upgini 1.2.52a2__py3-none-any.whl → 1.2.54__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.52a2"
+__version__ = "1.2.54"

upgini/features_enricher.py

@@ -268,7 +268,7 @@ class FeaturesEnricher(TransformerMixin):
         self.eval_set: Optional[List[Tuple]] = None
         self.autodetected_search_keys: Dict[str, SearchKey] = {}
         self.imbalanced = False
-        self.fit_select_features = False
+        self.fit_select_features = True
         self.__cached_sampled_datasets: Dict[str, Tuple[pd.DataFrame, pd.DataFrame, pd.Series, Dict, Dict, Dict]] = (
             dict()
         )

upgini/http.py

@@ -358,7 +358,10 @@ class _RestClient:
             self._syncronized_refresh_access_token()
             return request()
         except HttpError as e:
-            if (e.status_code == 429 or e.status_code >= 500) and try_number < 3:
+            if e.status_code == 429:
+                time.sleep(random.randint(1, 10))
+                return self._with_unauth_retry(request, try_number)
+            if e.status_code >= 500 and try_number < 3:
                 time.sleep(random.randint(1, 10))
                 return self._with_unauth_retry(request, try_number + 1)
             elif e.status_code == 400 and "MD5Exception".lower() in e.message.lower() and try_number < 3:

upgini/metadata.py

@@ -89,7 +89,7 @@ class SearchKey(Enum):
         if meaning_type == FileColumnMeaningType.EMAIL:
             return SearchKey.EMAIL
         if meaning_type == FileColumnMeaningType.HEM:
-            return SearchKey.HEM
+            return SearchKey.HEM  # TODO check that it wasn't EMAIL
         if meaning_type == FileColumnMeaningType.IP_ADDRESS:
             return SearchKey.IP
         if meaning_type == FileColumnMeaningType.MSISDN:
@@ -105,27 +105,27 @@ class SearchKey(Enum):
         if meaning_type == FileColumnMeaningType.POSTAL_CODE:
             return SearchKey.POSTAL_CODE
         if meaning_type == FileColumnMeaningType.IPV6_ADDRESS:
-            return SearchKey.IPV6_ADDRESS
-        if meaning_type == FileColumnMeaningType.IPV6_RANGE_FROM:
-            return SearchKey.IPV6_RANGE_FROM
-        if meaning_type == FileColumnMeaningType.IPV6_RANGE_TO:
-            return SearchKey.IPV6_RANGE_TO
-        if meaning_type == FileColumnMeaningType.EMAIL_ONE_DOMAIN:
-            return SearchKey.EMAIL_ONE_DOMAIN
-        if meaning_type == FileColumnMeaningType.IP_RANGE_FROM:
-            return SearchKey.IP_RANGE_FROM
-        if meaning_type == FileColumnMeaningType.IP_RANGE_TO:
-            return SearchKey.IP_RANGE_TO
-        if meaning_type == FileColumnMeaningType.MSISDN_RANGE_FROM:
-            return SearchKey.MSISDN_RANGE_FROM
-        if meaning_type == FileColumnMeaningType.MSISDN_RANGE_TO:
-            return SearchKey.MSISDN_RANGE_TO
+            return SearchKey.IP
+        # if meaning_type == FileColumnMeaningType.IPV6_RANGE_FROM:
+        #     return SearchKey.IPV6_RANGE_FROM
+        # if meaning_type == FileColumnMeaningType.IPV6_RANGE_TO:
+        #     return SearchKey.IPV6_RANGE_TO
+        # if meaning_type == FileColumnMeaningType.EMAIL_ONE_DOMAIN:
+        #     return SearchKey.EMAIL_ONE_DOMAIN
+        # if meaning_type == FileColumnMeaningType.IP_RANGE_FROM:
+        #     return SearchKey.IP_RANGE_FROM
+        # if meaning_type == FileColumnMeaningType.IP_RANGE_TO:
+        #     return SearchKey.IP_RANGE_TO
+        # if meaning_type == FileColumnMeaningType.MSISDN_RANGE_FROM:
+        #     return SearchKey.MSISDN_RANGE_FROM
+        # if meaning_type == FileColumnMeaningType.MSISDN_RANGE_TO:
+        #     return SearchKey.MSISDN_RANGE_TO
         if meaning_type == FileColumnMeaningType.IP_BINARY:
-            return SearchKey.IP_BINARY
-        if meaning_type == FileColumnMeaningType.IP_RANGE_FROM_BINARY:
-            return SearchKey.IP_RANGE_FROM_BINARY
-        if meaning_type == FileColumnMeaningType.IP_RANGE_TO_BINARY:
-            return SearchKey.IP_RANGE_TO_BINARY
+            return SearchKey.IP
+        # if meaning_type == FileColumnMeaningType.IP_RANGE_FROM_BINARY:
+        #     return SearchKey.IP_RANGE_FROM_BINARY
+        # if meaning_type == FileColumnMeaningType.IP_RANGE_TO_BINARY:
+        #     return SearchKey.IP_RANGE_TO_BINARY
 
     @staticmethod
     def find_key(search_keys: Dict[str, SearchKey], keys: Union[SearchKey, List[SearchKey]]) -> Optional[SearchKey]:
@@ -249,7 +249,9 @@ class FileMetadata(BaseModel):
             for key in keys_group:
                 column = self.column_by_name(key)
                 if column:
-                    search_keys[SearchKey.from_meaning_type(column.meaningType)] = column.name
+                    search_key = SearchKey.from_meaning_type(column.meaningType)
+                    if search_key is not None:
+                        search_keys[search_key] = column.name
         return search_keys
 
 

{upgini-1.2.52a2.dist-info → upgini-1.2.54.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.52a2
+Version: 1.2.54
 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-1.2.52a2.dist-info → upgini-1.2.54.dist-info}/RECORD

@@ -1,12 +1,12 @@
-upgini/__about__.py,sha256=975QRO3wSYiniBo2LVNW4q4A5uoxrBhfbb6AFwD83g0,25
+upgini/__about__.py,sha256=odKPoW2Uo_GtuB_RtRePNSus8XWCbeAFRoczr8nT784,23
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=vT4JyHmafLNbj54SySXr93f5hNS6-t94aFslbBy-7No,33535
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=mDpz2NcNBItvfdE2EllEetnv7-ApODXg0FQleYrGIfg,200628
-upgini/http.py,sha256=danPeX7nTMa_70S-pk-4UUm5yOvXYlR84jgyjoHYBkU,43367
+upgini/features_enricher.py,sha256=RDdzFJKBOg9ZT1fbOFMFOMn7O_gbG_8bvbUeNywHOl4,200627
+upgini/http.py,sha256=ud0Cp7h0jNeHuuZGpU_1dAAEiabGoJjGxc1X5oeBQr4,43496
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
-upgini/metadata.py,sha256=-bulW4ay0qxOxR4_5oDvENtgKiZgZI-QnU2stGHrKhg,12130
+upgini/metadata.py,sha256=Jh6YTaS00m_nbaOY_owvlSyn9zgkErkqu8iTr9ZjKI8,12279
 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=RlpKGss9kMibVSlA8iZuO_qxmyeplqzn7X8g6hiGGGs,14341
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.52a2.dist-info/METADATA,sha256=uP3OiyWH3nLIqCeEsbr1b6-2T3WR5X_uhjn7wyyDH4M,49057
-upgini-1.2.52a2.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.52a2.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.52a2.dist-info/RECORD,,
+upgini-1.2.54.dist-info/METADATA,sha256=UsKRAySU92ST26c9W_bfCOMEYHBNOQTweVVeL4mfA9I,49055
+upgini-1.2.54.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.54.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.54.dist-info/RECORD,,