tencent-wedata-feature-engineering-dev 0.1.49__py3-none-any.whl → 0.2.0__py3-none-any.whl

wedata/feature_store/spark_client/spark_client.py

@@ -1,7 +1,6 @@
 from collections import defaultdict
 from typing import Optional, Any, Dict, List
 
-import logging
 from pyspark.sql import SparkSession, DataFrame
 from pyspark.sql.catalog import Column
 from pyspark.sql.functions import when, isnull
@@ -15,7 +14,7 @@ from wedata.feature_store.constants.constants import (
 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, check_spark_table_exists, check_package_version
+from wedata.feature_store.utils.common_utils import unsanitize_identifier
 
 
 class SparkClient:
@@ -29,12 +28,10 @@ class SparkClient:
         返回:
             str: 当前catalog名称，如果未设置则返回None
         """
-        _, ok, _ = check_package_version("pyspark", "3.4.0", ">=")
-        if ok:
+        try:
             return unsanitize_identifier(self._spark.catalog.currentCatalog())
-        else:
-            catalog = self._spark.sql("SELECT current_catalog()").first()[0]
-            return unsanitize_identifier(catalog)
+        except Exception:
+            return None
 
     def get_current_database(self):
         """
@@ -52,9 +49,13 @@ class SparkClient:
             # 捕获所有异常并返回None
             return None
 
+
+
+
     def createDataFrame(self, data, schema) -> DataFrame:
         return self._spark.createDataFrame(data, schema)
 
+
     def read_table(self, table_name):
         """读取Spark表数据
 
@@ -67,28 +68,20 @@ class SparkClient:
         Raises:
             ValueError: 当表不存在或读取失败时抛出
         """
-        table_name = _translate_spark_table_name(table_name)
         try:
             # 验证表是否存在
-            if not  check_spark_table_exists(self._spark, table_name):
+            if not self._spark.catalog.tableExists(table_name):
                 raise ValueError(f"Table does not exist: {table_name}")
+
             return self._spark.table(table_name)
 
         except Exception as e:
             raise ValueError(f"Failed to read table {table_name}: {str(e)}")
 
+
     def get_features(self, table_name):
         # 查询列信息
-        table_name = _translate_spark_table_name(table_name)
-        split = table_name.split(".")
-        if len(split) == 2:
-            # db.table_name
-            columns = self._spark.catalog.listColumns(tableName=split[1], dbName=split[0])
-        elif len(split) == 3:
-            # catalog.db.table_name
-            columns = self._spark.catalog.listColumns(tableName=split[2], dbName=split[1])
-        else:
-            columns = self._spark.catalog.listColumns(tableName=table_name)
+        columns = self._spark.catalog.listColumns(tableName=table_name)
         return [
             Feature(
                 feature_table=table_name,
@@ -100,19 +93,15 @@ class SparkClient:
         ]
 
     def get_feature_table(self, table_name):
-        """
-        DLC支持table_name为catalog.schema.table
-        EMR支持table_name为schema.table
-        """
+        # 获取表元数据
+        table = self._spark.catalog.getTable(table_name)
 
-        table_name = _translate_spark_table_name(table_name)
-        # table = self._spark.catalog.getTable(table_name)
         # 获取表配置信息
         properties = self._spark.sql(f"SHOW TBLPROPERTIES {table_name}").collect()
         primary_key_str = next((row.value for row in properties if row.key == "primaryKeys"), None)
         primary_keys = primary_key_str.split(",") if primary_key_str else []
         table_id = next((row.value for row in properties if row.key == "table_id"), table_name)
-        description = next((row.value for row in properties if row.key == "comment"), None)
+        description = table.description or next((row.value for row in properties if row.key == "comment"), None)
         timestamp_keys_str = next((row.value for row in properties if row.key == "timestampKeys"), None)
         timestamp_keys = timestamp_keys_str.split(",") if timestamp_keys_str else []
         # 获取分区字段信息
@@ -269,18 +258,3 @@ class SparkClient:
             kwargs[_PREBUILT_ENV_URI] = prebuilt_env_uri
 
         return spark_udf(self._spark, model_uri, **kwargs)
-
-
-def _translate_spark_table_name(table_name):
-    from wedata.feature_store.constants.engine_types import judge_engine_type, CalculateEngineTypes
-    # 获取表元数据
-    if judge_engine_type() == CalculateEngineTypes.EMR:
-        split_names = table_name.split(".")
-        # print(f"==== EMR TABLE split len({len(split_names)})")
-        if len(split_names) <= 2:
-            return table_name
-        else:
-            table_name = ".".join(table_name.split(".")[1:])
-            return table_name
-    return table_name
-

wedata/feature_store/training_set_client/training_set_client.py

@@ -309,7 +309,16 @@ class TrainingSetClient:
             feature_spec.save(data_path)
 
             print(f'artifact_path:{artifact_path},data_path:{data_path},conda_env:{conda_env},'
-                  f'signature:{signature},input_example:{input_example}');
+                  f'signature:{signature},input_example:{input_example}')
+
+            # 设置实例ID标签
+            tdlc_home = os.getenv('TDLC_HOME', '')
+            if tdlc_home:
+                instance_id = tdlc_home.split('/')[-3]
+                mlflow.set_tag("instance_id", instance_id)
+
+                # 设置实验标签,血缘查询需要
+                mlflow.set_experiment_tag(f"instance_id_{instance_id}", instance_id)
 
             mlflow.pyfunc.log_model(
                 artifact_path=artifact_path,
@@ -360,7 +369,6 @@ class TrainingSetClient:
         env_manager: Optional[str] = None,
         local_uri: Optional[str] = None,
         params: Optional[dict[str, Any]] = None,
-        timestamp_key: str = None,
         **kwargs,
     ) -> DataFrame:
         # TODO:ML 待确定是否需要
@@ -424,11 +432,8 @@ class TrainingSetClient:
 
         # Validate that columns needed for joining feature tables exist and are not duplicates.
         feature_input_keys = []
-        print("====>timestamp_key:", timestamp_key)
         for fci in feature_spec.feature_column_infos:
-            print("====>fci:", fci.lookup_key)
             feature_input_keys.extend([k for k in fci.lookup_key])
-
         on_demand_input_names = uc_utils.get_unique_list_order(
             [
                 input_name
@@ -442,16 +447,12 @@ class TrainingSetClient:
         ]
         # print(f"wedata source_data_names:{source_data_names}")
 
-        print("===>source_data_names:", source_data_names)
-
         feature_output_names = [
             fci.output_name for fci in feature_spec.feature_column_infos
         ]
-        print("====>feature_output_names:", feature_output_names)
         on_demand_output_names = [
             odci.output_name for odci in feature_spec.on_demand_column_infos
         ]
-        print("====>on_demand_output_names:", on_demand_output_names)
         all_output_names = set(
             source_data_names + feature_output_names + on_demand_output_names
         )

wedata/feature_store/utils/common_utils.py

@@ -2,12 +2,14 @@
 通用工具函数
 """
 import os
+import json
 from collections import Counter
 from datetime import datetime, timezone
 from functools import wraps
 from typing import Any, Dict, List, Optional
 from urllib.parse import urlparse
 
+import mlflow
 from mlflow.exceptions import RestException
 from mlflow.store.artifact.artifact_repository_registry import get_artifact_repository
 from mlflow.store.artifact.models_artifact_repo import ModelsArtifactRepository
@@ -16,7 +18,6 @@ from mlflow.utils import databricks_utils
 
 from wedata.feature_store.constants import constants
 from wedata.feature_store.constants.constants import MODEL_DATA_PATH_ROOT
-from pyspark.sql import SparkSession
 
 import logging
 
@@ -116,7 +117,7 @@ def _get_dbutils():
 def utc_timestamp_ms_from_iso_datetime_string(date_string: str) -> int:
     dt = datetime.fromisoformat(date_string)
     utc_dt = dt.replace(tzinfo=timezone.utc)
-    return int(1000 * utc_dt.timestamp())
+    return 1000 * utc_dt.timestamp()
 
 
 def pip_depependency_pinned_major_version(pip_package_name, major_version):
@@ -303,49 +304,4 @@ def validate_database(database_name):
         database_name = os.environ.get(constants.WEDATA_DEFAULT_FEATURE_STORE_DATABASE)
     if database_name is None:
         raise ValueError("Database_name variable or default database is not set.")
-    return True
-
-
-def check_package_version(package_name, expected_version, op="=="):
-    """
-    检查指定包的版本是否满足预期版本要求。
-    Args:
-        package_name: 包名称
-        expected_version: 预期版本要求，例如3.5.5
-        op: 比较运算符，默认为 "=="
-    Returns:
-        (是否成功找到包，版本是否匹配，已安装版本)
-    如果满足，返回 (True, True, installed_version)；否则返回 (True, False, installed_version)。
-    如果指定包不存在，返回 (False, False, None)。
-    """
-    # 在脚本顶部添加
-    from packaging import version
-    import importlib.metadata
-    try:
-        installed_version = importlib.metadata.version(package_name)
-
-        if not op:
-            raise ValueError(f"Invalid op: {op}. need be in ['==', '>', '<', '>=', '<=', '!=', '~=']")
-        # 支持版本范围检查（如 ">=2.0,<3.0"）
-        # 使用 packaging.version 进行复杂版本`检查
-        i = version.parse(installed_version)
-        e = version.parse(expected_version)
-        return True, eval(f"i{op}e"), installed_version
-
-    except importlib.metadata.PackageNotFoundError:
-        return False, False, None
-
-
-def check_spark_table_exists(spark_client: SparkSession, full_table_name: str) -> bool:
-    _, ok, _ = check_package_version("pyspark", "3.5.0", ">=")
-    try:
-        return spark_client.catalog.tableExists(full_table_name)
-    except AttributeError:
-        split = full_table_name.split(".")
-        if len(split) == 2:
-            query = f"SHOW TABLES IN {split[0]} LIKE '{split[1]}'"
-        elif len(split) == 3:
-            query = f"SHOW TABLES IN {split[1]} LIKE '{split[2]}'"
-        else:
-            query = f"SHOW TABLES LIKE '{full_table_name}'"
-        return spark_client.sql(query).count() > 0
+    return True

wedata/feature_store/utils/feature_lookup_utils.py

@@ -6,10 +6,9 @@ from collections import defaultdict
 from functools import reduce
 from typing import Dict, List, Optional, Tuple
 
-from pyspark.sql import DataFrame
+from pyspark.sql import DataFrame, Window
 from pyspark.sql import functions as F
-import pyspark.sql.functions as psf
-
+from pyspark.sql.functions import sum, unix_timestamp
 
 from wedata.feature_store.entities.environment_variables import BROADCAST_JOIN_THRESHOLD
 from wedata.feature_store.entities.feature_column_info import FeatureColumnInfo
@@ -17,7 +16,7 @@ from wedata.feature_store.entities.feature_lookup import FeatureLookup
 from wedata.feature_store.entities.feature_spec import FeatureSpec
 from wedata.feature_store.entities.feature_table import FeatureTable
 
-from wedata.feature_store.utils import uc_utils
+from wedata.feature_store.utils import common_utils, validation_utils, uc_utils
 
 _logger = logging.getLogger(__name__)
 
@@ -75,21 +74,19 @@ def _spark_asof_join_features(
     else:
         joined_df = _spark_asof_join_features_tempo(
             df=df,
-            feature_df=feature_and_keys,
-            lookup_keys=df_lookup_keys,
-            timestamp_key=df_timestamp_lookup_key,
-            lookback_window=lookback_window_seconds,
+            df_lookup_keys=df_lookup_keys,
+            df_timestamp_lookup_key=df_timestamp_lookup_key,
+            feature_and_keys=feature_and_keys,
             ft_features=ft_features,
+            lookback_window_seconds=lookback_window_seconds,
         )
     return joined_df
 
-
 def _spark_asof_join_features_tempo(
         df: DataFrame,
         feature_df: DataFrame,
         lookup_keys: List[str],
         timestamp_key: str,
-        ft_features: List[Tuple[str, str]],
         lookback_window: Optional[float] = None
 ) -> DataFrame:
     """
@@ -101,33 +98,42 @@ def _spark_asof_join_features_tempo(
     :param lookback_window: 最大回溯时间(秒)
     :return: 连接后的DataFrame
     """
-    from wedata.tempo.tsdf import TSDF
+
     # 1. 只保留键列和时间戳列
-    df_tsdf = TSDF(df, ts_col=timestamp_key, partition_cols=lookup_keys)
-    ft_tsdf = TSDF(feature_df, ts_col=timestamp_key, partition_cols=lookup_keys)
-    # 进行as-of连接
-    joined_df = df_tsdf.asofJoin(
-        ft_tsdf,
-        left_prefix="left",
-        right_prefix="right",
-        skipNulls=False,
-        tolerance=lookback_window
-        if lookback_window is not None
-        else None,
-    ).df
-
-    # 去掉前缀，恢复列名
-    left_aliases = [
-        joined_df[f"left_{column_name}"].alias(column_name)
-        for column_name in df.columns
-        if column_name not in lookup_keys
-    ]
-    right_aliases = [
-        joined_df[f"right_{output_name}"].alias(output_name)
-        for (_, output_name) in ft_features
-    ]
-    return joined_df.select(lookup_keys + left_aliases + right_aliases)
+    df_keys = df.select(lookup_keys + [timestamp_key])
+    feature_keys = feature_df.select(lookup_keys + [timestamp_key])
+
+    # 2. 创建连接条件
+    join_cond = [df_keys[k] == feature_keys[k] for k in lookup_keys]
+    join_cond = reduce(lambda x, y: x & y, join_cond)
+    join_cond &= (df_keys[timestamp_key] >= feature_keys[timestamp_key])
+
+    if lookback_window:
+        join_cond &= (
+                (F.unix_timestamp(df_keys[timestamp_key]) -
+                 F.unix_timestamp(feature_keys[timestamp_key])) <= lookback_window
+        )
+
+    # 3. 执行连接并找出每个主表记录对应的最新特征记录
+    joined = df_keys.join(feature_keys, join_cond, "left")
+
+    # 按主表键分组，找出最大特征时间戳
+    window = Window.partitionBy(lookup_keys).orderBy(F.desc(timestamp_key))
+    latest_features = (
+        joined
+        .withColumn("rn", F.row_number().over(window))
+        .filter(F.col("rn") == 1)
+        .drop("rn")
+    )
+
+    # 4. 最终连接获取完整特征数据
+    result = df.join(
+        latest_features.select(lookup_keys + [timestamp_key, "feature_col"]),
+        lookup_keys + [timestamp_key],
+        "left"
+    )
 
+    return result
 
 def _spark_asof_join_features_native(
     labels_df: DataFrame,
@@ -184,8 +190,8 @@ def _spark_asof_join_features_native(
     )
     if lookback_window_seconds is not None:
         join_conditions &= (
-            psf.unix_timestamp(labels_df_keys_only[timestamp_key])
-            - psf.unix_timestamp(features_df_keys_only["__features_tk"])
+            unix_timestamp(labels_df_keys_only[timestamp_key])
+            - unix_timestamp(features_df_keys_only["__features_tk"])
         ) <= lookback_window_seconds
 
     # Join labels and features DataFrames

wedata/feature_store/utils/feature_spec_utils.py

@@ -1,7 +1,7 @@
 import logging
 from dataclasses import dataclass
 from functools import reduce
-from typing import Dict, List, Tuple, Union
+from typing import Dict, List, Set, Tuple, Type, Union
 
 import yaml
 from mlflow.utils.file_utils import YamlSafeDumper

wedata/feature_store/utils/uc_utils.py

@@ -287,7 +287,7 @@ def utc_timestamp_ms_from_iso_datetime_string(date_string: str) -> int:
     # The Feature Store backend returns timestamps in milliseconds, so this allows for direct comparisons.
     dt = datetime.fromisoformat(date_string)
     utc_dt = dt.replace(tzinfo=timezone.utc)
-    return int(1000 * utc_dt.timestamp())
+    return 1000 * utc_dt.timestamp()
 
 def get_unique_list_order(elements: List[Any]) -> List[Any]:
     """

tencent_wedata_feature_engineering_dev-0.1.49.dist-info/RECORD

@@ -1,66 +0,0 @@
-wedata/__init__.py,sha256=GYxqkkgH0oH4QtNiOCZHuGkc0sSH1LgEqmhSX6sB4So,200
-wedata/feature_store/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/client.py,sha256=B6fy-PGJZsEHGPE8tDmrTolyioJ_-Po2DK3p_HCW7Sw,19552
-wedata/feature_store/mlflow_model.py,sha256=OCUuccOoO0NXWSzIPoGeL03Ha1Q3aQTJW2RlJrTCmzc,554
-wedata/feature_store/cloud_sdk_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/cloud_sdk_client/client.py,sha256=B7nCQ_MvbLP4ieT7rsa32FHws2fOG4VQZT5lmQ3Cvzk,4914
-wedata/feature_store/cloud_sdk_client/models.py,sha256=7_QUq0kZcrcclRMsIYFoqBrlzVwaHoVY-yU5SHIrJWM,19789
-wedata/feature_store/cloud_sdk_client/utils.py,sha256=xwvXJpk2RXbJtgOaXCZQbGRrlzcTRzv27yQFxKp_X84,970
-wedata/feature_store/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/common/log/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/common/log/logger.py,sha256=c45DlIbIuwRP2na3ZXsncpHV5KUltqfyKzIgG9GG3g4,1151
-wedata/feature_store/common/protos/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/common/protos/feature_store_pb2.py,sha256=oMIUGGeGNP84g_nFqOQwTXjV1GiU2ehSOy7CyFu2__g,4207
-wedata/feature_store/common/store_config/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/common/store_config/redis.py,sha256=9R5npM2s1u0o9IakmpbRsFdJC0vNar_uvA62OLWuXBs,1145
-wedata/feature_store/constants/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/constants/constants.py,sha256=KY_EYyVH-rao3-rHUbdoayz7lcsGyiMDI44Ib7KFCKc,1959
-wedata/feature_store/constants/engine_types.py,sha256=42mI-kNDDtoA4_I3iqDe4FkF2M2l_Bt4Q1V6WUB-_k0,921
-wedata/feature_store/entities/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/entities/column_info.py,sha256=-AR6EKHwgoqIkRHFyguxVEtnYt6fvusWHkEjF4kvS0A,5141
-wedata/feature_store/entities/environment_variables.py,sha256=ZEFml5H9MQuzBKM074mUrFYu-Sga4Knmxqiwpke2WGc,1679
-wedata/feature_store/entities/feature.py,sha256=wX8fTBlJq3GYdj9rrBDCY3kFgcVBBAiOOZdxEhnQkNQ,1241
-wedata/feature_store/entities/feature_column_info.py,sha256=ZAS_I-MDg2ofCv3nwYvGCQrrpEljzrh_L1D-gqOV_mM,2407
-wedata/feature_store/entities/feature_function.py,sha256=R17INrCE-U_Uj9KLbFz69aYlOkTETTwQHMMo470F4lQ,1865
-wedata/feature_store/entities/feature_lookup.py,sha256=UYmYCzkQ1_KuooybS3F-7HDcjBMPZ72InL06UTHbEtw,8749
-wedata/feature_store/entities/feature_spec.py,sha256=Z2SXE_LObjNY3q5yBVKPXGTUiMZy7zaI6-ZbAoFlwG8,21769
-wedata/feature_store/entities/feature_spec_constants.py,sha256=YWDBfRiNDe6fUJFUBo3V4WYg2xsljoPAE-ZejfFZCgM,785
-wedata/feature_store/entities/feature_table.py,sha256=nHCCd7WUryROt9oTJpYkT-KiGbKcQd7BEE9L2_1dhYw,4107
-wedata/feature_store/entities/feature_table_info.py,sha256=yJ1P3AYaPiHW6ehCbMWhndzguHJqJKWfeFwYjwTLt2U,1481
-wedata/feature_store/entities/function_info.py,sha256=yDwIzTrBR-ECWubgeoy48SYZfdY7P0JcraZnWGCW0ag,2752
-wedata/feature_store/entities/on_demand_column_info.py,sha256=a44ep-f3FOruWNXl3c8v7733rNuoKXJaHTv1aqF905s,1739
-wedata/feature_store/entities/source_data_column_info.py,sha256=FyBmBPUSvc2S2OPFTvsQf2AdS-KFGkYBmd4yL_Vur8M,702
-wedata/feature_store/entities/training_set.py,sha256=ylt1h6Z_xU8hKYvnvd80CeewTGSN68-_kvFpoliwH7s,5679
-wedata/feature_store/feast_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/feast_client/feast_client.py,sha256=mCv-OiKehfgcOJhJV0wXMRs5d7e2zEBYmVmDguk0rxU,20728
-wedata/feature_store/feature_table_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/feature_table_client/feature_table_client.py,sha256=qyr-jS-nIyphFVZXcUXV_HSfAu-8c19f0b8iG5rYsl8,42669
-wedata/feature_store/spark_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/spark_client/spark_client.py,sha256=aTenEqfZoJYMrph98qjNHZ-H4dgNKnMaH14st8bCVRQ,11797
-wedata/feature_store/training_set_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/training_set_client/training_set_client.py,sha256=Ja_W1SKWKueW6wmwDx-623mfpwKQICm6A-ec_jgOFt4,23707
-wedata/feature_store/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/utils/common_utils.py,sha256=vkpoXxZTd6S-2MgdyTQZ6P_ckdqNSK50ECuVBG2BwfI,12314
-wedata/feature_store/utils/env_utils.py,sha256=NzJjT7WAXfw0Gksad3nSEeUDSAXfsKkC-v7aY6kzrpU,2888
-wedata/feature_store/utils/feature_lookup_utils.py,sha256=mNV6RhBdpv1iTZduCA9YwXwkeJCwU5MFQ1MkFeD9IhY,22003
-wedata/feature_store/utils/feature_spec_utils.py,sha256=j8t-zel2_r8Q9m88BmFKkHMdkGNIduWJB-28OZDASRY,11613
-wedata/feature_store/utils/feature_utils.py,sha256=KKq28bVB_lCuhnR9Hk6JegJBOVgcelWlvrRM-F9onkA,2796
-wedata/feature_store/utils/on_demand_utils.py,sha256=pazZRG5c0Se08MV_inBddIeX4Q9xlVN_H9SC_WK3xzs,4260
-wedata/feature_store/utils/schema_utils.py,sha256=y6EYY1pUxjVg6MP4C7avdW8ZEBBaDo1YTV2CmPF4i8o,4491
-wedata/feature_store/utils/signature_utils.py,sha256=SZFufd19m0jmGnOLmAl3JPKZC-qHq-wQezh6G7HOMfc,7773
-wedata/feature_store/utils/topological_sort.py,sha256=ebzKxmxeCLk9seB1zR0ASCGXsZsa-DjxJeTc4KUadtg,6475
-wedata/feature_store/utils/training_set_utils.py,sha256=MYsPZS1d9HKswHgjgxD8K7H9N3dWPyyTTx20Mkp4PVU,22497
-wedata/feature_store/utils/uc_utils.py,sha256=5jngdLT8quP1lfGHN_SSFQQlcOh_sUB9M1varCgdFwg,11436
-wedata/feature_store/utils/validation_utils.py,sha256=lJe6HCg5v5CZxH_pvT-vpGhCpo66LT2erXraHE2T0iI,2584
-wedata/tempo/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/tempo/interpol.py,sha256=3JF8dwcdKv2o10FN45aefgvxR5DjlR6FJAXrbAiGCro,16423
-wedata/tempo/intervals.py,sha256=L2ao7LlgQmfDTFwnBoFLXeuygSvwtIKXL52thiD80Yw,44078
-wedata/tempo/io.py,sha256=KWIn6IBSkuBxr8QCcpdZ6NFX_49-8UQdGftmZgs_ujw,1872
-wedata/tempo/ml.py,sha256=WtGa2szn6PditvZsTZoxo7wFDe4k1SRoMZ-jgNGIjvE,4323
-wedata/tempo/resample.py,sha256=h81RVVmCl4ect-YKE-KZZHPDi1rGI3sh-YIb-Btz0ck,9698
-wedata/tempo/tsdf.py,sha256=S4lZfxhSRFiezYoYS6gvGsl1mZA3zp-MWEKFHYZpDg0,70968
-wedata/tempo/utils.py,sha256=I9I6l2DMwUoY213L04Yc1UR_zTWgSkj1BVo4ZwzQd4Y,7977
-tencent_wedata_feature_engineering_dev-0.1.49.dist-info/METADATA,sha256=bNbO1CncVzLyyM2-pkch4bdSnAe75f8cZTkUKn0z4aE,582
-tencent_wedata_feature_engineering_dev-0.1.49.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-tencent_wedata_feature_engineering_dev-0.1.49.dist-info/top_level.txt,sha256=Xa0v1rh__RvfVTVDirW5r5UBKg7ZO_iuTeXfp8MNo2A,7
-tencent_wedata_feature_engineering_dev-0.1.49.dist-info/RECORD,,

wedata/feature_store/cloud_sdk_client/client.py

@@ -1,108 +0,0 @@
-import json
-
-from tencentcloud.wedata.v20210820.wedata_client import WedataClient
-from tencentcloud.wedata.v20250806.wedata_client import WedataClient as WedataClientV2
-from tencentcloud.common import credential
-from tencentcloud.common.exception.tencent_cloud_sdk_exception import TencentCloudSDKException
-from wedata.feature_store.cloud_sdk_client.utils import get_client_profile, set_request_header, is_mock
-import wedata.feature_store.cloud_sdk_client.models as models
-from wedata.feature_store.common.log.logger import get_logger
-
-
-class FeatureCloudSDK:
-    def __init__(self, secret_id: str, secret_key: str, region: str):
-        self._client = WedataClient(credential.Credential(secret_id, secret_key), region, get_client_profile())
-        self._client_v2 = WedataClientV2(credential.Credential(secret_id, secret_key), region, get_client_profile())
-
-    def CreateOnlineFeatureTable(self, request: models.CreateOnlineFeatureTableRequest) -> 'models.CreateOnlineFeatureTableResponse':
-        """
-        创建在线特征表
-        Args:
-            request: 创建请求参数
-
-        Returns:
-            创建结果响应
-        """
-        logger = get_logger()
-        if is_mock():
-            logger.debug("Mock CreateOnlineFeatureTable API")
-            return models.CreateOnlineFeatureTableResponse()
-        try:
-            params = request._serialize()
-            headers = set_request_header(request.headers)
-            logger.debug(f"CreateOnlineFeatureTable params: {params}")
-            logger.debug(f"CreateOnlineFeatureTable headers: {headers}")
-            self._client._apiVersion = "2021-08-20"
-            body = self._client.call("CreateOnlineFeatureTable", params, headers=headers)
-            response = json.loads(body)
-            model = models.CreateOnlineFeatureTableResponse()
-            model._deserialize(response["Response"])
-            logger.debug(f"CreateOnlineFeatureTable Response: {response}")
-            return model
-        except Exception as e:
-            if isinstance(e, TencentCloudSDKException):
-                raise
-            else:
-                raise TencentCloudSDKException(type(e).__name__, str(e))
-
-    def DescribeNormalSchedulerExecutorGroups(self, request: models.DescribeNormalSchedulerExecutorGroupsRequest) -> 'models.DescribeNormalSchedulerExecutorGroupsResponse':
-        """
-        查询普通调度器执行器组
-        Args:
-            request: 查询请求参数
-
-        Returns:
-            查询结果响应
-        """
-        logger = get_logger()
-        if is_mock():
-            logger.debug("Mock DescribeNormalSchedulerExecutorGroups API")
-            return models.DescribeNormalSchedulerExecutorGroupsResponse()
-
-        try:
-            params = request._serialize()
-            headers = set_request_header(request.headers)
-            logger.debug(f"DescribeNormalSchedulerExecutorGroups params: {params}")
-            logger.debug(f"DescribeNormalSchedulerExecutorGroups headers: {headers}")
-            self._client._apiVersion = "2021-08-20"
-            body = self._client.call("DescribeNormalSchedulerExecutorGroups", params, headers=headers)
-            response = json.loads(body)
-            model = models.DescribeNormalSchedulerExecutorGroupsResponse()
-            model._deserialize(response["Response"])
-            logger.debug(f"DescribeNormalSchedulerExecutorGroups Response: {response}")
-            return model
-        except Exception as e:
-            if isinstance(e, TencentCloudSDKException):
-                raise
-            else:
-                raise TencentCloudSDKException(type(e).__name__, str(e))
-
-    def RefreshFeatureTable(self, request: models.RefreshFeatureTableRequest) -> 'models.RefreshFeatureTableResponse':
-        """
-        刷新特征表
-        Args:
-            request: 刷新请求参数
-        Returns:
-            刷新结果响应
-        """
-        logger = get_logger()
-        if is_mock():
-            logger.debug("Mock RefreshFeatureTable API")
-            return models.RefreshFeatureTableResponse()
-        try:
-            params = request._serialize()
-            headers = set_request_header(request.headers)
-            logger.debug(f"RefreshFeatureTable params: {params}")
-            logger.debug(f"RefreshFeatureTable headers: {headers}")
-            self._client_v2._apiVersion = "2025-08-06"
-            body = self._client_v2.call("RefreshFeatureTable", params, headers=headers)
-            response = json.loads(body)
-            model = models.RefreshFeatureTableResponse()
-            model._deserialize(response["Response"])
-            logger.debug(f"RefreshFeatureTable Response: {response}")
-            return model
-        except Exception as e:
-            if isinstance(e, TencentCloudSDKException):
-                raise
-            else:
-                raise TencentCloudSDKException(type(e).__name__, str(e))