upgini 1.2.82a3853.dev2__py3-none-any.whl → 1.2.83__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.82a3853.dev2"
+__version__ = "1.2.83"

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(
@@ -2447,13 +2450,15 @@ if response.status_code == 200:
             meaning_types.update({col: FileColumnMeaningType.FEATURE for col in features_for_transform})
             meaning_types.update({col: key.value for col, key in search_keys.items()})
 
-            features_not_to_pass.extend([
-                c
-                for c in df.columns
-                if c not in search_keys.keys()
-                and c not in features_for_transform
-                and c not in [ENTITY_SYSTEM_RECORD_ID, SEARCH_KEY_UNNEST]
-            ])
+            features_not_to_pass.extend(
+                [
+                    c
+                    for c in df.columns
+                    if c not in search_keys.keys()
+                    and c not in features_for_transform
+                    and c not in [ENTITY_SYSTEM_RECORD_ID, SEARCH_KEY_UNNEST]
+                ]
+            )
 
             if DateTimeSearchKeyConverter.DATETIME_COL in df.columns:
                 df = df.drop(columns=DateTimeSearchKeyConverter.DATETIME_COL)
@@ -3712,7 +3717,7 @@ if response.status_code == 200:
         columns_to_sort = [date_column] if date_column is not None else []
 
         do_sorting = True
-        if self.id_columns and self.cv in [CVType.time_series, CVType.blocked_time_series]:
+        if self.id_columns and self.cv.is_time_series():
             # Check duplicates by date and id_columns
             reversed_columns_renaming = {v: k for k, v in columns_renaming.items()}
             renamed_id_columns = [reversed_columns_renaming.get(c, c) for c in self.id_columns]
@@ -3722,14 +3727,7 @@ if response.status_code == 200:
 
             duplicates = df.duplicated(subset=duplicate_check_columns, keep=False)
             if duplicates.any():
-                if not silent:
-                    self.__log_warning(self.bundle.get("date_and_id_columns_duplicates").format(duplicates.sum()))
-                else:
-                    self.logger.warning(
-                        f"Found {duplicates.sum()} duplicate rows by date and ID columns: {duplicate_check_columns}."
-                        " Will not sort dataset"
-                    )
-                do_sorting = False
+                raise ValueError(self.bundle.get("date_and_id_columns_duplicates").format(duplicates.sum()))
             else:
                 columns_to_hash = list(set(list(search_keys.keys()) + renamed_id_columns + [target_name]))
                 columns_to_hash = sort_columns(

upgini/resource_bundle/strings.properties

@@ -36,7 +36,6 @@ trial_quota_limit_riched=You have reached the quota limit of trial data usage. P
 loss_selection_warn=Loss `{0}` is not supported for feature selection with {1}
 loss_calc_metrics_warn=Loss `{0}` is not supported for metrics calculation with {1}
 multivariate_timeseries_detected=Multivariate TimeSeries detected. Blocked time series cross-validation split selected.\nMore details: https://github.com/upgini/upgini#-time-series-prediction-support
-date_and_id_columns_duplicates=Found {} duplicate rows by date and id_columns
 group_k_fold_in_classification=Using group K-fold cross-validation split for classification task.
 current_date_added=No date/datetime column was detected in X to be used as a search key. The current date will be used to match the latest version of data sources
 # Errors
@@ -191,6 +190,7 @@ timeseries_invalid_split_count=Cross-validation requires at least one train/test
 timeseries_invalid_test_size_type=test_size={} should be a float in the (0, 1) range
 timeseries_splits_more_than_samples=Number of splits={} can't be more than number of samples={}
 timeseries_invalid_test_size=Wrong number of samples in a test fold: (test_size * n_samples / n_splits) <= 1
+date_and_id_columns_duplicates=Found {} duplicate rows by date and id_columns. Please remove them and try again
     # Upload ads validation
 ads_upload_too_few_rows=At least 1000 records per sample are needed. Increase the sample size for evaluation and resubmit the data
 ads_upload_search_key_not_found=Search key {} wasn't found in dataframe columns

{upgini-1.2.82a3853.dev2.dist-info → upgini-1.2.83.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.82a3853.dev2
+Version: 1.2.83
 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-1.2.82a3853.dev2.dist-info → upgini-1.2.83.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=FXbALhFkuQ3hoEzhmp_olrO40HwaCvGiCKus4wSy940,33
+upgini/__about__.py,sha256=h2Ibse6YuHdXZHWt0iDDzwOXKJiV09m9RkgFgDU2HsY,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=2ryADtOVEEebuUBhimusvnBzGxUkdTaqpEh2F1PqHSs,212719
 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
@@ -38,7 +38,7 @@ 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=GmkTgxowpykuuviubVH5cMF_lNFQJEqfRoBJaj3c72E,27957
+upgini/resource_bundle/strings.properties,sha256=U_ewTI-qPww4X3WcFG3qDf_jv2vo6RrlCehVDjqtzEI,27991
 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
@@ -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-1.2.82a3853.dev2.dist-info/METADATA,sha256=rxFyB6IXqVf7wFvGuT5Y5rqK3cFafMDQQl28-i1j09M,49172
-upgini-1.2.82a3853.dev2.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.2.82a3853.dev2.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.82a3853.dev2.dist-info/RECORD,,
+upgini-1.2.83.dist-info/METADATA,sha256=roEvcDdV_9hyXf6geUHr-fBo6k-yBs7RfCXdrLEnhac,49162
+upgini-1.2.83.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.2.83.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.83.dist-info/RECORD,,