upgini 1.2.96a2__tar.gz → 1.2.96a3906.dev1__tar.gz

{upgini-1.2.96a2 → upgini-1.2.96a3906.dev1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.96a2
+Version: 1.2.96a3906.dev1
 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-1.2.96a3906.dev1/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.96a3906.dev1"

{upgini-1.2.96a2 → upgini-1.2.96a3906.dev1}/src/upgini/autofe/unary.py

@@ -190,3 +190,11 @@ class Bin(PandasOperator):
         if isinstance(value, str):
             return json.loads(value)
         return value
+
+
+class Cluster(PandasOperator):
+    name: str = "cluster"
+    is_unary: bool = True
+    input_type: Optional[str] = "vector"
+    output_type: Optional[str] = "category"
+    is_categorical: bool = True

{upgini-1.2.96a2 → upgini-1.2.96a3906.dev1}/src/upgini/features_enricher.py

@@ -1122,7 +1122,6 @@ class FeaturesEnricher(TransformerMixin):
                     # and calculate final metric (and uplift)
                     enriched_metric = None
                     uplift = None
-                    uplift_perc = None
                     enriched_estimator = None
                     if set(fitting_X.columns) != set(fitting_enriched_X.columns):
                         self.logger.info(
@@ -1154,7 +1153,6 @@ class FeaturesEnricher(TransformerMixin):
                             self.logger.info(f"Enriched {metric} on train combined features: {enriched_metric}")
                         if baseline_metric is not None and enriched_metric is not None:
                             uplift = (enriched_cv_result.metric - baseline_cv_result.metric) * multiplier
-                            uplift_perc = uplift / abs(baseline_cv_result.metric) * 100
 
                     train_metrics = {
                         self.bundle.get("quality_metrics_segment_header"): self.bundle.get(
@@ -1181,10 +1179,7 @@ class FeaturesEnricher(TransformerMixin):
                             enriched_metric
                         )
                     if uplift is not None:
-                        train_metrics[self.bundle.get("quality_metrics_uplift_header")] = round(uplift, 3)
-                        train_metrics[self.bundle.get("quality_metrics_uplift_perc_header")] = (
-                            f"{round(uplift_perc, 1)}%"
-                        )
+                        train_metrics[self.bundle.get("quality_metrics_uplift_header")] = uplift
                     metrics = [train_metrics]
 
                     # 3 If eval_set is presented - fit final model on train enriched data and score each
@@ -1233,10 +1228,8 @@ class FeaturesEnricher(TransformerMixin):
 
                             if etalon_eval_metric is not None and enriched_eval_metric is not None:
                                 eval_uplift = (enriched_eval_results.metric - etalon_eval_results.metric) * multiplier
-                                eval_uplift_perc = eval_uplift / abs(etalon_eval_results.metric) * 100
                             else:
                                 eval_uplift = None
-                                eval_uplift_perc = None
 
                             eval_metrics = {
                                 self.bundle.get("quality_metrics_segment_header"): self.bundle.get(
@@ -1267,10 +1260,7 @@ class FeaturesEnricher(TransformerMixin):
                                     enriched_eval_metric
                                 )
                             if eval_uplift is not None:
-                                eval_metrics[self.bundle.get("quality_metrics_uplift_header")] = round(eval_uplift, 3)
-                                eval_metrics[self.bundle.get("quality_metrics_uplift_perc_header")] = (
-                                    f"{round(eval_uplift_perc, 1)}%"
-                                )
+                                eval_metrics[self.bundle.get("quality_metrics_uplift_header")] = eval_uplift
 
                             metrics.append(eval_metrics)
 

{upgini-1.2.96a2 → upgini-1.2.96a3906.dev1}/src/upgini/resource_bundle/strings.properties

@@ -284,8 +284,8 @@ quality_metrics_segment_header=Dataset type
 quality_metrics_match_rate_header=Match rate
 quality_metrics_baseline_header=Baseline {}
 quality_metrics_enriched_header=Enriched {}
-quality_metrics_uplift_header=Uplift, abs
-quality_metrics_uplift_perc_header=Uplift, %
+quality_metrics_uplift_header=Uplift
+quality_metrics_uplift_prc_header=Uplift, %
 
 # Legacy native api messages
 dataset_dataframe_or_path_empty=Either `df` or `path` must be provided

upgini-1.2.96a2/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.96a2"