upgini 1.1.244a19__py3-none-any.whl → 1.1.244a20__py3-none-any.whl

upgini/features_enricher.py

@@ -1855,8 +1855,6 @@ class FeaturesEnricher(TransformerMixin):
             )
             meaning_types[SYSTEM_RECORD_ID] = FileColumnMeaningType.SYSTEM_RECORD_ID
 
-            df = clean_full_duplicates(df, self.logger, silent=silent_mode)
-
             df = df.reset_index(drop=True)
             system_columns_with_original_index = [SYSTEM_RECORD_ID] + generated_features
             df_with_original_index = df[system_columns_with_original_index].copy()
@@ -1865,6 +1863,8 @@ class FeaturesEnricher(TransformerMixin):
 
             df_without_features = df.drop(columns=non_keys_columns)
 
+            df_without_features = clean_full_duplicates(df_without_features, self.logger, silent=silent_mode)
+
             del df
             gc.collect()
 
@@ -2092,6 +2092,7 @@ class FeaturesEnricher(TransformerMixin):
                     msg = bundle.get("missing_generate_feature").format(gen_feature, x_columns)
                     print(msg)
                     self.logger.warning(msg)
+            self.runtime_parameters.properties["generate_features"] = ",".join(self.generate_features)
 
         validate_scoring_argument(scoring)
 

upgini/metrics.py

@@ -414,6 +414,9 @@ class CatBoostWrapper(EstimatorWrapper):
         self.emb_features = [c for c in X.columns if re.match(emb_pattern, c) and is_numeric_dtype(X[c])]
         embedding_features = []
         if len(self.emb_features) > 3:  # There is no reason to reduce embeddings dimension with less than 4
+            self.logger.info(
+                f"Embedding features count more than 3, so group them into one vector for CatBoost: {self.emb_features}"
+            )
             X, embedding_features = self.group_embeddings(X)
             params["embedding_features"] = embedding_features
         else:
@@ -421,7 +424,9 @@ class CatBoostWrapper(EstimatorWrapper):
 
         # Find text features from passed in generate_features
         if self.text_features is not None:
-            self.text_features = [f for f in self.text_features if not is_numeric_dtype(X[f])]
+            self.logger.info(f"Passed text features for CatBoost: {self.text_features}")
+            self.text_features = [f for f in self.text_features if f in X.columns and not is_numeric_dtype(X[f])]
+            self.logger.info(f"Rest text features after checks: {self.text_features}")
             params["text_features"] = self.text_features
 
         # Find rest categorical features
@@ -452,6 +457,7 @@ class CatBoostWrapper(EstimatorWrapper):
 
             del self.estimator._init_params["cat_features"]
 
+        self.logger.info(f"Selected categorical features: {self.cat_features}")
         params["cat_features"] = self.cat_features
 
         return X, y, groups, params

upgini/utils/deduplicate_utils.py

@@ -103,6 +103,8 @@ def clean_full_duplicates(
     unique_columns = df.columns.tolist()
     if SYSTEM_RECORD_ID in unique_columns:
         unique_columns.remove(SYSTEM_RECORD_ID)
+    if "sort_id" in unique_columns:
+        unique_columns.remove("sort_id")
     logger.info(f"Dataset shape before clean duplicates: {df.shape}")
     df = df.drop_duplicates(subset=unique_columns)
     logger.info(f"Dataset shape after clean duplicates: {df.shape}")

{upgini-1.1.244a19.dist-info → upgini-1.1.244a20.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.244a19
+Version: 1.1.244a20
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.244a19.dist-info → upgini-1.1.244a20.dist-info}/RECORD

@@ -2,11 +2,11 @@ upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=mre6xn44wcC_fg63iLT_kTh4mViZqR9AKRJZAtpQz8Y,2592
 upgini/dataset.py,sha256=WGpnmpnmfdyB2DAwaj7mkk2s0e-6Z6bg5BWj1lUE2p0,49960
 upgini/errors.py,sha256=pdzQl3MKuK52yvncxMWMRWeSIOGhUFzpQoszoRFBOk0,958
-upgini/features_enricher.py,sha256=-5Ofx0f3OHuwP2dgg4O2xL8zaxCb2F-9E1Nc1XnGdZE,165622
+upgini/features_enricher.py,sha256=xN-j01kEbph__ZycO2knKeDlscWdAf_vLzCpO0ERLFo,165759
 upgini/fingerprint.js,sha256=VygVIQlN1v4NGZfjHqtRogOw8zjTnnMNJg_f7M5iGQU,33442
 upgini/http.py,sha256=eSG4gOpmCGlXmB6KIPNzAG8tRZNUjyYpMeUeHw_2li4,42264
 upgini/metadata.py,sha256=55t0uQI910tzTcnwxZCUL1413BhTiSm8oqiwp-94NyA,9613
-upgini/metrics.py,sha256=b9efALHojYiAm_XHfCznZq7TVCU76ZM_zrwU6LI0yY0,25900
+upgini/metrics.py,sha256=0km-A0TNRqHy8jdf_VqfV5iuwA-nZmlJGhQ4fLd8rKg,26340
 upgini/search_task.py,sha256=5n4qGJmtu48s0-FHAtF3L5qVLMd1JVW3FJlM8dFbh-s,17063
 upgini/spinner.py,sha256=Dm1dQ5F_z_Ua2odLxZX7OypcOX9tSx_vE5MGaKtUmfw,1118
 upgini/version_validator.py,sha256=rDIncP6BEko4J2F2hUcMOtKm_vZbI4ICWcNcw8hrwM4,1400
@@ -40,7 +40,7 @@ upgini/utils/country_utils.py,sha256=1KXhLSNqkNYVL3on8-zK0Arc_SspUH7AMZvGZICysOU
 upgini/utils/custom_loss_utils.py,sha256=DBslpjWGPt7xTeypt78baR59012SYphbPsO_YLKdilo,3972
 upgini/utils/cv_utils.py,sha256=6pSSL_Ft_8C6n6aInJeiyeSBD7McjsMxKZpHqSBV0uY,2491
 upgini/utils/datetime_utils.py,sha256=awsLpnFjBNcrsCDyyiiJLicHgHiGCNAwi0UOwRKGD7s,8645
-upgini/utils/deduplicate_utils.py,sha256=UEk160TGAqShDYeofAJJehpmEqMSj-I82o4GqDOSGnk,5811
+upgini/utils/deduplicate_utils.py,sha256=D5zdbnpo0qW23Sy04hRbntaliImiLi76KS7Du1l-ea8,5888
 upgini/utils/display_utils.py,sha256=tiq5sFOfMwkKCjQ7OGdyK_twe0Qdr9F3mzkW1QXSDog,10664
 upgini/utils/email_utils.py,sha256=3CvHXTSzlgLyGsQOXfRYVfFhfPy6OXG4uXOBWRaLfHg,3479
 upgini/utils/fallback_progress_bar.py,sha256=cdbd1XGcWm4Ed4eAqV2_St3z7uC_kkH22gEyrN5ub6M,1090
@@ -54,8 +54,8 @@ upgini/utils/sklearn_ext.py,sha256=fvuTWJ5AnT3ED9KSaQu_yIgW2JR19hFlaGDoVP3k60g,4
 upgini/utils/target_utils.py,sha256=qyj-bGsIEl9X2Vc5gwXtsuRaocvId8bn46F7mZ9dy9A,1707
 upgini/utils/track_info.py,sha256=EPcJ13Jqa17_T0JjM37Ac9kWDz5Zk0GVsIZKutOb8aU,5207
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.244a19.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.244a19.dist-info/METADATA,sha256=i0jRNkFom9uR1I0tImg7U_PJFquFj5dq6LhqkAGC-bA,48265
-upgini-1.1.244a19.dist-info/WHEEL,sha256=pkctZYzUS4AYVn6dJ-7367OJZivF2e8RA9b_ZBjif18,92
-upgini-1.1.244a19.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
-upgini-1.1.244a19.dist-info/RECORD,,
+upgini-1.1.244a20.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.244a20.dist-info/METADATA,sha256=rpTVYdRU4VsFxnVRtiLyVREU_u3NwSEHQy-guOoaKOM,48265
+upgini-1.1.244a20.dist-info/WHEEL,sha256=pkctZYzUS4AYVn6dJ-7367OJZivF2e8RA9b_ZBjif18,92
+upgini-1.1.244a20.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
+upgini-1.1.244a20.dist-info/RECORD,,