upgini 1.1.267__py3-none-any.whl → 1.1.268__py3-none-any.whl

upgini/features_enricher.py

@@ -3665,7 +3665,7 @@ class FeaturesEnricher(TransformerMixin):
                     if y is not None:
                         with open(f"{tmp_dir}/y.pickle", "wb") as y_file:
                             pickle.dump(sample(y, xy_sample_index), y_file)
-                        if eval_set is not None:
+                        if eval_set:
                             eval_xy_sample_index = rnd.randint(0, _num_samples(eval_set[0][0]), size=1000)
                             with open(f"{tmp_dir}/eval_x.pickle", "wb") as eval_x_file:
                                 pickle.dump(sample(eval_set[0][0], eval_xy_sample_index), eval_x_file)

upgini/metrics.py

@@ -3,15 +3,16 @@ import re
 from copy import deepcopy
 from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 
+import catboost
 import numpy as np
 import pandas as pd
 from catboost import CatBoostClassifier, CatBoostRegressor
-import catboost
 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.features_validator import FeaturesValidator
 from upgini.utils.sklearn_ext import cross_validate
 
 try:
@@ -352,6 +353,7 @@ class EstimatorWrapper:
             "target_type": target_type,
             "groups": groups,
             "text_features": text_features,
+            "logger": logger,
         }
         if estimator is None:
             params = dict()
@@ -414,12 +416,22 @@ class CatBoostWrapper(EstimatorWrapper):
         target_type: ModelTaskType,
         groups: Optional[List[str]] = None,
         text_features: Optional[List[str]] = None,
+        logger: Optional[logging.Logger] = None,
     ):
         super(CatBoostWrapper, self).__init__(
-            estimator, scorer, metric_name, multiplier, cv, target_type, groups=groups, text_features=text_features
+            estimator,
+            scorer,
+            metric_name,
+            multiplier,
+            cv,
+            target_type,
+            groups=groups,
+            text_features=text_features,
+            logger=logger,
         )
         self.cat_features = None
         self.emb_features = None
+        self.exclude_features = []
 
     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)
@@ -437,9 +449,7 @@ class CatBoostWrapper(EstimatorWrapper):
                 X, embedding_features = self.group_embeddings(X)
                 params["embedding_features"] = embedding_features
             else:
-                self.logger.info(
-                    f"Embedding features count less than 3, so use them separately: {self.emb_features}"
-                )
+                self.logger.info(f"Embedding features count less than 3, so use them separately: {self.emb_features}")
                 self.emb_features = []
         else:
             self.logger.warning(f"Embedding features are not supported by Catboost version {catboost.__version__}")
@@ -498,6 +508,8 @@ class CatBoostWrapper(EstimatorWrapper):
         return df, [emb_name]
 
     def _prepare_to_calculate(self, X: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, np.ndarray, dict]:
+        if self.exclude_features:
+            X = X.drop(columns=self.exclude_features)
         X, y, params = super()._prepare_to_calculate(X, y)
         if self.text_features:
             params["text_features"] = self.text_features
@@ -510,6 +522,26 @@ class CatBoostWrapper(EstimatorWrapper):
 
         return X, y, params
 
+    def cross_val_predict(
+        self, X: pd.DataFrame, y: np.ndarray, baseline_score_column: Optional[Any] = None
+    ) -> Optional[float]:
+        try:
+            return super().cross_val_predict(X, y, baseline_score_column)
+        except Exception as e:
+            if "Dictionary size is 0" in e.args[0] and self.text_features:
+                high_cardinality_features = FeaturesValidator.find_high_cardinality(X[self.text_features])
+                self.logger.warning(
+                    "Failed to calculate metrics. Try to remove high cardinality"
+                    f" text features {high_cardinality_features} and retry"
+                )
+                for f in high_cardinality_features:
+                    self.text_features.remove(f)
+                    self.exclude_features.append(f)
+                    X = X.drop(columns=f)
+                return super().cross_val_predict(X, y, baseline_score_column)
+            else:
+                raise e
+
 
 class LightGBMWrapper(EstimatorWrapper):
     def __init__(
@@ -522,9 +554,18 @@ class LightGBMWrapper(EstimatorWrapper):
         target_type: ModelTaskType,
         groups: Optional[List[str]] = None,
         text_features: Optional[List[str]] = None,
+        logger: Optional[logging.Logger] = None,
     ):
         super(LightGBMWrapper, self).__init__(
-            estimator, scorer, metric_name, multiplier, cv, target_type, groups=groups, text_features=text_features
+            estimator,
+            scorer,
+            metric_name,
+            multiplier,
+            cv,
+            target_type,
+            groups=groups,
+            text_features=text_features,
+            logger=logger,
         )
         self.cat_features = None
 
@@ -561,9 +602,18 @@ class OtherEstimatorWrapper(EstimatorWrapper):
         target_type: ModelTaskType,
         groups: Optional[List[str]] = None,
         text_features: Optional[List[str]] = None,
+        logger: Optional[logging.Logger] = None,
     ):
         super(OtherEstimatorWrapper, self).__init__(
-            estimator, scorer, metric_name, multiplier, cv, target_type, groups=groups, text_features=text_features
+            estimator,
+            scorer,
+            metric_name,
+            multiplier,
+            cv,
+            target_type,
+            groups=groups,
+            text_features=text_features,
+            logger=logger,
         )
         self.cat_features = None
 

upgini/utils/sklearn_ext.py

@@ -1,5 +1,4 @@
 import functools
-import logging
 import numbers
 import time
 import warnings
@@ -313,7 +312,7 @@ def cross_validate(
 
         return ret
     except Exception:
-        logging.exception("Failed to execute overriden cross_validate. Fallback to original")
+        # logging.exception("Failed to execute overriden cross_validate. Fallback to original")
         raise
         # fit_params["use_best_model"] = False
         # return original_cross_validate(

{upgini-1.1.267.dist-info → upgini-1.1.268.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.267
+Version: 1.1.268
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.267.dist-info → upgini-1.1.268.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=xb4gIANyGbdcuM8Awyq2pJPiH_3k_LEbETApJgAoRBA,45529
 upgini/errors.py,sha256=pdzQl3MKuK52yvncxMWMRWeSIOGhUFzpQoszoRFBOk0,958
-upgini/features_enricher.py,sha256=poGGf5MZgangMFmfTxRWtE6FDPDy5VUtXLmW2tGiorI,174170
+upgini/features_enricher.py,sha256=1vHhSQBnFsq6IoYaG_oJbgEWqRZMpkt1rkoLOD-6nl4,174158
 upgini/fingerprint.js,sha256=VygVIQlN1v4NGZfjHqtRogOw8zjTnnMNJg_f7M5iGQU,33442
 upgini/http.py,sha256=zaO86LBBLmkieGbgYifk29eVoPCxXimZQ8YkQtKcM0I,42244
 upgini/metadata.py,sha256=fwVxtkR6Mn4iRoOqV6BfMJvJrx65I3YwZUMbZjhPyOI,9673
-upgini/metrics.py,sha256=3VvSZW1cCOIPHImXuqcnWzD3fWcpPzVa9k8eulLbUmY,27426
+upgini/metrics.py,sha256=VmxVc-plbRPZ1U3Ve3E-FZkhYqi0X2r7x8H5L-shux4,29058
 upgini/search_task.py,sha256=tmJ17WUxv3J5NWrYUJB_NKdZ792Ifz8Z8UnDXeQnpss,17077
 upgini/spinner.py,sha256=Dm1dQ5F_z_Ua2odLxZX7OypcOX9tSx_vE5MGaKtUmfw,1118
 upgini/version_validator.py,sha256=rDIncP6BEko4J2F2hUcMOtKm_vZbI4ICWcNcw8hrwM4,1400
@@ -52,12 +52,12 @@ upgini/utils/ip_utils.py,sha256=Zf3F2cnQmOCH09QLQHetpjMFu1PnD0cTmDymn0SnSy8,1672
 upgini/utils/phone_utils.py,sha256=JNSkF8G6mgsN8Czy11pamaJdsY6rBINEMpi7jbVt_RA,408
 upgini/utils/postal_code_utils.py,sha256=_8CR9tBqsPptQsmMUvnrCAmBaMIQSWH3JfJ4ly3x_zs,409
 upgini/utils/progress_bar.py,sha256=iNXyqT3vKCeHpfiG5HHwr7Lk2cTtKViM93Fl8iZnjGc,1564
-upgini/utils/sklearn_ext.py,sha256=fvuTWJ5AnT3ED9KSaQu_yIgW2JR19hFlaGDoVP3k60g,44027
+upgini/utils/sklearn_ext.py,sha256=e1aMNXk1zUt7uFnl0FcUF0zOnaXSE7z5xBHmJPknUVs,44014
 upgini/utils/target_utils.py,sha256=9K67tkY7LWhQMO-vbbPqBaO-KriAmg_6fVz5RQRaLQc,7802
 upgini/utils/track_info.py,sha256=EPcJ13Jqa17_T0JjM37Ac9kWDz5Zk0GVsIZKutOb8aU,5207
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.267.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.267.dist-info/METADATA,sha256=TiFi7bLKF7TP0gGesfvnN_rs-2htvjOYQko0K4GKdDM,48156
-upgini-1.1.267.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-upgini-1.1.267.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
-upgini-1.1.267.dist-info/RECORD,,
+upgini-1.1.268.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.268.dist-info/METADATA,sha256=gTuBYet6-H97ppvX37qAJuC8tQCZ7bPetPl11O9XEFY,48156
+upgini-1.1.268.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+upgini-1.1.268.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
+upgini-1.1.268.dist-info/RECORD,,