upgini 1.2.145a4065.dev1__tar.gz → 1.2.146a2__tar.gz

{upgini-1.2.145a4065.dev1 → upgini-1.2.146a2}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: upgini
-Version: 1.2.145a4065.dev1
+Version: 1.2.146a2
 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-1.2.146a2/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.146a2"

{upgini-1.2.145a4065.dev1 → upgini-1.2.146a2}/src/upgini/dataset.py

@@ -370,7 +370,10 @@ class Dataset:
                 self.data["valid_keys"] = self.data["valid_keys"] + self.data[f"{col}_is_valid"]
             self.data.drop(columns=f"{col}_is_valid", inplace=True)
 
-        self.data["is_valid"] = self.data["valid_keys"] > 0
+        if len(keys_to_validate) > 0:
+            self.data["is_valid"] = self.data["valid_keys"] > 0
+        else:
+            self.data["is_valid"] = True
         self.data["is_valid"] = self.data["is_valid"] & self.data["valid_mandatory"]
         self.data.drop(columns=["valid_keys", "valid_mandatory"], inplace=True)
 

{upgini-1.2.145a4065.dev1 → upgini-1.2.146a2}/src/upgini/features_enricher.py

@@ -3000,15 +3000,18 @@ if response.status_code == 200:
 
         return selected_input_columns + selected_generated_features
 
-    def __validate_search_keys(self, search_keys: dict[str, SearchKey], search_id: str | None = None):
+    def _validate_empty_search_keys(
+        self, search_keys: dict[str, SearchKey], is_transform: bool = False
+    ):
         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")
-                return
-            # else:
-            #     self.logger.warning("search_keys not provided")
-            #     raise ValidationError(self.bundle.get("empty_search_keys"))
+            if is_transform:
+                self.logger.debug("Transform started without search_keys")
+                # return
+            else:
+                self.logger.warning("search_keys not provided")
+                # raise ValidationError(self.bundle.get("empty_search_keys"))
 
+    def __validate_search_keys(self, search_keys: dict[str, SearchKey], search_id: str | None = None):
         key_types = search_keys.values()
 
         # Multiple search keys allowed only for PHONE, IP, POSTAL_CODE, EMAIL, HEM
@@ -4801,6 +4804,8 @@ if response.status_code == 200:
 
         self.logger.info(f"Prepared search keys: {valid_search_keys}")
 
+        # x = self._validate_empty_search_keys(x, valid_search_keys, is_transform=is_transform)
+
         return valid_search_keys
 
     def __show_metrics(
@@ -4941,10 +4946,6 @@ if response.status_code == 200:
                 )
                 self.__log_warning(self.bundle.get("phone_detected_not_registered"))
 
-        if (search_keys is None or len(search_keys) == 0) and self.country_code is None:
-            self.logger.warning("search_keys not provided")
-            raise ValidationError(self.bundle.get("empty_search_keys"))
-
         return search_keys
 
     def _validate_binary_observations(self, y, task_type: ModelTaskType):

{upgini-1.2.145a4065.dev1 → upgini-1.2.146a2}/src/upgini/resource_bundle/strings.properties

@@ -220,7 +220,7 @@ email_detected=Emails detected in column `{}`. It will be used as a search key\n
 email_detected_not_registered=Emails detected in column `{}`. It can be used only with api_key from profile.upgini.com\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns\n
 phone_detected=Phone numbers detected in column `{}`. It can be used only with api_key from profile.upgini.com\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns\n
 phone_detected_not_registered=Phone numbers detected in column `{}`. It can be used only with api_key from profile.upgini.com\nSee docs to turn off the automatic detection: https://github.com/upgini/upgini/blob/main/README.md#turn-off-autodetection-for-search-key-columns\n
-target_type_detected=\nDetected task type: {}. Reason: {}\nYou can set task type manually with argument `model_task_type` of FeaturesEnricher constructor if task type detected incorrectly\n
+target_type_detected=Detected task type: {}. Reason: {}\nYou can set task type manually with argument `model_task_type` of FeaturesEnricher constructor if task type detected incorrectly\n
 binary_target_reason=only two unique label-values observed
 non_numeric_multiclass_reason=non-numeric label values observed
 few_unique_label_multiclass_reason=few unique label-values observed and can be considered as categorical

upgini-1.2.145a4065.dev1/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.145a4065.dev1"