upgini 1.2.70a3832.dev2__py3-none-any.whl → 1.2.71__py3-none-any.whl

upgini/metadata.py

@@ -325,6 +325,10 @@ class RuntimeParameters(BaseModel):
     properties: Dict[str, Any] = {}
 
 
+class AutoFEParameters(BaseModel):
+    ts_gap_days: Optional[int] = None
+
+
 class SearchCustomization(BaseModel):
     featuresFilter: Optional[FeaturesFilter] = None
     extractFeatures: Optional[bool] = None

upgini/metrics.py

@@ -3,21 +3,23 @@ from __future__ import annotations
 import inspect
 import logging
 import re
-import warnings
 from collections import defaultdict
 from copy import deepcopy
 from dataclasses import dataclass
 from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 
+import lightgbm as lgb
 import numpy as np
 import pandas as pd
 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 sklearn.preprocessing import OrdinalEncoder
 
 from upgini.utils.features_validator import FeaturesValidator
 from upgini.utils.sklearn_ext import cross_validate
+from upgini.utils.blocked_time_series import BlockedTimeSeriesSplit
 
 try:
     from sklearn.metrics import get_scorer_names
@@ -29,7 +31,7 @@ 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
+from sklearn.model_selection import BaseCrossValidator, TimeSeriesSplit
 
 from upgini.errors import ValidationError
 from upgini.metadata import ModelTaskType
@@ -83,22 +85,6 @@ CATBOOST_MULTICLASS_PARAMS = {
     "auto_class_weights": "Balanced",
 }
 
-LIGHTGBM_PARAMS = {
-    "random_state": DEFAULT_RANDOM_STATE,
-    # "num_leaves": 16,
-    # "n_estimators": 150,
-    # "min_child_weight": 1,
-    "max_depth": 4,
-    "max_cat_threshold": 80,
-    "min_data_per_group": 25,
-    "num_boost_round": 150,
-    "cat_l2": 10,
-    "cat_smooth": 12,
-    "learning_rate": 0.05,
-    "feature_fraction": 1.0,
-    "min_sum_hessian_in_leaf": 0.01,
-}
-
 LIGHTGBM_REGRESSION_PARAMS = {
     "random_state": DEFAULT_RANDOM_STATE,
     "deterministic": True,
@@ -118,18 +104,16 @@ LIGHTGBM_REGRESSION_PARAMS = {
 
 LIGHTGBM_MULTICLASS_PARAMS = {
     "random_state": DEFAULT_RANDOM_STATE,
-    "deterministic": True,
-    "min_gain_to_split": 0.001,
     "n_estimators": 275,
-    "max_depth": 3,
+    "max_depth": 5,
+    "learning_rate": 0.05,
+    "min_gain_to_split": 0.001,
     "max_cat_threshold": 80,
-    "min_data_per_group": 25,
-    "cat_l2": 10,
-    "cat_smooth": 12,
-    "learning_rate": 0.25,  # CatBoost 0.25
-    "min_sum_hessian_in_leaf": 0.01,
-    "class_weight": "balanced",  # TODO pass dict with weights for each class
+    "min_data_per_group": 20,
+    "cat_smooth": 18,
+    "cat_l2": 8,
     "objective": "multiclass",
+    # "class_weight": "balanced",
     "use_quantized_grad": "true",
     "num_grad_quant_bins": "8",
     "stochastic_rounding": "true",
@@ -138,22 +122,22 @@ LIGHTGBM_MULTICLASS_PARAMS = {
 
 LIGHTGBM_BINARY_PARAMS = {
     "random_state": DEFAULT_RANDOM_STATE,
-    "deterministic": True,
     "min_gain_to_split": 0.001,
     "n_estimators": 275,
     "max_depth": 5,
-    "max_cat_threshold": 80,
-    "min_data_per_group": 25,
-    "cat_l2": 10,
-    "cat_smooth": 12,
     "learning_rate": 0.05,
-    "feature_fraction": 1.0,
-    "min_sum_hessian_in_leaf": 0.01,
     "objective": "binary",
-    "class_weight": "balanced",  # TODO pass dict with weights for each class
+    # "class_weight": "balanced",
+    "deterministic": True,
+    "max_cat_threshold": 80,
+    "min_data_per_group": 20,
+    "cat_smooth": 18,
+    "cat_l2": 8,
     "verbosity": -1,
 }
 
+LIGHTGBM_EARLY_STOPPING_ROUNDS = 20
+
 N_FOLDS = 5
 BLOCKED_TS_TEST_SIZE = 0.2
 
@@ -507,7 +491,8 @@ class EstimatorWrapper:
                 params = _get_add_params(params, add_params)
                 estimator = LightGBMWrapper(LGBMClassifier(**params), **kwargs)
             elif target_type == ModelTaskType.REGRESSION:
-                params = _get_add_params(params, LIGHTGBM_REGRESSION_PARAMS)
+                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:
@@ -756,13 +741,24 @@ class LightGBMWrapper(EstimatorWrapper):
             logger=logger,
         )
         self.cat_features = None
+        self.cat_encoder = None
+        self.n_classes = None
 
     def _prepare_to_fit(self, x: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, pd.Series, np.ndarray, dict]:
         x, y_numpy, groups, params = super()._prepare_to_fit(x, y)
+        if self.target_type in [ModelTaskType.BINARY, ModelTaskType.MULTICLASS]:
+            self.n_classes = len(np.unique(y_numpy))
+        if LIGHTGBM_EARLY_STOPPING_ROUNDS is not None:
+            params["callbacks"] = [lgb.early_stopping(stopping_rounds=LIGHTGBM_EARLY_STOPPING_ROUNDS, verbose=False)]
         self.cat_features = _get_cat_features(x)
-        x = fill_na_cat_features(x, self.cat_features)
-        for feature in self.cat_features:
-            x[feature] = x[feature].astype("category").cat.codes
+        if self.cat_features:
+            x = fill_na_cat_features(x, self.cat_features)
+            encoder = OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=-1)
+            encoded = pd.DataFrame(
+                encoder.fit_transform(x[self.cat_features]), columns=self.cat_features, dtype="category"
+            )
+            x[self.cat_features] = encoded
+            self.cat_encoder = encoder
         if not is_numeric_dtype(y_numpy):
             y_numpy = correct_string_target(y_numpy)
 
@@ -772,39 +768,50 @@ class LightGBMWrapper(EstimatorWrapper):
         x, y_numpy, params = super()._prepare_to_calculate(x, y)
         if self.cat_features is not None:
             x = fill_na_cat_features(x, self.cat_features)
-            for feature in self.cat_features:
-                x[feature] = x[feature].astype("category").cat.codes
+            if self.cat_encoder is not None:
+                x[self.cat_features] = pd.DataFrame(
+                    self.cat_encoder.transform(x[self.cat_features]), columns=self.cat_features, dtype="category"
+                )
         if not is_numeric_dtype(y):
             y_numpy = correct_string_target(y_numpy)
         return x, y_numpy, params
 
     def calculate_shap(self, x: pd.DataFrame, y: pd.Series, estimator) -> Optional[Dict[str, float]]:
         try:
-            # Suppress specific warning from SHAP for LightGBM binary classifier
-            warnings.filterwarnings(
-                "ignore",
-                message=(
-                    "LightGBM binary classifier with TreeExplainer shap values output has changed to a list of ndarray"
-                ),
+            shap_matrix = estimator.predict(
+                x,
+                predict_disable_shape_check=True,
+                raw_score=True,
+                pred_leaf=False,
+                pred_early_stop=True,
+                pred_contrib=True,
             )
-            from shap import TreeExplainer
-
-            if not isinstance(estimator, (LGBMRegressor, LGBMClassifier)):
-                return None
 
-            explainer = TreeExplainer(estimator)
-
-            shap_values = explainer.shap_values(x)
+            if self.target_type == ModelTaskType.MULTICLASS:
+                n_feat = x.shape[1]
+                shap_matrix.shape = (shap_matrix.shape[0], self.n_classes, n_feat + 1)
+                shap_matrix = np.mean(np.abs(shap_matrix), axis=1)
 
-            # For classification, shap_values is returned as a list for each class
-            # Take values for the positive class
-            if isinstance(shap_values, list):
-                shap_values = shap_values[1]
+            # exclude base value
+            shap_matrix = shap_matrix[:, :-1]
 
-            # Calculate mean absolute SHAP value for each feature
             feature_importance = {}
             for i, col in enumerate(x.columns):
-                feature_importance[col] = np.mean(np.abs(shap_values[:, i]))
+                feature_importance[col] = np.mean(np.abs(shap_matrix[:, i]))
+
+            # # exclude last column (base value)
+            # shap_values_only = shap_values[:, :-1]
+            # mean_abs_shap = np.mean(np.abs(shap_values_only), axis=0)
+
+            # # For classification, shap_values is returned as a list for each class
+            # # Take values for the positive class
+            # if isinstance(shap_values, list):
+            #     shap_values = shap_values[1]
+
+            # # Calculate mean absolute SHAP value for each feature
+            # feature_importance = {}
+            # for i, col in enumerate(x.columns):
+            #     feature_importance[col] = np.mean(np.abs(shap_values[:, i]))
 
             return feature_importance
 

upgini/resource_bundle/strings.properties

@@ -137,6 +137,7 @@ x_and_eval_x_diff_types=X and eval_set X has different types: {} and {}
 baseline_score_column_not_exists=baseline_score_column {} doesn't exist in input dataframe
 baseline_score_column_has_na=baseline_score_column contains NaN. Clear it and and retry
 missing_features_for_transform=Missing some features for transform that were presented on fit: {}
+missing_target_for_transform=Search contains features on target. Please add y to the call and try again
 missing_id_column=Id column {} not found in X
     # target validation
 empty_target=Target is empty in all rows

upgini/search_task.py

@@ -168,7 +168,13 @@ class SearchTask:
         for meta in self.provider_metadata_v2:
             if meta.features_used_for_embeddings is not None:
                 features_for_transform.update(meta.features_used_for_embeddings)
-
+            if meta.generated_features:
+                features_for_transform.update(
+                    c.original_name
+                    for f in meta.generated_features
+                    for c in f.base_columns
+                    if c.ads_definition_id is None
+                )
         return list(features_for_transform)
 
     def get_shuffle_kfold(self) -> Optional[bool]:

upgini/utils/mstats.py

@@ -118,7 +118,7 @@ def spearmanr(
     # - dof: degrees of freedom
     # - t_stat: t-statistic
     # - alternative: 'two-sided', 'greater', 'less'
-    def compute_t_pvalue(t_stat, dof, alternative='two-sided'):
+    def compute_t_pvalue(t_stat, dof, alternative="two-sided"):
         from scipy.stats import t
 
         if alternative == "two-sided":

upgini/utils/sklearn_ext.py

@@ -349,6 +349,14 @@ def is_catboost_estimator(estimator):
         return False
 
 
+def is_lightgbm_estimator(estimator):
+    try:
+        from lightgbm import LGBMClassifier, LGBMRegressor
+        return isinstance(estimator, (LGBMClassifier, LGBMRegressor))
+    except ImportError:
+        return False
+
+
 def _fit_and_score(
     estimator,
     X,
@@ -507,6 +515,9 @@ def _fit_and_score(
             if is_catboost_estimator(estimator):
                 fit_params = fit_params.copy()
                 fit_params["eval_set"] = [(X_test, y_test)]
+            elif is_lightgbm_estimator(estimator):
+                fit_params = fit_params.copy()
+                fit_params["eval_set"] = [(X_test, y_test)]
             estimator.fit(X_train, y_train, **fit_params)
 
     except Exception:

upgini/utils/sort.py

@@ -87,7 +87,7 @@ def get_sort_columns_dict(
     df_with_target = df_with_target.loc[~target.isna()]
     df = df_with_target.iloc[:, :-1]
     target = df_with_target.iloc[:, -1]
-    df = df.fillna(df.mean())
+    df = df.fillna(df.apply(lambda x: int(x.mean()) if pd.api.types.is_integer_dtype(x) else x.mean()))
     omit_nan = False
     hashes = [hash_series(df[col]) for col in columns_for_sort]
     df = np.asarray(df, dtype=np.float32)

upgini/utils/target_utils.py

@@ -204,7 +204,7 @@ def balance_undersample(
 def balance_undersample_forced(
     df: pd.DataFrame,
     target_column: str,
-    id_columns: List[str],
+    id_columns: Optional[List[str]],
     date_column: str,
     task_type: ModelTaskType,
     cv_type: Optional[CVType],
@@ -287,7 +287,7 @@ DEFAULT_TIME_UNIT_THRESHOLD = pd.Timedelta(weeks=4)
 
 def balance_undersample_time_series_trunc(
     df: pd.DataFrame,
-    id_columns: List[str],
+    id_columns: Optional[List[str]],
     date_column: str,
     sample_size: int,
     random_state: int = 42,
@@ -298,6 +298,8 @@ def balance_undersample_time_series_trunc(
     **kwargs,
 ):
     # Convert date column to datetime
+    if id_columns is None:
+        id_columns = [date_column]
     dates_df = df[id_columns + [date_column]].copy()
     dates_df[date_column] = pd.to_datetime(dates_df[date_column], unit="ms")
 

{upgini-1.2.70a3832.dev2.dist-info → upgini-1.2.71.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.70a3832.dev2
+Version: 1.2.71
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -17,12 +17,11 @@ Classifier: Intended Audience :: Science/Research
 Classifier: Intended Audience :: Telecommunications Industry
 Classifier: License :: OSI Approved :: BSD License
 Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Scientific/Engineering :: Information Analysis
-Requires-Python: <3.12,>=3.8
+Requires-Python: <3.12,>=3.10
 Requires-Dist: fastparquet>=0.8.1
 Requires-Dist: ipywidgets>=8.1.0
 Requires-Dist: jarowinkler>=2.0.0

{upgini-1.2.70a3832.dev2.dist-info → upgini-1.2.71.dist-info}/RECORD

@@ -1,14 +1,13 @@
-upgini/__about__.py,sha256=kdfsfbpVybww_eNOlX3jVjyk7oUeeXZvGBwotRAlM-U,33
+upgini/__about__.py,sha256=GEAFb-nM2N0vpxFRvsPnDG0tUOHq0YpnqvOcoHBpoqg,23
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
-upgini/dataset.py,sha256=1rb6BzyuiQFGVCTDmKL2wox3UFRNjtNaIJOwQnZ801A,34956
+upgini/dataset.py,sha256=aspri7ZAgwkNNUiIgQ1GRXvw8XQii3F4RfNXSrF4wrw,35365
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=GwBizSoaI17Meg2bPHCz-o_U8i6-wRgrXv6ZpyJqSvk,205718
+upgini/features_enricher.py,sha256=Li1sPihWVkPUPcma8HRbPFwpCqd9V9d2p5zQUgkpdpU,206998
 upgini/http.py,sha256=RvzcShpDXssLs6ycGN8xilkKi8ZV9XGUrrk8bwdUzbw,43607
-upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
-upgini/metadata.py,sha256=Jh6YTaS00m_nbaOY_owvlSyn9zgkErkqu8iTr9ZjKI8,12279
-upgini/metrics.py,sha256=I0sVJLNp4fiIq7ZFcUdNTxJjFkzStdFuKbnf2niEGjc,38207
-upgini/search_task.py,sha256=qxUxAD-bed-FpZYmTB_4orW7YJsW_O6a1TcgnZIRFr4,17307
+upgini/metadata.py,sha256=Yd6iW2f7Wz6vUkg5uvR4xylN16ANnCKVKqAsAkap7p8,12354
+upgini/metrics.py,sha256=a0bY4oTMb-MgB1yC1IuTcEtotKZxAxjgV_QV2Z4V8u4,38988
+upgini/search_task.py,sha256=EuCGp0iCWz2fpuJgN6M47aP_CtIi3Oq9zw78w0mkKiU,17595
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
 upgini/ads_management/__init__.py,sha256=qzyisOToVRP-tquAJD1PblZhNtMrOB8FiyF9JvfkvgE,50
@@ -16,19 +15,20 @@ upgini/ads_management/ads_manager.py,sha256=igVbN2jz80Umb2BUJixmJVj-zx8unoKpecVo
 upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/autofe/all_operators.py,sha256=rdjF5eaE4bC6Q4eu_el5Z7ekYt8DjOFermz2bePPbUc,333
 upgini/autofe/binary.py,sha256=MnQuFiERpocjCPQUjOljlsq5FE-04GPfwtNjzvfNMyU,7671
-upgini/autofe/date.py,sha256=I07psJerrxOcHao91PdSCk9X6KWu61IBVyFRLjGNgK8,10730
-upgini/autofe/feature.py,sha256=xgu6bVIlUJ5PCUgoXQRNcGkcMOhj-_BdDRmkB_qRFS4,14766
+upgini/autofe/date.py,sha256=C86F7sPiscUGq2a45UtQA9ADWBWg0kt54mePHHzjbLE,10633
+upgini/autofe/feature.py,sha256=y1x3wijhTVBmloayQAHiscqKU9Ll8kLcGm1PdvS357I,14910
 upgini/autofe/groupby.py,sha256=IYmQV9uoCdRcpkeWZj_kI3ObzoNCNx3ff3h8sTL01tk,3603
 upgini/autofe/operator.py,sha256=EOffJw6vKXpEh5yymqb1RFNJPxGxmnHdFRo9dB5SCFo,4969
 upgini/autofe/unary.py,sha256=yVgPvtfnPSOhrii0YgezddmgWPwyOBCR0JutaIkdTTc,4658
+upgini/autofe/utils.py,sha256=fK1am2_tQj3fL2vDslblye8lmyfWgGIUOX1beYVBz4k,2420
 upgini/autofe/vector.py,sha256=l0KdKg-txlZxDSE4hPPfCtfGQofYbl7oaABPr830sPI,667
 upgini/autofe/timeseries/__init__.py,sha256=PGwwDAMwvkXl3el12tXVEmZUgDUvlmIPlXtROm6bD18,738
-upgini/autofe/timeseries/base.py,sha256=T9Ec8LKJbiwTUGGsd_xhM0U0NUJblqmKchkzUI1sK88,3755
-upgini/autofe/timeseries/cross.py,sha256=Sh5hAXZFWKaFRqf_JGODu9pWO2tmuV5VKyK9eX3i7-I,4931
+upgini/autofe/timeseries/base.py,sha256=rWJqRuFAzTZEsUdWG5s1Vhif9zzRRmalASXvarufRxI,3610
+upgini/autofe/timeseries/cross.py,sha256=BTINVwuZSbm_4NKkVm0FGM68SrvZLENZKXN7-UyvhYI,5319
 upgini/autofe/timeseries/delta.py,sha256=h0YhmI1TlPJnjwFpN_GQxLb6r59DQuucnG5tQAXSgjU,3520
 upgini/autofe/timeseries/lag.py,sha256=LfQtg484vuqM0mgY4Wft1swHX_Srq7OKKgZswCXoiXI,1882
-upgini/autofe/timeseries/roll.py,sha256=bNFMDszSYTWvB7EyhHbRY1DJqzSURvHlPAcBebt0y0Y,2878
-upgini/autofe/timeseries/trend.py,sha256=9p2Q5ByAi6cx9RH9teBTe8FyjSzqthznC2Lo5dsJ0ho,2051
+upgini/autofe/timeseries/roll.py,sha256=zADKXU-eYWQnQ5R3am1yEal8uU6Tm0jLAixwPb_aCHg,2794
+upgini/autofe/timeseries/trend.py,sha256=K1_iw2ko_LIUU8YCUgrvN3n0MkHtsi7-63-8x9er1k4,2129
 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
@@ -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=XU5ulr5ZDQfGbFk9QdFDzl3oDMaw0eDYCPoEq3ZvIkw,27687
+upgini/resource_bundle/strings.properties,sha256=mwQrerdJj3adzT-fHqvs6Qjf-rqDccsUzELDIXJKAmY,27791
 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
@@ -60,17 +60,17 @@ upgini/utils/feature_info.py,sha256=Q9HN6A-fvfVD-irFWrmOqqZG9RsUSvh5MTY_k0xu-tE,
 upgini/utils/features_validator.py,sha256=lEfmk4DoxZ4ooOE1HC0ZXtUb_lFKRFHIrnFULZ4_rL8,3746
 upgini/utils/format.py,sha256=Yv5cvvSs2bOLUzzNu96Pu33VMDNbabio92QepUj41jU,243
 upgini/utils/ip_utils.py,sha256=TSQ_qDsLlVnm09X1HacpabEf_HNqSWpxBF4Sdc2xs08,6580
-upgini/utils/mstats.py,sha256=dLJQr5Ak5BAoV-pDPpnfvMURZVkZ3_v250QzAsSlqY4,6286
+upgini/utils/mstats.py,sha256=u3gQVUtDRbyrOQK6V1UJ2Rx1QbkSNYGjXa6m3Z_dPVs,6286
 upgini/utils/phone_utils.py,sha256=IrbztLuOJBiePqqxllfABWfYlfAjYevPhXKipl95wUI,10432
 upgini/utils/postal_code_utils.py,sha256=5M0sUqH2DAr33kARWCTXR-ACyzWbjDq_-0mmEml6ZcU,1716
 upgini/utils/progress_bar.py,sha256=N-Sfdah2Hg8lXP_fV9EfUTXz_PyRt4lo9fAHoUDOoLc,1550
-upgini/utils/sklearn_ext.py,sha256=E7zfYqBW597LetYXHxyM-i4f8luHsGIuP6mMJ2wtSMs,44661
-upgini/utils/sort.py,sha256=H79A17NMoHtLbqLCPFx_MBUloLZcDKjOba_H4gCE3t8,6965
-upgini/utils/target_utils.py,sha256=b1GzO8_gMcwXSZ2v98CY50MJJBzKbWHId_BJGybXfkM,16579
+upgini/utils/sklearn_ext.py,sha256=HpaNQaKJisgNE7IZ71n7uswxTj7kbPglU2G3s1sORAc,45042
+upgini/utils/sort.py,sha256=8uuHs2nfSMVnz8GgvbOmgMB1PgEIZP1uhmeRFxcwnYw,7039
+upgini/utils/target_utils.py,sha256=KNFzJta1SpGU4sp07dHKSeVJlDs_9qgD2wcw5YuJfOc,16661
 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-1.2.70a3832.dev2.dist-info/METADATA,sha256=O_4tZRoxEur3Ut9q-6kT2LEIm-JN5-mVps1ujZibt6A,49149
-upgini-1.2.70a3832.dev2.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.70a3832.dev2.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.70a3832.dev2.dist-info/RECORD,,
+upgini-1.2.71.dist-info/METADATA,sha256=Dvzwz4pOrA3V4OlH7BjxerA7UAZhn1H4-qh7SjMpc3E,49091
+upgini-1.2.71.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.71.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.71.dist-info/RECORD,,

upgini/lazy_import.py

@@ -1,35 +0,0 @@
-import importlib
-import importlib.util
-import importlib.machinery
-
-
-class LazyImport:
-    def __init__(self, module_name, class_name):
-        self.module_name = module_name
-        self.class_name = class_name
-        self._module = None
-        self._class = None
-
-    def _load(self):
-        if self._module is None:
-            # Load module and save link to it
-            spec = importlib.util.find_spec(self.module_name)
-            if spec is None:
-                raise ImportError(f"Module {self.module_name} not found")
-
-            # Create module
-            self._module = importlib.util.module_from_spec(spec)
-
-            # Execute module
-            spec.loader.exec_module(self._module)
-
-            # Get class from module
-            self._class = getattr(self._module, self.class_name)
-
-    def __call__(self, *args, **kwargs):
-        self._load()
-        return self._class(*args, **kwargs)
-
-    def __getattr__(self, name):
-        self._load()
-        return getattr(self._class, name)