upgini 1.2.115a1__tar.gz → 1.2.117a1__tar.gz

{upgini-1.2.115a1 → upgini-1.2.117a1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.115a1
+Version: 1.2.117a1
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -19,9 +19,10 @@ Classifier: License :: OSI Approved :: BSD License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Scientific/Engineering :: Information Analysis
-Requires-Python: <3.12,>=3.10
+Requires-Python: <3.13,>=3.10
 Requires-Dist: catboost>=1.0.3
 Requires-Dist: category-encoders>=2.8.1
 Requires-Dist: fastparquet>=0.8.1
@@ -904,7 +905,7 @@ Some convenient ways to start contributing are:
 ⚙️ **Gitpod** [![Gitpod Ready-to-Code](https://img.shields.io/badge/Gitpod-Ready--to--Code-blue?logo=gitpod)](https://gitpod.io/#https://github.com/upgini/upgini) You can use Gitpod to launch a fully functional development environment right in your browser.
 
 ## 🔗 Useful links
-- [Simple sales predictions as a template notebook](#-simple-sales-predictions-use-as-a-template)
+- [Simple sales predictions as a template notebook](#-simple-sales-prediction-for-retail-stores)
 - [Full list of Kaggle Guides & Examples](https://www.kaggle.com/romaupgini/code)
 - [Project on PyPI](https://pypi.org/project/upgini)
 - [More perks for registered users](https://profile.upgini.com)

{upgini-1.2.115a1 → upgini-1.2.117a1}/README.md

@@ -858,7 +858,7 @@ Some convenient ways to start contributing are:
 ⚙️ **Gitpod** [![Gitpod Ready-to-Code](https://img.shields.io/badge/Gitpod-Ready--to--Code-blue?logo=gitpod)](https://gitpod.io/#https://github.com/upgini/upgini) You can use Gitpod to launch a fully functional development environment right in your browser.
 
 ## 🔗 Useful links
-- [Simple sales predictions as a template notebook](#-simple-sales-predictions-use-as-a-template)
+- [Simple sales predictions as a template notebook](#-simple-sales-prediction-for-retail-stores)
 - [Full list of Kaggle Guides & Examples](https://www.kaggle.com/romaupgini/code)
 - [Project on PyPI](https://pypi.org/project/upgini)
 - [More perks for registered users](https://profile.upgini.com)

{upgini-1.2.115a1 → upgini-1.2.117a1}/pyproject.toml

@@ -7,7 +7,7 @@ name = "upgini"
 dynamic = ["version"]
 description = "Intelligent data search & enrichment for Machine Learning"
 readme = "README.md"
-requires-python = ">=3.10,<3.12"
+requires-python = ">=3.10,<3.13"
 authors = [
     { name = "Upgini Developers", email = "madewithlove@upgini.com" },
 ]
@@ -30,6 +30,7 @@ classifiers = [
     "Operating System :: OS Independent",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
     "Topic :: Scientific/Engineering :: Artificial Intelligence",
     "Topic :: Scientific/Engineering :: Information Analysis",
 ]
@@ -90,7 +91,7 @@ lint = "ruff check {args}"
 test_all = 'pytest -s -vv tests'
 
 [[tool.hatch.envs.test.matrix]]
-python = ["3.10", "3.11"]
+python = ["3.10", "3.11", "3.12"]
 pandas = ["1.2.0", "1.3.0", "1.4.0", "1.5.0", "2.0.0", "2.1.0", "2.2.0"]
 
 # from versions: 0.1, 0.2, 0.3.0, 0.4.0, 0.4.1, 0.4.2, 0.4.3, 0.5.0, 0.6.0, 0.6.1, 0.7.0, 0.7.1, 0.7.2, 0.7.3, 0.8.0, 0.8.1, 0.9.0, 0.9.1, 0.10.0, 0.10.1, 0.11.0, 0.12.0, 0.13.0, 0.13.1, 0.14.0, 0.14.1, 0.15.0, 0.15.1, 0.15.2, 0.16.0, 0.16.1, 0.16.2, 0.17.0, 0.17.1, 0.18.0, 0.18.1, 0.19.0, 0.19.1, 0.19.2, 0.20.0, 0.20.1, 0.20.2, 0.20.3, 0.21.0, 0.21.1, 0.22.0, 0.23.0, 0.23.1, 0.23.2, 0.23.3, 0.23.4, 0.24.0, 0.24.1, 0.24.2, 0.25.0, 0.25.1, 0.25.2, 0.25.3, 1.0.0, 1.0.1, 1.0.2, 1.0.3, 1.0.4, 1.0.5, 1.1.0, 1.1.1, 1.1.2, 1.1.3, 1.1.4, 1.1.5, 1.2.0, 1.2.1, 1.2.2, 1.2.3, 1.2.4, 1.2.5, 1.3.0, 1.3.1, 1.3.2, 1.3.3, 1.3.4, 1.3.5, 1.4.0rc0, 1.4.0, 1.4.1, 1.4.2, 1.4.3, 1.4.4, 1.5.0rc0, 1.5.0, 1.5.1, 1.5.2, 1.5.3, 2.0.0rc0, 2.0.0rc1, 2.0.0, 2.0.1, 2.0.2, 2.0.3

upgini-1.2.117a1/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.117a1"

{upgini-1.2.115a1 → upgini-1.2.117a1}/src/upgini/features_enricher.py

@@ -584,7 +584,7 @@ class FeaturesEnricher(TransformerMixin):
         eval_set: list[tuple] | tuple | None = None,
         *args,
         exclude_features_sources: list[str] | None | None = None,
-        keep_input: bool | None = None,
+        keep_input: bool = True,
         calculate_metrics: bool | None = None,
         scoring: Callable | str | None = None,
         estimator: Any | None = None,
@@ -612,10 +612,9 @@ class FeaturesEnricher(TransformerMixin):
             list of pairs (X, y) for validation.
 
         keep_input: bool, optional (default=True)
-            keep_input: bool, optional (default=None)
-            If True, copy original input columns to the output dataframe.
+            keep_input: bool, optional (default=True)
+            If True, then all search keys, ID columns, selected client features and enriched columns will be returned.
             If False, then only enriched columns are returned.
-            If None, then all search keys, ID columns, selected client features and enriched columns will be returned.
 
         estimator: sklearn-compatible estimator, optional (default=None)
             Custom estimator for metrics calculation.
@@ -751,7 +750,7 @@ class FeaturesEnricher(TransformerMixin):
         *args,
         y: pd.Series | None = None,
         exclude_features_sources: list[str] | None = None,
-        keep_input: bool | None = None,
+        keep_input: bool = True,
         trace_id: str | None = None,
         metrics_calculation: bool = False,
         silent_mode=False,
@@ -768,10 +767,11 @@ class FeaturesEnricher(TransformerMixin):
         X: pandas.DataFrame of shape (n_samples, n_features)
             Input samples.
 
-        keep_input: bool, optional (default=None)
-            If True, copy original input columns to the output dataframe.
+        keep_input: bool, optional (default=True)
+            keep_input: bool, optional (default=True)
+            If True, then all search keys, ID columns, selected client features, enriched columns and intput columns
+            that were not present on fit will be returned.
             If False, then only enriched columns are returned.
-            If None, then all search keys, ID columns, selected client features and enriched columns will be returned.
 
         Returns
         -------
@@ -2178,7 +2178,7 @@ class FeaturesEnricher(TransformerMixin):
         df = self.__combine_train_and_eval_sets(validated_X, validated_y, eval_set)
 
         # Exclude OOT eval sets from transform because they are not used for metrics calculation
-        if not is_for_metrics and EVAL_SET_INDEX in df.columns:
+        if is_for_metrics and EVAL_SET_INDEX in df.columns:
             for eval_index in df[EVAL_SET_INDEX].unique():
                 if eval_index == 0:
                     continue
@@ -2482,7 +2482,7 @@ if response.status_code == 200:
         progress_bar: ProgressBar | None = None,
         progress_callback: Callable[[SearchProgress], Any] | None = None,
         add_fit_system_record_id: bool = False,
-        keep_input: bool | None = None,
+        keep_input: bool = True,
     ) -> tuple[pd.DataFrame, dict[str, str], list[str], dict[str, SearchKey]]:
         if self._search_task is None:
             raise NotFittedError(self.bundle.get("transform_unfitted_enricher"))
@@ -2831,21 +2831,23 @@ if response.status_code == 200:
                 how="left",
             )
 
+            fit_input_columns = [c.originalName for c in self._search_task.get_file_metadata(trace_id).columns]
+            new_columns_on_transform = [c for c in validated_Xy.columns if c not in fit_input_columns]
+
             selected_generated_features = [
                 c for c in generated_features if not self.fit_select_features or c in self.feature_names_
             ]
-            if keep_input is None:
+            if keep_input is True:
                 selected_input_columns = [
                     c
                     for c in validated_Xy.columns
                     if not self.fit_select_features
                     or c in self.feature_names_
+                    or c in new_columns_on_transform
                     or c in self.search_keys
                     or c in (self.id_columns or [])
                     or c in [EVAL_SET_INDEX, TARGET]  # transform for metrics calculation
                 ]
-            elif keep_input is True:
-                selected_input_columns = validated_Xy.columns.to_list()
             else:
                 selected_input_columns = []
 

{upgini-1.2.115a1 → upgini-1.2.117a1}/src/upgini/metrics.py

@@ -815,9 +815,9 @@ class CatBoostWrapper(EstimatorWrapper):
                     encoded = cat_encoder.transform(x[self.cat_features]).astype(int)
                 else:
                     encoded = cat_encoder.transform(x[self.cat_features])
-                    cat_features = encoded.columns.to_list()
-                x.drop(columns=encoded.columns, inplace=True, errors="ignore")
-                x[encoded.columns] = encoded
+                    cat_features = self.cat_features
+                x = x.drop(columns=self.cat_features, errors="ignore")
+                x[self.cat_features] = encoded
             else:
                 cat_features = self.cat_features
 

upgini-1.2.115a1/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.115a1"