tencent-wedata-feature-engineering-dev 0.1.42__py3-none-any.whl → 0.2.5__py3-none-any.whl

wedata/feature_store/feature_table_client/feature_table_client.py

@@ -2,7 +2,7 @@
 特征表操作相关工具方法
 """
 import json
-from typing import Union, List, Dict, Optional, Sequence, Any
+from typing import Union, List, Dict, Optional, Any
 
 import tencentcloud.common.exception
 from pyspark.sql import DataFrame, SparkSession
@@ -10,23 +10,23 @@ from pyspark.sql.streaming import StreamingQuery
 from pyspark.sql.types import StructType
 import os
 import datetime
-from wedata.feature_store.constants.constants import (
+from wedata.common.constants.constants import (
     APPEND, DEFAULT_WRITE_STREAM_TRIGGER, FEATURE_TABLE_KEY,
     FEATURE_TABLE_VALUE, FEATURE_TABLE_PROJECT, FEATURE_TABLE_TIMESTAMP,
     FEATURE_TABLE_BACKUP_PRIMARY_KEY, FEATURE_DLC_TABLE_PRIMARY_KEY)
-from wedata.feature_store.constants.engine_types import EngineTypes
+from wedata.common.constants.engine_types import EngineTypes
+from wedata.common.log import get_logger
 from wedata.feature_store.common.store_config.redis import RedisStoreConfig
-from wedata.feature_store.entities.feature_table import FeatureTable
-from wedata.feature_store.spark_client.spark_client import SparkClient
-from wedata.feature_store.utils import common_utils, env_utils
-from wedata.feature_store.feast_client.feast_client import FeastClient
-from wedata.feature_store.cloud_sdk_client.models import (
-    TaskSchedulerConfiguration, OnlineFeatureConfiguration, OfflineFeatureConfiguration,
-    CreateOnlineFeatureTableRequest, DescribeNormalSchedulerExecutorGroupsRequest, RefreshFeatureTableRequest)
-from wedata.feature_store.cloud_sdk_client.client import FeatureCloudSDK
+from wedata.common.entities.feature_table import FeatureTable
+from wedata.common.spark_client import SparkClient
+from wedata.common.utils import common_utils, env_utils
+from wedata.common.feast_client.feast_client import FeastClient
+from wedata.common.cloud_sdk_client import models
+from wedata.common.cloud_sdk_client import FeatureCloudSDK
+from wedata.common.base_table_client import AbstractBaseTableClient
 
 
-class FeatureTableClient:
+class FeatureTableClient(AbstractBaseTableClient):
     """特征表操作类"""
 
     def __init__(
@@ -44,6 +44,11 @@ class FeatureTableClient:
             self.__cloud_secret_id, self.__cloud_secret_key = env_utils.get_cloud_secret()
         self.__project = env_utils.get_project_id()
         self.__region = env_utils.get_region()
+        self.__logger = get_logger()
+        default_online_table = self._get_offline_default_database()
+        if default_online_table:
+            env_utils.set_default_database(default_online_table.DatabaseName)
+
 
     @property
     def cloud_secret_id(self) -> str:
@@ -77,51 +82,6 @@ class FeatureTableClient:
     def region(self) -> str:
         return self.__region
 
-    @staticmethod
-    def _normalize_params(
-            param: Optional[Union[str, Sequence[str]]],
-            default_type: type = list
-    ) -> list:
-        """统一处理参数标准化"""
-        if param is None:
-            return default_type()
-        return list(param) if isinstance(param, Sequence) else [param]
-
-    @staticmethod
-    def _validate_schema(df: DataFrame, schema: StructType):
-        """校验DataFrame和schema的有效性和一致性"""
-        # 检查是否同时为空
-        if df is None and schema is None:
-            raise ValueError("Either DataFrame or schema must be provided")
-
-        # 检查schema匹配
-        if df is not None and schema is not None:
-            df_schema = df.schema
-            if df_schema != schema:
-                diff_fields = set(df_schema.fieldNames()).symmetric_difference(set(schema.fieldNames()))
-                raise ValueError(
-                    f"DataFrame schema does not match. Differences: "
-                    f"{diff_fields if diff_fields else 'field type mismatch'}"
-                )
-
-    @staticmethod
-    def _validate_key_conflicts(primary_keys: List[str], timestamp_keys: str):
-        """校验主键与时间戳键是否冲突"""
-        if timestamp_keys in primary_keys:
-            raise ValueError(f"Timestamp keys conflict with primary keys: {timestamp_keys}")
-
-    @staticmethod
-    def _validate_key_exists(primary_keys: List[str], timestamp_keys: str):
-        """校验主键与时间戳键是否存在"""
-        if not primary_keys:
-            raise ValueError("Primary keys cannot be empty")
-        if not timestamp_keys:
-            raise ValueError("Timestamp keys cannot be empty")
-
-    @staticmethod
-    def _escape_sql_value(value: str) -> str:
-        """转义SQL值中的特殊字符"""
-        return value.replace("'", "''")
 
     def create_table(
             self,
@@ -165,6 +125,10 @@ class FeatureTableClient:
         primary_keys = self._normalize_params(primary_keys)
         partition_columns = self._normalize_params(partition_columns)
 
+        assert self._check_sequence_element_type(primary_keys, str), "primary_keys must be a list of strings"
+        assert self._check_sequence_element_type(partition_columns, str), "partition_columns must be a list of strings"
+        assert isinstance(timestamp_key, str), "timestamp key must be string"
+
         # 元数据校验
         self._validate_schema(df, schema)
         self._validate_key_exists(primary_keys, timestamp_key)
@@ -301,7 +265,7 @@ class FeatureTableClient:
             raise ValueError(f"Engine type {engine_type} is not supported")
 
         # 打印sql
-        print(f"create table ddl: {ddl}\n")
+        self.__logger.info(f"create table ddl: {ddl}\n")
 
         # 执行DDL
         try:
@@ -311,8 +275,6 @@ class FeatureTableClient:
         except Exception as e:
             raise ValueError(f"Failed to create table: {str(e)}") from e
 
-        print("async table info to feast")
-
         self._feast_client.create_table(
             table_name=table_name,
             primary_keys=primary_keys,
@@ -323,7 +285,7 @@ class FeatureTableClient:
             description=description
         )
 
-        print(f"create table {name} done")
+        self.__logger.info(f"Table '{name}' created successfully. Starting web synchronization.")
 
         try:
             self._sync_table_info(table_name=name, action_name="create",
@@ -331,7 +293,8 @@ class FeatureTableClient:
                                   data_source_name=data_source_name, engine_name=env_utils.get_engine_name(),
                                   is_try=False)
         except tencentcloud.common.exception.TencentCloudSDKException as e:
-            raise RuntimeError(f"Table '{name}' is can't create. {str(e)}")
+            raise RuntimeError(f"Failed to synchronize web data for table '{name}'. "
+                               f"Please manually operate on the web page. Error: {str(e)}")
 
         # 构建并返回FeatureTable对象
         return FeatureTable(
@@ -444,6 +407,10 @@ class FeatureTableClient:
         common_utils.validate_table_name(name)
         common_utils.validate_database(database_name)
 
+        if primary_keys:
+            assert self._check_sequence_element_type(primary_keys, str), "primary_keys must be a list of strings"
+        assert isinstance(timestamp_key, str), "timestamp key must be string"
+
         # 构建完整表名
         table_name = common_utils.build_full_table_name(name, database_name)
 
@@ -456,11 +423,12 @@ class FeatureTableClient:
 
             # 检查Primary Key和Timestamp Key是否为空
             if engine_type == engine_type.ICEBERG_ENGINE and props.get("format-version", "") == "2":
-                if props.get('dlc.ao.data.govern.sorted.keys', "") == "":
-                    raise ValueError(
-                        "table dlc.ao.data.govern.sorted.keys is empty. you must set dlc.ao.data.govern.sorted.keys")
-                else:
-                    primary_keys = props.get('dlc.ao.data.govern.sorted.keys').split(",")
+                if not primary_keys:
+                    if props.get('dlc.ao.data.govern.sorted.keys', "") == "":
+                        raise ValueError(
+                            "table dlc.ao.data.govern.sorted.keys is empty. you must set dlc.ao.data.govern.sorted.keys")
+                    else:
+                        primary_keys = props.get('dlc.ao.data.govern.sorted.keys').split(",")
             elif engine_type == engine_type.HIVE_ENGINE:
                 if not primary_keys:
                     raise ValueError("primary_keys cannot be None for HIVE_ENGINE")
@@ -513,27 +481,28 @@ class FeatureTableClient:
 
             try:
                 self._sync_table_info(table_name=name, action_name="create",
-                                  database_name=env_utils.get_database_name(database_name),
-                                  data_source_name=data_source_name, engine_name=env_utils.get_engine_name(), is_try=True)
+                                      database_name=env_utils.get_database_name(database_name),
+                                      data_source_name=data_source_name, engine_name=env_utils.get_engine_name(), is_try=True)
             except tencentcloud.common.exception.TencentCloudSDKException as e:
                 raise RuntimeError(f"Table '{name}' is can't create. {str(e)}")
 
             # 执行修改
-            print("alter table sql", alter_sql)
+            self.__logger.info(f"alter table sql: \n {alter_sql}")
             self._spark.sql(alter_sql)
-            print("Execute sql done, start sync table info to feast")
+            self.__logger.debug("Execute sql done, start sync table info to feast")
             self._feast_client.alter_table(full_table_name=table_name, primary_keys=primary_keys,
                                            timestamp_key=timestamp_key)
-            print(f"Successfully register table '{table_name}'")
+            self.__logger.info(f"Successfully register table '{table_name}'. Starting web synchronization.")
 
             try:
                 self._sync_table_info(table_name=name, action_name="create",
-                                  database_name=env_utils.get_database_name(database_name),
-                                  data_source_name=data_source_name, engine_name=env_utils.get_engine_name(), is_try=False)
+                                      database_name=env_utils.get_database_name(database_name),
+                                      data_source_name=data_source_name, engine_name=env_utils.get_engine_name(), is_try=False)
             except tencentcloud.common.exception.TencentCloudSDKException as e:
-                raise RuntimeError(f"sync table info failed. you need to sync table info manually. {str(e)}")
-        except ValueError as e:
-            raise  # 直接抛出已知的ValueError
+                raise RuntimeError(f"Failed to synchronize web data for table '{name}'. "
+                                   f"Please manually operate on the web page. Error: {str(e)}")
+        except (ValueError, RuntimeError):
+            raise
         except Exception as e:
             raise RuntimeError(f"Failed to modify properties for table '{table_name}': {str(e)}") from e
 
@@ -610,36 +579,34 @@ class FeatureTableClient:
         try:
             # 检查表是否存在
             if not self._check_table_exists(table_name):
-                print(f"Table '{name}' does not exist")
+                self.__logger.error(f"Table '{name}' does not exist")
                 return
 
-            # 检查
-            df = self._spark.table(tableName=table_name)
-
             try:
                 feature_view = self._feast_client.get_feature_view(table_name)
             except Exception as e:
-                print(f"Table '{name}' is not a feature table, skip delete. {str(e)}")
+                pass
+                # self.__logger.warning(f"Table '{name}' is not a feature table, skip delete. {str(e)}")
             else:
                 if feature_view.online:
                     raise ValueError(f"Table '{name}' has a online table, please call drop_online_table first")
             try:
                 self._sync_table_info(table_name=name, action_name="delete",
-                                  database_name=env_utils.get_database_name(database_name),
-                                  data_source_name="", engine_name=env_utils.get_engine_name(), is_try=True)
+                                      database_name=env_utils.get_database_name(database_name),
+                                      data_source_name="", engine_name=env_utils.get_engine_name(), is_try=True)
             except tencentcloud.common.exception.TencentCloudSDKException as e:
                 raise RuntimeError(f"Table '{name}' is can't delete. {str(e)}")
 
             # 执行删除
             self._spark.sql(f"DROP TABLE {table_name}")
-            print(f"Table '{name}' dropped")
+            self.__logger.info(f"Table '{name}' dropped")
             try:
                 self._feast_client.remove_offline_table(table_name=table_name)
             except Exception as e:
                 raise
                 # raise ValueError(f"Failed to delete table '{name}' in feast: {str(e)}")
             else:
-                print(f"Table '{name}' removed from feast")
+                self.__logger.info(f"Table '{name}' removed from feast")
 
             try:
                 self._sync_table_info(table_name=name, action_name="delete",
@@ -695,7 +662,7 @@ class FeatureTableClient:
         schema_name_list = [field.name for field in tmp_schema_list]
         schema = StructType(tmp_schema_list)
         for field in schema:
-            print(f"{field.name} => {field.dataType}")
+            self.__logger.debug(f"translate {field.name} to feast Type: {field.dataType}")
 
         feast_client = FeastClient(offline_store=self._spark, online_store_config=online_config)
         # 构建离线表的entity的数据过滤
@@ -710,7 +677,7 @@ class FeatureTableClient:
                     full_table_name=full_table_name,
                     columns_name=columns_name_list,
                     entity_rows=[result_row.asDict()])
-                print("=====>read online dataframe:\n", online_view[schema_name_list])
+                self.__logger.debug(f"=====>read online dataframe:\n{online_view[schema_name_list]}")
                 return self._spark.createDataFrame(online_view[schema_name_list], schema=schema, verifySchema=False)
             else:
                 return self._spark.createDataFrame([])
@@ -719,7 +686,7 @@ class FeatureTableClient:
                 full_table_name=full_table_name,
                 columns_name=columns_name_list,
                 entity_rows=entity_row)
-            print("=====>read online dataframe:\n", online_view[schema_name_list])
+            self.__logger.debug(f"=====>read online dataframe:\n{online_view[schema_name_list]}")
             return self._spark.createDataFrame(online_view[schema_name_list], schema=schema, verifySchema=False)
 
     def get_table(
@@ -808,7 +775,9 @@ class FeatureTableClient:
 
             # 执行修改
             self._spark.sql(alter_sql)
-            self._feast_client.modify_tags(table_name=table_name, tags=properties)
+            tbl_pro = self._spark.sql(f"SHOW TBLPROPERTIES {table_name}")
+            props = {row['key']: row['value'] for row in tbl_pro.collect()}
+            self._feast_client.modify_tags(table_name=table_name, tags=props)
             print(f"Successfully updated properties for table '{name}': {list(properties.keys())}")
 
         except ValueError as e:
@@ -816,9 +785,9 @@ class FeatureTableClient:
         except Exception as e:
             raise RuntimeError(f"Failed to modify properties for table '{name}': {str(e)}") from e
 
-    def publish_table(self, table_name: str, data_source_name: str, cloud_secret_id: str, cloud_secret_key: str,
+    def publish_table(self, table_name: str, data_source_name: str,
                       database_name: Optional[str] = None,
-                      is_cycle: bool = False, cycle_obj: TaskSchedulerConfiguration = None,
+                      is_cycle: bool = False, cycle_obj: models.TaskSchedulerConfiguration = None,
                       is_use_default_online: bool = True, online_config: RedisStoreConfig = None):
         """
         将离线特征表发布为在线特征表
@@ -841,46 +810,43 @@ class FeatureTableClient:
         # 检查是否已经发布,查看Redis中是否有值
         try:
         # 获取离线表的列名
-            online_data = self._read_online_table(
-                table_name=table_name,
-                database_name=database_name,
-                online_config=online_config)
+            online_data = self._feast_client.get_feature_view(full_table_name)
         except Exception as e:
             print(f"Failed to get online table view for table '{full_table_name}': {str(e)}")
         else:
-            if online_data:
+            if online_data.online:
                 raise ValueError(f"Table '{full_table_name}' has already been published")
 
         # 配置周期性参数
         if is_cycle:
-            if not isinstance(cycle_obj, TaskSchedulerConfiguration):
+            if not isinstance(cycle_obj, models.TaskSchedulerConfiguration):
                 raise ValueError("cycle_obj must be a TaskSchedulerConfiguration object when is_cycle is True")
 
             cycle_obj.CycleType = "CRONTAB_CYCLE"
         else:
-            if isinstance(cycle_obj, TaskSchedulerConfiguration):
+            if isinstance(cycle_obj, models.TaskSchedulerConfiguration):
                 cycle_obj.CycleType = "ONEOFF_CYCLE"
             else:
-                cycle_obj = TaskSchedulerConfiguration()
+                cycle_obj = models.TaskSchedulerConfiguration()
                 cycle_obj.CycleType = "ONEOFF_CYCLE"
                 # 设置默认当前时间延后1分钟
                 cycle_obj.CrontabExpression = (datetime.datetime.now() + datetime.timedelta(minutes=3)).strftime(
                     "%M %H %d %m %w ? %y")
 
         if is_use_default_online:
-            online_feature_config = OnlineFeatureConfiguration()
+            online_feature_config = models.OnlineFeatureConfiguration()
             online_feature_config.UserDefault = True
         else:
             if not isinstance(online_config, RedisStoreConfig):
                 raise ValueError("online_config must be a RedisStoreConfig object when is_use_default_online is False")
 
-            online_feature_config = OnlineFeatureConfiguration()
+            online_feature_config = models.OnlineFeatureConfiguration()
             online_feature_config.UserDefault = False
             online_feature_config.Host = online_config.host
             online_feature_config.Port = online_config.port
             online_feature_config.DB = online_config.db
 
-        offline_feature_config = OfflineFeatureConfiguration()
+        offline_feature_config = models.OfflineFeatureConfiguration()
         offline_feature_config.DatabaseName = env_utils.get_database_name(database_name)
         offline_feature_config.TableName = table_name
 
@@ -891,7 +857,7 @@ class FeatureTableClient:
         offline_feature_config.DatasourceType = env_utils.get_engine_type()
         offline_feature_config.EngineName = env_utils.get_engine_name()
 
-        api_requests = CreateOnlineFeatureTableRequest()
+        api_requests = models.CreateOnlineFeatureTableRequest()
         api_requests.OfflineFeatureConfiguration = offline_feature_config
         api_requests.OnlineFeatureConfiguration = online_feature_config
         api_requests.TaskSchedulerConfiguration = cycle_obj
@@ -899,11 +865,11 @@ class FeatureTableClient:
         region = env_utils.get_region()
         if not os.environ.get("RESOURCE_GROUP_ID", ""):
             res_group_item = _get_default_resource_group(
-                api_requests.ProjectId, cloud_secret_id, cloud_secret_key, region)
+                api_requests.ProjectId, self.__cloud_secret_id, self.__cloud_secret_key, region)
             api_requests.ResourceGroupId = res_group_item.ExecutorGroupId
         else:
             api_requests.ResourceGroupId = os.environ.get("RESOURCE_GROUP_ID")
-        client = FeatureCloudSDK(secret_id=cloud_secret_id, secret_key=cloud_secret_key, region=region)
+        client = FeatureCloudSDK(secret_id=self.__cloud_secret_id, secret_key=self.__cloud_secret_key, region=region)
         resp = client.CreateOnlineFeatureTable(api_requests)
         if cycle_obj.CycleType == "ONEOFF_CYCLE":
             print(f"publish online task create success. it will be execute after 3 min. {resp.Data.OnlineTableId} {resp.Data.OfflineTableId} ")
@@ -914,7 +880,18 @@ class FeatureTableClient:
         # 构建完整表名
         full_table_name = common_utils.build_full_table_name(table_name, database_name)
         feast_client = FeastClient(self._spark, online_config)
+        try:
+            self._sync_table_info(table_name=table_name, database_name=database_name, action_name="delete_online",
+                                  data_source_name="", engine_name=env_utils.get_engine_name(), is_try=True)
+        except Exception as e:
+            raise RuntimeError(f"drop online table failed. table_name: {full_table_name}. {str(e)}")
+
         feast_client.remove_online_table(full_table_name)
+        try:
+            self._sync_table_info(table_name=table_name, database_name=database_name, action_name="delete_online",
+                                  data_source_name="", engine_name=env_utils.get_engine_name(), is_try=False)
+        except Exception as e:
+            raise RuntimeError(f"drop online table failed. table_name: {full_table_name}. {str(e)}")
         print(f"drop online table success. table_name: {full_table_name}")
 
     def _get_table_primary_keys_and_timestamp_key(self, full_table_name: str) -> 'str, str':
@@ -933,10 +910,23 @@ class FeatureTableClient:
     def _check_table_exists(self, full_table_name: str) -> bool:
         return common_utils.check_spark_table_exists(self._spark, full_table_name)
 
+    def _get_offline_default_database(self) -> Optional[models.FeatureStoreDatabase]:
+        client = FeatureCloudSDK(secret_id=self.__cloud_secret_id, secret_key=self.__cloud_secret_key,
+                                 region=self.__region)
+        req = models.DescribeFeatureStoreDatabasesRequest()
+        req.ProjectId = self.__project
+        rsp = client.DescribeFeatureStoreDatabases(req)
+        if len(rsp.Data) == 0:
+            return None
+        for item in rsp.Data:
+            if item.OnlineMode == 0 and item.IsDefault == 1:
+                return item
+        return None
+
 
 def _get_default_resource_group(project_id: str, secret_id: str, secret_key: str, region: str):
     client = FeatureCloudSDK(secret_id=secret_id, secret_key=secret_key, region=region)
-    request = DescribeNormalSchedulerExecutorGroupsRequest()
+    request = models.DescribeNormalSchedulerExecutorGroupsRequest()
     request.ProjectId = project_id
     resp = client.DescribeNormalSchedulerExecutorGroups(request)
     # 默认取第一个健康可用的资源组进行执行
@@ -950,7 +940,7 @@ def _refresh_table(project_id: str, secret_id: str, secret_key: str, region: str
                    action: str, database_name: str, data_source_name: str, data_source_type: str,
                    engine_name: str, is_try: bool):
     client = FeatureCloudSDK(secret_id=secret_id, secret_key=secret_key, region=region)
-    request = RefreshFeatureTableRequest()
+    request = models.RefreshFeatureTableRequest()
     request.ProjectId = project_id
     request.TableName = table_name
     request.DatabaseName = database_name

wedata/feature_store/training_set_client/training_set_client.py

@@ -1,7 +1,7 @@
 import logging
 import os
 from types import ModuleType
-from typing import Any, List, Optional, Set, Union, Dict
+from typing import Any, List, Optional, Union, Dict
 
 import mlflow
 from mlflow.models import Model
@@ -9,18 +9,17 @@ from mlflow.utils.file_utils import TempDir, read_yaml
 from pyspark.sql import DataFrame
 from pyspark.sql.functions import struct
 
-from wedata.feature_store.constants import constants
-from wedata.feature_store.entities.feature_function import FeatureFunction
-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.entities.training_set import TrainingSet
+from wedata.common.constants import constants
+from wedata.common.entities.feature_function import FeatureFunction
+from wedata.common.entities.feature_lookup import FeatureLookup
+from wedata.common.entities.feature_spec import FeatureSpec
+from wedata.common.entities.training_set import TrainingSet
 from wedata.feature_store.mlflow_model import _FeatureStoreModelWrapper
-from wedata.feature_store.spark_client.spark_client import SparkClient
-from wedata.feature_store.utils import validation_utils
-from wedata.feature_store.entities.feature_table import FeatureTable
+from wedata.common.spark_client import SparkClient
+from wedata.common.utils import validation_utils, common_utils, training_set_utils
+from wedata.common.entities.feature_table import FeatureTable
 
-from wedata.feature_store.constants.constants import (
+from wedata.common.constants.constants import (
     _NO_RESULT_TYPE_PASSED,
     _USE_SPARK_NATIVE_JOIN,
     MODEL_DATA_PATH_ROOT,
@@ -28,8 +27,8 @@ from wedata.feature_store.constants.constants import (
     _PREBUILT_ENV_URI
 )
 
-from wedata.feature_store.utils import common_utils, training_set_utils, uc_utils
-from wedata.feature_store.utils.signature_utils import get_mlflow_signature_from_feature_spec, \
+from wedata.common.utils import uc_utils
+from wedata.common.utils.signature_utils import get_mlflow_signature_from_feature_spec, \
     drop_signature_inputs_and_invalid_params
 
 _logger = logging.getLogger(__name__)
@@ -360,6 +359,7 @@ 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
@@ -388,16 +388,13 @@ class TrainingSetClient:
             "The provided DataFrame for scoring must have unique column names. Found duplicates {}.",
         )
         artifact_path = os.path.join("artifacts", MODEL_DATA_PATH_ROOT)
-        # print(f"artifact_path: {artifact_path}")
         with (TempDir() as tmp_location):
             local_path = (
                 local_uri
                 if local_uri
                 else common_utils.download_model_artifacts(model_uri, tmp_location.path())
             )
-            # print(f"wedata local_path:{local_path}")
             model_data_path = os.path.join(local_path, artifact_path)
-            # print(f"artifact_path: {artifact_path}")
 
         # Augment local workspace metastore tables from 2L to 3L,
             # this will prevent us from erroneously reading data from other catalogs
@@ -425,6 +422,7 @@ class TrainingSetClient:
         feature_input_keys = []
         for fci in feature_spec.feature_column_infos:
             feature_input_keys.extend([k for k in fci.lookup_key])
+
         on_demand_input_names = uc_utils.get_unique_list_order(
             [
                 input_name
@@ -436,7 +434,6 @@ class TrainingSetClient:
         source_data_names = [
             sdci.name for sdci in feature_spec.source_data_column_infos
         ]
-        # print(f"wedata source_data_names:{source_data_names}")
 
         feature_output_names = [
             fci.output_name for fci in feature_spec.feature_column_infos

wedata/tempo/interpol.py

@@ -23,7 +23,7 @@ class Interpolation:
         """
         Validate if the fill provided is within the allowed list of values.
 
-        :param fill: Fill type e.g. "zero", "null", "bfill", "ffill", "linear"
+        :param method: Fill type e.g. "zero", "null", "bfill", "ffill", "linear"
         """
         if method not in method_options:
             raise ValueError(
@@ -43,8 +43,8 @@ class Interpolation:
 
         :param df: DataFrame to be validated
         :param partition_cols: Partition columns to be validated
-        :param target_col: Target column to be validated
         :param ts_col: Timestamp column to be validated
+        :param ts_col_dtype: Timestamp column type
         """
 
         if partition_cols is not None:

tencent_wedata_feature_engineering_dev-0.1.42.dist-info/RECORD

@@ -1,64 +0,0 @@
-wedata/__init__.py,sha256=GYxqkkgH0oH4QtNiOCZHuGkc0sSH1LgEqmhSX6sB4So,200
-wedata/feature_store/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/client.py,sha256=rXQfSC14vvxPed9P0PoboDTwhD47aPwmGndY825Sl6k,19484
-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=NtzV0EmLTzMLYqWhnUyOx3bmxoIIgxw8REid-Gy96Pc,4234
-wedata/feature_store/cloud_sdk_client/models.py,sha256=7_QUq0kZcrcclRMsIYFoqBrlzVwaHoVY-yU5SHIrJWM,19789
-wedata/feature_store/cloud_sdk_client/utils.py,sha256=6ESwVhlrftnp0h9ojTzbB-m-0hktLI1PLcyk6zpNgrs,857
-wedata/feature_store/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-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=d4xnvPZeVKMFi8cYp6Ya9GdoUl9NQzyH4hIaXOgTWd4,1959
-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=TT1ESVYbP9kT5LyfYEYfnsM2mvOiJBug3527Y73lg3o,20694
-wedata/feature_store/feature_table_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/feature_table_client/feature_table_client.py,sha256=wLawB-97ZJ4og5Y8f0VfRYsuygXY6DzMeorTTzdA9mM,41176
-wedata/feature_store/spark_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/spark_client/spark_client.py,sha256=ACWaRaDChqr2qAM8st6e0BP-LSEBSIj2xZAElX2nxHE,11799
-wedata/feature_store/training_set_client/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wedata/feature_store/training_set_client/training_set_client.py,sha256=teaWM-xDgp2TwnadovUm0i4A26roTozgRefIZaHORko,23376
-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=ffDhQVW96vZxWurzOhYfZQk_dQ1LHC-y8tl4PQlp9Tg,2570
-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-0.1.42.dist-info/METADATA,sha256=92FGxlFyakPGdx3bwUjkpmImzCl5eB_KxiYMU2yqc_8,582
-tencent_wedata_feature_engineering_dev-0.1.42.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-tencent_wedata_feature_engineering_dev-0.1.42.dist-info/top_level.txt,sha256=Xa0v1rh__RvfVTVDirW5r5UBKg7ZO_iuTeXfp8MNo2A,7
-tencent_wedata_feature_engineering_dev-0.1.42.dist-info/RECORD,,