upgini 1.2.32__py3-none-any.whl → 1.2.33__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.32"
+__version__ = "1.2.33"

upgini/features_enricher.py

@@ -111,7 +111,11 @@ try:
 except Exception:
     from upgini.utils.fallback_progress_bar import CustomFallbackProgressBar as ProgressBar
 
-from upgini.utils.target_utils import calculate_psi, define_task
+from upgini.utils.target_utils import (
+    balance_undersample_forced,
+    calculate_psi,
+    define_task,
+)
 from upgini.utils.warning_counter import WarningCounter
 from upgini.version_validator import validate_version
 
@@ -967,6 +971,13 @@ class FeaturesEnricher(TransformerMixin):
                     self.__log_warning(self.bundle.get("metrics_no_important_free_features"))
                     return None
 
+                maybe_phone_column = self._get_phone_column(self.search_keys)
+                text_features = (
+                    [f for f in self.generate_features if f != maybe_phone_column]
+                    if self.generate_features is not None
+                    else None
+                )
+
                 print(self.bundle.get("metrics_start"))
                 with Spinner():
                     self._check_train_and_eval_target_distribution(y_sorted, fitting_eval_set_dict)
@@ -982,7 +993,7 @@ class FeaturesEnricher(TransformerMixin):
                         fitting_enriched_X,
                         scoring,
                         groups=groups,
-                        text_features=self.generate_features,
+                        text_features=text_features,
                         has_date=has_date,
                     )
                     metric = wrapper.metric_name
@@ -1009,7 +1020,7 @@ class FeaturesEnricher(TransformerMixin):
                             cat_features,
                             add_params=custom_loss_add_params,
                             groups=groups,
-                            text_features=self.generate_features,
+                            text_features=text_features,
                             has_date=has_date,
                         )
                         etalon_cv_result = baseline_estimator.cross_val_predict(
@@ -1044,7 +1055,7 @@ class FeaturesEnricher(TransformerMixin):
                             cat_features,
                             add_params=custom_loss_add_params,
                             groups=groups,
-                            text_features=self.generate_features,
+                            text_features=text_features,
                             has_date=has_date,
                         )
                         enriched_cv_result = enriched_estimator.cross_val_predict(fitting_enriched_X, enriched_y_sorted)
@@ -1827,7 +1838,27 @@ class FeaturesEnricher(TransformerMixin):
 
             # downsample if need to eval_set threshold
             num_samples = _num_samples(df)
-            if num_samples > Dataset.FIT_SAMPLE_WITH_EVAL_SET_THRESHOLD:
+            phone_column = self._get_phone_column(self.search_keys)
+            force_downsampling = (
+                not self.disable_force_downsampling
+                and self.generate_features is not None
+                and phone_column is not None
+                and self.fit_columns_renaming[phone_column] in self.generate_features
+                and num_samples > Dataset.FORCE_SAMPLE_SIZE
+            )
+            if force_downsampling:
+                self.logger.info(f"Force downsampling from {num_samples} to {Dataset.FORCE_SAMPLE_SIZE}")
+                df = balance_undersample_forced(
+                    df=df,
+                    target_column=TARGET,
+                    task_type=self.model_task_type,
+                    random_state=self.random_state,
+                    sample_size=Dataset.FORCE_SAMPLE_SIZE,
+                    logger=self.logger,
+                    bundle=self.bundle,
+                    warning_callback=self.__log_warning,
+                )
+            elif num_samples > Dataset.FIT_SAMPLE_WITH_EVAL_SET_THRESHOLD:
                 self.logger.info(f"Downsampling from {num_samples} to {Dataset.FIT_SAMPLE_WITH_EVAL_SET_ROWS}")
                 df = df.sample(n=Dataset.FIT_SAMPLE_WITH_EVAL_SET_ROWS, random_state=self.random_state)
 
@@ -2063,6 +2094,15 @@ class FeaturesEnricher(TransformerMixin):
                 self.__display_support_link(msg)
                 return None, {c: c for c in X.columns}, []
 
+            features_meta = self._search_task.get_all_features_metadata_v2()
+            online_api_features = [fm.name for fm in features_meta if fm.from_online_api]
+            if len(online_api_features) > 0:
+                self.logger.warning(
+                    f"There are important features for transform, that generated by online API: {online_api_features}"
+                )
+                # TODO
+                raise Exception("There are features selected that are paid. Contact support (sales@upgini.com)")
+
             if not metrics_calculation:
                 transform_usage = self.rest_client.get_current_transform_usage(trace_id)
                 self.logger.info(f"Current transform usage: {transform_usage}. Transforming {len(X)} rows")
@@ -2708,8 +2748,9 @@ class FeaturesEnricher(TransformerMixin):
             and self.generate_features is not None
             and phone_column is not None
             and self.fit_columns_renaming[phone_column] in self.generate_features
+            and len(df) > Dataset.FORCE_SAMPLE_SIZE
         )
-        if force_downsampling and len(df) > Dataset.FORCE_SAMPLE_SIZE:
+        if force_downsampling:
             runtime_parameters.properties["fast_fit"] = True
 
         dataset = Dataset(

upgini/metadata.py

@@ -255,6 +255,7 @@ class FeaturesMetadataV2(BaseModel):
     data_source_links: Optional[List[str]] = None
     doc_link: Optional[str] = None
     update_frequency: Optional[str] = None
+    from_online_api: Optional[bool] = None
 
 
 class HitRateMetrics(BaseModel):

{upgini-1.2.32.dist-info → upgini-1.2.33.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.32
+Version: 1.2.33
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/
@@ -110,7 +110,7 @@ Description-Content-Type: text/markdown
   </tr>
 </table>   
 
-⭐️ [Simple Drag & Drop Search UI](https://upgini.com/upgini-widget):   
+⭐️ [Simple Drag & Drop Search UI](https://www.upgini.com/data-search-widget):   
 <a href="https://upgini.com/upgini-widget">
 <img width="710" alt="Drag & Drop Search UI" src="https://github.com/upgini/upgini/assets/95645411/36b6460c-51f3-400e-9f04-445b938bf45e">
 </a>

{upgini-1.2.32.dist-info → upgini-1.2.33.dist-info}/RECORD

@@ -1,12 +1,12 @@
-upgini/__about__.py,sha256=UIgtmuCowO7KL6tTNZJcBfDcGQ4kWH7MjulZqCj9os8,23
+upgini/__about__.py,sha256=ozUAhuj1IzPzq1FQeoqbf-7laxntI-m4qA0LSTBVtrw,23
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=KnkqV7Nnx3kxfQ89giDao3bmCm4MFJWqJUrONy85E-k,32030
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=ZUbq6ZsIYznFSyU7tTmCPNzEyr-yRI0r-FJcz4i_Ads,192899
+upgini/features_enricher.py,sha256=q11aMFPlCJy1m4sOFfGZFfb4vdG3-hdd0wgm2BXgs9A,194748
 upgini/http.py,sha256=plZGTGoi1h2edd8Cnjt4eYB8t4NbBGnZz7DtPTByiNc,42885
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
-upgini/metadata.py,sha256=lUa2xYhBhnCeTqNt6lWc9iP_YuikYGIsDSn8Vwyjv1I,11235
+upgini/metadata.py,sha256=ACzIQQwCHCFHlUqXqKpxd3IQ4bBAaVvy8UaCGTqLGQs,11278
 upgini/metrics.py,sha256=hr7UwLphbZ_FEglLuO2lzr_pFgxOJ4c3WBeg7H-fNqY,35521
 upgini/search_task.py,sha256=qxUxAD-bed-FpZYmTB_4orW7YJsW_O6a1TcgnZIRFr4,17307
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
@@ -59,7 +59,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=Ed5IXkPjV9AfAZQAwCYksAmKaPGQliplvDYS_yeWdfk,11330
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.32.dist-info/METADATA,sha256=GTTmeHuetD3Mrl8pR9K3YFzJcPE8Zl8UdWb23vG-R_s,48578
-upgini-1.2.32.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.32.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.32.dist-info/RECORD,,
+upgini-1.2.33.dist-info/METADATA,sha256=EG9Nr1Z8cls4rBaqrPykCTWZhSSoSxPaICd1EylsiKE,48587
+upgini-1.2.33.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.33.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.33.dist-info/RECORD,,