upgini 1.2.81a3832.dev1__py3-none-any.whl → 1.2.81a3832.dev3__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.81a3832.dev1"
+__version__ = "1.2.81a3832.dev3"

upgini/features_enricher.py

@@ -310,6 +310,7 @@ class FeaturesEnricher(TransformerMixin):
                     self._search_task = search_task.poll_result(trace_id, quiet=True, check_fit=True)
                     file_metadata = self._search_task.get_file_metadata(trace_id)
                     x_columns = [c.originalName or c.name for c in file_metadata.columns]
+                    self.fit_columns_renaming = {c.name: c.originalName for c in file_metadata.columns}
                     df = pd.DataFrame(columns=x_columns)
                     self.__prepare_feature_importances(trace_id, df, silent=True)
                     # TODO validate search_keys with search_keys from file_metadata
@@ -476,7 +477,7 @@ class FeaturesEnricher(TransformerMixin):
             self.__validate_search_keys(self.search_keys)
 
             # Validate client estimator params
-            self._get_client_cat_features(estimator, X, self.search_keys)
+            self._get_and_validate_client_cat_features(estimator, X, self.search_keys)
 
             try:
                 self.X = X
@@ -957,9 +958,17 @@ class FeaturesEnricher(TransformerMixin):
                     self.__display_support_link(msg)
                     return None
 
-                client_cat_features, search_keys_for_metrics = self._get_client_cat_features(
+                cat_features_from_backend = self.__get_categorical_features()
+                client_cat_features, search_keys_for_metrics = self._get_and_validate_client_cat_features(
                     estimator, validated_X, self.search_keys
                 )
+                for cat_feature in cat_features_from_backend:
+                    original_cat_feature = self.fit_columns_renaming.get(cat_feature)
+                    if original_cat_feature in self.search_keys:
+                        if self.search_keys[original_cat_feature] in [SearchKey.COUNTRY, SearchKey.POSTAL_CODE]:
+                            search_keys_for_metrics.append(original_cat_feature)
+                        else:
+                            self.logger.warning(self.bundle.get("cat_feature_search_key").format(original_cat_feature))
                 search_keys_for_metrics.extend([c for c in self.id_columns or [] if c not in search_keys_for_metrics])
                 self.logger.info(f"Search keys for metrics: {search_keys_for_metrics}")
 
@@ -976,7 +985,7 @@ class FeaturesEnricher(TransformerMixin):
                     search_keys_for_metrics=search_keys_for_metrics,
                     progress_bar=progress_bar,
                     progress_callback=progress_callback,
-                    cat_features=client_cat_features,
+                    client_cat_features=client_cat_features,
                 )
                 if prepared_data is None:
                     return None
@@ -1027,7 +1036,6 @@ class FeaturesEnricher(TransformerMixin):
 
                     has_date = self._get_date_column(search_keys) is not None
                     model_task_type = self.model_task_type or define_task(y_sorted, has_date, self.logger, silent=True)
-                    cat_features_from_backend = self.__get_categorical_features()
                     cat_features = list(set(client_cat_features + cat_features_from_backend))
                     baseline_cat_features = [f for f in cat_features if f in fitting_X.columns]
                     enriched_cat_features = [f for f in cat_features if f in fitting_enriched_X.columns]
@@ -1423,7 +1431,7 @@ class FeaturesEnricher(TransformerMixin):
 
         return _cv, groups
 
-    def _get_client_cat_features(
+    def _get_and_validate_client_cat_features(
         self, estimator: Optional[Any], X: pd.DataFrame, search_keys: Dict[str, SearchKey]
     ) -> Tuple[Optional[List[str]], List[str]]:
         cat_features = None
@@ -1468,7 +1476,7 @@ class FeaturesEnricher(TransformerMixin):
         search_keys_for_metrics: Optional[List[str]] = None,
         progress_bar: Optional[ProgressBar] = None,
         progress_callback: Optional[Callable[[SearchProgress], Any]] = None,
-        cat_features: Optional[List[str]] = None,
+        client_cat_features: Optional[List[str]] = None,
     ):
         is_input_same_as_fit, X, y, eval_set = self._is_input_same_as_fit(X, y, eval_set)
         is_demo_dataset = hash_input(X, y, eval_set) in DEMO_DATASET_HASHES
@@ -1542,7 +1550,7 @@ class FeaturesEnricher(TransformerMixin):
 
         # 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 []) + (cat_features or [])
+        non_excluding_columns = (self.generate_features or []) + (client_cat_features or [])
         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(
@@ -2080,10 +2088,12 @@ class FeaturesEnricher(TransformerMixin):
         search_keys: Dict,
         columns_renaming: Dict[str, str],
     ):
+        # X_sampled - with hash-suffixes
+        reversed_renaming = {v: k for k, v in columns_renaming.items()}
         search_keys = {
-            columns_renaming.get(k, k): v
+            reversed_renaming.get(k, k): v
             for k, v in search_keys.items()
-            if columns_renaming.get(k, k) in X_sampled.columns.to_list()
+            if reversed_renaming.get(k, k) in X_sampled.columns.to_list()
         }
         return FeaturesEnricher._SampledDataForMetrics(
             X_sampled=X_sampled,
@@ -3871,7 +3881,7 @@ if response.status_code == 200:
         if features_meta is None:
             raise Exception(self.bundle.get("missing_features_meta"))
 
-        return [f.name for f in features_meta if f.type == "categorical"]
+        return [f.name for f in features_meta if f.type == "categorical" and f.shap_value > 0.0]
 
     def __prepare_feature_importances(
         self, trace_id: str, df: pd.DataFrame, updated_shaps: Optional[Dict[str, float]] = None, silent=False

upgini/http.py

@@ -20,7 +20,7 @@ import jwt
 # import pandas as pd
 import requests
 from pydantic import BaseModel
-from pythonjsonlogger import jsonlogger
+from pythonjsonlogger import json as jsonlogger
 from requests.exceptions import RequestException
 
 from upgini.__about__ import __version__
@@ -459,19 +459,19 @@ class _RestClient:
                 content = file.read()
                 md5_hash.update(content)
                 digest = md5_hash.hexdigest()
-                metadata_with_md5 = metadata.copy(update={"checksumMD5": digest})
+                metadata_with_md5 = metadata.model_copy(update={"checksumMD5": digest})
 
             # digest_sha256 = hashlib.sha256(
             #     pd.util.hash_pandas_object(pd.read_parquet(file_path, engine="fastparquet")).values
             # ).hexdigest()
             digest_sha256 = self.compute_file_digest(file_path)
-            metadata_with_md5 = metadata_with_md5.copy(update={"digest": digest_sha256})
+            metadata_with_md5 = metadata_with_md5.model_copy(update={"digest": digest_sha256})
 
             with open(file_path, "rb") as file:
                 files = {
                     "metadata": (
                         "metadata.json",
-                        metadata_with_md5.json(exclude_none=True).encode(),
+                        metadata_with_md5.model_dump_json(exclude_none=True).encode(),
                         "application/json",
                     ),
                     "tracking": (
@@ -481,7 +481,7 @@ class _RestClient:
                     ),
                     "metrics": (
                         "metrics.json",
-                        metrics.json(exclude_none=True).encode(),
+                        metrics.model_dump_json(exclude_none=True).encode(),
                         "application/json",
                     ),
                     "file": (metadata_with_md5.name, file, "application/octet-stream"),
@@ -489,7 +489,7 @@ class _RestClient:
                 if search_customization is not None:
                     files["customization"] = (
                         "customization.json",
-                        search_customization.json(exclude_none=True).encode(),
+                        search_customization.model_dump_json(exclude_none=True).encode(),
                         "application/json",
                     )
                 additional_headers = {self.SEARCH_KEYS_HEADER_NAME: ",".join(self.search_keys_meaning_types(metadata))}
@@ -504,7 +504,7 @@ class _RestClient:
     def check_uploaded_file_v2(self, trace_id: str, file_upload_id: str, metadata: FileMetadata) -> bool:
         api_path = self.CHECK_UPLOADED_FILE_URL_FMT_V2.format(file_upload_id)
         response = self._with_unauth_retry(
-            lambda: self._send_post_req(api_path, trace_id, metadata.json(exclude_none=True))
+            lambda: self._send_post_req(api_path, trace_id, metadata.model_dump_json(exclude_none=True))
         )
         return bool(response)
 
@@ -518,11 +518,11 @@ class _RestClient:
     ) -> SearchTaskResponse:
         api_path = self.INITIAL_SEARCH_WITHOUT_UPLOAD_URI_FMT_V2.format(file_upload_id)
         files = {
-            "metadata": ("metadata.json", metadata.json(exclude_none=True).encode(), "application/json"),
-            "metrics": ("metrics.json", metrics.json(exclude_none=True).encode(), "application/json"),
+            "metadata": ("metadata.json", metadata.model_dump_json(exclude_none=True).encode(), "application/json"),
+            "metrics": ("metrics.json", metrics.model_dump_json(exclude_none=True).encode(), "application/json"),
         }
         if search_customization is not None:
-            files["customization"] = search_customization.json(exclude_none=True).encode()
+            files["customization"] = search_customization.model_dump_json(exclude_none=True).encode()
         additional_headers = {self.SEARCH_KEYS_HEADER_NAME: ",".join(self.search_keys_meaning_types(metadata))}
         response = self._with_unauth_retry(
             lambda: self._send_post_file_req_v2(
@@ -548,19 +548,19 @@ class _RestClient:
                 content = file.read()
                 md5_hash.update(content)
                 digest = md5_hash.hexdigest()
-                metadata_with_md5 = metadata.copy(update={"checksumMD5": digest})
+                metadata_with_md5 = metadata.model_copy(update={"checksumMD5": digest})
 
             # digest_sha256 = hashlib.sha256(
             #     pd.util.hash_pandas_object(pd.read_parquet(file_path, engine="fastparquet")).values
             # ).hexdigest()
             digest_sha256 = self.compute_file_digest(file_path)
-            metadata_with_md5 = metadata_with_md5.copy(update={"digest": digest_sha256})
+            metadata_with_md5 = metadata_with_md5.model_copy(update={"digest": digest_sha256})
 
             with open(file_path, "rb") as file:
                 files = {
                     "metadata": (
                         "metadata.json",
-                        metadata_with_md5.json(exclude_none=True).encode(),
+                        metadata_with_md5.model_dump_json(exclude_none=True).encode(),
                         "application/json",
                     ),
                     "tracking": (
@@ -570,7 +570,7 @@ class _RestClient:
                     ),
                     "metrics": (
                         "metrics.json",
-                        metrics.json(exclude_none=True).encode(),
+                        metrics.model_dump_json(exclude_none=True).encode(),
                         "application/json",
                     ),
                     "file": (metadata_with_md5.name, file, "application/octet-stream"),
@@ -578,7 +578,7 @@ class _RestClient:
                 if search_customization is not None:
                     files["customization"] = (
                         "customization.json",
-                        search_customization.json(exclude_none=True).encode(),
+                        search_customization.model_dump_json(exclude_none=True).encode(),
                         "application/json",
                     )
 
@@ -602,11 +602,11 @@ class _RestClient:
     ) -> SearchTaskResponse:
         api_path = self.VALIDATION_SEARCH_WITHOUT_UPLOAD_URI_FMT_V2.format(file_upload_id, initial_search_task_id)
         files = {
-            "metadata": ("metadata.json", metadata.json(exclude_none=True).encode(), "application/json"),
-            "metrics": ("metrics.json", metrics.json(exclude_none=True).encode(), "application/json"),
+            "metadata": ("metadata.json", metadata.model_dump_json(exclude_none=True).encode(), "application/json"),
+            "metrics": ("metrics.json", metrics.model_dump_json(exclude_none=True).encode(), "application/json"),
         }
         if search_customization is not None:
-            files["customization"] = search_customization.json(exclude_none=True).encode()
+            files["customization"] = search_customization.model_dump_json(exclude_none=True).encode()
         additional_headers = {self.SEARCH_KEYS_HEADER_NAME: ",".join(self.search_keys_meaning_types(metadata))}
         response = self._with_unauth_retry(
             lambda: self._send_post_file_req_v2(
@@ -670,7 +670,7 @@ class _RestClient:
                     "file": (metadata.name, file, "application/octet-stream"),
                     "metadata": (
                         "metadata.json",
-                        metadata.json(exclude_none=True).encode(),
+                        metadata.model_dump_json(exclude_none=True).encode(),
                         "application/json",
                     ),
                 }
@@ -682,12 +682,12 @@ class _RestClient:
     def get_search_file_metadata(self, search_task_id: str, trace_id: str) -> FileMetadata:
         api_path = self.SEARCH_FILE_METADATA_URI_FMT_V2.format(search_task_id)
         response = self._with_unauth_retry(lambda: self._send_get_req(api_path, trace_id))
-        return FileMetadata.parse_obj(response)
+        return FileMetadata.model_validate(response)
 
     def get_provider_search_metadata_v3(self, provider_search_task_id: str, trace_id: str) -> ProviderTaskMetadataV2:
         api_path = self.SEARCH_TASK_METADATA_FMT_V3.format(provider_search_task_id)
         response = self._with_unauth_retry(lambda: self._send_get_req(api_path, trace_id))
-        return ProviderTaskMetadataV2.parse_obj(response)
+        return ProviderTaskMetadataV2.model_validate(response)
 
     def get_current_transform_usage(self, trace_id) -> TransformUsage:
         track_metrics = get_track_metrics(self.client_ip, self.client_visitorid)

upgini/mdc/__init__.py

@@ -5,7 +5,7 @@
 
 import logging
 
-from pythonjsonlogger import jsonlogger
+from pythonjsonlogger import json as jsonlogger
 
 from upgini.mdc.context import get_mdc_fields, new_log_context
 

upgini/metrics.py

@@ -11,13 +11,14 @@ from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 import lightgbm as lgb
 import numpy as np
 import pandas as pd
+from catboost import CatBoostClassifier, CatBoostRegressor
 from category_encoders.cat_boost import CatBoostEncoder
 from lightgbm import LGBMClassifier, LGBMRegressor
 from numpy import log1p
 from pandas.api.types import is_numeric_dtype
 from sklearn.metrics import check_scoring, get_scorer, make_scorer, roc_auc_score
 
-from upgini.utils.blocked_time_series import BlockedTimeSeriesSplit
+# from upgini.utils.blocked_time_series import BlockedTimeSeriesSplit
 from upgini.utils.features_validator import FeaturesValidator
 from upgini.utils.sklearn_ext import cross_validate
 
@@ -31,7 +32,7 @@ except ImportError:
     available_scorers = SCORERS
 from sklearn.metrics import mean_squared_error
 from sklearn.metrics._regression import _check_reg_targets, check_consistent_length
-from sklearn.model_selection import BaseCrossValidator, TimeSeriesSplit
+from sklearn.model_selection import BaseCrossValidator  # , TimeSeriesSplit
 
 from upgini.errors import ValidationError
 from upgini.metadata import ModelTaskType
@@ -328,10 +329,14 @@ class EstimatorWrapper:
     ) -> Tuple[pd.DataFrame, np.ndarray, np.ndarray]:
         self.logger.info(f"Before preparing data columns: {x.columns.to_list()}")
         for c in x.columns:
-            if is_numeric_dtype(x[c]):
-                x[c] = x[c].astype(float)
-            elif not x[c].dtype == "category":
-                x[c] = x[c].astype(str)
+            if c not in self.cat_features:
+                if is_numeric_dtype(x[c]):
+                    x[c] = x[c].astype(float)
+                elif not x[c].dtype == "category":
+                    x[c] = x[c].astype(str)
+            else:
+                if x[c].dtype == "category" and x[c].cat.categories.dtype == np.int64:
+                    x[c] = x[c].astype(np.int64)
 
         if not isinstance(y, pd.Series):
             raise Exception(bundle.get("metrics_unsupported_target_type").format(type(y)))
@@ -411,7 +416,6 @@ class EstimatorWrapper:
                 shaps = self.calculate_shap(cv_x, cv_y, estimator)
                 if shaps is not None:
                     for feature, shap_value in shaps.items():
-                        # shap_values_all_folds[feature] = shap_values_all_folds.get(feature, []) + shap_value.tolist()
                         shap_values_all_folds[feature].append(shap_value)
 
         if shap_values_all_folds:
@@ -488,20 +492,29 @@ class EstimatorWrapper:
             "logger": logger,
         }
         if estimator is None:
-            params = {"random_state": DEFAULT_RANDOM_STATE, "verbose": -1}
+            params = {"has_time": has_date}
             if target_type == ModelTaskType.MULTICLASS:
-                params = _get_add_params(params, LIGHTGBM_MULTICLASS_PARAMS)
+                params = _get_add_params(params, CATBOOST_MULTICLASS_PARAMS)
                 params = _get_add_params(params, add_params)
-                estimator = LightGBMWrapper(LGBMClassifier(**params), **kwargs)
+                estimator = CatBoostWrapper(CatBoostClassifier(**params), **kwargs)
+                # params = _get_add_params(params, LIGHTGBM_MULTICLASS_PARAMS)
+                # params = _get_add_params(params, add_params)
+                # estimator = LightGBMWrapper(LGBMClassifier(**params), **kwargs)
             elif target_type == ModelTaskType.BINARY:
-                params = _get_add_params(params, LIGHTGBM_BINARY_PARAMS)
+                params = _get_add_params(params, CATBOOST_BINARY_PARAMS)
                 params = _get_add_params(params, add_params)
-                estimator = LightGBMWrapper(LGBMClassifier(**params), **kwargs)
+                estimator = CatBoostWrapper(CatBoostClassifier(**params), **kwargs)
+                # params = _get_add_params(params, LIGHTGBM_BINARY_PARAMS)
+                # params = _get_add_params(params, add_params)
+                # estimator = LightGBMWrapper(LGBMClassifier(**params), **kwargs)
             elif target_type == ModelTaskType.REGRESSION:
-                if not isinstance(cv, TimeSeriesSplit) and not isinstance(cv, BlockedTimeSeriesSplit):
-                    params = _get_add_params(params, LIGHTGBM_REGRESSION_PARAMS)
+                params = _get_add_params(params, CATBOOST_REGRESSION_PARAMS)
                 params = _get_add_params(params, add_params)
-                estimator = LightGBMWrapper(LGBMRegressor(**params), **kwargs)
+                estimator = CatBoostWrapper(CatBoostRegressor(**params), **kwargs)
+                # if not isinstance(cv, TimeSeriesSplit) and not isinstance(cv, BlockedTimeSeriesSplit):
+                #     params = _get_add_params(params, LIGHTGBM_REGRESSION_PARAMS)
+                # params = _get_add_params(params, add_params)
+                # estimator = LightGBMWrapper(LGBMRegressor(**params), **kwargs)
             else:
                 raise Exception(bundle.get("metrics_unsupported_target_type").format(target_type))
         else:
@@ -517,8 +530,6 @@ class EstimatorWrapper:
             else:
                 if isinstance(estimator, (LGBMClassifier, LGBMRegressor)):
                     estimator = LightGBMWrapper(**kwargs)
-                elif is_catboost_estimator(estimator):
-                    estimator = CatBoostWrapper(**kwargs)
                 else:
                     logger.warning(
                         f"Unexpected estimator is used for metrics: {estimator}. "
@@ -558,6 +569,7 @@ class CatBoostWrapper(EstimatorWrapper):
         self.emb_features = None
         self.grouped_embedding_features = None
         self.drop_cat_features = []
+        self.features_to_encode = []
 
     def _prepare_to_fit(self, x: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, np.ndarray, np.ndarray, dict]:
         x, y, groups, params = super()._prepare_to_fit(x, y)
@@ -597,7 +609,13 @@ class CatBoostWrapper(EstimatorWrapper):
         self.cat_features, self.features_to_encode, self.exclude_features = _get_cat_features(
             self.logger, x, self.cat_features, self.text_features, self.grouped_embedding_features
         )
-        params["cat_features"] = self.cat_features
+        if self.features_to_encode:
+            for c in self.features_to_encode:
+                if is_numeric_dtype(x[c]):
+                    x[c] = x[c].fillna(np.nan)
+                else:
+                    x[c] = x[c].fillna("NA")
+            params["cat_features"] = self.features_to_encode
 
         return x, y, groups, params
 
@@ -626,8 +644,14 @@ class CatBoostWrapper(EstimatorWrapper):
         if self.grouped_embedding_features:
             x, emb_columns = self.group_embeddings(x)
             params["embedding_features"] = emb_columns
-        if self.cat_features:
-            params["cat_features"] = self.cat_features
+
+        if self.features_to_encode:
+            for c in self.features_to_encode:
+                if is_numeric_dtype(x[c]):
+                    x[c] = x[c].fillna(np.nan)
+                else:
+                    x[c] = x[c].fillna("NA")
+            params["cat_features"] = self.features_to_encode
 
         return x, y, params
 
@@ -671,23 +695,29 @@ class CatBoostWrapper(EstimatorWrapper):
                 embedding_features=self.grouped_embedding_features,
             )
 
-            # Get SHAP values of current estimator
-            shap_values_fold = estimator.get_feature_importance(data=fold_pool, type="ShapValues")
+            shap_values = estimator.get_feature_importance(data=fold_pool, type="ShapValues")
 
-            # Remove last columns (base value) and flatten
             if self.target_type == ModelTaskType.MULTICLASS:
-                all_shaps = shap_values_fold[:, :, :-1]
-                all_shaps = [all_shaps[:, :, k].flatten() for k in range(all_shaps.shape[2])]
+                # For multiclass, shap_values has shape (n_samples, n_classes, n_features + 1)
+                # Last column is bias term
+                shap_values = shap_values[:, :, :-1]  # Remove bias term
+                # Average SHAP values across classes
+                shap_values = np.mean(np.abs(shap_values), axis=1)
             else:
-                all_shaps = shap_values_fold[:, :-1]
-                all_shaps = [all_shaps[:, k].flatten() for k in range(all_shaps.shape[1])]
+                # For binary/regression, shap_values has shape (n_samples, n_features + 1)
+                # Last column is bias term
+                shap_values = shap_values[:, :-1]  # Remove bias term
+                # Take absolute values
+                shap_values = np.abs(shap_values)
 
-            all_shaps = np.abs(all_shaps)
+            feature_importance = {}
+            for i, col in enumerate(x.columns):
+                feature_importance[col] = np.mean(np.abs(shap_values[:, i]))
 
-            return dict(zip(estimator.feature_names_, all_shaps))
+            return feature_importance
 
-        except Exception:
-            self.logger.exception("Failed to recalculate new SHAP values")
+        except Exception as e:
+            self.logger.exception(f"Failed to recalculate new SHAP values: {str(e)}")
             return None
 
 
@@ -830,9 +860,9 @@ class OtherEstimatorWrapper(EstimatorWrapper):
             num_features = [col for col in x.columns if col not in self.cat_features]
             x[num_features] = x[num_features].fillna(-999)
             if self.features_to_encode and self.cat_encoder is not None:
-                x[self.features_to_encode] = self.cat_encoder.transform(x[self.features_to_encode].astype("object")).astype(
-                    "category"
-                )
+                x[self.features_to_encode] = self.cat_encoder.transform(
+                    x[self.features_to_encode].astype("object")
+                ).astype("category")
         return x, y, params
 
 
@@ -935,17 +965,17 @@ def _get_cat_features(
     drop_cat_features = []
     for name in cat_features:
         # Remove constant categorical features
-        if x[name].nunique() > 1:
+        if x[name].nunique(dropna=False) > 1:
             unique_cat_features.append(name)
         else:
-            logger.info(f"Drop column {name} on preparing data for fit")
-            x = x.drop(columns=name)
+            logger.warning(f"Drop column {name} on preparing data for fit")
+            x.drop(columns=name, inplace=True)
             drop_cat_features.append(name)
     cat_features = unique_cat_features
 
     logger.info(f"Selected categorical features: {cat_features}")
 
-    features_to_encode = list(set(x.select_dtypes(exclude=[np.number, np.datetime64, pd.CategoricalDtype]).columns))
+    features_to_encode = list(set(x.select_dtypes(exclude=[np.number, np.datetime64, pd.CategoricalDtype()]).columns))
 
     logger.info(f"Features to encode: {features_to_encode}")
 

{upgini-1.2.81a3832.dev1.dist-info → upgini-1.2.81a3832.dev3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.81a3832.dev1
+Version: 1.2.81a3832.dev3
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -22,6 +22,7 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Scientific/Engineering :: Information Analysis
 Requires-Python: <3.12,>=3.10
+Requires-Dist: catboost>=1.0.3
 Requires-Dist: category-encoders>=2.8.1
 Requires-Dist: fastparquet>=0.8.1
 Requires-Dist: ipywidgets>=8.1.0

{upgini-1.2.81a3832.dev1.dist-info → upgini-1.2.81a3832.dev3.dist-info}/RECORD

@@ -1,12 +1,12 @@
-upgini/__about__.py,sha256=-WSXUS5Ith33qArTnDO4LmrI0wUaXbJ8bIzoMZvAsWU,33
+upgini/__about__.py,sha256=sQSOnYXU8JfHaCG4spEa8dwpUzrTX39X2sSVYCzITIk,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=aspri7ZAgwkNNUiIgQ1GRXvw8XQii3F4RfNXSrF4wrw,35365
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=qtrQJwF2QbKdQ8Tqk5RQj3aAqOzDgygD6nIHrco3AzE,209728
-upgini/http.py,sha256=UH7nswcZ221un3O_VW9limCBO5oRsyg1eKUHiVslRPs,43737
+upgini/features_enricher.py,sha256=WiSVfmlHI9oKJQbyf46FH0yY80hBJ6hheFpugw0f_vE,210583
+upgini/http.py,sha256=AfaJ3c8z_tK2hZFEehNybDKE0mp1tYcyAP_l0_p8bLQ,43933
 upgini/metadata.py,sha256=Yd6iW2f7Wz6vUkg5uvR4xylN16ANnCKVKqAsAkap7p8,12354
-upgini/metrics.py,sha256=95sK1Kr3dYxqQcdkkoNFDe9OZY7OhgLjYwe3bhMQd38,38087
+upgini/metrics.py,sha256=fhBhMM455C__1adECAk2H3K-zyO_WUnVqZV_AJ-rQBo,39633
 upgini/search_task.py,sha256=RcvAE785yksWTsTNWuZFVNlk32jHElMoEna1T_C5N8Q,17823
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
@@ -32,7 +32,7 @@ upgini/autofe/timeseries/trend.py,sha256=K1_iw2ko_LIUU8YCUgrvN3n0MkHtsi7-63-8x9e
 upgini/autofe/timeseries/volatility.py,sha256=9shUmIKjpWTHVYjj80YBsk0XheBJ9uBuLv5NW9Mchnk,7953
 upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/data_source/data_source_publisher.py,sha256=4S9qwlAklD8vg9tUU_c1pHE2_glUHAh15-wr5hMwKFw,22879
-upgini/mdc/__init__.py,sha256=aM08nIWFc2gWdWUa3_IuEnNND0cQPkBGnYpRMnfFN8k,1019
+upgini/mdc/__init__.py,sha256=iHJlXQg6xRM1-ZOUtaPSJqw5SpQDszvxp4LyqviNLIQ,1027
 upgini/mdc/context.py,sha256=3u1B-jXt7tXEvNcV3qmR9SDCseudnY7KYsLclBdwVLk,1405
 upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/normalizer/normalize_utils.py,sha256=Ft2MwSgVoBilXAORAOYAuwPD79GOLfwn4qQE3IUFzzg,7218
@@ -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-1.2.81a3832.dev1.dist-info/METADATA,sha256=ShIRi8EeeujsKBJ0byR2XWJ6DKFka2vrViq9d5VwjzU,49141
-upgini-1.2.81a3832.dev1.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.81a3832.dev1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.81a3832.dev1.dist-info/RECORD,,
+upgini-1.2.81a3832.dev3.dist-info/METADATA,sha256=rjTrlaR6RTthHUMnhRDn3QFCs9EhW6dDUHukgwnObxI,49172
+upgini-1.2.81a3832.dev3.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.81a3832.dev3.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.81a3832.dev3.dist-info/RECORD,,