upgini 1.1.267__tar.gz → 1.1.268__tar.gz

{upgini-1.1.267/src/upgini.egg-info → upgini-1.1.268}/PKG-INFO

@@ -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 → upgini-1.1.268}/setup.py

@@ -40,7 +40,7 @@ def send_log(msg: str):
 
 
 here = Path(__file__).parent.resolve()
-version = "1.1.267"
+version = "1.1.268"
 try:
     send_log(f"Start setup PyLib version {version}")
     setup(

{upgini-1.1.267 → upgini-1.1.268}/src/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-1.1.267 → upgini-1.1.268}/src/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-1.1.267 → upgini-1.1.268}/src/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 → upgini-1.1.268/src/upgini.egg-info}/PKG-INFO

@@ -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 → upgini-1.1.268}/tests/test_target_utils.py

@@ -140,7 +140,7 @@ def test_binary_psi_calculation():
         "target": [0, 0, 0, 0, 0, 1, 1, 1, 1, 1,   0, 0, 0, 0, 0, 1, 0, 1, 0, 1]
     })
     df["date"] = pd.date_range("2020-01-01", "2020-01-20")
-    enricher = FeaturesEnricher(search_keys={"date": SearchKey.DATE})
+    enricher = FeaturesEnricher(search_keys={"date": SearchKey.DATE}, logs_enabled=False)
     enricher._validate_PSI(df)
     assert not enricher.warning_counter.has_warnings()
 
@@ -148,7 +148,7 @@ def test_binary_psi_calculation():
         "target": [0, 0, 0, 0, 0, 1, 1, 1, 1, 1,   0, 0, 0, 0, 0, 0, 0, 1, 0, 1]
     })
     df["date"] = pd.date_range("2020-01-01", "2020-01-20")
-    enricher = FeaturesEnricher(search_keys={"date": SearchKey.DATE})
+    enricher = FeaturesEnricher(search_keys={"date": SearchKey.DATE}, logs_enabled=False)
     enricher._validate_PSI(df)
     assert enricher.warning_counter._count == 1
 
@@ -157,7 +157,7 @@ def test_binary_psi_calculation():
         "eval_set_index": [0] * 10 + [1] * 10,
     })
     df["date"] = pd.date_range("2020-01-01", "2020-01-20")
-    enricher = FeaturesEnricher(search_keys={"date": SearchKey.DATE})
+    enricher = FeaturesEnricher(search_keys={"date": SearchKey.DATE}, logs_enabled=False)
     enricher._validate_PSI(df)
     assert enricher.warning_counter._count == 1
 
@@ -166,7 +166,7 @@ def test_binary_psi_calculation():
         "eval_set_index": [0] * 10 + [1] * 10,
     })
     df["date"] = pd.date_range("2020-01-01", "2020-01-20")
-    enricher = FeaturesEnricher(search_keys={"date": SearchKey.DATE})
+    enricher = FeaturesEnricher(search_keys={"date": SearchKey.DATE}, logs_enabled=False)
     enricher._validate_PSI(df)
     assert enricher.warning_counter._count == 2
 
@@ -177,7 +177,7 @@ def test_regression_psi_calculation():
         "target": random.rand(20)
     })
     df["date"] = pd.date_range("2020-01-01", "2020-01-20")
-    enricher = FeaturesEnricher(search_keys={"date": SearchKey.DATE})
+    enricher = FeaturesEnricher(search_keys={"date": SearchKey.DATE}, logs_enabled=False)
     enricher._validate_PSI(df)
     assert enricher.warning_counter._count == 1
 
@@ -189,6 +189,6 @@ def test_regression_psi_calculation():
         "target": list(values1) + list(values2)
     })
     df["date"] = pd.date_range("2020-01-01", "2020-01-20")
-    enricher = FeaturesEnricher(search_keys={"date": SearchKey.DATE})
+    enricher = FeaturesEnricher(search_keys={"date": SearchKey.DATE}, logs_enabled=False)
     enricher._validate_PSI(df)
     assert not enricher.warning_counter.has_warnings()