upgini 1.2.42__tar.gz → 1.2.44__tar.gz

{upgini-1.2.42 → upgini-1.2.44}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.42
+Version: 1.2.44
 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-1.2.44/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.44"

{upgini-1.2.42 → upgini-1.2.44}/src/upgini/features_enricher.py

@@ -277,7 +277,7 @@ class FeaturesEnricher(TransformerMixin):
             dict()
         )
 
-        validate_version(self.logger, self.__log_warning)
+        validate_version(self.logger)
 
         self.search_keys = search_keys or {}
         self.id_columns = id_columns
@@ -584,6 +584,7 @@ class FeaturesEnricher(TransformerMixin):
             Transformed dataframe, enriched with valuable features.
         """
 
+        self.warning_counter.reset()
         trace_id = str(uuid.uuid4())
         start_time = time.time()
         with MDC(trace_id=trace_id):
@@ -720,7 +721,7 @@ class FeaturesEnricher(TransformerMixin):
         X_new: pandas.DataFrame of shape (n_samples, n_features_new)
             Transformed dataframe, enriched with valuable features.
         """
-
+        self.warning_counter.reset()
         search_progress = SearchProgress(0.0, ProgressStage.START_TRANSFORM)
         if progress_callback is not None:
             progress_callback(search_progress)
@@ -1086,13 +1087,16 @@ class FeaturesEnricher(TransformerMixin):
                         self.bundle.get("quality_metrics_segment_header"): self.bundle.get(
                             "quality_metrics_train_segment"
                         ),
-                        self.bundle.get("quality_metrics_rows_header"): _num_samples(effective_X),
+                        # self.bundle.get("quality_metrics_rows_header"): _num_samples(effective_X),
+                        # Show actually used for metrics dataset size
+                        self.bundle.get("quality_metrics_rows_header"): _num_samples(fitting_X),
                     }
                     if model_task_type in [ModelTaskType.BINARY, ModelTaskType.REGRESSION] and is_numeric_dtype(
                         validated_y
                     ):
                         train_metrics[self.bundle.get("quality_metrics_mean_target_header")] = round(
-                            np.mean(validated_y), 4
+                            # np.mean(validated_y), 4
+                            np.mean(y_sorted), 4
                         )
                     if etalon_metric is not None:
                         train_metrics[self.bundle.get("quality_metrics_baseline_header").format(metric)] = etalon_metric
@@ -1153,13 +1157,14 @@ class FeaturesEnricher(TransformerMixin):
                             else:
                                 eval_uplift = None
 
-                            # effective_eval_set = eval_set if eval_set is not None else self.eval_set
                             eval_metrics = {
                                 self.bundle.get("quality_metrics_segment_header"): self.bundle.get(
                                     "quality_metrics_eval_segment"
                                 ).format(idx + 1),
                                 self.bundle.get("quality_metrics_rows_header"): _num_samples(
-                                    effective_eval_set[idx][0]
+                                    # effective_eval_set[idx][0]
+                                    # Use actually used for metrics dataset
+                                    eval_X_sorted
                                 ),
                                 # self.bundle.get("quality_metrics_match_rate_header"): eval_hit_rate,
                             }
@@ -1167,7 +1172,9 @@ class FeaturesEnricher(TransformerMixin):
                                 validated_eval_set[idx][1]
                             ):
                                 eval_metrics[self.bundle.get("quality_metrics_mean_target_header")] = round(
-                                    np.mean(validated_eval_set[idx][1]), 4
+                                    # np.mean(validated_eval_set[idx][1]), 4
+                                    # Use actually used for metrics dataset
+                                    np.mean(eval_y_sorted), 4
                                 )
                             if etalon_eval_metric is not None:
                                 eval_metrics[self.bundle.get("quality_metrics_baseline_header").format(metric)] = (
@@ -2527,11 +2534,9 @@ if response.status_code == 200:
     def __is_registered(self) -> bool:
         return self.api_key is not None and self.api_key != ""
 
-    def __log_warning(self, message: str, show_support_link: bool = False, is_red=False):
+    def __log_warning(self, message: str, show_support_link: bool = False):
         warning_num = self.warning_counter.increment()
         formatted_message = f"WARNING #{warning_num}: {message}\n"
-        if is_red:
-            formatted_message = Format.RED + formatted_message + Format.END
         if show_support_link:
             self.__display_support_link(formatted_message)
         else:
@@ -2584,7 +2589,12 @@ if response.status_code == 200:
             checked_generate_features = []
             for gen_feature in self.generate_features:
                 if gen_feature not in x_columns:
-                    self.__log_warning(self.bundle.get("missing_generate_feature").format(gen_feature, x_columns))
+                    if gen_feature == self._get_phone_column(self.search_keys):
+                        raise ValidationError(
+                            self.bundle.get("missing_generate_feature").format(gen_feature, x_columns)
+                        )
+                    else:
+                        self.__log_warning(self.bundle.get("missing_generate_feature").format(gen_feature, x_columns))
                 else:
                     checked_generate_features.append(gen_feature)
             self.generate_features = checked_generate_features

{upgini-1.2.42 → upgini-1.2.44}/src/upgini/utils/datetime_utils.py

@@ -167,6 +167,12 @@ class DateTimeSearchKeyConverter:
             # Drop intermediate columns if not needed
             df.drop(columns=["second", "minute", "hour"], inplace=True)
 
+        for generated_feature in self.generated_features[:]:
+            if df[generated_feature].dropna().nunique() <= 1:
+                self.logger.warning(f"Generated constant feature {generated_feature} will be dropped")
+                df.drop(columns=generated_feature, inplace=True)
+                self.generated_features.remove(generated_feature)
+
         df.drop(columns=seconds, inplace=True)
 
         if keep_time:

{upgini-1.2.42 → upgini-1.2.44}/src/upgini/version_validator.py

@@ -1,9 +1,10 @@
 import json
 import threading
-from typing import Callable, Optional
 
 import requests
 
+from upgini.utils.format import Format
+
 try:
     from packaging.version import parse
 except ImportError:
@@ -31,18 +32,16 @@ def get_version(package, url_pattern=URL_PATTERN):
     return version
 
 
-def validate_version(logger: logging.Logger, warning_function: Optional[Callable[[str], None]] = None):
+def validate_version(logger: logging.Logger):
     def task():
         try:
             current_version = parse(__version__)
             latest_version = get_version("upgini")
             if current_version < latest_version:
                 msg = bundle.get("version_warning").format(current_version, latest_version)
-                if warning_function:
-                    warning_function(msg, is_red=True)
-                else:
-                    logger.warning(msg)
-                    print(msg)
+                formatted_message = Format.RED + msg + Format.END
+                logger.warning(msg)
+                print(formatted_message)
         except Exception:
             logger.warning("Failed to validate version", exc_info=True)
 

upgini-1.2.42/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.42"