns, keep=False))
                 num_dup_rows = len(df) - nrows_after_tgt_dedup
                 share_tgt_dedup = 100 * num_dup_rows / len(df)

upgini-1.2.167a4220.dev12/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.167.a4220.dev12"