upgini 1.1.285a3418.post1__tar.gz → 1.1.286__tar.gz

{upgini-1.1.285a3418.post1 → upgini-1.1.286}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.285a3418.post1
+Version: 1.1.286
 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-1.1.286/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.286"

{upgini-1.1.285a3418.post1 → upgini-1.1.286}/src/upgini/autofe/date.py

@@ -188,7 +188,7 @@ class DatePercentile(PandasOperand):
 
         month_diffs = 12 * (years - (self.zero_year or 0)) + (months - (self.zero_month or 0))
         bounds = month_diffs.apply(
-            lambda d: np.array(self.zero_bounds if self.zero_bounds is not None else []) + d * 30
+            lambda d: np.array(self.zero_bounds if self.zero_bounds is not None else []) + d * self.step
         )
 
         return right.index.to_series().apply(lambda i: self.__perc(right[i], bounds[i]))

{upgini-1.1.285a3418.post1 → upgini-1.1.286}/src/upgini/features_enricher.py

@@ -423,7 +423,7 @@ class FeaturesEnricher(TransformerMixin):
 
             self.logger.info("Start fit")
 
-            self.__validate_search_keys(self.search_keys, self.search_id)
+            self.__validate_search_keys(self.search_keys)
 
             # Validate client estimator params
             self._get_client_cat_features(estimator, X, self.search_keys)
@@ -557,7 +557,7 @@ class FeaturesEnricher(TransformerMixin):
 
             self.logger.info("Start fit_transform")
 
-            self.__validate_search_keys(self.search_keys, self.search_id)
+            self.__validate_search_keys(self.search_keys)
 
             search_progress = SearchProgress(0.0, ProgressStage.START_FIT)
             if progress_callback is not None:
@@ -972,6 +972,8 @@ class FeaturesEnricher(TransformerMixin):
 
                     # 2 Fit and predict with KFold estimator on enriched tds
                     # and calculate final metric (and uplift)
+                    enriched_metric = None
+                    uplift = None
                     enriched_estimator = None
                     if set(fitting_X.columns) != set(fitting_enriched_X.columns):
                         self.logger.info(
@@ -992,18 +994,15 @@ class FeaturesEnricher(TransformerMixin):
                             has_date=has_date,
                         )
                         enriched_metric = enriched_estimator.cross_val_predict(fitting_enriched_X, enriched_y_sorted)
-                        if etalon_metric is None:
+                        if enriched_metric is None:
                             self.logger.warning(
                                 f"Enriched {metric} on train combined features is None (maybe all features was removed)"
                             )
                             enriched_estimator = None
-                            uplift = None
                         else:
                             self.logger.info(f"Enriched {metric} on train combined features: {enriched_metric}")
+                        if etalon_metric is not None and enriched_metric is not None:
                             uplift = (enriched_metric - etalon_metric) * multiplier
-                    else:
-                        enriched_metric = None
-                        uplift = None
 
                     train_metrics = {
                         self.bundle.get("quality_metrics_segment_header"): self.bundle.get(
@@ -2147,7 +2146,7 @@ class FeaturesEnricher(TransformerMixin):
             ]
             return excluded_features[feature_name_header].values.tolist()
 
-    def __validate_search_keys(self, search_keys: Dict[str, SearchKey], search_id: Optional[str]):
+    def __validate_search_keys(self, search_keys: Dict[str, SearchKey], search_id: Optional[str] = None):
         if (search_keys is None or len(search_keys) == 0) and self.country_code is None:
             if search_id:
                 self.logger.debug(f"search_id {search_id} provided without search_keys")

{upgini-1.1.285a3418.post1 → upgini-1.1.286}/src/upgini/utils/custom_loss_utils.py

@@ -11,46 +11,49 @@ def get_runtime_params_custom_loss(
     runtime_parameters: RuntimeParameters,
     logger: Optional[logging.Logger] = None,
 ) -> RuntimeParameters:
+    if not loss:
+        return runtime_parameters
+
     if logger is None:
         logger = logging.getLogger()
-    if loss is not None:
-        selection_loss_reg = [
-            "regression",
-            "regression_l1",
-            "huber",
-            "poisson",
-            "quantile",
-            "mape",
-            "mean_absolute_percentage_error",
-            "gamma",
-            "tweedie",
-        ]
-        selection_loss_binary = ["binary"]
-        selection_loss_multi_clf = ["multiclass", "multiclassova", "multiclass_ova", "ova", "ovr"]
-        use_custom_loss = (
-            True
-            if (
-                (model_task_type == ModelTaskType.REGRESSION)
-                and (loss in selection_loss_reg)
-                or (model_task_type == ModelTaskType.BINARY)
-                and (loss in selection_loss_binary)
-                or (model_task_type == ModelTaskType.MULTICLASS)
-                and (loss in selection_loss_multi_clf)
-            )
-            else False
+
+    selection_loss_reg = [
+        "regression",
+        "regression_l1",
+        "huber",
+        "poisson",
+        "quantile",
+        "mape",
+        "mean_absolute_percentage_error",
+        "gamma",
+        "tweedie",
+    ]
+    selection_loss_binary = ["binary"]
+    selection_loss_multi_clf = ["multiclass", "multiclassova", "multiclass_ova", "ova", "ovr"]
+    use_custom_loss = (
+        True
+        if (
+            (model_task_type == ModelTaskType.REGRESSION)
+            and (loss in selection_loss_reg)
+            or (model_task_type == ModelTaskType.BINARY)
+            and (loss in selection_loss_binary)
+            or (model_task_type == ModelTaskType.MULTICLASS)
+            and (loss in selection_loss_multi_clf)
         )
+        else False
+    )
 
-        if use_custom_loss:
-            runtime_parameters.properties["lightgbm_params_preselection.objective"] = loss
-            runtime_parameters.properties["lightgbm_params_base.objective"] = loss
-            runtime_parameters.properties["lightgbm_params_segment.objective"] = loss
-            msg = bundle.get("loss_selection_info").format(loss)
-            logger.info(msg)
-            print(msg)
-        else:
-            msg = bundle.get("loss_selection_warn").format(loss, model_task_type)
-            logger.warning(msg)
-            print(msg)
+    if use_custom_loss:
+        runtime_parameters.properties["lightgbm_params_preselection.objective"] = loss
+        runtime_parameters.properties["lightgbm_params_base.objective"] = loss
+        runtime_parameters.properties["lightgbm_params_segment.objective"] = loss
+        msg = bundle.get("loss_selection_info").format(loss)
+        logger.info(msg)
+        print(msg)
+    else:
+        msg = bundle.get("loss_selection_warn").format(loss, model_task_type)
+        logger.warning(msg)
+        print(msg)
 
     return runtime_parameters
 

{upgini-1.1.285a3418.post1 → upgini-1.1.286}/src/upgini/version_validator.py

@@ -35,7 +35,7 @@ def validate_version(logger: logging.Logger):
         try:
             current_version = parse(__version__)
             latest_version = get_version("upgini")
-            if current_version < latest_version:  # type: ignore
+            if current_version < latest_version:
                 msg = bundle.get("version_warning").format(current_version, latest_version)
                 logger.warning(msg)
                 print(msg)

upgini-1.1.285a3418.post1/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.285a3418-1"