upgini 1.2.81a3853.dev2__py3-none-any.whl → 1.2.82__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.81a3853.dev2"
+__version__ = "1.2.82"

upgini/autofe/feature.py

@@ -161,7 +161,7 @@ class Feature:
         if self.cached_display_name is not None and cache:
             return self.cached_display_name
 
-        should_stack_op = not isinstance(self.children[-1], Column) if self.op.is_unary or self.op.is_vector else False
+        should_stack_op = not isinstance(self.children[0], Column) if self.op.is_unary else False
         components = []
 
         if self.alias:
@@ -169,7 +169,7 @@ class Feature:
         elif should_stack_op:
             components.extend(
                 [
-                    self.children[-1].get_display_name(
+                    self.children[0].get_display_name(
                         cache=cache, shorten=shorten, use_op_alias=use_op_alias, **kwargs
                     ),
                     self.get_op_display_name(use_alias=use_op_alias),

upgini/dataset.py

@@ -394,7 +394,7 @@ class Dataset:  # (pd.DataFrame):
             if col in mandatory_columns:
                 self.data["valid_mandatory"] = self.data["valid_mandatory"] & self.data[f"{col}_is_valid"]
 
-            invalid_values = list(self.data.loc[self.data[f"{col}_is_valid"] == 0, col].head().values)  # type: ignore
+            invalid_values = list(set(self.data.loc[self.data[f"{col}_is_valid"] == 0, col].head().values))
             valid_share = self.data[f"{col}_is_valid"].sum() / nrows
             original_col_name = self.columns_renaming[col]
             validation_stats[original_col_name] = {}

upgini/features_enricher.py

@@ -1559,9 +1559,12 @@ class FeaturesEnricher(TransformerMixin):
         fitting_X = X_sorted[client_features].copy()
         fitting_enriched_X = enriched_X_sorted[client_features + existing_filtered_enriched_features].copy()
 
+        renamed_generate_features = [columns_renaming.get(c, c) for c in (self.generate_features or [])]
+        renamed_client_cat_features = [columns_renaming.get(c, c) for c in (client_cat_features or [])]
+
         # Detect and drop high cardinality columns in train
         columns_with_high_cardinality = FeaturesValidator.find_high_cardinality(fitting_X)
-        non_excluding_columns = (self.generate_features or []) + (client_cat_features or [])
+        non_excluding_columns = renamed_generate_features + renamed_client_cat_features
         columns_with_high_cardinality = [c for c in columns_with_high_cardinality if c not in non_excluding_columns]
         if len(columns_with_high_cardinality) > 0:
             self.logger.warning(

{upgini-1.2.81a3853.dev2.dist-info → upgini-1.2.82.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.81a3853.dev2
+Version: 1.2.82
 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-1.2.81a3853.dev2.dist-info → upgini-1.2.82.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=e1Um-_kNS2yvbUQQXa5wdQmMciYIP11tSaPy9X5Z46s,33
+upgini/__about__.py,sha256=wIfaTYNNq8gXQfG6X1cQaeNbsFlmRpelLJv8NMITZE0,23
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
-upgini/dataset.py,sha256=aspri7ZAgwkNNUiIgQ1GRXvw8XQii3F4RfNXSrF4wrw,35365
+upgini/dataset.py,sha256=fRtqSkXNONLnPe6cCL967GMt349FTIpXzy_u8LUKncw,35354
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=cWbEA2lOt51x62NrLkyxu1G8I4KQo_2aOgqt3Ypyr1M,212819
+upgini/features_enricher.py,sha256=jq7y3KNAMd3oVi6whIY5PU3ikfrZs7mg4U_ILfuinm4,213024
 upgini/http.py,sha256=AfaJ3c8z_tK2hZFEehNybDKE0mp1tYcyAP_l0_p8bLQ,43933
 upgini/metadata.py,sha256=zt_9k0iQbWXuiRZcel4ORNPdQKt6Ou69ucZD_E1Q46o,12341
 upgini/metrics.py,sha256=3cip0_L6-OFew74KsRwzxJDU6UFq05h2v7IsyHLcMRc,43164
@@ -16,7 +16,7 @@ upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/autofe/all_operators.py,sha256=rdjF5eaE4bC6Q4eu_el5Z7ekYt8DjOFermz2bePPbUc,333
 upgini/autofe/binary.py,sha256=oOEECc4nRzZN2tYaiqx8F2XHnfWpk1bVvb7ZkZJ0lO8,7709
 upgini/autofe/date.py,sha256=MM1S-6imNSzCDOhbNnmsc_bwSqUWBcS8vWAdHF8j1kY,11134
-upgini/autofe/feature.py,sha256=9R5IQZ-w24ixM79jVRdF3eKEoHmnJZ6VqW8NpO-X3aI,15328
+upgini/autofe/feature.py,sha256=G_YgnsauIoaMgByx9JXDPiKc4nqs0pwWZUfvoIGMKxY,15305
 upgini/autofe/groupby.py,sha256=IYmQV9uoCdRcpkeWZj_kI3ObzoNCNx3ff3h8sTL01tk,3603
 upgini/autofe/operator.py,sha256=EOffJw6vKXpEh5yymqb1RFNJPxGxmnHdFRo9dB5SCFo,4969
 upgini/autofe/unary.py,sha256=Sx11IoHRh5nwyALzjgG9GQOrVNIs8NZ1JzunAJuN66A,5731
@@ -70,7 +70,7 @@ upgini/utils/target_utils.py,sha256=LRN840dzx78-wg7ftdxAkp2c1eu8-JDvkACiRThm4HE,
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/ts_utils.py,sha256=26vhC0pN7vLXK6R09EEkMK3Lwb9IVPH7LRdqFIQ3kPs,1383
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.81a3853.dev2.dist-info/METADATA,sha256=39jILeLwudZuiX95dnXU8if_jAKIP_eOQZ2h8xRKy4E,49172
-upgini-1.2.81a3853.dev2.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.2.81a3853.dev2.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.81a3853.dev2.dist-info/RECORD,,
+upgini-1.2.82.dist-info/METADATA,sha256=cambuYE-iqUo5mvnJN1CI1Qn8QgqdM5e54-h2giPj50,49162
+upgini-1.2.82.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.82.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.82.dist-info/RECORD,,

{upgini-1.2.81a3853.dev2.dist-info → upgini-1.2.82.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.24.2
+Generator: hatchling 1.25.0
 Root-Is-Purelib: true
 Tag: py3-none-any