wedata-feature-engineering 0.1.8__py3-none-any.whl → 0.1.10__py3-none-any.whl

wedata/__init__.py

@@ -3,4 +3,4 @@ WeData Feature Engineering
 A toolkit for automated feature engineering
 """
 
-__version__ = "0.1.8"
+__version__ = "0.1.10"

wedata/feature_store/client.py

@@ -202,6 +202,7 @@ class FeatureStoreClient:
             flavor: ModuleType,
             training_set: Optional[TrainingSet] = None,
             registered_model_name: Optional[str] = None,
+            model_registry_uri: Optional[str] = None,
             await_registration_for: int = mlflow.tracking._model_registry.DEFAULT_AWAIT_MAX_SLEEP_SECONDS,
             infer_input_example: bool = False,
             **kwargs,
@@ -218,6 +219,7 @@ class FeatureStoreClient:
              flavor: MLflow模型类型模块(如mlflow.sklearn)
              training_set: 训练模型使用的TrainingSet对象(可选)
              registered_model_name: 要注册的模型名称(可选)
+             model_registry_uri: 模型注册中心地址(可选)
              await_registration_for: 等待模型注册完成的秒数(默认300秒)
              infer_input_example: 是否自动记录输入示例(默认False)
 
@@ -231,6 +233,7 @@ class FeatureStoreClient:
             flavor=flavor,
             training_set=training_set,
             registered_model_name=registered_model_name,
+            model_registry_uri=model_registry_uri,
             await_registration_for=await_registration_for,
             infer_input_example=infer_input_example,
             **kwargs

wedata/feature_store/feature_table_client/feature_table_client.py

@@ -113,7 +113,7 @@ class FeatureTableClient:
         try:
             if self._spark.catalog.tableExists(table_name):
                 raise ValueError(
-                    f"Table '{table_name}' already exists\n"
+                    f"Table '{name}' already exists\n"
                     "Solutions:\n"
                     "1. Use a different table name\n"
                     "2. Drop the existing table: spark.sql(f'DROP TABLE {name}')\n"
@@ -125,11 +125,6 @@ class FeatureTableClient:
         table_schema = schema or df.schema
 
         # 构建时间戳键属性
-        timestamp_keys_ddl = []
-        for timestamp_key in timestamp_keys:
-            if timestamp_key not in primary_keys:
-                raise ValueError(f"Timestamp key '{timestamp_key}' must be a primary key")
-            timestamp_keys_ddl.append(f"`{timestamp_key}` TIMESTAMP")
 
         #从环境变量获取额外标签
         env_tags = {
@@ -142,6 +137,7 @@ class FeatureTableClient:
         tbl_properties = {
             "feature_table": "TRUE",
             "primaryKeys": ",".join(primary_keys),
+            "timestampKeys": ",".join(timestamp_keys) if timestamp_keys else "",
             "comment": description or "",
             **{f"{k}": v for k, v in (tags or {}).items()},
             **{f"feature_{k}": v for k, v in (env_tags or {}).items()}
@@ -171,7 +167,7 @@ class FeatureTableClient:
         CREATE TABLE {table_name} (
             {', '.join(columns_ddl)}
         )
-        USING PARQUET
+        USING iceberg
         {partition_expr}
         TBLPROPERTIES (
             {', '.join(f"'{k}'='{self._escape_sql_value(v)}'" for k, v in tbl_properties.items())}
@@ -293,13 +289,13 @@ class FeatureTableClient:
         try:
             # 检查表是否存在
             if not self._spark.catalog.tableExists(table_name):
-                raise ValueError(f"表 '{table_name}' 不存在")
+                raise ValueError(f"Table '{name}' does not exist")
 
             # 读取表数据
             return self._spark.read.table(table_name)
 
         except Exception as e:
-            raise ValueError(f"读取表 '{table_name}' 失败: {str(e)}") from e
+            raise ValueError(f"Failed to read table '{name}': {str(e)}") from e
 
     def drop_table(self, name: str):
 
@@ -327,7 +323,7 @@ class FeatureTableClient:
         try:
             # 检查表是否存在
             if not self._spark.catalog.tableExists(table_name):
-                raise ValueError(f"表 '{table_name}' 不存在")
+                raise ValueError(f"Table '{name}' does not exist")
 
             # 执行删除
             self._spark.sql(f"DROP TABLE {table_name}")
@@ -335,7 +331,7 @@ class FeatureTableClient:
         except ValueError as e:
             raise  # 直接抛出已知的ValueError
         except Exception as e:
-            raise RuntimeError(f"删除表 '{table_name}' 失败: {str(e)}") from e
+            raise RuntimeError(f"Failed to delete table '{name}': {str(e)}") from e
 
     def get_table(
             self,
@@ -365,4 +361,4 @@ class FeatureTableClient:
         try:
             return spark_client.get_feature_table(table_name)
         except Exception as e:
-            raise ValueError(f"获取表'{name}'元数据失败: {str(e)}") from e
+            raise ValueError(f"Failed to get metadata for table '{table_name}': {str(e)}") from e

wedata/feature_store/spark_client/spark_client.py

@@ -9,13 +9,39 @@ from pyspark.sql.types import StructType, StringType, StructField
 from wedata.feature_store.entities.feature import Feature
 from wedata.feature_store.entities.feature_table import FeatureTable
 from wedata.feature_store.entities.function_info import FunctionParameterInfo, FunctionInfo
-from wedata.feature_store.utils.common_utils import unsanitize_identifier, sanitize_multi_level_name
+from wedata.feature_store.utils.common_utils import unsanitize_identifier
 
 
 class SparkClient:
     def __init__(self, spark: SparkSession):
         self._spark = spark
 
+    def _parse_table_name(self, table_name):
+        """解析表名并返回表名部分
+
+        参数:
+            table_name: 完整表名，支持格式: catalog.schema.table、schema.table 或 table
+
+        返回:
+            str: 解析后的表名部分
+        """
+        if not isinstance(table_name, str):
+            raise ValueError("Table name must be string type")
+
+        table_name = table_name.strip()
+        if not table_name:
+            raise ValueError("Table name cannot be empty")
+
+        parts = table_name.split('.')
+        if len(parts) == 3:
+            # 对于三部分名称(catalog.schema.table)，只使用表名部分
+            return parts[2]
+        elif len(parts) == 2:
+            # 对于两部分名称(schema.table)，只使用表名部分
+            return parts[1]
+        else:
+            # 单表名，直接使用
+            return table_name
 
     def get_current_catalog(self):
         """
@@ -66,19 +92,13 @@ class SparkClient:
         """
         try:
             # 解析表名
-            parts = table_name.split('.')
-            if len(parts) == 3:
-                catalog, schema, table = parts
-            elif len(parts) == 2:
-                schema, table = parts
-            else:
-                table = table_name
+            schema_table_name = self._parse_table_name(table_name)
 
             # 验证表是否存在
-            if not self._spark.catalog.tableExists(table):
+            if not self._spark.catalog.tableExists(schema_table_name):
                 raise ValueError(f"表不存在: {table_name}")
 
-            return self._spark.table(table)
+            return self._spark.table(schema_table_name)
 
         except Exception as e:
             raise ValueError(f"读取表 {table_name} 失败: {str(e)}")
@@ -86,23 +106,10 @@ class SparkClient:
 
     def get_features(self, table_name):
         # 解析表名
-        parts = table_name.split('.')
-        if len(parts) == 3:
-            # 对于三部分名称(catalog.schema.table)，使用schema.table格式
-            _, schema, table = parts
-            full_table_name = f"{schema}.{table}"
-        elif len(parts) == 2:
-            # 对于两部分名称(schema.table)，直接使用
-            full_table_name = table_name
-        else:
-            # 单表名，使用当前数据库
-            current_db = self.get_current_database()
-            if not current_db:
-                raise ValueError("无法确定当前数据库")
-            full_table_name = f"{current_db}.{table_name}"
+        schema_table_name = self._parse_table_name(table_name)
 
         # 使用dbName.tableName格式查询列信息
-        columns = self._spark.catalog.listColumns(tableName=full_table_name)
+        columns = self._spark.catalog.listColumns(tableName=schema_table_name)
         return [
             Feature(
                 feature_table=table_name,
@@ -114,22 +121,14 @@ class SparkClient:
         ]
 
     def get_feature_table(self, table_name):
+        # 解析表名
+        schema_table_name = self._parse_table_name(table_name)
 
         # 获取表元数据
-        table = self._spark.catalog.getTable(table_name)
+        table = self._spark.catalog.getTable(schema_table_name)
 
-        parts = table_name.split('.')
-        if len(parts) == 3:
-            # 对于三部分名称(catalog.schema.table)，只使用表名部分
-            table_to_describe = parts[2]
-        elif len(parts) == 2:
-            # 对于两部分名称(schema.table)，只使用表名部分
-            table_to_describe = parts[1]
-        else:
-            # 单表名，直接使用
-            table_to_describe = table_name
         # 获取表详细信息
-        table_details = self._spark.sql(f"DESCRIBE TABLE EXTENDED {table_to_describe}").collect()
+        table_details = self._spark.sql(f"DESCRIBE TABLE EXTENDED {schema_table_name}").collect()
 
         table_properties = {}
         for row in table_details:

wedata/feature_store/training_set_client/training_set_client.py

@@ -186,6 +186,7 @@ class TrainingSetClient:
             flavor: ModuleType,
             training_set: Optional[TrainingSet],
             registered_model_name: Optional[str],
+            model_registry_uri: Optional[str],
             await_registration_for: int,
             infer_input_example: bool,
             **kwargs,
@@ -334,8 +335,7 @@ class TrainingSetClient:
             except Exception:
                 input_example = None
 
-            # todo:
-            #feature_spec.save(data_path)
+            feature_spec.save(data_path)
 
             # Log the packaged model. If no run is active, this call will create an active run.
             mlflow.pyfunc.log_model(
@@ -355,13 +355,12 @@ class TrainingSetClient:
             # If the user provided an explicit model_registry_uri when constructing the FeatureStoreClient,
             # we respect this by setting the registry URI prior to reading the model from Model
             # Registry.
-            # todo:
-            # if self._model_registry_uri:
-            #     # This command will override any previously set registry_uri.
-            #     mlflow.set_registry_uri(self._model_registry_uri)
+        if model_registry_uri is not None:
+             # This command will override any previously set registry_uri.
+            mlflow.set_registry_uri(model_registry_uri)
 
             mlflow.register_model(
                 "runs:/%s/%s" % (run_id, artifact_path),
                 registered_model_name,
                 await_registration_for=await_registration_for,
-                )
+            )

{wedata_feature_engineering-0.1.8.dist-info → wedata_feature_engineering-0.1.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: wedata-feature-engineering
-Version: 0.1.8
+Version: 0.1.10
 Summary: Wedata Feature Engineering Library
 Home-page: 
 Author: meahqian
@@ -14,4 +14,10 @@ Description-Content-Type: text/markdown
 Requires-Dist: pyspark>=3.0.0
 Requires-Dist: delta-spark>=1.0.0
 Requires-Dist: pandas>=1.0.0
-
+Dynamic: author
+Dynamic: classifier
+Dynamic: description-content-type
+Dynamic: license
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary

{wedata_feature_engineering-0.1.8.dist-info → wedata_feature_engineering-0.1.10.dist-info}/RECORD

@@ -1,6 +1,6 @@
-wedata/__init__.py,sha256=yIceuEY46nh56GEjtGNrDMIKTYtBHEf-Wj5Rc-cJS-g,101
+wedata/__init__.py,sha256=_M49ivoMq-NogMzHKd9DW6GfjUBWL18mb4gB5dK1Vbw,102
 wedata/feature_store/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/client.py,sha256=7a-9C8HIBHnQNQD6I4W3UtBQwkJE8G-Q7N24zydjpkY,8100
+wedata/feature_store/client.py,sha256=DO68yHiaJQ3LmrZ-owWEuRjuwM6vUjcaEdAcF65mdhs,8271
 wedata/feature_store/constants/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 wedata/feature_store/constants/constants.py,sha256=b4tgcSt66YIq0Fg7pMbqvbqPOI77Cz8znLVZ4ihUKss,1479
 wedata/feature_store/entities/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -20,11 +20,11 @@ wedata/feature_store/entities/on_demand_column_info.py,sha256=Eh5ieaj1TxC7DG6ipB
 wedata/feature_store/entities/source_data_column_info.py,sha256=a9jQOJvehwDIrKPwsP6W9YRBSPNK2nZYypE6-p80CwA,542
 wedata/feature_store/entities/training_set.py,sha256=ylt1h6Z_xU8hKYvnvd80CeewTGSN68-_kvFpoliwH7s,5679
 wedata/feature_store/feature_table_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/feature_table_client/feature_table_client.py,sha256=W6_TJ6PNc5o6SotVppBmu6VWZ7q_lPgIeg9Xsbr9r-g,12136
+wedata/feature_store/feature_table_client/feature_table_client.py,sha256=AoqlXWsR95UgrKuh7QNBUF4ygNmAgTQ_bRsJpmajRmc,11938
 wedata/feature_store/spark_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/spark_client/spark_client.py,sha256=DBCYjLsFrIVRvLErTNyfLIHRul3v0y9uZIY2JR1N92s,10323
+wedata/feature_store/spark_client/spark_client.py,sha256=SwMf-TsAeV7_8pDmh4927pKEwwKcIFK3JJ-J8rzUp_Q,10129
 wedata/feature_store/training_set_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/training_set_client/training_set_client.py,sha256=gHeZU0rvvUcyNTfroXD3LAinFPdhDpnwTOIWj6z84Tc,15102
+wedata/feature_store/training_set_client/training_set_client.py,sha256=CVcdgqfHL2S-fSCkfDwQgqtMhkB8haGEi1kEjbudDOk,15087
 wedata/feature_store/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 wedata/feature_store/utils/common_utils.py,sha256=cR3Vd49sWZrclaXvNO6B52Sk2v88iXmYmCIhi9xWsPM,10000
 wedata/feature_store/utils/feature_lookup_utils.py,sha256=da6ULwf5D-FRVpZoNyag1rroBfq_XPSH4a3uEMB_8io,22372
@@ -37,7 +37,7 @@ wedata/feature_store/utils/topological_sort.py,sha256=ebzKxmxeCLk9seB1zR0ASCGXsZ
 wedata/feature_store/utils/training_set_utils.py,sha256=MYsPZS1d9HKswHgjgxD8K7H9N3dWPyyTTx20Mkp4PVU,22497
 wedata/feature_store/utils/uc_utils.py,sha256=A-W8Cd8yvTmAMEWaHeWmGmcIDMvUtjAfx2G2x_di1QE,10774
 wedata/feature_store/utils/validation_utils.py,sha256=FslvrNs3kstqvM6THScLOluEE6O9RWlDrD9xiihTzlw,1735
-wedata_feature_engineering-0.1.8.dist-info/METADATA,sha256=HX42mSJie1KwNQnrB3temigb7fmxxEqShuE065NDcL8,493
-wedata_feature_engineering-0.1.8.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-wedata_feature_engineering-0.1.8.dist-info/top_level.txt,sha256=Xa0v1rh__RvfVTVDirW5r5UBKg7ZO_iuTeXfp8MNo2A,7
-wedata_feature_engineering-0.1.8.dist-info/RECORD,,
+wedata_feature_engineering-0.1.10.dist-info/METADATA,sha256=a3hj-GU81Glxtr14wsUdmothFfw5h9vdGYb2PWL5G5A,645
+wedata_feature_engineering-0.1.10.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
+wedata_feature_engineering-0.1.10.dist-info/top_level.txt,sha256=Xa0v1rh__RvfVTVDirW5r5UBKg7ZO_iuTeXfp8MNo2A,7
+wedata_feature_engineering-0.1.10.dist-info/RECORD,,

{wedata_feature_engineering-0.1.8.dist-info → wedata_feature_engineering-0.1.10.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.45.1)
+Generator: setuptools (79.0.1)
 Root-Is-Purelib: true
 Tag: py3-none-any