upgini 1.1.152__py3-none-any.whl → 1.1.154a1__py3-none-any.whl

upgini/features_enricher.py

@@ -142,6 +142,7 @@ class FeaturesEnricher(TransformerMixin):
         round_embeddings: Optional[int] = None,
         logs_enabled: bool = True,
         raise_validation_error: bool = False,
+        exclude_columns: Optional[List[str]] = None,
         **kwargs,
     ):
         self._api_key = api_key or os.environ.get(UPGINI_API_KEY)
@@ -207,21 +208,19 @@ class FeaturesEnricher(TransformerMixin):
         self.shared_datasets = shared_datasets
         if shared_datasets is not None:
             self.runtime_parameters.properties["shared_datasets"] = ",".join(shared_datasets)
-        self.generate_features: Optional[List[str]] = None
+        self.generate_features = generate_features
+        self.round_embeddings = round_embeddings
         if generate_features is not None:
             if len(generate_features) > 2:
                 msg = bundle.get("too_many_generate_features")
                 self.logger.error(msg)
                 raise ValidationError(msg)
-            self.generate_features = generate_features
             self.runtime_parameters.properties["generate_features"] = ",".join(generate_features)
-            self.round_embeddings: Optional[int] = None
             if round_embeddings is not None:
                 if not isinstance(round_embeddings, int) or round_embeddings < 0:
                     msg = bundle.get("invalid_round_embeddings")
                     self.logger.error(msg)
                     raise ValidationError(msg)
-                self.round_embeddings = round_embeddings
                 self.runtime_parameters.properties["round_embeddings"] = round_embeddings
 
         self.passed_features: List[str] = []
@@ -238,6 +237,7 @@ class FeaturesEnricher(TransformerMixin):
         self.imbalanced = False
         self.__cached_sampled_datasets: Optional[Tuple[pd.DataFrame, pd.DataFrame, pd.Series, Dict, Dict]] = None
         self.raise_validation_error = raise_validation_error
+        self.exclude_columns = exclude_columns
 
     def _get_api_key(self):
         return self._api_key
@@ -678,11 +678,11 @@ class FeaturesEnricher(TransformerMixin):
 
             try:
                 self.__log_debug_information(
-                    X,
-                    y,
-                    eval_set,
+                    X if X is not None else self.X,
+                    y if y is not None else self.y,
+                    eval_set if eval_set is not None else self.eval_set,
                     exclude_features_sources=exclude_features_sources,
-                    cv=cv,
+                    cv=cv if cv is not None else self.cv,
                     importance_threshold=importance_threshold,
                     max_features=max_features,
                     scoring=scoring,
@@ -1801,6 +1801,9 @@ class FeaturesEnricher(TransformerMixin):
         if not is_transform and not validated_X.index.is_unique:
             raise ValidationError(bundle.get("x_non_unique_index"))
 
+        if self.exclude_columns is not None:
+            validated_X = drop_existing_columns(validated_X, self.exclude_columns)
+
         if TARGET in validated_X.columns:
             raise ValidationError(bundle.get("x_contains_reserved_column_name").format(TARGET))
         if not is_transform and EVAL_SET_INDEX in validated_X.columns:
@@ -1970,51 +1973,58 @@ class FeaturesEnricher(TransformerMixin):
         estimator: Optional[Any] = None,
         remove_outliers_calc_metrics: Optional[bool] = None,
     ):
-        resolved_api_key = self.api_key or os.environ.get(UPGINI_API_KEY)
-        self.logger.info(
-            f"Search keys: {self.search_keys}\n"
-            f"Country code: {self.country_code}\n"
-            f"Model task type: {self.model_task_type}\n"
-            f"Api key presented?: {resolved_api_key is not None and resolved_api_key != ''}\n"
-            f"Endpoint: {self.endpoint}\n"
-            f"Runtime parameters: {self.runtime_parameters}\n"
-            f"Date format: {self.date_format}\n"
-            f"CV: {cv}\n"
-            f"importance_threshold: {importance_threshold}\n"
-            f"max_features: {max_features}"
-            f"Shared datasets: {self.shared_datasets}\n"
-            f"Random state: {self.random_state}\n"
-            f"Generate features: {self.generate_features}\n"
-            f"Round embeddings: {self.round_embeddings}\n"
-            f"Detect missing search keys: {self.detect_missing_search_keys}\n"
-            f"Exclude features sources: {exclude_features_sources}\n"
-            f"Calculate metrics: {calculate_metrics}\n"
-            f"Scoring: {scoring}\n"
-            f"Estimator: {estimator}\n"
-            f"Remove target outliers: {remove_outliers_calc_metrics}\n"
-            f"Search id: {self.search_id}\n"
-        )
+        try:
+            resolved_api_key = self.api_key or os.environ.get(UPGINI_API_KEY)
+            self.logger.info(
+                f"Search keys: {self.search_keys}\n"
+                f"Country code: {self.country_code}\n"
+                f"Model task type: {self.model_task_type}\n"
+                f"Api key presented?: {resolved_api_key is not None and resolved_api_key != ''}\n"
+                f"Endpoint: {self.endpoint}\n"
+                f"Runtime parameters: {self.runtime_parameters}\n"
+                f"Date format: {self.date_format}\n"
+                f"CV: {cv}\n"
+                f"importance_threshold: {importance_threshold}\n"
+                f"max_features: {max_features}\n"
+                f"Shared datasets: {self.shared_datasets}\n"
+                f"Random state: {self.random_state}\n"
+                f"Generate features: {self.generate_features}\n"
+                f"Round embeddings: {self.round_embeddings}\n"
+                f"Detect missing search keys: {self.detect_missing_search_keys}\n"
+                f"Exclude features sources: {exclude_features_sources}\n"
+                f"Calculate metrics: {calculate_metrics}\n"
+                f"Scoring: {scoring}\n"
+                f"Estimator: {estimator}\n"
+                f"Remove target outliers: {remove_outliers_calc_metrics}\n"
+                f"Exclude columns: {self.exclude_columns}\n"
+                f"Search id: {self.search_id}\n"
+            )
 
-        def sample(df):
-            if isinstance(df, pd.Series) or isinstance(df, pd.DataFrame):
-                return df.head(10)
-            else:
-                return df[:10]
+            def sample(df):
+                if isinstance(df, pd.Series) or isinstance(df, pd.DataFrame):
+                    return df.head(10)
+                else:
+                    return df[:10]
 
-        def print_datasets_sample():
-            self.logger.info(f"First 10 rows of the X with shape {X.shape}:\n{sample(X)}")
-            if y is not None:
-                self.logger.info(f"First 10 rows of the y with shape {_num_samples(y)}:\n{sample(y)}")
-            if eval_set is not None:
-                for idx, eval_pair in enumerate(eval_set):
-                    eval_X: pd.DataFrame = eval_pair[0]
-                    eval_y = eval_pair[1]
-                    self.logger.info(f"First 10 rows of the eval_X_{idx} with shape {eval_X.shape}:\n{sample(eval_X)}")
-                    self.logger.info(
-                        f"First 10 rows of the eval_y_{idx} with shape {_num_samples(eval_y)}:\n{sample(eval_y)}"
-                    )
+            def print_datasets_sample():
+                if X is not None:
+                    self.logger.info(f"First 10 rows of the X with shape {X.shape}:\n{sample(X)}")
+                if y is not None:
+                    self.logger.info(f"First 10 rows of the y with shape {_num_samples(y)}:\n{sample(y)}")
+                if eval_set is not None:
+                    for idx, eval_pair in enumerate(eval_set):
+                        eval_X: pd.DataFrame = eval_pair[0]
+                        eval_y = eval_pair[1]
+                        self.logger.info(
+                            f"First 10 rows of the eval_X_{idx} with shape {eval_X.shape}:\n{sample(eval_X)}"
+                        )
+                        self.logger.info(
+                            f"First 10 rows of the eval_y_{idx} with shape {_num_samples(eval_y)}:\n{sample(eval_y)}"
+                        )
 
-        do_without_pandas_limits(print_datasets_sample)
+            do_without_pandas_limits(print_datasets_sample)
+        except Exception:
+            self.logger.exception("Failed to log debug information")
 
     def __handle_index_search_keys(self, df: pd.DataFrame, search_keys: Dict[str, SearchKey]) -> pd.DataFrame:
         index_names = df.index.names if df.index.names != [None] else [DEFAULT_INDEX]

{upgini-1.1.152.dist-info → upgini-1.1.154a1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.152
+Version: 1.1.154a1
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.152.dist-info → upgini-1.1.154a1.dist-info}/RECORD

@@ -2,7 +2,7 @@ upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=mre6xn44wcC_fg63iLT_kTh4mViZqR9AKRJZAtpQz8Y,2592
 upgini/dataset.py,sha256=Jmteorv9nMn0bASMUixPXkTfBsONDuol0UIyPznOmRw,44111
 upgini/errors.py,sha256=BqpvfhW2jJW5fa5KXj0alhXatGl-WK4xTl309-QNLp8,959
-upgini/features_enricher.py,sha256=q5NKJI1Waogl9j5juKU4rkzEFNAS5xAsP_oggho4514,125454
+upgini/features_enricher.py,sha256=zWIZmROTY3Fi1PsivJhMrGBpznZ-K5mMZApFD6H0AXM,126119
 upgini/fingerprint.js,sha256=wfzunoC87TdquCdABOwcrkoGOoJsX89ICTOb4rsrO50,34162
 upgini/http.py,sha256=ke85Fb1ffD29tjgpnbHF_6gtV3nBJe4Xoxpp9i1GuLA,37176
 upgini/metadata.py,sha256=Oefg-rkA4PsZUHIho_clZcnyZwdtVJ1gXPvEY6oBmpg,5969
@@ -42,8 +42,8 @@ upgini/utils/postal_code_utils.py,sha256=_8CR9tBqsPptQsmMUvnrCAmBaMIQSWH3JfJ4ly3
 upgini/utils/target_utils.py,sha256=cu52icjhDIPpEStHYMXrD2hIl9gzvfnxZr0Ra5osV0k,1616
 upgini/utils/track_info.py,sha256=2IGGyHPXBLhWcLO8-Q-5qir52k_kD6DtdU-sv_Z2hHY,5325
 upgini/utils/warning_counter.py,sha256=vnmdFo5-7GBkU2bK9h_uC0K0Y_wtfcYstxOdeRfacO0,228
-upgini-1.1.152.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.152.dist-info/METADATA,sha256=4O-RTzAPG1pGfqZJTynOMxQVSEdNnGVoKImTsMypalo,47895
-upgini-1.1.152.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
-upgini-1.1.152.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
-upgini-1.1.152.dist-info/RECORD,,
+upgini-1.1.154a1.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.154a1.dist-info/METADATA,sha256=fQ2EK-jmAweNVHlfc3eoRKYs3IEzPkDA6iO8mzByczs,47897
+upgini-1.1.154a1.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
+upgini-1.1.154a1.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
+upgini-1.1.154a1.dist-info/RECORD,,