feat(factor): 财务因子适配层——三表+forecast parquet→PIT日频特征列(财务批P0 WP1) [nas]
- fundamental_adapter.build_fundamental_features: NAS 静态域三表(按股文件)+ forecast(按报告期全市场文件) → vt_symbol×datetime×33 特征列 - 口径红线全落地: 单季差分缺上期NaN不填0 / TTM连续4季 / PIT=NOTICE_DATE≤决策日 (三表最晚,重述取UPDATE_DATE终值) / NOTICE_DATE缺失报告期整期跳过 / 金融股(无营业成本模板)盈利质量+成长族置NaN - SUE=Foster标准化(diff4/std过去8期ddof=1); forecast归母净利润行优先+fallback - 容错: 零行文件(北交920xxx)/缺文件(退市355只)/缺列(银行模板)全跳过不炸 - 合成数据端到端15测全绿: PIT边界/前向填充/NaN传染与恢复/SUE/forecast事件 [nas] Co-Authored-By: Claude Code <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,466 @@
|
||||
# sanguo_factor/fundamental_adapter.py
|
||||
"""财务因子适配层: NAS 静态域三表+forecast parquet → PIT 日频特征列.
|
||||
|
||||
口径红线(docs/fundamental_factor_survey_20260907.md §7):
|
||||
- R1 单季差分: Q1 直接取累计,其余 = 本期累计 − 年内上期累计;缺上期置 NaN 不填 0
|
||||
- R2 TTM: 连续 4 个单季之和,不足 4 期 NaN
|
||||
- R3 PIT: NOTICE_DATE ≤ 决策日才可见(有效披露日 = 三表 NOTICE_DATE 最大值,保守);
|
||||
NOTICE_DATE 缺失的报告期整期跳过(宁缺毋假)
|
||||
- 金融股(OPERATE_COST 缺失/为 0 的银行模板): 盈利质量/成长族特征置 NaN(估值族保留)
|
||||
|
||||
数据形态(NAS 实测 2026-09-07):
|
||||
- 三表按股: static/{income,balance,cashflow}/{code}.{SH|SZ}_{table}.parquet
|
||||
(北交 920xxx 残留零行文件、沪深退市 355 只文件不存在 → 读取容错跳过)
|
||||
- forecast 按报告期全市场: static/forecast/{YYYYMMDD}_forecast.parquet(中文列,
|
||||
一股多行=按「预测指标」,归母净利润行优先)
|
||||
- 日期列为 "YYYY-MM-DD 00:00:00" 字符串;东财金额单位=元
|
||||
- valuation(中文列)不读: 估值类因子市值 = close × SHARE_CAPITAL 自算(表达式层)
|
||||
|
||||
输出: vt_symbol × datetime(日频) × FEATURE_COLUMNS,join 到 alpha_df 后
|
||||
供 cs_rank(列) 表达式直接消费。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
from datetime import datetime
|
||||
|
||||
import polars as pl
|
||||
|
||||
DEFAULT_STATIC_DIR = "/volume1/stock/sanguo_vnpy_v2/data/static"
|
||||
_SYM = "vt_symbol" # 时序分组键
|
||||
|
||||
# vt_symbol 后缀 → NAS 文件名后缀(600000.SSE → 600000.SH)
|
||||
_VT_TO_FILE_SUFFIX = {"SSE": "SH", "SZSE": "SZ"}
|
||||
|
||||
# forecast 预告类型 → 有序分(§3.6 F04)
|
||||
FORECAST_TYPE_SCORE: dict[str, int] = {
|
||||
"预增": 3, "略增": 2, "扭亏": 2, "续盈": 1, "减亏": 1, "不确定": 0,
|
||||
"略减": -1, "增亏": -2, "续亏": -2, "预减": -3, "首亏": -3,
|
||||
}
|
||||
|
||||
# 累计口径列映射: 源列 → 短名(需单季化+TTM)
|
||||
_CUM_MAP = {
|
||||
"TOTAL_OPERATE_INCOME": "rev",
|
||||
"OPERATE_COST": "cogs",
|
||||
"PARENT_NETPROFIT": "np",
|
||||
"DEDUCT_PARENT_NETPROFIT": "dnp",
|
||||
"TOTAL_PROFIT": "tp",
|
||||
"INVEST_INCOME": "invest_inc",
|
||||
"FAIRVALUE_CHANGE_INCOME": "fv_inc",
|
||||
"ASSET_IMPAIRMENT_LOSS": "asset_imp",
|
||||
"CREDIT_IMPAIRMENT_LOSS": "credit_imp",
|
||||
"NETCASH_OPERATE": "cfo",
|
||||
"SALES_SERVICES": "sales_cash",
|
||||
"ACCEPT_INVEST_CASH": "acc_inv_cash",
|
||||
}
|
||||
# 存量列(balance,时点值直接用;缺列 → null)
|
||||
_BALANCE_COLS = ["TOTAL_ASSETS", "TOTAL_PARENT_EQUITY", "ACCOUNTS_RECE",
|
||||
"OTHER_RECE", "GOODWILL", "SHARE_CAPITAL", "SHORT_LOAN",
|
||||
"SHORT_FIN_PAYABLE", "NONCURRENT_LIAB_1YEAR", "LONG_LOAN",
|
||||
"BOND_PAYABLE", "LEASE_LIAB"]
|
||||
_IBD_PARTS = ["SHORT_LOAN", "SHORT_FIN_PAYABLE", "NONCURRENT_LIAB_1YEAR",
|
||||
"LONG_LOAN", "BOND_PAYABLE", "LEASE_LIAB"]
|
||||
_DATE_COLS = ["REPORT_DATE", "NOTICE_DATE", "UPDATE_DATE"]
|
||||
|
||||
# 输出特征列(32 因子的全部原料;契约由 test_fundamental_library 锁定)
|
||||
FEATURE_COLUMNS: list[str] = [
|
||||
# 报告期级比率(盈利能力 A / 盈利质量 B / 成长 C / 资本结构 E / 预期事件 F)
|
||||
"roe_ttm", "roe_deduct_ttm", "roa_ttm", "gp_over_assets", "gross_margin",
|
||||
"net_margin", "cfo_over_assets",
|
||||
"tacc", "nonrec_ratio", "impairment_ratio", "invest_income_dep",
|
||||
"receivables_anomaly", "sales_cash_ratio", "other_rece_ratio",
|
||||
"rev_q_yoy", "np_q_yoy", "growth_scissors", "gm_delta", "roe_delta",
|
||||
"asset_growth", "nsi", "ibd_ratio", "goodwill_ratio",
|
||||
"sue_np", "sue_rev",
|
||||
"forecast_type_score", "forecast_change_pct",
|
||||
# 估值/资本行为因子的日频原料(表达式层 ÷ close×share_capital)
|
||||
"np_ttm", "dnp_ttm", "cfo_ttm", "equity", "share_capital",
|
||||
"acc_invest_cash_ttm",
|
||||
]
|
||||
# 金融股置 NaN 的特征(盈利质量 B 族 + 成长 C 族,§7 红线 5)
|
||||
_FIN_NULL_COLS = ["tacc", "nonrec_ratio", "impairment_ratio",
|
||||
"invest_income_dep", "receivables_anomaly",
|
||||
"sales_cash_ratio", "other_rece_ratio",
|
||||
"rev_q_yoy", "np_q_yoy", "growth_scissors", "gm_delta",
|
||||
"roe_delta", "asset_growth"]
|
||||
_FORECAST_COLS = ("forecast_type_score", "forecast_change_pct")
|
||||
|
||||
|
||||
# ==================== 读取层 ====================
|
||||
|
||||
def _vt_to_file_code(vt_symbol: str) -> str | None:
|
||||
"""``600000.SSE`` → ``600000.SH``;无法映射的(ETF/北交)返回 None."""
|
||||
code, _, suffix = vt_symbol.partition(".")
|
||||
file_suffix = _VT_TO_FILE_SUFFIX.get(suffix.upper())
|
||||
return f"{code}.{file_suffix}" if file_suffix else None
|
||||
|
||||
|
||||
def _read_static(path: str, want_cols: list[str]) -> pl.DataFrame | None:
|
||||
"""读单股单表 parquet,缺列补 null;零行/缺文件/坏文件 → None(容错跳过)."""
|
||||
if not os.path.exists(path):
|
||||
return None
|
||||
try:
|
||||
schema = pl.read_parquet_schema(path)
|
||||
if "REPORT_DATE" not in schema:
|
||||
return None
|
||||
cols = [c for c in _DATE_COLS + want_cols if c in schema]
|
||||
df = pl.read_parquet(path, columns=cols)
|
||||
except Exception:
|
||||
return None
|
||||
if df.height == 0:
|
||||
return None
|
||||
missing = [c for c in _DATE_COLS + want_cols if c not in df.columns]
|
||||
if missing:
|
||||
df = df.with_columns([pl.lit(None, dtype=pl.Utf8).alias(c) for c in missing])
|
||||
for c in want_cols:
|
||||
df = df.with_columns(pl.col(c).cast(pl.Float64, strict=False))
|
||||
return df
|
||||
|
||||
|
||||
def _norm_dates(df: pl.DataFrame, cols: list[str]) -> pl.DataFrame:
|
||||
"""日期列归一为 pl.Date:字符串截前 10 位解析,Date/Datetime 直接 cast."""
|
||||
exprs = []
|
||||
for c in cols:
|
||||
dtype = df.schema[c]
|
||||
if dtype == pl.Utf8:
|
||||
exprs.append(pl.col(c).str.slice(0, 10).str.to_date("%Y-%m-%d", strict=False).alias(c))
|
||||
elif dtype != pl.Date:
|
||||
exprs.append(pl.col(c).cast(pl.Date, strict=False).alias(c))
|
||||
return df.with_columns(exprs) if exprs else df
|
||||
|
||||
|
||||
def _dedupe_reports(df: pl.DataFrame, value_cols: list[str]) -> pl.DataFrame:
|
||||
"""按 (vt_symbol, REPORT_DATE) 去重:值取 (UPDATE_DATE, NOTICE_DATE) 排序末行
|
||||
(重述取终值),有效披露日取组内 NOTICE_DATE 最大值(保守,不提前)."""
|
||||
df = df.sort(["vt_symbol", "REPORT_DATE", "UPDATE_DATE", "NOTICE_DATE"],
|
||||
nulls_last=False)
|
||||
aggs = [pl.col(c).last().alias(c) for c in value_cols]
|
||||
aggs.append(pl.col("NOTICE_DATE").max().alias("notice_eff"))
|
||||
return df.group_by(["vt_symbol", "REPORT_DATE"]).agg(aggs)
|
||||
|
||||
|
||||
# 各表显式读取清单(income/cashflow 列集不相交,join 不加后缀)
|
||||
_TABLE_RAW = {
|
||||
"income": ["TOTAL_OPERATE_INCOME", "OPERATE_COST", "PARENT_NETPROFIT",
|
||||
"DEDUCT_PARENT_NETPROFIT", "TOTAL_PROFIT", "INVEST_INCOME",
|
||||
"FAIRVALUE_CHANGE_INCOME", "ASSET_IMPAIRMENT_LOSS",
|
||||
"CREDIT_IMPAIRMENT_LOSS"],
|
||||
"balance": _BALANCE_COLS,
|
||||
"cashflow": ["NETCASH_OPERATE", "SALES_SERVICES", "ACCEPT_INVEST_CASH"],
|
||||
}
|
||||
|
||||
|
||||
def _load_statements(codes: list[str], data_dir: str) -> pl.DataFrame:
|
||||
"""全 codes 三表 → 报告期宽表(每 vt_symbol × REPORT_DATE 一行).
|
||||
|
||||
income/cashflow 值列重命名为短名(_CUM_MAP),balance 保持源列名;
|
||||
anchor = 三表报告期并集,left join 保证单表缺期不拖垮其它表特征。
|
||||
"""
|
||||
table_cols = _TABLE_RAW
|
||||
per_table: dict[str, pl.DataFrame] = {}
|
||||
for table, raw_cols in table_cols.items():
|
||||
frames = []
|
||||
for vt in codes:
|
||||
file_code = _vt_to_file_code(vt)
|
||||
if file_code is None:
|
||||
continue
|
||||
df = _read_static(
|
||||
os.path.join(data_dir, table, f"{file_code}_{table}.parquet"), raw_cols)
|
||||
if df is None:
|
||||
continue
|
||||
df = _norm_dates(df, _DATE_COLS)
|
||||
frames.append(df.with_columns(pl.lit(vt).alias("vt_symbol")))
|
||||
if not frames:
|
||||
continue
|
||||
merged = pl.concat(frames).select(["vt_symbol", *_DATE_COLS, *raw_cols])
|
||||
if table == "balance":
|
||||
short = {c: c for c in raw_cols}
|
||||
else:
|
||||
short = {k: v for k, v in _CUM_MAP.items() if k in raw_cols}
|
||||
dedup = _dedupe_reports(merged, list(raw_cols)).rename(short)
|
||||
per_table[table] = dedup
|
||||
|
||||
empty = pl.DataFrame(schema={"vt_symbol": pl.Utf8, "REPORT_DATE": pl.Date})
|
||||
if not per_table:
|
||||
return empty
|
||||
|
||||
out = pl.concat([t.select(["vt_symbol", "REPORT_DATE"])
|
||||
for t in per_table.values()]).unique()
|
||||
notice_cols = []
|
||||
for table, dedup in per_table.items():
|
||||
renamed = dedup.rename({"notice_eff": f"_notice_{table}"})
|
||||
notice_cols.append(f"_notice_{table}")
|
||||
out = out.join(renamed, on=["vt_symbol", "REPORT_DATE"], how="left")
|
||||
# 有效披露日 = 三表 NOTICE_DATE 行最大(最晚可见,保守不提前)
|
||||
return out.with_columns(pl.max_horizontal(notice_cols).alias("notice_eff"))
|
||||
|
||||
|
||||
# ==================== 报告期级指标预计算 ====================
|
||||
# 所有 shift/rolling 必须在 .over(_SYM) 组内执行(跨股串行 = 致命错误)。
|
||||
|
||||
def _qidx() -> pl.Expr:
|
||||
"""连续季度索引: year*4 + quarter(月 3/6/9/12 → 1/2/3/4)."""
|
||||
return (pl.col("REPORT_DATE").dt.year() * 4
|
||||
+ (pl.col("REPORT_DATE").dt.month() - 1) // 3 + 1)
|
||||
|
||||
|
||||
def _single_quarter(col: str) -> pl.Expr:
|
||||
"""R1 单季化: Q1 直接取累计;其余要求上期恰为上一季度(同年)做差,否则 NaN."""
|
||||
cur = pl.col(col)
|
||||
prev = cur.shift(1)
|
||||
prev_ok = (pl.col("_qidx") - pl.col("_qidx").shift(1)) == 1
|
||||
return (
|
||||
pl.when(cur.is_null()).then(None)
|
||||
.when(pl.col("REPORT_DATE").dt.month() == 3).then(cur)
|
||||
.when(prev_ok & prev.is_not_null()).then(cur - prev)
|
||||
.otherwise(None)
|
||||
).over(_SYM)
|
||||
|
||||
|
||||
def _ttm_of(col: str) -> pl.Expr:
|
||||
"""R2 TTM = 连续 4 个报告期单季之和(窗内任一单季 NaN → NaN)."""
|
||||
q = pl.col(col)
|
||||
window_ok = (pl.col("_qidx") - pl.col("_qidx").shift(3)) == 3
|
||||
s = q + q.shift(1) + q.shift(2) + q.shift(3)
|
||||
return pl.when(window_ok).then(s).otherwise(None).over(_SYM)
|
||||
|
||||
|
||||
def _yoy4(col: str) -> pl.Expr:
|
||||
"""yoy = X_t / X_{t−4季} − 1;基期缺失/≤0 → NaN(负基数 yoy 无意义)."""
|
||||
cur, base = pl.col(col), pl.col(col).shift(4)
|
||||
ok = (pl.col("_qidx") - pl.col("_qidx").shift(4)) == 4
|
||||
return (
|
||||
pl.when(ok & base.is_not_null() & (base > 0) & cur.is_not_null())
|
||||
.then(cur / base - 1.0).otherwise(None)
|
||||
).over(_SYM)
|
||||
|
||||
|
||||
def _delta4(col: str) -> pl.Expr:
|
||||
"""ΔX = X_t − X_{t−4季}(要求恰好隔 4 个季度)."""
|
||||
ok = (pl.col("_qidx") - pl.col("_qidx").shift(4)) == 4
|
||||
return pl.when(ok).then(pl.col(col) - pl.col(col).shift(4)).otherwise(None).over(_SYM)
|
||||
|
||||
|
||||
def _safe_ratio(num: pl.Expr, den: pl.Expr) -> pl.Expr:
|
||||
"""分母缺失/为 0 → NaN(比率类通用守卫)."""
|
||||
return pl.when(den.is_not_null() & (den != 0)).then(num / den).otherwise(None)
|
||||
|
||||
|
||||
def _compute_report_features(reports: pl.DataFrame) -> pl.DataFrame:
|
||||
"""报告期宽表 → 全部报告期级特征(逐级 with_columns,over 组内时序)."""
|
||||
df = reports.sort([_SYM, "REPORT_DATE"]).with_columns(_qidx().alias("_qidx"))
|
||||
|
||||
# 第一级: 单季化 + TTM(累计列)
|
||||
df = df.with_columns(
|
||||
[_single_quarter(c).alias(f"q_{c}") for c in _CUM_MAP.values()]
|
||||
).with_columns(
|
||||
[_ttm_of(f"q_{c}").alias(f"ttm_{c}") for c in _CUM_MAP.values()]
|
||||
)
|
||||
|
||||
# 第二级: IBD(缺组件按 0) + 金融股判定(银行模板无营业成本) + 毛利
|
||||
ibd = pl.sum_horizontal([pl.col(p).fill_null(0.0) for p in _IBD_PARTS])
|
||||
is_fin = pl.col("cogs").is_null() | (pl.col("cogs") == 0)
|
||||
df = df.with_columns(
|
||||
ibd.alias("_ibd"),
|
||||
is_fin.alias("_is_fin"),
|
||||
(pl.col("ttm_rev") - pl.col("ttm_cogs")).alias("_gp_ttm"),
|
||||
)
|
||||
|
||||
# 第三级: 行本地比率(无时序,无需 over)
|
||||
eq, ta = pl.col("TOTAL_PARENT_EQUITY"), pl.col("TOTAL_ASSETS")
|
||||
df = df.with_columns(
|
||||
# 盈利能力 A
|
||||
_safe_ratio(pl.col("ttm_np"), eq).alias("roe_ttm"),
|
||||
_safe_ratio(pl.col("ttm_dnp"), eq).alias("roe_deduct_ttm"),
|
||||
_safe_ratio(pl.col("ttm_np"), ta).alias("roa_ttm"),
|
||||
_safe_ratio(pl.col("_gp_ttm"), ta).alias("gp_over_assets"),
|
||||
_safe_ratio(pl.col("_gp_ttm"), pl.col("ttm_rev")).alias("gross_margin"),
|
||||
_safe_ratio(pl.col("ttm_np"), pl.col("ttm_rev")).alias("net_margin"),
|
||||
_safe_ratio(pl.col("ttm_cfo"), ta).alias("cfo_over_assets"),
|
||||
# 盈利质量 B
|
||||
_safe_ratio(pl.col("ttm_np") - pl.col("ttm_cfo"), ta).alias("tacc"),
|
||||
_safe_ratio(pl.col("ttm_np") - pl.col("ttm_dnp"),
|
||||
pl.col("ttm_np").abs()).alias("nonrec_ratio"),
|
||||
_safe_ratio((pl.col("ttm_asset_imp") + pl.col("ttm_credit_imp")).abs(),
|
||||
ta).alias("impairment_ratio"),
|
||||
_safe_ratio(pl.col("ttm_invest_inc") + pl.col("ttm_fv_inc"),
|
||||
pl.col("ttm_tp").abs()).alias("invest_income_dep"),
|
||||
_safe_ratio(pl.col("ttm_sales_cash"), pl.col("ttm_rev")).alias("sales_cash_ratio"),
|
||||
_safe_ratio(pl.col("OTHER_RECE"), ta).alias("other_rece_ratio"),
|
||||
# 成长 C / 资本结构 E
|
||||
_safe_ratio(pl.col("_ibd"), ta).alias("ibd_ratio"),
|
||||
_safe_ratio(pl.col("GOODWILL"), ta).alias("goodwill_ratio"),
|
||||
)
|
||||
|
||||
# 第四级: 跨期差分/同比/剪刀差(over 组内时序)
|
||||
df = df.with_columns(
|
||||
_yoy4("q_rev").alias("rev_q_yoy"),
|
||||
_yoy4("q_np").alias("np_q_yoy"),
|
||||
_yoy4("ACCOUNTS_RECE").alias("_ar_yoy"),
|
||||
_yoy4("ttm_rev").alias("_rev_ttm_yoy"),
|
||||
_yoy4("SHARE_CAPITAL").alias("nsi"),
|
||||
_yoy4("TOTAL_ASSETS").alias("asset_growth"),
|
||||
_delta4("gross_margin").alias("gm_delta"),
|
||||
_delta4("roe_ttm").alias("roe_delta"),
|
||||
_delta4("q_np").alias("_diff4_np"),
|
||||
_delta4("q_rev").alias("_diff4_rev"),
|
||||
).with_columns(
|
||||
(pl.col("np_q_yoy") - pl.col("rev_q_yoy")).alias("growth_scissors"),
|
||||
(pl.col("_ar_yoy") - pl.col("_rev_ttm_yoy")).alias("receivables_anomaly"),
|
||||
)
|
||||
|
||||
# 第五级: SUE(Foster 标准化)= diff4 / std(过去 8 期 diff4, ddof=1)
|
||||
for src, out in (("_diff4_np", "sue_np"), ("_diff4_rev", "sue_rev")):
|
||||
sd = pl.col(src).rolling_std(window_size=8, ddof=1).over(_SYM)
|
||||
df = df.with_columns(
|
||||
pl.when(sd.is_not_null() & (sd > 0) & pl.col(src).is_not_null())
|
||||
.then(pl.col(src) / sd).otherwise(None).alias(out)
|
||||
)
|
||||
|
||||
# 金融股: 盈利质量/成长族特征置 NaN(§7 红线 5)
|
||||
df = df.with_columns([
|
||||
pl.when(pl.col("_is_fin")).then(None).otherwise(pl.col(c)).alias(c)
|
||||
for c in _FIN_NULL_COLS
|
||||
])
|
||||
|
||||
# 输出别名(估值/资本行为因子的日频原料)
|
||||
df = df.with_columns(
|
||||
pl.col("ttm_np").alias("np_ttm"),
|
||||
pl.col("ttm_dnp").alias("dnp_ttm"),
|
||||
pl.col("ttm_cfo").alias("cfo_ttm"),
|
||||
pl.col("ttm_acc_inv_cash").alias("acc_invest_cash_ttm"),
|
||||
pl.col("TOTAL_PARENT_EQUITY").alias("equity"),
|
||||
pl.col("SHARE_CAPITAL").alias("share_capital"),
|
||||
)
|
||||
return df
|
||||
|
||||
|
||||
# ==================== forecast 事件层 ====================
|
||||
|
||||
def _load_forecast_events(codes: list[str], data_dir: str) -> pl.DataFrame:
|
||||
"""forecast 按期文件 → (vt_symbol, eff=公告日期, type_score, change_pct) 事件行.
|
||||
|
||||
一股一公告日多行(按预测指标): 归母净利润行优先(含"净利润"且不含"扣"),
|
||||
无净利润行 fallback 任意行。同股多公告日全保留(asof 取最新)。
|
||||
"""
|
||||
schema = {"vt_symbol": pl.Utf8, "eff": pl.Date,
|
||||
"forecast_type_score": pl.Float64, "forecast_change_pct": pl.Float64}
|
||||
fc_dir = os.path.join(data_dir, "forecast")
|
||||
if not os.path.isdir(fc_dir):
|
||||
return pl.DataFrame(schema=schema)
|
||||
code_set = set(codes)
|
||||
frames = []
|
||||
for fname in sorted(os.listdir(fc_dir)):
|
||||
if not fname.endswith(".parquet"):
|
||||
continue
|
||||
try:
|
||||
f = pl.read_parquet(os.path.join(fc_dir, fname))
|
||||
except Exception:
|
||||
continue
|
||||
if f.height == 0 or not all(c in f.columns for c in
|
||||
("股票代码", "预告类型", "公告日期")):
|
||||
continue
|
||||
code = pl.col("股票代码").cast(pl.Utf8).str.strip_chars().str.zfill(6)
|
||||
vt = (pl.when(code.str.starts_with("60")).then(code + pl.lit(".SSE"))
|
||||
.otherwise(code + pl.lit(".SZSE")).alias("vt_symbol"))
|
||||
if "预测指标" in f.columns:
|
||||
ind = pl.col("预测指标").cast(pl.Utf8)
|
||||
pref = (ind.str.contains("净利润") & ~ind.str.contains("扣")).cast(pl.Int32)
|
||||
else:
|
||||
pref = pl.lit(0, pl.Int32)
|
||||
pct = (pl.col("业绩变动幅度").cast(pl.Float64, strict=False)
|
||||
if "业绩变动幅度" in f.columns else pl.lit(None, pl.Float64))
|
||||
f = f.with_columns(
|
||||
vt,
|
||||
pref.alias("_pref"),
|
||||
pct.alias("_pct"),
|
||||
pl.col("公告日期").cast(pl.Date, strict=False).alias("eff"),
|
||||
pl.col("预告类型").cast(pl.Utf8).replace(
|
||||
FORECAST_TYPE_SCORE, default=None, return_dtype=pl.Float64
|
||||
).alias("_score"),
|
||||
).filter(pl.col("vt_symbol").is_in(code_set) & pl.col("eff").is_not_null())
|
||||
if f.height:
|
||||
frames.append(f.select(["vt_symbol", "eff", "_pref", "_score", "_pct"]))
|
||||
if not frames:
|
||||
return pl.DataFrame(schema=schema)
|
||||
fc = pl.concat(frames).sort(["vt_symbol", "eff", "_pref"])
|
||||
# 同 (vt_symbol, eff) 取优先级最高行(_pref 大者排序在后 → last)
|
||||
return fc.group_by(["vt_symbol", "eff"]).agg(
|
||||
pl.col("_score").last().alias("forecast_type_score"),
|
||||
pl.col("_pct").last().alias("forecast_change_pct"),
|
||||
)
|
||||
|
||||
|
||||
# ==================== 对外主入口 ====================
|
||||
|
||||
def _build_grid(codes: list[str], start: str, end: str,
|
||||
trading_dates) -> pl.DataFrame:
|
||||
"""日频 grid: vt_symbol × datetime(交易日子集或日历日)."""
|
||||
if trading_dates is not None:
|
||||
days = pl.Series("datetime", trading_dates).cast(pl.Datetime("us"))
|
||||
days = days.unique().sort()
|
||||
else:
|
||||
s = datetime.strptime(start, "%Y-%m-%d")
|
||||
e = datetime.strptime(end, "%Y-%m-%d")
|
||||
days = pl.datetime_range(s, e, interval="1d", eager=True).cast(pl.Datetime("us"))
|
||||
day_list = days.to_list()
|
||||
return pl.DataFrame({
|
||||
"vt_symbol": pl.Series([c for c in codes for _ in day_list], dtype=pl.Utf8),
|
||||
"datetime": pl.Series(day_list * len(codes), dtype=pl.Datetime("us")),
|
||||
}, schema={"vt_symbol": pl.Utf8, "datetime": pl.Datetime("us")})
|
||||
|
||||
|
||||
def build_fundamental_features(
|
||||
codes: list[str],
|
||||
start: str,
|
||||
end: str,
|
||||
data_dir: str = DEFAULT_STATIC_DIR,
|
||||
trading_dates: pl.Series | list | None = None,
|
||||
) -> pl.DataFrame:
|
||||
"""构建 PIT 日频财务特征: vt_symbol × datetime × FEATURE_COLUMNS.
|
||||
|
||||
Args:
|
||||
codes: vt_symbol 列表(如 "600000.SSE")
|
||||
start/end: "YYYY-MM-DD" 窗口(trading_dates=None 时生成日历日 grid)
|
||||
data_dir: 静态域根目录(NAS=/volume1/stock/sanguo_vnpy_v2/data/static)
|
||||
trading_dates: 交易日子集(传 bars 的 unique datetime 免造非交易日行)
|
||||
|
||||
Returns:
|
||||
每行 = 决策日可见的最新报告期特征(NOTICE_DATE ≤ 决策日,asof 前向填充)。
|
||||
"""
|
||||
stmt_cols = [c for c in FEATURE_COLUMNS if c not in _FORECAST_COLS]
|
||||
if not codes:
|
||||
return pl.DataFrame(schema={"vt_symbol": pl.Utf8, "datetime": pl.Datetime("us"),
|
||||
**{c: pl.Float64 for c in FEATURE_COLUMNS}})
|
||||
|
||||
grid = _build_grid(codes, start, end, trading_dates)
|
||||
|
||||
reports = _load_statements(codes, data_dir)
|
||||
if reports.height == 0:
|
||||
stmt_events = pl.DataFrame(schema={
|
||||
"vt_symbol": pl.Utf8, "eff": pl.Datetime("us"), **{c: pl.Float64 for c in stmt_cols}})
|
||||
else:
|
||||
feat = _compute_report_features(reports)
|
||||
# NOTICE_DATE 缺失报告期整期跳过(红线: 宁缺毋假)
|
||||
feat = feat.filter(pl.col("notice_eff").is_not_null())
|
||||
stmt_events = feat.select(
|
||||
pl.col("vt_symbol"),
|
||||
pl.col("notice_eff").cast(pl.Datetime("us")).alias("eff"),
|
||||
*stmt_cols,
|
||||
).sort("eff")
|
||||
|
||||
fc_events = _load_forecast_events(codes, data_dir).select(
|
||||
pl.col("vt_symbol"),
|
||||
pl.col("eff").cast(pl.Datetime("us")),
|
||||
*_FORECAST_COLS,
|
||||
).sort("eff")
|
||||
|
||||
# asof 前向填充: 决策日可见的最新披露
|
||||
out = grid.sort("datetime").join_asof(
|
||||
stmt_events, left_on="datetime", right_on="eff",
|
||||
by="vt_symbol", strategy="backward")
|
||||
out = out.sort("datetime").join_asof(
|
||||
fc_events, left_on="datetime", right_on="eff",
|
||||
by="vt_symbol", strategy="backward")
|
||||
return out.sort(["vt_symbol", "datetime"]).select(
|
||||
["vt_symbol", "datetime", *FEATURE_COLUMNS])
|
||||
@@ -6,3 +6,130 @@ import os
|
||||
_VNPY_SRC = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "..", "vnpy_v4.4.0"))
|
||||
if _VNPY_SRC not in sys.path:
|
||||
sys.path.insert(0, _VNPY_SRC)
|
||||
|
||||
|
||||
# ==================== 合成财务静态域(财务因子批测试共用) ====================
|
||||
# 3 只股 × 16 报告期(2020Q1~2023Q4,2020 为 SUE 滚动窗预热),NOTICE_DATE 错位:
|
||||
# Q1→当年4-28 / H1→当年8-29 / Q3→当年10-27 / 年报→次年4-25
|
||||
# 数值全部手算可验证(断言用),公式见各 build 函数内注释。
|
||||
from datetime import date
|
||||
|
||||
import polars as pl
|
||||
|
||||
REPORT_DATES = [
|
||||
f"{y}-{m}" for y in (2020, 2021, 2022, 2023) for m in ("03-31", "06-30", "09-30", "12-31")
|
||||
]
|
||||
|
||||
# 单季 REV/NP 序列(累计=年内前缀和): 报告期索引 i=0..15(2020Q1..2023Q4)
|
||||
# 2020 为 SUE 滚动窗预热史;2021+ 的断言数值由 2021 段起算
|
||||
REV_Q = [90, 130, 140, 150] + [100, 120, 150, 160, 110, 140, 150, 180, 130, 140, 170, 180]
|
||||
NP_Q = [9, 13, 14, 15] + [10, 12, 15, 16, 11, 14, 15, 18, 13, 14, 17, 18]
|
||||
|
||||
# 资产负债表(时点存量,随报告期线性演化;2021Q1 起算,idx=i-4)
|
||||
TA_OF = lambda i: 1000 + 50 * max(i - 4, 0)
|
||||
EQ_OF = lambda i: 500 + 20 * max(i - 4, 0)
|
||||
AR_OF = lambda i: 100 + 10 * max(i - 4, 0)
|
||||
SC_OF = lambda i: 100 if i < 12 else 110 # 2023 起股本扩张 10%(NSI=0.1)
|
||||
|
||||
SYN_STOCKS = {
|
||||
"600000.SH": {"vt": "600000.SSE", "scale": 1.0,
|
||||
"drop_periods": [], "null_notice_periods": []},
|
||||
"000001.SZ": {"vt": "000001.SZSE", "scale": 1.0,
|
||||
"drop_periods": ["2022-03-31"], # 缺 2022Q1 → 单季差分/TTM 链 NaN
|
||||
"null_notice_periods": ["2022-09-30"]}, # NOTICE_DATE 缺失 → 该报告期跳过
|
||||
"300001.SZ": {"vt": "300001.SZSE", "scale": 2.0,
|
||||
"drop_periods": [], "null_notice_periods": []},
|
||||
}
|
||||
|
||||
|
||||
def _notice_date(report_date: str) -> str:
|
||||
"""A 股典型披露节奏(年报次年 4-25 / 一季报 4-28 / 中报 8-29 / 三季报 10-27)."""
|
||||
y, m = int(report_date[:4]), int(report_date[5:7])
|
||||
if m == 3:
|
||||
return f"{y}-04-28"
|
||||
if m == 6:
|
||||
return f"{y}-08-29"
|
||||
if m == 9:
|
||||
return f"{y}-10-27"
|
||||
return f"{y + 1}-04-25"
|
||||
|
||||
|
||||
def _cum_in_year(q_values: list[float], i: int) -> float:
|
||||
"""报告期 i 的年内累计值 = 当年前几季单季之和."""
|
||||
year_start = (i // 4) * 4
|
||||
return float(sum(q_values[year_start:i + 1]))
|
||||
|
||||
|
||||
def build_synthetic_static(root: str) -> str:
|
||||
"""写合成静态域 parquet 树(data_dir),返回 static 根目录路径.
|
||||
|
||||
目录结构与 NAS 一致: static/{income,balance,cashflow}/{code}.{SH|SZ}_{table}.parquet
|
||||
forecast 按报告期全市场文件: static/forecast/{YYYYMMDD}_forecast.parquet
|
||||
"""
|
||||
static_dir = os.path.join(str(root), "static")
|
||||
for table in ("income", "balance", "cashflow"):
|
||||
os.makedirs(os.path.join(static_dir, table), exist_ok=True)
|
||||
|
||||
for file_code, spec in SYN_STOCKS.items():
|
||||
s, drop, null_notice = spec["scale"], set(spec["drop_periods"]), set(spec["null_notice_periods"])
|
||||
income_rows, balance_rows, cashflow_rows = [], [], []
|
||||
for i, rd in enumerate(REPORT_DATES):
|
||||
if rd in drop:
|
||||
continue
|
||||
notice = None if rd in null_notice else _notice_date(rd)
|
||||
rev_c, np_c = s * _cum_in_year(REV_Q, i), s * _cum_in_year(NP_Q, i)
|
||||
common = {
|
||||
"REPORT_DATE": f"{rd} 00:00:00",
|
||||
"NOTICE_DATE": (f"{notice} 00:00:00" if notice else None),
|
||||
"UPDATE_DATE": f"{notice} 00:00:00" if notice else None,
|
||||
}
|
||||
income_rows.append({**common,
|
||||
"TOTAL_OPERATE_INCOME": rev_c, "OPERATE_COST": 0.6 * rev_c,
|
||||
"PARENT_NETPROFIT": np_c, "DEDUCT_PARENT_NETPROFIT": 0.9 * np_c,
|
||||
"TOTAL_PROFIT": 1.1 * np_c, "INVEST_INCOME": 0.05 * np_c,
|
||||
"FAIRVALUE_CHANGE_INCOME": 0.01 * np_c,
|
||||
"ASSET_IMPAIRMENT_LOSS": 0.02 * np_c, "CREDIT_IMPAIRMENT_LOSS": 0.01 * np_c})
|
||||
# IBD 只给 SHORT_LOAN 一列(其余组件列缺失,测 schema 缺列容错)
|
||||
balance_rows.append({**common,
|
||||
"TOTAL_ASSETS": s * TA_OF(i), "TOTAL_PARENT_EQUITY": s * EQ_OF(i),
|
||||
"ACCOUNTS_RECE": s * AR_OF(i), "OTHER_RECE": s * (5 + max(i - 4, 0)),
|
||||
"GOODWILL": 50.0, "SHARE_CAPITAL": float(SC_OF(i)),
|
||||
"SHORT_LOAN": s * (100 + max(i - 4, 0))})
|
||||
cashflow_rows.append({**common,
|
||||
"NETCASH_OPERATE": 1.2 * np_c, "SALES_SERVICES": 1.05 * rev_c,
|
||||
"ACCEPT_INVEST_CASH": 0.1 * rev_c})
|
||||
|
||||
for table, rows in (("income", income_rows), ("balance", balance_rows), ("cashflow", cashflow_rows)):
|
||||
pl.DataFrame(rows).write_parquet(
|
||||
os.path.join(static_dir, table, f"{file_code}_{table}.parquet"))
|
||||
|
||||
# forecast: 按报告期全市场文件(中文列,归母净利润行优先 + 无净利润行 fallback)
|
||||
os.makedirs(os.path.join(static_dir, "forecast"), exist_ok=True)
|
||||
pl.DataFrame([
|
||||
{"股票代码": "600000", "预测指标": "归属于上市公司股东的净利润",
|
||||
"业绩变动幅度": 56.79, "预告类型": "预增", "公告日期": date(2023, 7, 15)},
|
||||
{"股票代码": "000001", "预测指标": "归属于上市公司股东的净利润",
|
||||
"业绩变动幅度": -30.0, "预告类型": "预减", "公告日期": date(2023, 7, 20)},
|
||||
{"股票代码": "300001", "预测指标": "营业收入",
|
||||
"业绩变动幅度": 5.0, "预告类型": "略增", "公告日期": date(2023, 7, 10)},
|
||||
]).write_parquet(os.path.join(static_dir, "forecast", "20230630_forecast.parquet"))
|
||||
pl.DataFrame([
|
||||
{"股票代码": "600000", "预测指标": "净利润",
|
||||
"业绩变动幅度": 100.0, "预告类型": "扭亏", "公告日期": date(2023, 10, 15)},
|
||||
]).write_parquet(os.path.join(static_dir, "forecast", "20230930_forecast.parquet"))
|
||||
return static_dir
|
||||
|
||||
|
||||
import pytest
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def synthetic_static(tmp_path_factory) -> str:
|
||||
"""session 级合成静态域根目录(test_fundamental_* 共用)."""
|
||||
return build_synthetic_static(tmp_path_factory.mktemp("fund_static"))
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def np_q_series() -> list[float]:
|
||||
"""合成归母净利单季序列(SUE 期望值独立重算用)."""
|
||||
return list(NP_Q)
|
||||
|
||||
@@ -0,0 +1,197 @@
|
||||
# tests/factor/test_fundamental_adapter.py
|
||||
"""财务因子适配层:合成三表+forecast parquet → PIT 日频特征列.
|
||||
|
||||
核心口径红线(docs/fundamental_factor_survey_20260907.md §7):
|
||||
- 单季差分缺上期 → NaN 不填 0
|
||||
- PIT = NOTICE_DATE ≤ 决策日,NOTICE_DATE 缺失行整报告期跳过
|
||||
- TTM 不足连续 4 季 → NaN
|
||||
"""
|
||||
import sys, os
|
||||
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "..")))
|
||||
sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "..", "vnpy_v4.4.0")))
|
||||
|
||||
import pytest
|
||||
|
||||
from sanguo_factor.fundamental_adapter import build_fundamental_features, FEATURE_COLUMNS
|
||||
|
||||
A, B, C = "600000.SSE", "000001.SZSE", "300001.SZSE"
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def feat(synthetic_static):
|
||||
return build_fundamental_features(
|
||||
[A, B, C], "2023-01-01", "2023-12-31", data_dir=synthetic_static)
|
||||
|
||||
|
||||
def _dt(day: str):
|
||||
import datetime as _d
|
||||
return _d.datetime.strptime(day, "%Y-%m-%d")
|
||||
|
||||
|
||||
def val(df, vt: str, day: str, col: str):
|
||||
row = df.filter((df["vt_symbol"] == vt) & (df["datetime"] == _dt(day)))
|
||||
assert row.height == 1, f"grid 缺行 {vt} {day}"
|
||||
v = row[col][0]
|
||||
return None if v is None else float(v)
|
||||
|
||||
|
||||
# ---------- 单季差分(R1) ----------
|
||||
|
||||
def test_single_quarter_diff_and_q1_direct(feat):
|
||||
# 报告期级断言走 equity 之外的特征:用 grid 在披露日后取值
|
||||
# 2022H1 披露于 2022-08-29,2023 年窗口看不到;单季值通过 rev_q_yoy 间接锁
|
||||
# 直接锁:2023Q3 (i=10) rev_q_yoy = 170/150 - 1(单季差分链正确才可得)
|
||||
assert val(feat, A, "2023-10-27", "rev_q_yoy") == pytest.approx(170 / 150 - 1)
|
||||
|
||||
|
||||
def test_missing_prev_quarter_is_nan_not_zero(synthetic_static):
|
||||
# B 缺 2022Q1 → 2022Q2 单季差分 NaN;传染:TTM 至 2023Q1、yoy 至 2023H1 均 NaN
|
||||
df = build_fundamental_features([B], "2023-01-01", "2023-12-31", data_dir=synthetic_static)
|
||||
# 2023Q1(i=8) 报告期 TTM 窗含 2022Q2(差分 NaN) → np_ttm NaN
|
||||
assert val(df, B, "2023-04-28", "np_ttm") is None
|
||||
# 2023H1(i=9) yoy 基期 = 2022H1 单季 NaN → NaN
|
||||
assert val(df, B, "2023-08-29", "rev_q_yoy") is None
|
||||
# 窗口滑出坏点后恢复:2023Q3(i=10) 基期 2022Q3 单季=15 有效
|
||||
assert val(df, B, "2023-10-27", "rev_q_yoy") == pytest.approx(170 / 150 - 1)
|
||||
assert val(df, B, "2023-08-29", "np_ttm") == pytest.approx(60.0)
|
||||
|
||||
|
||||
def test_ttm_rolling_four_quarters(feat):
|
||||
# A 2023Q2 报告期(i=9): NP_TTM = 15+18+13+14 = 60(=上年年报580+H1−上年H1 交叉验证同值)
|
||||
assert val(feat, A, "2023-08-29", "np_ttm") == pytest.approx(60.0)
|
||||
# 年报 NOTICE=2024-04-25,2023 窗末 np_ttm 停留在 Q3 报告期(i=10): 18+13+14+17=62
|
||||
assert val(feat, A, "2023-12-31", "np_ttm") == pytest.approx(62.0)
|
||||
|
||||
|
||||
# ---------- PIT(R3):NOTICE_DATE 前不可见 ----------
|
||||
|
||||
def test_pit_no_lookahead(feat):
|
||||
# A 2023H1(报告期 06-30) NOTICE=08-29;equity 平衡表时点值 i=9→680, i=8→660
|
||||
assert val(feat, A, "2023-08-28", "equity") == pytest.approx(660.0)
|
||||
assert val(feat, A, "2023-08-29", "equity") == pytest.approx(680.0)
|
||||
|
||||
|
||||
def test_notice_date_null_period_skipped(feat):
|
||||
# B 2022Q3 NOTICE 缺失 → 整期跳过:2023-01-01 可见的最新披露 = 2022H1(i=5, EQ=600)
|
||||
assert val(feat, B, "2023-01-01", "equity") == pytest.approx(600.0)
|
||||
# 恢复:2022 年报(i=7) 2023-04-25 可见
|
||||
assert val(feat, B, "2023-04-25", "equity") == pytest.approx(640.0)
|
||||
|
||||
|
||||
def test_forward_fill_between_notices(feat):
|
||||
assert val(feat, A, "2023-09-15", "equity") == pytest.approx(680.0)
|
||||
assert val(feat, A, "2023-10-26", "equity") == pytest.approx(680.0)
|
||||
assert val(feat, A, "2023-10-27", "equity") == pytest.approx(700.0)
|
||||
# 年报 NOTICE=次年 04-25,2023 窗末仍是 Q3 值
|
||||
assert val(feat, A, "2023-12-31", "equity") == pytest.approx(700.0)
|
||||
|
||||
|
||||
# ---------- 报告期级指标公式 ----------
|
||||
|
||||
def test_profitability_ratios(feat):
|
||||
# A 2023H1(i=9): NP_TTM=60, EQ=680, TA=1450, CFO_TTM=72, GP_TTM=0.4*REV_TTM
|
||||
assert val(feat, A, "2023-08-29", "roe_ttm") == pytest.approx(60 / 680)
|
||||
assert val(feat, A, "2023-08-29", "roa_ttm") == pytest.approx(60 / 1450)
|
||||
assert val(feat, A, "2023-08-29", "cfo_over_assets") == pytest.approx(72 / 1450)
|
||||
assert val(feat, A, "2023-08-29", "gp_over_assets") == pytest.approx(240 / 1450)
|
||||
assert val(feat, A, "2023-08-29", "gross_margin") == pytest.approx(0.4, abs=1e-9)
|
||||
assert val(feat, A, "2023-08-29", "net_margin") == pytest.approx(60 / 600, rel=1e-6)
|
||||
assert val(feat, A, "2023-08-29", "roe_deduct_ttm") == pytest.approx(0.9 * 60 / 680)
|
||||
|
||||
|
||||
def test_quality_ratios(feat):
|
||||
assert val(feat, A, "2023-08-29", "tacc") == pytest.approx((60 - 72) / 1450)
|
||||
assert val(feat, A, "2023-08-29", "nonrec_ratio") == pytest.approx(6 / 60)
|
||||
# 减值 = abs(0.02+0.01)*NP_TTM / TA
|
||||
assert val(feat, A, "2023-08-29", "impairment_ratio") == pytest.approx(1.8 / 1450)
|
||||
# 投资收益依赖 = (0.05+0.01)*NP_TTM / abs(1.1*NP_TTM)
|
||||
assert val(feat, A, "2023-08-29", "invest_income_dep") == pytest.approx(0.06 / 1.1)
|
||||
assert val(feat, A, "2023-08-29", "sales_cash_ratio") == pytest.approx(1.05 * 600 / 600, rel=1e-6)
|
||||
assert val(feat, A, "2023-08-29", "other_rece_ratio") == pytest.approx((5 + 9) / 1450)
|
||||
# 应收异常 = AR同比 − REV_TTM 同比(2023H1 vs 2022H1; TTM 窗含 2022Q2..2023H1)
|
||||
ar_yoy = (100 + 90) / (100 + 50) - 1
|
||||
rev_ttm_yoy = 600 / (150 + 160 + 110 + 140) - 1
|
||||
assert val(feat, A, "2023-08-29", "receivables_anomaly") == pytest.approx(ar_yoy - rev_ttm_yoy)
|
||||
|
||||
|
||||
def test_growth_and_capital_features(feat):
|
||||
assert val(feat, A, "2023-08-29", "np_q_yoy") == pytest.approx(14 / 14 - 1)
|
||||
assert val(feat, A, "2023-10-27", "np_q_yoy") == pytest.approx(17 / 15 - 1)
|
||||
assert val(feat, A, "2023-08-29", "growth_scissors") == pytest.approx(0.0, abs=1e-9)
|
||||
assert val(feat, A, "2023-08-29", "gm_delta") == pytest.approx(0.0, abs=1e-9)
|
||||
# roe_delta = ROE(2023H1) − ROE(2022H1) = 60/680 − 56/600
|
||||
assert val(feat, A, "2023-08-29", "roe_delta") == pytest.approx(60 / 680 - 56 / 600)
|
||||
# 2023Q1(i=8): 资产增速 = 1400/1200−1; NSI = (110−100)/100
|
||||
assert val(feat, A, "2023-04-28", "asset_growth") == pytest.approx(1400 / 1200 - 1)
|
||||
assert val(feat, A, "2023-04-28", "nsi") == pytest.approx(0.1)
|
||||
# IBD = SHORT_LOAN 唯一组件(其余列缺失按 0) = 109 (i=9)
|
||||
assert val(feat, A, "2023-08-29", "ibd_ratio") == pytest.approx(109 / 1450)
|
||||
assert val(feat, A, "2023-08-29", "goodwill_ratio") == pytest.approx(50 / 1450)
|
||||
|
||||
|
||||
def test_sue_foster_standardization(feat, np_q_series):
|
||||
# 独立重算: diff4 = Q_t − Q_{t-4}, SUE = diff4 / std(过去 8 期 diff4, ddof=1)
|
||||
import statistics
|
||||
q = [float(x) for x in np_q_series] # 16 期序列,2020 为 SUE 滚动窗预热
|
||||
diff4 = [q[i] - q[i - 4] for i in range(4, 16)] # diff4[r] ↔ 报告期 r+4
|
||||
|
||||
def sue_at(rep_idx: int):
|
||||
r = rep_idx - 4
|
||||
if r < 7:
|
||||
return None
|
||||
win = diff4[r - 7:r + 1]
|
||||
return diff4[r] / statistics.stdev(win)
|
||||
|
||||
# 2023Q3(报告期 i=14, 披露 2023-10-27): 窗 diff4[3..10]
|
||||
assert val(feat, A, "2023-10-27", "sue_np") == pytest.approx(sue_at(14))
|
||||
# 前一日仍见 2023H1(i=13)
|
||||
assert val(feat, A, "2023-10-26", "sue_np") == pytest.approx(sue_at(13))
|
||||
# 2023Q4 披露在 2024-04-25,窗末仍是 Q3 值
|
||||
assert val(feat, A, "2023-12-31", "sue_np") == pytest.approx(sue_at(14))
|
||||
# 合成史 16 期 → i=11(2022Q4)起才有完整 8 期窗,更早报告期 SUE=NaN(间接受 PIT 保护)
|
||||
|
||||
|
||||
def test_forecast_event_features(feat):
|
||||
# A: 2023-07-15 预增(+3, 56.79);2023-10-15 扭亏(+2, 100.0)覆盖
|
||||
assert val(feat, A, "2023-07-14", "forecast_type_score") is None
|
||||
assert val(feat, A, "2023-07-15", "forecast_type_score") == 3.0
|
||||
assert val(feat, A, "2023-07-15", "forecast_change_pct") == pytest.approx(56.79)
|
||||
assert val(feat, A, "2023-10-14", "forecast_type_score") == 3.0
|
||||
assert val(feat, A, "2023-10-15", "forecast_type_score") == 2.0
|
||||
# B 预减(−3); C 无净利润行 fallback 营业收入行 略增(+2)
|
||||
assert val(feat, B, "2023-07-20", "forecast_type_score") == -3.0
|
||||
assert val(feat, B, "2023-07-20", "forecast_change_pct") == pytest.approx(-30.0)
|
||||
assert val(feat, C, "2023-07-10", "forecast_type_score") == 2.0
|
||||
|
||||
|
||||
# ---------- 结构与容错 ----------
|
||||
|
||||
def test_feature_columns_complete(feat):
|
||||
out_cols = set(feat.columns) - {"vt_symbol", "datetime"}
|
||||
assert out_cols == set(FEATURE_COLUMNS)
|
||||
assert feat.height > 0
|
||||
|
||||
|
||||
def test_missing_file_and_empty_rows_tolerated(synthetic_static):
|
||||
# 600999 无文件(退市股形态) → 行存在但特征全 null,不炸
|
||||
df = build_fundamental_features(["600999.SSE"], "2023-06-01", "2023-06-10",
|
||||
data_dir=synthetic_static)
|
||||
assert df.height > 0
|
||||
for col in FEATURE_COLUMNS:
|
||||
assert df[col].null_count() == df.height, f"{col} 应全 null"
|
||||
|
||||
|
||||
def test_trading_dates_grid(feat, synthetic_static):
|
||||
# 传入交易日子集 → grid 只含这些日期
|
||||
df = build_fundamental_features(
|
||||
[A], "2023-08-01", "2023-08-31", data_dir=synthetic_static,
|
||||
trading_dates=[_dt("2023-08-14"), _dt("2023-08-29")])
|
||||
assert df.height == 2
|
||||
assert val(df, A, "2023-08-14", "equity") == pytest.approx(660.0)
|
||||
assert val(df, A, "2023-08-29", "equity") == pytest.approx(680.0)
|
||||
|
||||
|
||||
def test_scale_two_stock(feat):
|
||||
# C(scale=2): TA=2*1450, NP_TTM=2*60 → roa 同 A(比率不变), np_ttm 翻倍
|
||||
assert val(feat, C, "2023-08-29", "roa_ttm") == pytest.approx(60 / 1450)
|
||||
assert val(feat, C, "2023-08-29", "np_ttm") == pytest.approx(120.0)
|
||||
Reference in New Issue
Block a user