datahub_binary 1.4.8__cp312-cp312-win_amd64.whl → 1.4.10__cp312-cp312-win_amd64.whl

datahub/__init__.pyi

@@ -0,0 +1,16 @@
+from .setting import *
+import datahub.protos as protos
+import datahub.utils.logger as logger
+import datahub.utils.sftp as sftp
+from .datahub import BarDataMatrix as BarDataMatrix, CronTask as CronTask, DataHub as DataHub
+from datahub.ats import client_sdk as ats_client
+
+__all__ = ['DataHub', 'Setting', 'StarRocksSetting', 'RedisSetting', 'PostgresSetting', 'BarDataMatrix', 'protos', 'sftp', 'logger', 'SftpSetting', 'CronServerSetting', 'CronTask', 'ats_client']
+
+# Names in __all__ with no definition:
+#   CronServerSetting
+#   PostgresSetting
+#   RedisSetting
+#   Setting
+#   SftpSetting
+#   StarRocksSetting

datahub/ats/client_sdk.pyi

@@ -0,0 +1,73 @@
+import datetime
+from _typeshed import Incomplete
+from dataclasses import dataclass
+from datahub.protos import client_msg as client_msg
+from enum import Enum
+
+QuoteType: Incomplete
+SubscribeType: Incomplete
+
+class ChannelType(Enum):
+    Subscribe = 1
+    Quote = 3
+    Query = 4
+    Reply = 5
+    Event = 6
+
+class StrategyError(Exception): ...
+
+@dataclass
+class Setting:
+    user_id: str
+    password: str
+    strategy_id: int
+    interval: int
+    quote_sub_url: str
+    event_sub_url: str
+    client_dealer_url: str
+
+class BaseStrategy:
+    setting: Incomplete
+    def __init__(self, setting: Setting) -> None: ...
+    @property
+    def strategy_id(self): ...
+    @property
+    def subscribed_topic(self): ...
+    def subscribe(self, instrument_id: str, quote_type: QuoteType): ...
+    def unsubscribe(self, instrument_id: str, quote_type: QuoteType): ...
+    def on_init(self) -> None: ...
+    def on_start(self) -> None: ...
+    def on_stop(self) -> None: ...
+    def on_order(self, event: client_msg.OrderEvent): ...
+    def qry_instrument_req(self, instrument_id: str = None, basket_instrument_id: str = None, market_list: list[str] = ()) -> str: ...
+    def on_qry_instrument_rsp(self, rsp: client_msg.QryInstrumentRsp): ...
+    def qry_strategy_info_req(self, strategy_id: int) -> str: ...
+    def on_qry_strategy_info_rsp(self, rsp: client_msg.QryStrategyInfoRsp): ...
+    def qry_trade_req(self) -> str: ...
+    def on_qry_trade_rsp(self, rsp: client_msg.QryTradesRsp): ...
+    def qry_order_req(self, cl_order_id: str = None, order_id: str = None, is_active: int = 0) -> str: ...
+    def on_qry_order_rsp(self, rsp: client_msg.QryOrdersRsp): ...
+    def qry_strategy_posi_req(self) -> str: ...
+    def on_qry_strategy_posi_rsp(self, rsp: client_msg.QryStrategyPositionRsp): ...
+    def qry_book_stat_req(self, book_id: str = None) -> str: ...
+    def on_qry_book_stat_rsp(self, rsp: client_msg.QryBookStatRsp): ...
+    def qry_signal_kline_req(self, signal_id: int, start_date: datetime.date = None) -> str: ...
+    def on_qry_signal_kline_rsp(self, rsp: client_msg.QrySignalKlineRsp): ...
+    def qry_quote_req(self, instrument_id: str | None = None) -> str: ...
+    def on_qry_quote_rsp(self, qry_quote_rsp: client_msg.QryQuoteRsp): ...
+    def on_snapshot(self, snapshot: client_msg.MDSnapshot): ...
+    def place_order(self, order: client_msg.PlaceOrder): ...
+    def book_trade_req(self, trade: client_msg.BookTradeReq): ...
+    def on_book_trade_rsp(self, rsp: client_msg.BookTradeRsp): ...
+    def on_trade_confirm(self, trade: client_msg.TradeConfirm): ...
+    def on_order_reject(self, order: client_msg.OrderReject): ...
+    def cancel_order(self, order: client_msg.CancelOrder): ...
+    def cancel_all_order(self) -> None: ...
+    def on_cancel_confirm(self, order: client_msg.CancelConfirm): ...
+    def on_cancel_pending_confirm(self, order: client_msg.CancelPendingConfirm): ...
+    def on_cancel_reject(self, order: client_msg.CancelReject): ...
+    def on_qry_lock_record_rsp(self, rsp: client_msg.QryLockRecordRsp): ...
+    def calc(self) -> None: ...
+    def qry_lock_record_req(self) -> None: ...
+    def proxy(self) -> None: ...
+    def run(self) -> None: ...

datahub/datacache.pyi

@@ -0,0 +1,68 @@
+import polars as pl
+from _typeshed import Incomplete
+from datahub import PostgresSetting as PostgresSetting, Setting as Setting, StarRocksSetting as StarRocksSetting
+from datahub.datahub import DataHub as DataHub
+from datahub.utils.logger import logger as logger
+from datetime import datetime, time
+from enum import Enum
+from typing import Any, Literal, Sequence
+
+class UpdateLevel(Enum):
+    META = 'meta'
+    DF = 'df'
+
+class KVJsonDB:
+    db_path: Incomplete
+    def __init__(self, db_path: str) -> None: ...
+    def set(self, key: str, value: Any): ...
+    def get(self, key: str, default: Any | None = None) -> Any | None: ...
+    def delete(self, key: str) -> bool: ...
+    def all(self) -> dict[str, Any]: ...
+    def all_keys(self) -> list[str]: ...
+    def clear(self) -> None: ...
+    def close(self) -> None: ...
+
+class DataCache:
+    prefix: Incomplete
+    data_path: Incomplete
+    update_cache: Incomplete
+    cache_only: Incomplete
+    datahub: Incomplete
+    meta_db: Incomplete
+    data_files: Incomplete
+    def __init__(self, datahub: DataHub, data_path: str, prefix: str, update_cache: bool = False, cache_only: bool = False) -> None: ...
+    def get_data_matrix(self, trade_time: datetime, factors: list[str], instrument_ids: list[str], **kwargs) -> pl.DataFrame: ...
+    def get_cache_filepath(self, trade_time: datetime) -> str: ...
+    def update_datacache(self, filepath: str, df: pl.DataFrame, update_level: Sequence[UpdateLevel] = ()): ...
+    def read_from_cache(self, trade_time: datetime, factors: list[str], instrument_ids: list[str], **kwargs) -> pl.DataFrame: ...
+    def sync_all_meta_info(self) -> None: ...
+    @staticmethod
+    def f64_to_f32(df: pl.DataFrame) -> pl.DataFrame: ...
+    @staticmethod
+    def get_missing_times(df: pl.DataFrame, intra_time_list: list[time]) -> list[time]: ...
+    @staticmethod
+    def get_missing_instruments(df: pl.DataFrame, instruments: list[str]) -> list[str]: ...
+    @staticmethod
+    def get_missing_factors(df: pl.DataFrame, factors: list[str]) -> list[str]: ...
+
+class FactorDataCache(DataCache):
+    def get_data_matrix(self, trade_time: datetime, factors: list[str], instrument_ids: list[str], **kwargs) -> pl.DataFrame: ...
+    def read_factor_from_cache(self, trade_time: datetime, factors: list[str], instrument_ids: list[str]) -> pl.DataFrame: ...
+
+class RiskFactorDataCache(DataCache):
+    version: Incomplete
+    def __init__(self, datahub: DataHub, version: str, data_path: str, prefix: str, update_cache: bool = False) -> None: ...
+    def get_data_matrix(self, trade_time: datetime, factors: list[str], instrument_ids: list[str], **kwargs) -> pl.DataFrame: ...
+    def read_risk_factors_from_cache(self, trade_time: datetime, factors: list[str], instrument_ids: list[str]) -> pl.DataFrame: ...
+
+class ReturnDataCache(DataCache):
+    def get_data_matrix(self, trade_time: datetime, factors: list[str], instrument_ids: list[str], **kwargs) -> pl.DataFrame: ...
+    def read_return_from_cache(self, trade_time: datetime, factors: list[str], instrument_ids: list[str], adj_method: Literal['forward'] = 'forward') -> pl.DataFrame: ...
+
+class HFTFactorDataCache(DataCache):
+    def read_factor_from_cache(self, trade_time: datetime, factors: list[str], instrument_ids: list[str]) -> pl.DataFrame: ...
+
+class HFTReturnDataCache(DataCache):
+    def read_return_from_cache(self, trade_time: datetime, factors: list[str], instrument_ids: list[str], adj_method: Literal['forward'] = 'forward') -> pl.DataFrame: ...
+
+def main() -> None: ...

datahub/datahub.pyi

@@ -0,0 +1,121 @@
+import numpy.typing as npt
+import polars as pl
+from .dbo.pg import Postgres as Postgres
+from .dbo.redis_stream import RedisStream as RedisStream
+from .dbo.sr import StarRocks as StarRocks
+from .protos.client_msg import BarMatrix as BarMatrix, MsgType as MsgType
+from .setting import Setting as Setting
+from .utils.logger import logger as logger
+from _typeshed import Incomplete
+from dataclasses import dataclass
+from datetime import date, datetime, time
+from pydantic import BaseModel
+from typing import Any, Iterator, Literal, Sequence
+
+class DataHubError(Exception): ...
+
+class CronTask(BaseModel):
+    task_id: str
+    task_type: str
+    task_name: str
+    task_status: str
+    task_params: dict[str, Any]
+    result: str | None
+    create_time: str | None
+    end_time: str | None
+
+@dataclass
+class BarDataMatrix:
+    msg_sequence: int
+    trade_time: datetime
+    last_timestamp: datetime
+    instrument_ids: Sequence[str]
+    cols: Sequence[str]
+    data_matrix: npt.NDArray[Any]
+    def to_df(self) -> pl.DataFrame: ...
+    @staticmethod
+    def get_empty_matrix(instrument_ids: Sequence[str], cols: Sequence[str], trade_time: datetime) -> BarDataMatrix: ...
+    @staticmethod
+    def from_df(instrument_ids: Sequence[str], cols: Sequence[str], trade_time: datetime, df: pl.DataFrame) -> BarDataMatrix: ...
+    @staticmethod
+    def from_proto(proto_msg: BarMatrix) -> BarDataMatrix: ...
+    def to_proto(self) -> BarMatrix: ...
+
+class RsTopic:
+    indicator_5min: str
+    factor_5min: str
+    predictor: str
+
+class DataHub:
+    setting: Incomplete
+    def __init__(self, setting: Setting) -> None: ...
+    @property
+    def calendar(self): ...
+    @property
+    def starrocks(self): ...
+    @property
+    def postgres(self): ...
+    @property
+    def redis(self): ...
+    def post_task(self, task: CronTask) -> dict[str, Any]: ...
+    def get_kline(self, freq: str, instruments: Sequence[str] = (), start_time: datetime | None = None, end_time: datetime | None = None, adj_method: str | None = None) -> pl.DataFrame: ...
+    def get_indicator_type(self): ...
+    def get_factor_type(self) -> pl.DataFrame: ...
+    def get_indicator_info(self, indicators: Sequence[str] = (), types: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_factor_info(self, factors: Sequence[str] = (), types: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_seq_factor_info(self, resample_type: str, factors: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_seq_y_info(self, resample_type: str, factors: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_seq_factor_stat(self, start_time: datetime, end_time: datetime, stat_type: str, factors: Sequence[str] = (), instruments: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_seq_y_stat(self, start_time: datetime, end_time: datetime, stat_type: str, factors: Sequence[str] = (), instruments: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_indicator_data(self, start_time: datetime, end_time: datetime | None = None, indicators: Sequence[str] = (), instruments: Sequence[str] = (), types: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_instrument_list(self, trade_date: date, indicators: Sequence[str] = ()) -> Sequence[str]: ...
+    def get_instrument_info(self, trade_date: date, fields: Sequence[str] | None = None, market: str | None = None, instrument_type: Literal['option', 'spot', 'future', 'etf'] | None = None) -> pl.DataFrame: ...
+    def get_future_domain_info(self, instrument_sub_type: str | None = None, start_date: date | None = None, end_date: date | None = None, market: str = 'CCFX', rank_id: int = 1, domain_factor: str = 'volume') -> pl.DataFrame: ...
+    def get_future_snapshot(self, instrument_sub_type: str, start_date: date, end_date: date, market: str = 'CCFX', rank_id: int = 1, domain_factor: str = 'volume') -> pl.DataFrame: ...
+    def get_universe(self, trade_date: date, universe: str | None = None) -> pl.DataFrame: ...
+    def get_indicator_matrix(self, trade_time: datetime, indicators: Sequence[str], instrument_ids: Sequence[str], expire_days: int = 1) -> BarDataMatrix: ...
+    def get_seq_factor_data(self, start_time: datetime, end_time: datetime, factors: Sequence[str] = (), instruments: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_indicator_matrix_list(self, start_date: date, end_date: date, indicators: Sequence[str], instrument_ids: Sequence[str], expire_days: int = 1) -> list[BarDataMatrix]: ...
+    def get_risk_factor_matrix(self, version: str, trade_time: datetime, factors: Sequence[str], instrument_ids: Sequence[str]) -> BarDataMatrix: ...
+    def read_indicator_matrix(self, start_time: datetime | None = None, topic: str = ..., block: int = 0) -> Iterator[BarDataMatrix]: ...
+    def write_indicator_matrix(self, matrix: BarDataMatrix, topic: str = ...): ...
+    def delete_indicator_matrix(self, topic: str = ...): ...
+    def read_factor_matrix(self, start_time: datetime | None = None, topic: str = ..., block: int = 0) -> Iterator[BarDataMatrix]: ...
+    def write_factor_matrix(self, matrix: BarDataMatrix, topic: str = ...): ...
+    def delete_factor_matrix(self, topic: str = ...): ...
+    def read_predictor_matrix(self, start_time: datetime | None = None, topic: str = ..., block: int = 0) -> Iterator[BarDataMatrix]: ...
+    def write_predictor_matrix(self, matrix: BarDataMatrix, topic: str = ...): ...
+    def delete_predictor_matrix(self, topic: str = ...): ...
+    def get_factor_data(self, start_time: datetime, end_time: datetime | None = None, factors: Sequence[str] = (), instruments: Sequence[str] = (), types: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_factor_matrix(self, trade_time: datetime, factors: Sequence[str], instrument_ids: Sequence[str]) -> BarDataMatrix: ...
+    def get_return_data(self, start_time: datetime, end_time: datetime | None = None, factors: Sequence[str] = (), instruments: Sequence[str] = (), adj_method: Literal['forward'] = 'forward') -> pl.DataFrame: ...
+    def get_seq_y_data(self, start_time: datetime, end_time: datetime | None = None, factors: Sequence[str] = (), instruments: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_return_matrix(self, trade_time: datetime, factors: Sequence[str], instrument_ids: Sequence[str], adj_method: Literal['forward'] = 'forward') -> BarDataMatrix: ...
+    def get_ex_factor_info(self, instruments: Sequence[str] = (), trade_date: date | None = None) -> pl.DataFrame: ...
+    def get_instrument_industry(self, trade_date: date, industry_source: str = 'sws', industry_level: Literal[1, 2, 3] = 1, use_last: bool = False) -> pl.DataFrame: ...
+    def get_md_transaction(self, start_date: date, end_date: date | None = None, instruments: Sequence[str] = (), markets: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_md_snapshot(self, start_date: date, end_date: date | None = None, instruments: Sequence[str] = (), markets: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_seq_snapshot(self, start_date: date, end_date: date | None = None, instruments: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_resample_lob(self, resample_type: str, start_date: date, end_date: date | None = None, instruments: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_last_seq_snapshot(self, end_time: datetime, instruments: Sequence[str] = (), is_filter_limit: bool = False) -> pl.DataFrame: ...
+    def get_trading_days(self, start_date: date, end_date: date, market: str = 'XSHG') -> list[date]: ...
+    def upsert_from_file(self, database: str, table: str, file_path: str): ...
+    def get_blacklist(self, blacklist_ids: Sequence[str], end_date: date = None) -> pl.DataFrame: ...
+    def get_sbl_list(self, brokers: Sequence[str] = (), sbl_ids: Sequence[str] = (), start_date: date | None = None, end_date: date | None = None) -> pl.DataFrame: ...
+
+class Calendar:
+    def __init__(self, datahub: DataHub) -> None: ...
+    def after(self, trade_date: date, n: int): ...
+    def before(self, trade_date: date, n: int): ...
+    def between(self, start_date: date, end_date: date): ...
+    @staticmethod
+    def str2date(dt: str, fmt: str = '%Y-%m-%d') -> date: ...
+    @staticmethod
+    def str2datetime(dt: str, fmt: str = '%Y-%m-%d') -> datetime: ...
+    @staticmethod
+    def date2datetime(dt: date, hour: int = 0, minute: int = 0, second: int = 0) -> datetime: ...
+    @staticmethod
+    def datetime2date(dt: datetime) -> date: ...
+    def get_latest_trade_date(self, dt: date | None = None) -> date: ...
+    @staticmethod
+    def get_trading_hours(trade_date: date, freq: str, morning_time_range: tuple[time, time] = ..., afternoon_time_range: tuple[time, time] = ...) -> list[datetime]: ...

datahub/dbo/database.pyi

@@ -0,0 +1,19 @@
+import polars as pl
+from _typeshed import Incomplete
+from contextlib import contextmanager
+from datahub.utils.logger import logger as logger
+from sqlalchemy.engine import Connection as Connection, Engine as Engine
+from sqlalchemy.orm import Session as Session
+from typing import Any, Generator, Literal
+
+class Database:
+    engine: Incomplete
+    metadata: Incomplete
+    schema: Incomplete
+    session_factory: Incomplete
+    def __init__(self, connection_string: str, pool_size: int = 3, max_overflow: int = 10, pool_timeout: int = 30, pool_recycle: int = 3600) -> None: ...
+    def insert_many(self, table_name: str, data: list[dict[str, Any]]) -> int: ...
+    def query(self, sql: str, return_format: Literal['dataframe', 'records'] = 'dataframe') -> pl.DataFrame | list[dict] | None: ...
+    @contextmanager
+    def get_session(self) -> Generator[Session, Any, None]: ...
+    def query_with_session(self, sql: str, session: Session, return_format: Literal['dataframe', 'records'] = 'dataframe'): ...

datahub/dbo/pg.pyi

@@ -0,0 +1,15 @@
+import polars as pl
+from .database import Database as Database
+from _typeshed import Incomplete
+from datahub.setting import PostgresSetting as PostgresSetting
+from datahub.utils.logger import logger as logger
+from datetime import date
+from typing import Any, Sequence
+
+class Postgres(Database):
+    db_url: Incomplete
+    def __init__(self, setting: PostgresSetting) -> None: ...
+    def upsert_many(self, table_name: str, data: list[dict[str, Any]], keys: list[str]) -> int: ...
+    def get_trading_days(self, start_date: date, end_date: date, market: str = 'XSHG') -> list[date]: ...
+    def get_blacklist(self, blacklist_ids: Sequence[str], end_date: date = None) -> pl.DataFrame: ...
+    def get_sbl_list(self, brokers: Sequence[str] = (), sbl_ids: Sequence[str] = (), start_date: date | None = None, end_date: date | None = None) -> pl.DataFrame: ...

datahub/dbo/redis_stream.pyi

@@ -0,0 +1,15 @@
+from ..protos.client_msg import deserialize as deserialize, serialize as serialize
+from _typeshed import Incomplete
+from datahub.setting import RedisSetting as RedisSetting
+from typing import Any, Iterator, Sequence
+
+class RedisStream:
+    client: Incomplete
+    ident: Incomplete
+    def __init__(self, setting: RedisSetting) -> None: ...
+    def ensure_group(self, topics: Sequence[str]): ...
+    def set_position(self, topic: str, posi: str): ...
+    def read(self, topics: Sequence[str], count: int = 1, ignore_pending: bool = False, block: int = 0) -> Iterator[Any]: ...
+    def write(self, topic: str, proto_msg: Any): ...
+    def delete(self, topic: str): ...
+    def ack(self, topic: str, message_id: str): ...

datahub/dbo/sr.pyi

@@ -0,0 +1,55 @@
+import polars as pl
+from .database import Database as Database
+from _typeshed import Incomplete
+from datahub.setting import StarRocksSetting as StarRocksSetting
+from datahub.utils.logger import logger as logger
+from datahub.utils.sftp import SFTPClient as SFTPClient
+from datetime import date, datetime
+from typing import Literal, Sequence
+
+class StarRocks(Database):
+    db_url: Incomplete
+    http_url: Incomplete
+    username: Incomplete
+    password: Incomplete
+    setting: Incomplete
+    home_path: str
+    sftp_setting: Incomplete
+    force_query: Incomplete
+    def __init__(self, setting: StarRocksSetting) -> None: ...
+    def query_with_cache(self, sql: str, return_format: Literal['dataframe', 'records'] = 'dataframe') -> pl.DataFrame | list[dict] | None: ...
+    def query_large_data(self, sql: str) -> pl.DataFrame: ...
+    def get_indicator_type(self) -> pl.DataFrame: ...
+    @property
+    def factor_info(self) -> pl.DataFrame: ...
+    def get_factor_info(self, factors: Sequence[str] = (), types: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_seq_factor_info(self, resample_type: str, factors: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_seq_y_info(self, resample_type: str, factors: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_factor_type(self) -> pl.DataFrame: ...
+    def get_indicator_info(self, indicators: Sequence[str] = (), types: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_future_domain_info(self, instrument_sub_type: str | None = None, start_date: date | None = None, end_date: date | None = None, market: str = 'CCFX', rank_id: int = 1, domain_factor: str = 'volume') -> pl.DataFrame: ...
+    def get_future_snapshot(self, instrument_sub_type: str, start_date: date, end_date: date, market: str = 'CCFX', rank_id: int = 1, domain_factor: str = 'volume') -> pl.DataFrame: ...
+    def get_indicator_data(self, start_time: datetime, end_time: datetime, indicators: Sequence[str] = (), instruments: Sequence[str] = (), types: Sequence[str] = (), use_last: bool = False) -> pl.DataFrame: ...
+    def get_seq_factor_data(self, start_time: datetime, end_time: datetime, factors: Sequence[str] = (), instruments: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_seq_factor_stat(self, start_time: datetime, end_time: datetime, stat_type: str, factors: Sequence[str] = (), instruments: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_factor_data(self, start_time: datetime, end_time: datetime, factors: Sequence[str] = (), instruments: Sequence[str] = (), types: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_risk_factor_data(self, version: str, start_time: datetime, end_time: datetime, factors: Sequence[str] = (), instruments: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_return_data(self, start_time: datetime, end_time: datetime, factors: Sequence[str] = (), instruments: Sequence[str] = (), adj_method: Literal['forward'] = 'forward') -> pl.DataFrame: ...
+    def get_seq_y_data(self, start_time: datetime, end_time: datetime, factors: Sequence[str] = (), instruments: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_seq_y_stat(self, start_time: datetime, end_time: datetime, stat_type: str, factors: Sequence[str] = (), instruments: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_ex_factor_info(self, instruments: Sequence[str] = (), trade_date: date | None = None) -> pl.DataFrame: ...
+    def get_trading_days(self, start_date: date, end_date: date, market: str = 'XSHG') -> list[date]: ...
+    def get_kline(self, freq: str, instruments: Sequence[str] = (), start_time: datetime | None = None, end_time: datetime | None = None, adj_method: str | None = None) -> pl.DataFrame: ...
+    def get_md_transaction(self, start_date: date, end_date: date, instruments: Sequence[str] = (), markets: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_instrument_industry(self, trade_date: date, industry_source: str = 'sws', industry_level: Literal[1, 2, 3] = 1, use_last: bool = False) -> pl.DataFrame: ...
+    def get_instrument_list(self, trade_date: date, indicators: Sequence[str] = ()) -> Sequence[str]: ...
+    def get_universe(self, trade_date: date, universe: str | None = None) -> pl.DataFrame: ...
+    def get_instrument_info(self, trade_date: date, fields: Sequence[str] | None = None, market: str | None = None, instrument_type: Literal['option', 'spot', 'future', 'etf'] | None = None) -> pl.DataFrame: ...
+    def get_md_snapshot(self, start_date: date, end_date: date, instruments: Sequence[str] = (), markets: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_seq_snapshot(self, start_date: date, end_date: date, instruments: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_resample_lob(self, resample_type: str, start_date: date, end_date: date, instruments: Sequence[str] = ()) -> pl.DataFrame: ...
+    def get_last_seq_snapshot(self, end_time: datetime, instruments: Sequence[str] = (), is_filter_limit: bool = False) -> pl.DataFrame: ...
+    def get_loads(self, label: str) -> pl.DataFrame: ...
+    def stream_load(self, database: str, table: str, file_path: str): ...
+    def broker_load_parquet(self, database: str, table: str, fields: Sequence[str], file_path: str, timeout: int = 3600, label: str | None = None, is_sync: bool = False) -> str: ...
+    def get_profile(self, sql: str) -> str: ...

datahub/setting.pyi

@@ -0,0 +1,46 @@
+from dataclasses import dataclass
+
+@dataclass
+class RedisSetting:
+    url: str
+    ident: str
+
+@dataclass
+class SftpSetting:
+    host: str
+    port: int
+    username: str
+    password: str
+    home_path: str
+
+@dataclass
+class StarRocksSetting:
+    host: str
+    db_port: int
+    http_port: int
+    username: str
+    password: str
+    timezone: str = ...
+    force_query: bool = ...
+    sftp: SftpSetting | None = ...
+
+@dataclass
+class PostgresSetting:
+    host: str
+    db_port: int
+    username: str
+    password: str
+
+@dataclass
+class CronServerSetting:
+    host: str
+    port: int
+
+@dataclass
+class Setting:
+    redis: RedisSetting | None = ...
+    starrocks: StarRocksSetting | None = ...
+    postgres: PostgresSetting | None = ...
+    sftp: SftpSetting | None = ...
+    cron_server: CronServerSetting | None = ...
+    timezone: str = ...

datahub/utils/logger.pyi

@@ -0,0 +1,27 @@
+from .monitor import Feishu as Feishu
+from _typeshed import Incomplete
+from typing import Callable, Literal
+
+LOGURU_LEVEL: Incomplete
+
+def timer_decorator(func: Callable) -> Callable: ...
+def filter_log_level(record, level): ...
+
+class Logger:
+    log_dir: Incomplete
+    retention: Incomplete
+    name: Incomplete
+    log_format: Incomplete
+    trace: Incomplete
+    debug: Incomplete
+    info: Incomplete
+    warning: Incomplete
+    error: Incomplete
+    exception: Incomplete
+    min_level: Incomplete
+    min_level_no: Incomplete
+    monitor_type: Incomplete
+    monitor: Incomplete
+    def __init__(self, name: str, log_dir: str | None = None, retention: int = 5, monitor_type: Literal['Feishu'] = 'Feishu') -> None: ...
+
+def main() -> None: ...

datahub/utils/monitor/__init__.pyi

@@ -0,0 +1,2 @@
+from .base import Monitor as Monitor
+from .feishu import Feishu as Feishu

datahub/utils/monitor/base.pyi

@@ -0,0 +1,11 @@
+from dataclasses import dataclass
+
+@dataclass
+class Monitor:
+    def to(self, who: str): ...
+    def at(self, who: str): ...
+    def clear(self) -> None: ...
+    def info(self, msg: str): ...
+    def error(self, msg: str): ...
+    def warning(self, msg: str): ...
+    def debug(self, msg: str): ...

datahub/utils/monitor/feishu.pyi

@@ -0,0 +1,14 @@
+from .base import Monitor as Monitor
+from _typeshed import Incomplete
+from dataclasses import dataclass, field
+
+TARGET: Incomplete
+
+@dataclass
+class Feishu(Monitor):
+    app_id: str = ...
+    app_secret: str = ...
+    users: dict = field(default_factory=Incomplete)
+    chats: dict = field(default_factory=Incomplete)
+    def to(self, who: TARGET): ...
+    def at(self, who: TARGET): ...

datahub/utils/sftp.pyi

@@ -0,0 +1,18 @@
+from _typeshed import Incomplete
+from datahub.setting import SftpSetting
+from paramiko import SFTPClient as _SFTPClient
+
+__all__ = ['SFTPClient']
+
+class SFTPClient:
+    setting: Incomplete
+    chmod: Incomplete
+    ssh: Incomplete
+    sftp: _SFTPClient
+    def __init__(self, setting: SftpSetting, chmod: int = 509) -> None: ...
+    def ensure_dir(self, dir_path: str, chmod: int = 509) -> bool: ...
+    def rmdir_recursive(self, path: str): ...
+    def connect(self): ...
+    def close(self) -> None: ...
+    def __enter__(self): ...
+    def __exit__(self, exc_type: type[BaseException] | None, exc_val: BaseException | None, exc_tb: types.TracebackType | None) -> None: ...

datahub.pyi

@@ -17,7 +17,6 @@ __name__ = ...
 
 # Modules used internally, to allow implicit dependencies to be seen:
 import os
-import _frozen_importlib_external
 import datetime
 import time
 import dataclasses

datahub_binary-1.4.10.dist-info/METADATA

@@ -0,0 +1,252 @@
+Metadata-Version: 2.4
+Name: datahub_binary
+Version: 1.4.10
+Summary: A comprehensive Python library for data processing, integration, and management.
+Requires-Python: <3.13,>=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: SQLAlchemy>=1.0.0
+Requires-Dist: httpx[socks]>=0.28.0
+Requires-Dist: starrocks>=1.0.0
+Requires-Dist: polars-lts-cpu>=1.0.0; sys_platform == "darwin"
+Requires-Dist: polars>=1.0.0; sys_platform != "darwin"
+Requires-Dist: loguru>=0.7.3
+Requires-Dist: numpy>=2.0.0
+Requires-Dist: protobuf>=6.30.1
+Requires-Dist: redis>=5.2.1
+Requires-Dist: psycopg2-binary>=2.9.10
+Requires-Dist: paramiko>=3.5.1
+Requires-Dist: toml>=0.10.0
+Requires-Dist: pydantic>=2.11.3
+Requires-Dist: lark-oapi>=1.4.14
+Requires-Dist: pyzmq>=26.4.0
+Requires-Dist: sortedcontainers>=2.4.0
+
+### 使用示例
+
+```python3
+import os
+from datetime import datetime
+
+import polars as pl
+
+os.environ["LOGURU_LEVEL"] = "TRACE"
+
+from datahub import *
+
+
+def main():
+    starrocks_setting = StarRocksSetting(
+        host="xxx",
+        db_port=9030,
+        http_port=8040,
+        username="xxx",
+        password="xxx",
+        # sftp=sftp_setting  # 设置sftp后会启用大查询缓存
+    )
+
+    setting = Setting(
+        starrocks=starrocks_setting,
+    )
+    datahub = DataHub(setting)
+    start_time = datetime(2024, 12, 19)
+    end_time = datetime(2024, 12, 29)
+    # pl.Config.set_tbl_cols(-1)  # -1 表示显示所有列
+    # pl.Config.set_fmt_str_lengths(100)  # 设置字符串显示长度
+    # pl.Config.set_tbl_width_chars(200)  # 设置表格宽度字符数
+
+    # 发送监控报警
+    # mylogger = logger.Logger("test")
+    # mylogger.monitor.to("alpha运维").info("test")
+    # mylogger.monitor.to("alpha运维").at("all").error("test")
+
+    print("获取交易日")
+    result = datahub.get_trading_days(start_time, end_time)
+    print(result)
+
+    print("获取指定日期, 指定indicator 可用标的")
+    result = datahub.get_instrument_list(
+        trade_date=start_time.date(),
+        indicators=["premiums_income"],
+    )
+    print(result)
+
+    print("获取指定日期标的信息")
+    result = datahub.get_instrument_info(
+        trade_date=start_time.date(), market="XSHG", instrument_type="spot")
+    print(result)
+
+    print("获取指定日期标的池")
+    result = datahub.get_universe(trade_date=datetime(
+        2025, 2, 20), universe="basic_alpha")
+    print(result)
+
+    print("获取某日逐笔成交")
+    result = datahub.get_md_transaction(
+        start_date=datetime(2025, 1, 27).date(),
+        instruments=["508086.XSHG"],
+    )
+    print(result)
+
+    print("获取某日快照行情")
+    result = datahub.get_md_snapshot(
+        start_date=datetime(2025, 1, 27).date(),
+        instruments=["508086.XSHG"],
+    )
+    print(result)
+
+    print("获取某日快照行情")
+    result = datahub.get_trading_days(
+        start_date=start_time.date(),
+        end_date=end_time.date(),
+    )
+    print(result)
+
+    print("获取指标值")
+    result = datahub.get_indicator_data(
+        start_time=start_time,
+        end_time=end_time,
+        # indicators=["5min_stat_open"],
+        instruments=["600519.XSHG"],
+        types=["5min_stat"]
+    )
+    print(result)
+
+    print("获取BarDataMatrix")
+    bar_data = datahub.get_indicator_matrix(
+        trade_time=datetime(2024, 12, 19, 10),
+        indicators=["5min_stat_open", "5min_stat_low"],
+        instrument_ids=["600519.XSHG", "000001.XSHE", "000002.XSHG"],
+    )
+    print(bar_data)
+
+    print("获取BarDataMatrix列表")
+    bar_data = datahub.get_indicator_matrix_list(
+        start_date=datetime(2024, 12, 19, 10),
+        end_date=datetime(2024, 12, 20, 10),
+        indicators=["5min_stat_open", "5min_stat_low"],
+        instrument_ids=["600519.XSHG", "000001.XSHE", "000002.XSHG"],
+    )
+    print(bar_data)
+
+    print("获取因子值")
+    result = datahub.get_factor_data(
+        start_time=start_time,
+        end_time=end_time,
+        # factors=["5min_stat_open"],
+        instruments=["600519.XSHG"],
+        types=["5min_stat"]
+    )
+    print(result)
+
+    print("获取因子值矩阵")
+    result = datahub.get_factor_matrix(
+        trade_time=datetime(2024, 12, 19, 10),
+        factors=["5min_stat_open", "5min_stat_low"],
+        instrument_ids=["600519.XSHG", "000001.XSHE", "000002.XSHG"],
+    )
+    print(result)
+
+    print("获取收益率数据")
+    result = datahub.get_return_data(
+        start_time=start_time,
+        end_time=end_time,
+        instruments=["600519.XSHG"],
+    )
+    print(result)
+
+    print("获取收益率矩阵")
+    result = datahub.get_return_matrix(
+        trade_time=datetime(2024, 10, 31, 19, 15),
+        factors=["forward_ret_raw_1d"],
+        instrument_ids=["600519.XSHG", "000001.XSHE", "000002.XSHG"],
+    )
+    print(result)
+
+    print("获取K线")
+    result = datahub.get_kline(
+        "5min", instruments=["600519.XSHG", "603350.XSHG"],
+        start_time=start_time, end_time=end_time, adj_method="backward"
+    )
+    print(result)
+
+    print("获取指标信息")
+    result = datahub.get_indicator_info()
+    print(result)
+
+    print("获取指标类型信息")
+    result = datahub.get_indicator_type()
+    print(result)
+
+    print("获取因子类型信息")
+    result = datahub.get_factor_type()
+    print(result)
+
+    print("获取行业分类信息")
+    result = datahub.get_instrument_industry(datetime(2018, 1, 5).date())
+    print(result)
+
+    print("获取交易日")
+    result = datahub.calendar.get_latest_trade_date(
+        dt=datetime(2025, 1, 4).date())
+    print(result)
+
+    print("获取主力期货合约信息")
+    result = datahub.get_future_domain_info("IC")
+    print(result)
+
+    print("获取主力期货快照行情")
+    result = datahub.get_future_snapshot(
+        "IC", start_date=start_time.date(), end_date=end_time.date())
+    print(result)
+
+    print("获取return_factor的数据")
+    df = datahub.get_return_matrix(
+        trade_time=datetime(2018, 1, 29, 9, 35),
+        factors=["ret_raw_1d", "ret_raw_3d", "ret_raw_5d"],
+        instrument_ids=["600519.XSHG", "000001.XSHE", "000002.XSHG"],
+    )
+    print(df)
+
+    print("获取risk_factor的数据")
+    df = datahub.get_risk_factor_matrix(
+        version="rq_v2_sws2021",
+        trade_time=datetime(2018, 1, 11, 20),
+        factors=["liquidity", "longterm_reversal", "mid_cap"],
+        instrument_ids=["600519.XSHG", "000001.XSHE", "000002.XSHG"],
+    )
+    print(df)
+
+    print("获取最新黑名单列表, 可以指定日期")
+    df = datahub.get_blacklist(blacklist_ids=["cms_dma_blacklist", "XXX"], end_date=None)
+    print(df)
+
+    print("获取券池列表, 可以指定券池和日期")
+    df = datahub.get_sbl_list(end_date=datetime(2025, 1, 1))
+    print(df)
+
+    print("获取seq y")
+    df = datahub.get_seq_y_info(resample_type="time_interval_ms_500",)
+    print(df)
+
+    print("获取seq factor info")
+    df = datahub.get_seq_factor_info(resample_type="time_interval_ms_500",)
+    print(df)
+
+    print("获取 seq factor")
+    df = datahub.get_seq_factor_data(
+        start_time=datetime(2025, 2, 10, 9, 30, 9, 920000),
+        end_time=datetime(2025, 2, 10, 9, 30, 11, 920000),
+        factors=["ActiveCashFlowFactors__lookback_tick_30s__time_interval_ms_500__buy_amount"],
+        instruments=["000029.XSHE"]
+    )
+    print(df)
+
+    print("获取get_seq_y_stat")
+    df = datahub.get_seq_y_stat(start_time=datetime(2025, 1, 10, 23), end_time=datetime(2025, 1, 10, 23),
+                                stat_type="std_1d")
+    print(df)
+
+
+if __name__ == "__main__":
+    main()
+```

datahub_binary-1.4.10.dist-info/RECORD

@@ -0,0 +1,31 @@
+datahub.cp312-win_amd64.pyd,sha256=kWmDuLEYfXKYeLaNn3CC5wSy8aOktPyw_1yrt7CuRtg,1786880
+datahub.pyi,sha256=IXQ1dWxIq3itkkoYNJiPuRMWksWE1_4XVpjRYjy9tnQ,1449
+datahub/__init__.pyi,sha256=hX8D9Qd6uPjZiUBd6rIq7Llkt_H4l_RvRXsws3sdYbI,630
+datahub/datacache.pyi,sha256=rVDkzr0nLn54RT6EkYMDBh41t788XfVFyL4XKTJ2eSM,3587
+datahub/datahub.pyi,sha256=yGFRSDc0lBTZROyVGxzmuLqvfVqzgL657J6EGgjufyM,8751
+datahub/setting.pyi,sha256=u6gYjjF6r1thSpp2XNMvg_1JUcqB64dRTkNoHlOoKUQ,889
+datahub/ats/client_sdk.pyi,sha256=wwYRrVlM_qnpGhUifS-xgBAwoUDgQgFAC6TkTq8CLX8,3263
+datahub/dbo/database.pyi,sha256=O8Gp0Os3tzznLa6hdmCaXnq7Iw4xAAkW4YcjK0jUSUY,1024
+datahub/dbo/pg.pyi,sha256=zSr5GAiPVwvqXSN6qctkUh1My7c2tMyGETJB0Ir1Uvo,871
+datahub/dbo/redis_stream.pyi,sha256=B3DJ5GQ_gnGqaPAGwgHwvTAVubMz99mAaoS8EK_2VaQ,734
+datahub/dbo/sr.pyi,sha256=S-xVb0WDkxgusdot4FGQJ6dyTsMdehFUybllWYPe-BU,5375
+datahub/protos/client_pb2.pyi,sha256=CZTEbNX3LduN31Ir1gNb4iK9GFEbP75kc4yeuAwg-dA,220830
+datahub/protos/common_pb2.pyi,sha256=KCzIIakHr0iViKFNFcK1ZotkqcQuZ9_XTNIfvyvcSbM,32839
+datahub/protos/management_pb2.pyi,sha256=DtHNxR31C1T4HTUWT7KSsFPMvHiq37u_3G3aO__McA8,23183
+datahub/protos/position_pb2.pyi,sha256=C4FCpOCjQrNtqvtjvxPZFbDG7aWBsjmQEBSzNVmRKp4,32252
+datahub/protos/query_pb2.pyi,sha256=V6-yht8zbiCm02e7MTb1Ag_afoMnBFX1YsIETdom87I,15945
+datahub/protos/quote_pb2.pyi,sha256=RULvl4NNbnE2O8sFuGfs8tZKJkwJoUyeadzUnHG_E-w,27254
+datahub/protos/signal_pb2.pyi,sha256=HJxCtrEOlc1cBtH-ywFRvKItT0IiLyQVb0jzdkRF6mY,15879
+datahub/protos/strategy_pb2.pyi,sha256=JmRoiuRdyE_1m6qQxxBMAvLp2OngDSHxTYivkcZQ2PU,32767
+datahub/protos/trade_pb2.pyi,sha256=YLZFMLEMR3q1fSQxgyR81BsVvYngNQPbKPKvLA7ktjs,49810
+datahub/utils/__init__.pyi,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+datahub/utils/logger.pyi,sha256=1rATh8QpyrOnfRWut5QcnnY7kfNaDq9sBu166znKypI,778
+datahub/utils/sftp.pyi,sha256=J-lWxtTSZfnvqBRPmEHi1Tw5CpS0fsy6ySj-xnyXjZc,694
+datahub/utils/monitor/__init__.pyi,sha256=EOwgf8CbJ4g3iUAaFoR6O-mYemJ9xjP42zlBj2KeA9c,76
+datahub/utils/monitor/base.pyi,sha256=n1dKYK73JJ_7QPkCWFc-6Aj_a16j2z_VBaQ9zkN9A3E,310
+datahub/utils/monitor/feishu.pyi,sha256=GgvJXYeX3cPOQjqpV0GJUr_Ri1_cZe2-viRBkpe6O_g,402
+datahub.build/.gitignore,sha256=aEiIwOuxfzdCmLZe4oB1JsBmCUxwG8x-u-HBCV9JT8E,1
+datahub_binary-1.4.10.dist-info/METADATA,sha256=D70IvDmHs7fjTK9H6VP9FsCGJ0V4Tg51llWqNjaFZFM,7841
+datahub_binary-1.4.10.dist-info/WHEEL,sha256=wQGB_Dged6RIso_Q-D9Gk_VsGJ3cQzyC7g9I2lGvFV4,97
+datahub_binary-1.4.10.dist-info/top_level.txt,sha256=J0rzqYfZghMgpObWaPGhQtV88I-KXrgArDvi_ddf6ZA,8
+datahub_binary-1.4.10.dist-info/RECORD,,

{datahub_binary-1.4.8.dist-info → datahub_binary-1.4.10.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: Nuitka (2.7.10)
+Generator: Nuitka (2.7.11)
 Root-Is-Purelib: false
 Tag: cp312-cp312-win_amd64
 

datahub_binary-1.4.8.dist-info/METADATA

@@ -1,22 +0,0 @@
-Metadata-Version: 2.4
-Name: datahub_binary
-Version: 1.4.8
-Summary: A comprehensive Python library for data processing, integration, and management.
-Requires-Python: <3.13,>=3.9
-Description-Content-Type: text/markdown
-Requires-Dist: SQLAlchemy>=1.0.0
-Requires-Dist: httpx[socks]>=0.28.0
-Requires-Dist: starrocks>=1.0.0
-Requires-Dist: polars-lts-cpu>=1.0.0; sys_platform == "darwin"
-Requires-Dist: polars>=1.0.0; sys_platform != "darwin"
-Requires-Dist: loguru>=0.7.3
-Requires-Dist: numpy>=2.0.0
-Requires-Dist: protobuf>=6.30.1
-Requires-Dist: redis>=5.2.1
-Requires-Dist: psycopg2-binary>=2.9.10
-Requires-Dist: paramiko>=3.5.1
-Requires-Dist: toml>=0.10.0
-Requires-Dist: pydantic>=2.11.3
-Requires-Dist: lark-oapi>=1.4.14
-Requires-Dist: pyzmq>=26.4.0
-Requires-Dist: sortedcontainers>=2.4.0

datahub_binary-1.4.8.dist-info/RECORD

@@ -1,16 +0,0 @@
-datahub.cp312-win_amd64.pyd,sha256=HLIUeeWOqFlvIXkoSkS765KS8RYJIH_XwPwkumRMcQA,1788416
-datahub.pyi,sha256=8HXrC_9uuH03DtGCJIlr4-jb33B9rgHhs9ZZ4Q4li4A,1483
-datahub/protos/client_pb2.pyi,sha256=CZTEbNX3LduN31Ir1gNb4iK9GFEbP75kc4yeuAwg-dA,220830
-datahub/protos/common_pb2.pyi,sha256=KCzIIakHr0iViKFNFcK1ZotkqcQuZ9_XTNIfvyvcSbM,32839
-datahub/protos/management_pb2.pyi,sha256=DtHNxR31C1T4HTUWT7KSsFPMvHiq37u_3G3aO__McA8,23183
-datahub/protos/position_pb2.pyi,sha256=C4FCpOCjQrNtqvtjvxPZFbDG7aWBsjmQEBSzNVmRKp4,32252
-datahub/protos/query_pb2.pyi,sha256=V6-yht8zbiCm02e7MTb1Ag_afoMnBFX1YsIETdom87I,15945
-datahub/protos/quote_pb2.pyi,sha256=RULvl4NNbnE2O8sFuGfs8tZKJkwJoUyeadzUnHG_E-w,27254
-datahub/protos/signal_pb2.pyi,sha256=HJxCtrEOlc1cBtH-ywFRvKItT0IiLyQVb0jzdkRF6mY,15879
-datahub/protos/strategy_pb2.pyi,sha256=JmRoiuRdyE_1m6qQxxBMAvLp2OngDSHxTYivkcZQ2PU,32767
-datahub/protos/trade_pb2.pyi,sha256=YLZFMLEMR3q1fSQxgyR81BsVvYngNQPbKPKvLA7ktjs,49810
-datahub.build/.gitignore,sha256=aEiIwOuxfzdCmLZe4oB1JsBmCUxwG8x-u-HBCV9JT8E,1
-datahub_binary-1.4.8.dist-info/METADATA,sha256=_XcmsNuyj1wFaluQ2Qb6L4_lrY3tGvkPQGD6F2kTE5E,806
-datahub_binary-1.4.8.dist-info/WHEEL,sha256=MxVmlm1hxT_8bw-UkqNPc4xLJcr7HjPq7rr3bHdack4,97
-datahub_binary-1.4.8.dist-info/top_level.txt,sha256=J0rzqYfZghMgpObWaPGhQtV88I-KXrgArDvi_ddf6ZA,8
-datahub_binary-1.4.8.dist-info/RECORD,,