upgini 1.2.96a3906.dev1__py3-none-any.whl → 1.2.96a3906.dev2__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.96a3906.dev1"
+__version__ = "1.2.96a3906.dev2"

upgini/normalizer/normalize_utils.py

@@ -74,33 +74,19 @@ class Normalizer:
         new_columns = []
         dup_counter = 0
         for column in df.columns:
-            if (
-                column
-                in [
-                    TARGET,
-                    EVAL_SET_INDEX,
-                    SYSTEM_RECORD_ID,
-                    ENTITY_SYSTEM_RECORD_ID,
-                    SEARCH_KEY_UNNEST,
-                    DateTimeSearchKeyConverter.DATETIME_COL,
-                ]
-            ):
+            if column in [
+                TARGET,
+                EVAL_SET_INDEX,
+                SYSTEM_RECORD_ID,
+                ENTITY_SYSTEM_RECORD_ID,
+                SEARCH_KEY_UNNEST,
+                DateTimeSearchKeyConverter.DATETIME_COL,
+            ]:
                 self.columns_renaming[column] = column
                 new_columns.append(column)
                 continue
 
-            new_column = str(column)
-            suffix = hashlib.sha256(new_column.encode()).hexdigest()[:6]
-            if len(new_column) == 0:
-                raise ValidationError(self.bundle.get("dataset_empty_column_names"))
-            # db limit for column length
-            if len(new_column) > 250:
-                new_column = new_column[:250]
-
-            # make column name unique relative to server features
-            new_column = f"{new_column}_{suffix}"
-
-            new_column = new_column.lower()
+            new_column = add_hash_suffix(column, self.bundle)
 
             # if column starts with non alphabetic symbol then add "a" to the beginning of string
             if ord(new_column[0]) not in range(ord("a"), ord("z") + 1):
@@ -198,3 +184,19 @@ class Normalizer:
             if not is_numeric_dtype(df[f]):
                 df[f] = df[f].astype("string")
         return df
+
+
+def add_hash_suffix(column: str, bundle: ResourceBundle | None = None) -> str:
+    new_column = str(column)
+    suffix = hashlib.sha256(new_column.encode()).hexdigest()[:6]
+    if bundle is not None and len(new_column) == 0:
+        raise ValidationError(bundle.get("dataset_empty_column_names"))
+    # db limit for column length
+    if len(new_column) > 250:
+        new_column = new_column[:250]
+
+    # make column name unique relative to server features
+    new_column = f"{new_column}_{suffix}"
+
+    new_column = new_column.lower()
+    return new_column

{upgini-1.2.96a3906.dev1.dist-info → upgini-1.2.96a3906.dev2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.96a3906.dev1
+Version: 1.2.96a3906.dev2
 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.dist-info → upgini-1.2.96a3906.dev2.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=PUiYzCofvZt-NqYbWaNaLcmWYA89yEpQxOLTh8v2lac,33
+upgini/__about__.py,sha256=8ZaMc0M4yKUigIQciHTdkff0EFfiqt8pmRDvJz70MsQ,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=e6JDYTZ2AwC5aF-dqclKZKkiKrHo2f6cFmMQO2ZZmjM,32724
@@ -35,7 +35,7 @@ upgini/data_source/data_source_publisher.py,sha256=ufL8qK1vg8iUKd5bLWz6hEMGiC3Je
 upgini/mdc/__init__.py,sha256=iHJlXQg6xRM1-ZOUtaPSJqw5SpQDszvxp4LyqviNLIQ,1027
 upgini/mdc/context.py,sha256=3u1B-jXt7tXEvNcV3qmR9SDCseudnY7KYsLclBdwVLk,1405
 upgini/normalizer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-upgini/normalizer/normalize_utils.py,sha256=g2TcDXZeJp9kAFO2sTqZ4CAsN4J1qHNgoJHZ8gtzUWo,7376
+upgini/normalizer/normalize_utils.py,sha256=hMHi5u6Oleqp885UW0Q0Uf1F8fRdZ5jJ7NYoY52SqaI,7403
 upgini/resource_bundle/__init__.py,sha256=S5F2G47pnJd2LDpmFsjDqEwiKkP8Hm-hcseDbMka6Ko,8345
 upgini/resource_bundle/exceptions.py,sha256=5fRvx0_vWdE1-7HcSgF0tckB4A9AKyf5RiinZkInTsI,621
 upgini/resource_bundle/strings.properties,sha256=Hfpr2-I5Ws6ugIN1QSz549OHayZeLYglRsbrGDT6g9g,28491
@@ -71,7 +71,7 @@ upgini/utils/target_utils.py,sha256=i3Xt5l9ybB2_nF_ma5cfPuL3OeFTs2dY2xDI0p4Azpg,
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/ts_utils.py,sha256=26vhC0pN7vLXK6R09EEkMK3Lwb9IVPH7LRdqFIQ3kPs,1383
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.96a3906.dev1.dist-info/METADATA,sha256=tsYVKpMvgRQC8vNFCNlPhKvjxD8mysNzj7E4BWM18Gc,49538
-upgini-1.2.96a3906.dev1.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.2.96a3906.dev1.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.96a3906.dev1.dist-info/RECORD,,
+upgini-1.2.96a3906.dev2.dist-info/METADATA,sha256=IiF040yVE4K20_1kus6Y4tzj6rDeA2X8kYkhJ0_Kxr8,49538
+upgini-1.2.96a3906.dev2.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.2.96a3906.dev2.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.96a3906.dev2.dist-info/RECORD,,