Yuxuan Yan
110 lines
4.8 KiB
Python
110 lines
4.8 KiB
Python
"""Column contracts for pipeline parquet files."""
|
|
|
|
from typing import Final
|
|
|
|
# Required columns for data parquet files (daily bars, alternative data, etc.)
|
|
DATA_COLUMNS: Final[list[str]] = [
|
|
"symbol_id", # str: internal code like 'sh600000'
|
|
"symbol_name", # str: stock name like '浦发银行'
|
|
"date", # date
|
|
"open", # float64
|
|
"high", # float64
|
|
"low", # float64
|
|
"close", # float64
|
|
"preclose", # float64: previous trading day's close
|
|
"volume", # float64 (shares)
|
|
"amount", # float64 (turnover in yuan, raw/unadjusted)
|
|
"vwap", # float64: daily VWAP = amount / volume. NB raw price scale —
|
|
# NOT comparable with adjusted OHLC under qfq/hfq.
|
|
"turn", # float64: turnover rate (%)
|
|
"pctChg", # float64: daily % change
|
|
"tradestatus", # int: 1 = traded, 0 = suspended
|
|
"isST", # int: 1 = ST/special-treatment, 0 = normal
|
|
"peTTM", # float64: trailing-12m P/E
|
|
"pbMRQ", # float64: P/B (most recent quarter)
|
|
"psTTM", # float64: trailing-12m P/S
|
|
"pcfNcfTTM", # float64: P/CF (net cash flow, TTM)
|
|
]
|
|
|
|
# Required columns for raw intraday minute bar parquet files.
|
|
MINUTE_BAR_COLUMNS: Final[list[str]] = [
|
|
"symbol_id", # str: internal code like 'sh600000'
|
|
"symbol_name", # str: stock name like '浦发银行'
|
|
"datetime", # datetime64: intraday bar timestamp
|
|
"date", # date component, aligned with daily DATA_COLUMNS date
|
|
"time", # str: HH:MM:SS bar time
|
|
"frequency", # str: e.g. '5m'
|
|
"open", # float64
|
|
"high", # float64
|
|
"low", # float64
|
|
"close", # float64
|
|
"volume", # float64 (shares)
|
|
"amount", # float64 (turnover in yuan, raw/unadjusted)
|
|
"vwap", # float64: amount / volume
|
|
"adjustflag", # str: baostock adjustment flag; '3' for raw/unadjusted
|
|
]
|
|
|
|
# Required key columns for daily derived-data parquet files. Value columns are
|
|
# user/plugin-defined and must be numeric.
|
|
DERIVED_KEY_COLUMNS: Final[list[str]] = [
|
|
"symbol_id", # str
|
|
"date", # date: normalized daily timestamp
|
|
]
|
|
|
|
# Required columns for alpha parquet files.
|
|
# Alphas are position WEIGHTS: positive=long, negative=short.
|
|
ALPHA_COLUMNS: Final[list[str]] = [
|
|
"symbol_id", # str: matches DATA_COLUMNS symbol_id
|
|
"date", # date: aligned with data dates
|
|
"alpha_name", # str: identifies which alpha (e.g. 'reversal_5d')
|
|
"weight", # float64: position weight, signed
|
|
]
|
|
|
|
# Required columns for combo parquet files.
|
|
COMBO_COLUMNS: Final[list[str]] = [
|
|
"symbol_id", # str
|
|
"date", # date
|
|
"combo_name", # str: identifies which combo (e.g. 'equal_weight')
|
|
"weight", # float64: combined weight, signed
|
|
]
|
|
|
|
# Required columns for portfolio (position) parquet files.
|
|
# A position is a tradable integer holding derived from a target weight under
|
|
# A-share lot/board rules. Produced by the `portfolio build` phase.
|
|
POSITION_COLUMNS: Final[list[str]] = [
|
|
"symbol_id", # str
|
|
"date", # date
|
|
"portfolio_name", # str: identifies this construction run
|
|
"target_weight", # float64: w = alpha / sum(|alpha|); signed, sum(|w|)=1
|
|
"target_value", # float64: v_target = booksize * w (signed dollar exposure)
|
|
"target_shares", # float64: q_target = v_target / price (continuous, signed)
|
|
"position_shares", # int64: discretized + repaired integer shares (signed)
|
|
"position_value", # float64: position_shares * price (signed)
|
|
"price", # float64: construction price (close by default)
|
|
]
|
|
|
|
# Required columns for execution-simulator fill parquet files.
|
|
FILL_COLUMNS: Final[list[str]] = [
|
|
"symbol_id", # str
|
|
"date", # date: the EXECUTION date (open[t+1] of the target date)
|
|
"portfolio_name", # str
|
|
"prev_shares", # int64: realized position carried in
|
|
"target_shares", # int64: requested target for this execution
|
|
"traded_shares", # int64: signed delta actually executed
|
|
"realized_shares", # int64: resulting position (blocked trades revert to prev)
|
|
"blocked", # int: 1 if the trade was (fully or partially) blocked
|
|
"trade_cost", # float64: commission + slippage in yuan
|
|
]
|
|
|
|
# Required columns for execution-simulator per-day PnL parquet files.
|
|
PNL_COLUMNS: Final[list[str]] = [
|
|
"date", # date
|
|
"portfolio_name", # str
|
|
"gross_exposure", # float64: sum(|position_value|)
|
|
"net_exposure", # float64: sum(signed position_value)
|
|
"pnl", # float64: daily mark-to-market PnL (yuan), net of cost
|
|
"cost", # float64: total trade cost that day (yuan)
|
|
"turnover", # float64: sum(|traded_value|) / booksize
|
|
"n_positions", # int: count of nonzero holdings
|
|
]
|