upgini 1.2.113a3974.dev2__tar.gz → 1.2.114__tar.gz

{upgini-1.2.113a3974.dev2 → upgini-1.2.114}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.113a3974.dev2
+Version: 1.2.114
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -38,7 +38,7 @@ Requires-Dist: python-bidi==0.4.2
 Requires-Dist: python-dateutil>=2.8.0
 Requires-Dist: python-json-logger>=3.3.0
 Requires-Dist: requests>=2.8.0
-Requires-Dist: scikit-learn>=1.3.0
+Requires-Dist: scikit-learn<1.8.0,>=1.3.0
 Requires-Dist: scipy>=1.10.0
 Requires-Dist: shap>=0.44.0
 Requires-Dist: xhtml2pdf<0.3.0,>=0.2.11
@@ -270,9 +270,9 @@ from upgini.metadata import SearchKey
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
-    		"country": SearchKey.COUNTRY,
-    		"zip_code": SearchKey.POSTAL_CODE,
-    		"hashed_email": SearchKey.HEM,
+		"country": SearchKey.COUNTRY,
+		"zip_code": SearchKey.POSTAL_CODE,
+		"hashed_email": SearchKey.HEM,
 		"last_visit_ip_address": SearchKey.IP,
 		"registered_with_phone": SearchKey.PHONE
 	})
@@ -358,9 +358,9 @@ from upgini.metadata import SearchKey
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
-    		"country": SearchKey.COUNTRY,
-    		"zip_code": SearchKey.POSTAL_CODE,
-    		"hashed_email": SearchKey.HEM,
+		"country": SearchKey.COUNTRY,
+		"zip_code": SearchKey.POSTAL_CODE,
+		"hashed_email": SearchKey.HEM,
 		"last_visit_ip_address": SearchKey.IP,
 		"registered_with_phone": SearchKey.PHONE
 	}, 
@@ -381,7 +381,7 @@ from upgini.metadata import SearchKey
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
-    		"zip_code": SearchKey.POSTAL_CODE,
+		"zip_code": SearchKey.POSTAL_CODE,
 	}, 
 	country_code = "US",
 	date_format = "%Y-%d-%m"
@@ -409,8 +409,8 @@ y = train_df["churn_flag"]
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
-    		"country": SearchKey.COUNTRY,
-    		"zip_code": SearchKey.POSTAL_CODE
+		"country": SearchKey.COUNTRY,
+		"zip_code": SearchKey.POSTAL_CODE
 	})
 
 # everything is ready to fit! For 200к records fitting should take around 10 minutes,
@@ -464,8 +464,8 @@ And then, for `transform` in a production ML pipeline, you'll get enrichment wit
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
-    		"country": SearchKey.COUNTRY,
-    		"zip_code": SearchKey.POSTAL_CODE,
+		"country": SearchKey.COUNTRY,
+		"zip_code": SearchKey.POSTAL_CODE,
 	},
 ) 
 ```
@@ -516,8 +516,8 @@ enricher = FeaturesEnricher(
 If you're working with multivariate time series, you should specify id columns of individual univariate series in `FeaturesEnricher`. For example, if you have a dataset predicting sales for different stores and products, you should specify store and product id columns as follows:
 ```python
 enricher = FeaturesEnricher(
-    search_keys={
-        "sales_date": SearchKey.DATE,
+		search_keys={
+				"sales_date": SearchKey.DATE,
     },
     id_columns=["store_id", "product_id"],
     cv=CVType.time_series
@@ -733,9 +733,52 @@ enricher.fit(
 )
 ```
 #### ⚠️ Requirements for out-of-time dataset  
-- Same data schema as for search initialization dataset  
+- Same data schema as for search initialization X dataset
 - Pandas dataframe representation
 
+There are 3 options to pass out-of-time without labels:
+```python
+enricher.fit(
+  train_ids_and_features,
+  train_label,
+  eval_set = [
+    (eval_ids_and_features_1,),  # Just tuple of 1 element
+    (eval_ids_and_features_2, None),  # None as labels
+    (eval_ids_and_features_3, [np.nan] * len(eval_ids_and_features_3)),  # List or Series of the same size as eval X
+  ]
+)
+```
+
+### Control feature stability with PSI parameters
+
+`FeaturesEnricher` supports Population Stability Index (PSI) calculation on eval_set to evaluate feature stability over time. You can control this behavior using stability parameters in `fit` and `fit_transform` methods:
+
+```python
+enricher = FeaturesEnricher(
+    search_keys={"registration_date": SearchKey.DATE}
+)
+
+# Control feature stability during fit
+enricher.fit(
+    X, y, 
+    stability_threshold=0.2,  # PSI threshold: features with PSI above this value will be dropped
+    stability_agg_func="max"  # Aggregation function for stability values: "max", "min", "mean"
+)
+
+# Same parameters work for fit_transform
+enriched_df = enricher.fit_transform(
+    X, y,
+    stability_threshold=0.1,   # Stricter threshold for more stable features
+    stability_agg_func="mean"  # Use mean aggregation instead of max
+)
+```
+
+**Stability parameters:**
+- `stability_threshold` (float, default=0.2): PSI threshold value. Features with PSI below this threshold will be excluded from the final feature set. Lower values mean stricter stability requirements.
+- `stability_agg_func` (str, default="max"): Function to aggregate PSI values across time intervals. Options: "max" (most conservative), "min" (least conservative), "mean" (balanced approach).
+
+**PSI (Population Stability Index)** measures how much feature distribution changes over time. Lower PSI values indicate more stable features, which are generally more reliable for production ML models.
+
 ### Use custom loss function in feature selection & metrics calculation
 
 `FeaturesEnricher` can be initialized with additional string parameter `loss`. 
@@ -756,20 +799,6 @@ enricher = FeaturesEnricher(
 enriched_dataframe.fit(X, y)
 ```
 
-### Return initial dataframe enriched with TOP external features by importance
-
-`transform` and `fit_transform` methods of `FeaturesEnricher` can be used with two additional parameters:
-- `importance_threshold`: float = 0 - only features with *importance >= threshold* will be added to the output dataframe
-- `max_features`: int  - only first TOP N features by importance will be returned, where *N = max_features*  
-
-And `keep_input=True` will keep all initial columns from search dataset X:  
-```python
-enricher = FeaturesEnricher(
-	search_keys={"subscription_activation_date": SearchKey.DATE}
-)
-enriched_dataframe.fit_transform(X, y, keep_input=True, max_features=2)
-```
-
 ### Exclude premium data sources from fit, transform and metrics calculation
 
 `fit`, `fit_transform`, `transform` and `calculate_metrics` methods of `FeaturesEnricher` can be used with parameter `exclude_features_sources` that allows to exclude Trial or Paid features from Premium data sources:
@@ -797,7 +826,7 @@ enricher = FeaturesEnricher(
 enricher.fit(X, y)
 ```
 
-## Turn off removing of target outliers
+### Turn off removing of target outliers
 Upgini detect rows with target outlier for regression tasks. By default such rows are dropped on metrics calculation. To turn off removing of target outlier rows use parameter `remove_outliers_calc_metrics=False` in fit, fit_transform or calculate_metrics methods:
 
 ```python
@@ -808,7 +837,7 @@ enricher = FeaturesEnricher(
 enricher.fit(X, y, remove_outliers_calc_metrics=False)
 ```
 
-## Turn off generating features on search keys
+### Turn off generating features on search keys
 Upgini tries to generate features on email, date and datetime search keys. By default this generation is enabled. To disable it use parameter `generate_search_key_features` of FeaturesEnricher constructor:
 
 ```python
@@ -816,6 +845,7 @@ enricher = FeaturesEnricher(
   search_keys={"date": SearchKey.DATE},
   generate_search_key_features=False,
 )
+```
 
 ## 🔑 Open up all capabilities of Upgini
 

{upgini-1.2.113a3974.dev2 → upgini-1.2.114}/README.md

@@ -224,9 +224,9 @@ from upgini.metadata import SearchKey
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
-    		"country": SearchKey.COUNTRY,
-    		"zip_code": SearchKey.POSTAL_CODE,
-    		"hashed_email": SearchKey.HEM,
+		"country": SearchKey.COUNTRY,
+		"zip_code": SearchKey.POSTAL_CODE,
+		"hashed_email": SearchKey.HEM,
 		"last_visit_ip_address": SearchKey.IP,
 		"registered_with_phone": SearchKey.PHONE
 	})
@@ -312,9 +312,9 @@ from upgini.metadata import SearchKey
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
-    		"country": SearchKey.COUNTRY,
-    		"zip_code": SearchKey.POSTAL_CODE,
-    		"hashed_email": SearchKey.HEM,
+		"country": SearchKey.COUNTRY,
+		"zip_code": SearchKey.POSTAL_CODE,
+		"hashed_email": SearchKey.HEM,
 		"last_visit_ip_address": SearchKey.IP,
 		"registered_with_phone": SearchKey.PHONE
 	}, 
@@ -335,7 +335,7 @@ from upgini.metadata import SearchKey
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
-    		"zip_code": SearchKey.POSTAL_CODE,
+		"zip_code": SearchKey.POSTAL_CODE,
 	}, 
 	country_code = "US",
 	date_format = "%Y-%d-%m"
@@ -363,8 +363,8 @@ y = train_df["churn_flag"]
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
-    		"country": SearchKey.COUNTRY,
-    		"zip_code": SearchKey.POSTAL_CODE
+		"country": SearchKey.COUNTRY,
+		"zip_code": SearchKey.POSTAL_CODE
 	})
 
 # everything is ready to fit! For 200к records fitting should take around 10 minutes,
@@ -418,8 +418,8 @@ And then, for `transform` in a production ML pipeline, you'll get enrichment wit
 enricher = FeaturesEnricher(
 	search_keys={
 		"subscription_activation_date": SearchKey.DATE,
-    		"country": SearchKey.COUNTRY,
-    		"zip_code": SearchKey.POSTAL_CODE,
+		"country": SearchKey.COUNTRY,
+		"zip_code": SearchKey.POSTAL_CODE,
 	},
 ) 
 ```
@@ -470,8 +470,8 @@ enricher = FeaturesEnricher(
 If you're working with multivariate time series, you should specify id columns of individual univariate series in `FeaturesEnricher`. For example, if you have a dataset predicting sales for different stores and products, you should specify store and product id columns as follows:
 ```python
 enricher = FeaturesEnricher(
-    search_keys={
-        "sales_date": SearchKey.DATE,
+		search_keys={
+				"sales_date": SearchKey.DATE,
     },
     id_columns=["store_id", "product_id"],
     cv=CVType.time_series
@@ -687,9 +687,52 @@ enricher.fit(
 )
 ```
 #### ⚠️ Requirements for out-of-time dataset  
-- Same data schema as for search initialization dataset  
+- Same data schema as for search initialization X dataset
 - Pandas dataframe representation
 
+There are 3 options to pass out-of-time without labels:
+```python
+enricher.fit(
+  train_ids_and_features,
+  train_label,
+  eval_set = [
+    (eval_ids_and_features_1,),  # Just tuple of 1 element
+    (eval_ids_and_features_2, None),  # None as labels
+    (eval_ids_and_features_3, [np.nan] * len(eval_ids_and_features_3)),  # List or Series of the same size as eval X
+  ]
+)
+```
+
+### Control feature stability with PSI parameters
+
+`FeaturesEnricher` supports Population Stability Index (PSI) calculation on eval_set to evaluate feature stability over time. You can control this behavior using stability parameters in `fit` and `fit_transform` methods:
+
+```python
+enricher = FeaturesEnricher(
+    search_keys={"registration_date": SearchKey.DATE}
+)
+
+# Control feature stability during fit
+enricher.fit(
+    X, y, 
+    stability_threshold=0.2,  # PSI threshold: features with PSI above this value will be dropped
+    stability_agg_func="max"  # Aggregation function for stability values: "max", "min", "mean"
+)
+
+# Same parameters work for fit_transform
+enriched_df = enricher.fit_transform(
+    X, y,
+    stability_threshold=0.1,   # Stricter threshold for more stable features
+    stability_agg_func="mean"  # Use mean aggregation instead of max
+)
+```
+
+**Stability parameters:**
+- `stability_threshold` (float, default=0.2): PSI threshold value. Features with PSI below this threshold will be excluded from the final feature set. Lower values mean stricter stability requirements.
+- `stability_agg_func` (str, default="max"): Function to aggregate PSI values across time intervals. Options: "max" (most conservative), "min" (least conservative), "mean" (balanced approach).
+
+**PSI (Population Stability Index)** measures how much feature distribution changes over time. Lower PSI values indicate more stable features, which are generally more reliable for production ML models.
+
 ### Use custom loss function in feature selection & metrics calculation
 
 `FeaturesEnricher` can be initialized with additional string parameter `loss`. 
@@ -710,20 +753,6 @@ enricher = FeaturesEnricher(
 enriched_dataframe.fit(X, y)
 ```
 
-### Return initial dataframe enriched with TOP external features by importance
-
-`transform` and `fit_transform` methods of `FeaturesEnricher` can be used with two additional parameters:
-- `importance_threshold`: float = 0 - only features with *importance >= threshold* will be added to the output dataframe
-- `max_features`: int  - only first TOP N features by importance will be returned, where *N = max_features*  
-
-And `keep_input=True` will keep all initial columns from search dataset X:  
-```python
-enricher = FeaturesEnricher(
-	search_keys={"subscription_activation_date": SearchKey.DATE}
-)
-enriched_dataframe.fit_transform(X, y, keep_input=True, max_features=2)
-```
-
 ### Exclude premium data sources from fit, transform and metrics calculation
 
 `fit`, `fit_transform`, `transform` and `calculate_metrics` methods of `FeaturesEnricher` can be used with parameter `exclude_features_sources` that allows to exclude Trial or Paid features from Premium data sources:
@@ -751,7 +780,7 @@ enricher = FeaturesEnricher(
 enricher.fit(X, y)
 ```
 
-## Turn off removing of target outliers
+### Turn off removing of target outliers
 Upgini detect rows with target outlier for regression tasks. By default such rows are dropped on metrics calculation. To turn off removing of target outlier rows use parameter `remove_outliers_calc_metrics=False` in fit, fit_transform or calculate_metrics methods:
 
 ```python
@@ -762,7 +791,7 @@ enricher = FeaturesEnricher(
 enricher.fit(X, y, remove_outliers_calc_metrics=False)
 ```
 
-## Turn off generating features on search keys
+### Turn off generating features on search keys
 Upgini tries to generate features on email, date and datetime search keys. By default this generation is enabled. To disable it use parameter `generate_search_key_features` of FeaturesEnricher constructor:
 
 ```python
@@ -770,6 +799,7 @@ enricher = FeaturesEnricher(
   search_keys={"date": SearchKey.DATE},
   generate_search_key_features=False,
 )
+```
 
 ## 🔑 Open up all capabilities of Upgini
 

{upgini-1.2.113a3974.dev2 → upgini-1.2.114}/pyproject.toml

@@ -46,7 +46,7 @@ dependencies = [
     "python-dateutil>=2.8.0",
     "python-json-logger>=3.3.0",
     "requests>=2.8.0",
-    "scikit-learn>=1.3.0",
+    "scikit-learn>=1.3.0,<1.8.0",
     "scipy>=1.10.0",
     "python-bidi==0.4.2",
     "xhtml2pdf>=0.2.11,<0.3.0",

upgini-1.2.114/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.114"

{upgini-1.2.113a3974.dev2 → upgini-1.2.114}/src/upgini/dataset.py

@@ -25,7 +25,6 @@ from upgini.metadata import (
     AutoFEParameters,
     CVType,
     DataType,
-    FeaturesFilter,
     FileColumnMeaningType,
     FileColumnMetadata,
     FileMetadata,
@@ -37,8 +36,9 @@ from upgini.metadata import (
 )
 from upgini.resource_bundle import ResourceBundle, get_custom_bundle
 from upgini.search_task import SearchTask
+from upgini.utils.config import SampleConfig
 from upgini.utils.email_utils import EmailSearchKeyConverter
-from upgini.utils.sample_utils import SampleColumns, SampleConfig, sample
+from upgini.utils.sample_utils import SampleColumns, sample
 
 try:
     from upgini.utils.progress_bar import CustomProgressBar as ProgressBar
@@ -50,10 +50,7 @@ except Exception:
 
 class Dataset:
     MIN_ROWS_COUNT = 100
-    MAX_ROWS = 100_000
-    IMBALANCE_THESHOLD = 0.6
-    MIN_TARGET_CLASS_ROWS = 100
-    MAX_MULTICLASS_CLASS_COUNT = 100
+    MAX_ROWS = 200_000
     MIN_SUPPORTED_DATE_TS = 946684800000  # 2000-01-01
     MAX_FEATURES_COUNT = 3500
     MAX_UPLOADING_FILE_SIZE = 268435456  # 256 Mb
@@ -73,6 +70,7 @@ class Dataset:
         cv_type: Optional[CVType] = None,
         date_column: Optional[str] = None,
         id_columns: Optional[List[str]] = None,
+        is_imbalanced: bool = False,
         random_state: Optional[int] = None,
         sample_config: Optional[SampleConfig] = None,
         rest_client: Optional[_RestClient] = None,
@@ -117,8 +115,9 @@ class Dataset:
         self.rest_client = rest_client
         self.random_state = random_state
         self.columns_renaming: Dict[str, str] = {}
-        self.imbalanced: bool = False
+        self.is_imbalanced: bool = False
         self.id_columns = id_columns
+        self.is_imbalanced = is_imbalanced
         self.date_column = date_column
         if logger is not None:
             self.logger = logger
@@ -184,7 +183,19 @@ class Dataset:
     def __validate_target(self):
         # self.logger.info("Validating target")
         target_column = self.etalon_def_checked.get(FileColumnMeaningType.TARGET.value, "")
-        target = self.data[target_column]
+
+        oot_indices = []
+        if EVAL_SET_INDEX in self.data.columns:
+            for eval_set_index in self.data[EVAL_SET_INDEX].unique():
+                eval_set = self.data[self.data[EVAL_SET_INDEX] == eval_set_index]
+                if eval_set[target_column].isna().all():
+                    oot_indices.append(eval_set_index)
+
+        df_to_check = self.data.copy()
+        if oot_indices:
+            df_to_check = df_to_check[~df_to_check[EVAL_SET_INDEX].isin(oot_indices)]
+
+        target = df_to_check[target_column]
 
         if self.task_type == ModelTaskType.BINARY:
             if not is_integer_dtype(target):
@@ -201,7 +212,7 @@ class Dataset:
         elif self.task_type == ModelTaskType.MULTICLASS:
             if not is_integer_dtype(target):
                 try:
-                    target = self.data[target_column].astype("category").cat.codes
+                    target = target.astype("category").cat.codes
                 except Exception:
                     self.logger.exception("Failed to cast target to category codes for multiclass task type")
                     raise ValidationError(self.bundle.get("dataset_invalid_multiclass_target").format(target.dtype))
@@ -227,8 +238,6 @@ class Dataset:
         else:
             train_segment = self.data
 
-        self.imbalanced = self.__is_imbalanced(train_segment)
-
         sample_columns = SampleColumns(
             ids=self.id_columns,
             date=self.date_column,
@@ -237,55 +246,19 @@ class Dataset:
         )
 
         self.data = sample(
-            train_segment if self.imbalanced else self.data,  # for imbalanced data we will be doing transform anyway
+            train_segment if self.is_imbalanced else self.data,  # for imbalanced data we will be doing transform anyway
             self.task_type,
             self.cv_type,
             self.sample_config,
             sample_columns,
             self.random_state,
-            balance=self.imbalanced,
+            balance=self.is_imbalanced,
             force_downsampling=force_downsampling,
             logger=self.logger,
             bundle=self.bundle,
             warning_callback=self.warning_callback,
         )
 
-    def __is_imbalanced(self, data: pd.DataFrame) -> bool:
-        if self.task_type is None or not self.task_type.is_classification():
-            return False
-
-        if self.task_type == ModelTaskType.BINARY and len(data) <= self.sample_config.binary_min_sample_threshold:
-            return False
-
-        count = len(data)
-        target_column = self.etalon_def_checked.get(FileColumnMeaningType.TARGET.value, TARGET)
-        target = data[target_column]
-        target_classes_count = target.nunique()
-
-        if target_classes_count > self.MAX_MULTICLASS_CLASS_COUNT:
-            msg = self.bundle.get("dataset_to_many_multiclass_targets").format(
-                target_classes_count, self.MAX_MULTICLASS_CLASS_COUNT
-            )
-            self.logger.warning(msg)
-            raise ValidationError(msg)
-
-        vc = target.value_counts()
-        min_class_value = vc.index[len(vc) - 1]
-        min_class_count = vc[min_class_value]
-
-        if min_class_count < self.MIN_TARGET_CLASS_ROWS:
-            msg = self.bundle.get("dataset_rarest_class_less_min").format(
-                min_class_value, min_class_count, self.MIN_TARGET_CLASS_ROWS
-            )
-            self.logger.warning(msg)
-            raise ValidationError(msg)
-
-        min_class_percent = self.IMBALANCE_THESHOLD / target_classes_count
-        min_class_threshold = min_class_percent * count
-
-        # If min class count less than 30% for binary or (60 / classes_count)% for multiclass
-        return bool(min_class_count < min_class_threshold)
-
     def __validate_dataset(self, validate_target: bool, silent_mode: bool):
         """Validate DataSet"""
         # self.logger.info("validating etalon")
@@ -335,15 +308,37 @@ class Dataset:
         all_valid_message = self.bundle.get("validation_all_valid_message")
         invalid_message = self.bundle.get("validation_invalid_message")
 
+        oot_indices = []
+        if EVAL_SET_INDEX in self.data.columns:
+            for eval_set_index in self.data[EVAL_SET_INDEX].unique():
+                eval_set = self.data[self.data[EVAL_SET_INDEX] == eval_set_index]
+                if eval_set[target].isna().all():
+                    oot_indices.append(eval_set_index)
+
         for col in columns_to_validate:
-            self.data[f"{col}_is_valid"] = ~self.data[col].isnull()
             if validate_target and target is not None and col == target:
-                self.data.loc[self.data[target] == np.inf, f"{col}_is_valid"] = False
+                if oot_indices:
+                    mask_not_oot = ~self.data[EVAL_SET_INDEX].isin(oot_indices)
+                    invalid_target_mask = (
+                        self.data[col].isnull() | (self.data[col] == np.inf) | (self.data[col] == -np.inf)
+                    )
+                    # Initialize as valid and mark invalid only for non-OOT rows with NaN or +/-inf
+                    self.data[f"{col}_is_valid"] = True
+                    self.data.loc[mask_not_oot & invalid_target_mask, f"{col}_is_valid"] = False
+                else:
+                    # No OOT: mark invalid where target is NaN or +/-inf
+                    self.data[f"{col}_is_valid"] = ~(
+                        self.data[col].isnull() | (self.data[col] == np.inf) | (self.data[col] == -np.inf)
+                    )
+            else:
+                self.data[f"{col}_is_valid"] = ~self.data[col].isnull()
 
             if col in mandatory_columns:
                 self.data["valid_mandatory"] = self.data["valid_mandatory"] & self.data[f"{col}_is_valid"]
 
-            invalid_values = list(set(self.data.loc[self.data[f"{col}_is_valid"] == 0, col].head().values))
+            # Use stable pandas API across versions: Series.unique keeps order
+            # and collapses multiple NaNs into a single NaN
+            invalid_values = self.data.loc[self.data[f"{col}_is_valid"] == 0, col].unique().tolist()[:5]
             valid_share = self.data[f"{col}_is_valid"].sum() / nrows
             original_col_name = self.columns_renaming[col]
             validation_stats[original_col_name] = {}
@@ -503,9 +498,6 @@ class Dataset:
         return_scores: bool,
         extract_features: bool,
         accurate_model: Optional[bool] = None,
-        importance_threshold: Optional[float] = None,
-        max_features: Optional[int] = None,
-        filter_features: Optional[dict] = None,
         runtime_parameters: Optional[RuntimeParameters] = None,
         metrics_calculation: Optional[bool] = False,
         auto_fe_parameters: Optional[AutoFEParameters] = None,
@@ -514,28 +506,12 @@ class Dataset:
         search_customization = SearchCustomization(
             extractFeatures=extract_features,
             accurateModel=accurate_model,
-            importanceThreshold=importance_threshold,
-            maxFeatures=max_features,
             returnScores=return_scores,
             runtimeParameters=runtime_parameters,
             metricsCalculation=metrics_calculation,
         )
-        if filter_features:
-            if [
-                key
-                for key in filter_features
-                if key not in {"min_importance", "max_psi", "max_count", "selected_features"}
-            ]:
-                raise ValidationError(self.bundle.get("dataset_invalid_filter"))
-            feature_filter = FeaturesFilter(
-                minImportance=filter_features.get("min_importance"),
-                maxPSI=filter_features.get("max_psi"),
-                maxCount=filter_features.get("max_count"),
-                selectedFeatures=filter_features.get("selected_features"),
-            )
-            search_customization.featuresFilter = feature_filter
 
-        search_customization.runtimeParameters.properties["etalon_imbalanced"] = self.imbalanced
+        search_customization.runtimeParameters.properties["etalon_imbalanced"] = self.is_imbalanced
         if auto_fe_parameters is not None:
             search_customization.runtimeParameters.properties["feature_generation_params.ts.gap_days"] = (
                 auto_fe_parameters.ts_gap_days
@@ -590,9 +566,6 @@ class Dataset:
         extract_features: bool = False,
         accurate_model: bool = False,
         exclude_features_sources: Optional[List[str]] = None,
-        importance_threshold: Optional[float] = None,  # deprecated
-        max_features: Optional[int] = None,  # deprecated
-        filter_features: Optional[dict] = None,  # deprecated
         runtime_parameters: Optional[RuntimeParameters] = None,
         auto_fe_parameters: Optional[AutoFEParameters] = None,
         force_downsampling: bool = False,
@@ -609,9 +582,6 @@ class Dataset:
             return_scores=return_scores,
             extract_features=extract_features,
             accurate_model=accurate_model,
-            importance_threshold=importance_threshold,
-            max_features=max_features,
-            filter_features=filter_features,
             runtime_parameters=runtime_parameters,
             auto_fe_parameters=auto_fe_parameters,
         )