upgini 1.1.274a2__tar.gz → 1.1.274a4__tar.gz

{upgini-1.1.274a2/src/upgini.egg-info → upgini-1.1.274a4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.274a2
+Version: 1.1.274a4
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.274a2 → upgini-1.1.274a4}/setup.py

@@ -40,7 +40,7 @@ def send_log(msg: str):
 
 
 here = Path(__file__).parent.resolve()
-version = "1.1.274a2"
+version = "1.1.274a4"
 try:
     send_log(f"Start setup PyLib version {version}")
     setup(

{upgini-1.1.274a2 → upgini-1.1.274a4}/src/upgini/features_enricher.py

@@ -1809,12 +1809,10 @@ class FeaturesEnricher(TransformerMixin):
             features_section = ""
 
         search_id = self._search_task.search_task_id
-        api_example = (
-            f"""curl 'https://search.upgini.com/online/api/http_inference_trigger?search_id={search_id}' \\
+        api_example = f"""curl 'https://search.upgini.com/online/api/http_inference_trigger?search_id={search_id}' \\
     -H 'Authorization: {self.api_key}' \\
     -H 'Content-Type: application/json' \\
     -d '{{"search_keys": {keys}{features_section}}}'"""
-        )
         return api_example
 
     def _get_copy_of_runtime_parameters(self) -> RuntimeParameters:
@@ -1910,8 +1908,7 @@ class FeaturesEnricher(TransformerMixin):
             else:
                 self.logger.info("Input dataset hasn't date column")
                 if self.add_date_if_missing:
-                    df = self._add_current_date_as_key(df)
-                    search_keys[self.CURRENT_DATE] = SearchKey.DATE
+                    df = self._add_current_date_as_key(df, search_keys, self.logger, self.bundle)
             email_column = self._get_email_column(search_keys)
             hem_column = self._get_hem_column(search_keys)
             email_converted_to_hem = False
@@ -2282,8 +2279,7 @@ class FeaturesEnricher(TransformerMixin):
         else:
             self.logger.info("Input dataset hasn't date column")
             if self.add_date_if_missing:
-                df = self._add_current_date_as_key(df)
-                self.fit_search_keys[self.CURRENT_DATE] = SearchKey.DATE
+                df = self._add_current_date_as_key(df, self.fit_search_keys, self.logger, self.bundle)
         email_column = self._get_email_column(self.fit_search_keys)
         hem_column = self._get_hem_column(self.fit_search_keys)
         email_converted_to_hem = False
@@ -2865,8 +2861,23 @@ class FeaturesEnricher(TransformerMixin):
                 return col
 
     @staticmethod
-    def _add_current_date_as_key(df: pd.DataFrame) -> pd.DataFrame:
-        df[FeaturesEnricher.CURRENT_DATE] = datetime.date.today()
+    def _add_current_date_as_key(
+        df: pd.DataFrame, search_keys: Dict[str, SearchKey], logger: logging.Logger, bundle: ResourceBundle
+    ) -> pd.DataFrame:
+        if (
+            set(search_keys.values()) == {SearchKey.PHONE}
+            or set(search_keys.values()) == {SearchKey.EMAIL}
+            or set(search_keys.values()) == {SearchKey.HEM}
+            or set(search_keys.values()) == {SearchKey.COUNTRY, SearchKey.POSTAL_CODE}
+        ):
+            msg = bundle.get("current_date_added")
+            print(msg)
+            logger.warning(msg)
+            df[FeaturesEnricher.CURRENT_DATE] = datetime.date.today()
+            search_keys[FeaturesEnricher.CURRENT_DATE] = SearchKey.DATE
+            converter = DateTimeSearchKeyConverter(FeaturesEnricher.CURRENT_DATE, None, logger, bundle)
+            df = converter.convert(df)
+        return df
 
     @staticmethod
     def _get_group_columns(df: pd.DataFrame, search_keys: Dict[str, SearchKey]) -> List[str]:

{upgini-1.1.274a2 → upgini-1.1.274a4}/src/upgini/resource_bundle/strings.properties

@@ -38,6 +38,7 @@ loss_selection_warn=\nWARNING: Loss `{0}` is not supported for feature selection
 loss_calc_metrics_warn=\nWARNING: Loss `{0}` is not supported for metrics calculation with {1}
 multivariate_timeseries_detected=\nWARNING: Multivariate TimeSeries detected. Blocked time series cross-validation split selected.\nMore details: https://github.com/upgini/upgini#-time-series-prediction-support
 group_k_fold_in_classification=\nWARNING: Using group K-fold cross-validation split for classification task.
+current_date_added=\nWARNING: No date/datetime column was detected in X to be used as a search key. The current date will be used to match the latest version of data sources
 
 # Errors
 failed_search_by_task_id=Failed to retrieve the specified search results

{upgini-1.1.274a2 → upgini-1.1.274a4/src/upgini.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.274a2
+Version: 1.1.274a4
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.274a2 → upgini-1.1.274a4}/tests/test_features_enricher.py

@@ -487,10 +487,7 @@ def test_saved_features_enricher(requests_mock: Mocker):
     train_random_indices = random.choice(train_target.index, size=9000, replace=False)
     train_target.loc[train_random_indices] = 0
 
-    metrics = enricher.calculate_metrics(
-        train_features,
-        train_target
-    )
+    metrics = enricher.calculate_metrics(train_features, train_target)
     expected_metrics = pd.DataFrame(
         {
             segment_header: [train_segment],
@@ -2230,8 +2227,9 @@ def test_email_search_key(requests_mock: Mocker):
             "hashed_email_64ff8c",
             "email_one_domain_3b0a68",
             "email_domain_10c73f",
+            "current_date_b993c4",
         }
-        assert {"hashed_email_64ff8c", "email_one_domain_3b0a68"} == {
+        assert {"hashed_email_64ff8c", "email_one_domain_3b0a68", "current_date_b993c4"} == {
             sk for sublist in self.search_keys for sk in sublist
         }
         raise TestException()
@@ -2276,10 +2274,18 @@ def test_composit_index_search_key(requests_mock: Mocker):
         **kwargs,
     ):
         self.validate()
-        assert set(self.columns.to_list()) == {"system_record_id", "country_aff64e", "postal_code_13534a", "target"}
+        assert set(self.columns.to_list()) == {
+            "system_record_id",
+            "country_aff64e",
+            "postal_code_13534a",
+            "current_date_b993c4",
+            "target",
+        }
         assert "country_aff64e" in self.columns
         assert "postal_code_13534a"
-        assert {"country_aff64e", "postal_code_13534a"} == {sk for sublist in self.search_keys for sk in sublist}
+        assert {"country_aff64e", "postal_code_13534a", "current_date_b993c4"} == {
+            sk for sublist in self.search_keys for sk in sublist
+        }
         # assert "country_fake_a" in self.columns
         # assert "postal_code_fake_a" in self.columns
         # assert {"country_fake_a", "postal_code_fake_a"} == {sk for sublist in self.search_keys for sk in sublist}