upgini 1.2.68a3832.dev10__py3-none-any.whl → 1.2.68a3832.dev12__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.68a3832.dev10"
+__version__ = "1.2.68a3832.dev12"

upgini/http.py

@@ -16,6 +16,7 @@ from typing import Any, Dict, List, Optional, Tuple
 from urllib.parse import urljoin
 
 import jwt
+
 # import pandas as pd
 import requests
 from pydantic import BaseModel
@@ -342,7 +343,9 @@ class _RestClient:
         else:
             return self._syncronized_refresh_access_token()
 
-    def _with_unauth_retry(self, request, try_number: int = 0, need_connection_retry: bool = True):
+    def _with_unauth_retry(
+        self, request, try_number: int = 0, need_connection_retry: bool = True, silent: bool = False
+    ):
         try:
             return request()
         except RequestException as e:
@@ -373,8 +376,9 @@ class _RestClient:
             elif "more than one concurrent search request" in e.message.lower():
                 raise ValidationError(bundle.get("concurrent_request"))
             else:
-                print(e)
-                show_status_error()
+                if not silent:
+                    print(e)
+                    show_status_error()
                 raise e
 
     @staticmethod
@@ -706,6 +710,7 @@ class _RestClient:
                     silent=True,
                 ),
                 need_connection_retry=False,
+                silent=True,
             )
         except Exception:
             self.send_log_event_unauth(log_event)
@@ -716,7 +721,7 @@ class _RestClient:
         try:
             requests.post(
                 url=urljoin(_RestClient.PROD_BACKEND_URL, api_path),
-                json=log_event.dict(exclude_none=True),
+                json=log_event.model_dump(exclude_none=True),
                 headers=_RestClient._get_base_headers(content_type="application/json"),
             )
         except Exception:

upgini/metrics.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import inspect
 import logging
 import re
+import warnings
 from collections import defaultdict
 from copy import deepcopy
 from dataclasses import dataclass
@@ -359,7 +360,7 @@ class EstimatorWrapper:
         self.logger.info(f"After preparing data columns: {x.columns.to_list()}")
         return x, y, groups
 
-    def _remove_empty_target_rows(self, x: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, pd.Series]:
+    def _remove_empty_target_rows(self, x: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, np.ndarray]:
         joined = pd.concat([x, y], axis=1)
         joined = joined[joined[y.name].notna()]
         joined = joined.reset_index(drop=True)
@@ -413,7 +414,10 @@ class EstimatorWrapper:
             for estimator, split in zip(self.cv_estimators, splits):
                 _, validation_idx = split
                 cv_x = x.iloc[validation_idx]
-                cv_y = y[validation_idx]
+                if isinstance(y, pd.Series):
+                    cv_y = y.iloc[validation_idx]
+                else:
+                    cv_y = y[validation_idx]
                 shaps = self.calculate_shap(cv_x, cv_y, estimator)
                 if shaps is not None:
                     for feature, shap_value in shaps.items():
@@ -760,29 +764,35 @@ class LightGBMWrapper(EstimatorWrapper):
         for feature in self.cat_features:
             x[feature] = x[feature].astype("category").cat.codes
         if not is_numeric_dtype(y_numpy):
-            y = correct_string_target(y)
+            y_numpy = correct_string_target(y_numpy)
 
-        return x, y, groups, params
+        return x, y_numpy, groups, params
 
     def _prepare_to_calculate(self, x: pd.DataFrame, y: pd.Series) -> Tuple[pd.DataFrame, np.ndarray, dict]:
-        x, y, params = super()._prepare_to_calculate(x, y)
+        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 not is_numeric_dtype(y):
-            y = correct_string_target(y)
-        return x, y, params
+            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:
-            import lightgbm as lgb
-            import shap
+            # 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"
+                ),
+            )
+            from shap import TreeExplainer
 
-            if not isinstance(estimator, (lgb.LGBMRegressor, lgb.LGBMClassifier)):
+            if not isinstance(estimator, (LGBMRegressor, LGBMClassifier)):
                 return None
 
-            explainer = shap.TreeExplainer(estimator)
+            explainer = TreeExplainer(estimator)
 
             shap_values = explainer.shap_values(x)
 

upgini/utils/deduplicate_utils.py

@@ -74,6 +74,8 @@ def remove_fintech_duplicates(
         # Checking for different dates by the same personal keys
         uniques = grouped_by_personal_cols[date_col].nunique()
         total = len(uniques)
+        if total == 0:
+            return segment_df, None
         diff_dates = len(uniques[uniques > 1])
         if diff_dates / total >= 0.6:
             return segment_df, None

{upgini-1.2.68a3832.dev10.dist-info → upgini-1.2.68a3832.dev12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.68a3832.dev10
+Version: 1.2.68a3832.dev12
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/

{upgini-1.2.68a3832.dev10.dist-info → upgini-1.2.68a3832.dev12.dist-info}/RECORD

@@ -1,13 +1,13 @@
-upgini/__about__.py,sha256=NECt_QVSJ70tMRsZIpIUFWfKQ8_I5wEO7XsXimpLyHc,34
+upgini/__about__.py,sha256=U3w9ipbCUQQonL603X2mBrHUqIttoTSqcgno2WwRvzk,34
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=1rb6BzyuiQFGVCTDmKL2wox3UFRNjtNaIJOwQnZ801A,34956
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
 upgini/features_enricher.py,sha256=GXXx14jwf3F26_KrfJ6O40Vcu1hRx5iBjUB_jxy3Xvg,205476
-upgini/http.py,sha256=ud0Cp7h0jNeHuuZGpU_1dAAEiabGoJjGxc1X5oeBQr4,43496
+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=GVvpBADnIfU2dg-YALwfsT-DUgJs0sv0IhzGkEFRgFs,37733
+upgini/metrics.py,sha256=I0sVJLNp4fiIq7ZFcUdNTxJjFkzStdFuKbnf2niEGjc,38207
 upgini/search_task.py,sha256=qxUxAD-bed-FpZYmTB_4orW7YJsW_O6a1TcgnZIRFr4,17307
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
 upgini/version_validator.py,sha256=DvbaAvuYFoJqYt0fitpsk6Xcv-H1BYDJYHUMxaKSH_Y,1509
@@ -52,7 +52,7 @@ upgini/utils/country_utils.py,sha256=lY-eXWwFVegdVENFttbvLcgGDjFO17Sex8hd2PyJaRk
 upgini/utils/custom_loss_utils.py,sha256=kieNZYBYZm5ZGBltF1F_jOSF4ea6C29rYuCyiDcqVNY,3857
 upgini/utils/cv_utils.py,sha256=w6FQb9nO8BWDx88EF83NpjPLarK4eR4ia0Wg0kLBJC4,3525
 upgini/utils/datetime_utils.py,sha256=_jq-kn_dGNFfs-DGXcWCGzy9bkplfAjrZ8SsmN28zXc,13535
-upgini/utils/deduplicate_utils.py,sha256=SMZx9IKIhWI5HqXepfKiQb3uDJrogQZtG6jcWuMo5Z4,8855
+upgini/utils/deduplicate_utils.py,sha256=AcMLoObMjhOTQ_fMS1LWy0GKp6WXnZ-FNux_8V3nbZU,8914
 upgini/utils/display_utils.py,sha256=DsBjJ8jEYAh8BPgfAbzq5imoGFV6IACP20PQ78BQCX0,11964
 upgini/utils/email_utils.py,sha256=pZ2vCfNxLIPUhxr0-OlABNXm12jjU44isBk8kGmqQzA,5277
 upgini/utils/fallback_progress_bar.py,sha256=PDaKb8dYpVZaWMroNcOHsTc3pSjgi9mOm0--cOFTwJ0,1074
@@ -70,7 +70,7 @@ upgini/utils/target_utils.py,sha256=b1GzO8_gMcwXSZ2v98CY50MJJBzKbWHId_BJGybXfkM,
 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-1.2.68a3832.dev10.dist-info/METADATA,sha256=o4STq3GAoy8RwnR1PyQPyA5Qhuck0WDUMGEYXI8dkQA,49150
-upgini-1.2.68a3832.dev10.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.68a3832.dev10.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.68a3832.dev10.dist-info/RECORD,,
+upgini-1.2.68a3832.dev12.dist-info/METADATA,sha256=ElzWiZHc8K-GAYoV-4oqiAyyMHin2uzqhXXkZcHrvjE,49150
+upgini-1.2.68a3832.dev12.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.68a3832.dev12.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.68a3832.dev12.dist-info/RECORD,,