feat(factors): reproduce valley-relative-VWAP factor (PR-I, both assessed axes PASS → Watch)

config/phase_i_valley_relative_vwap.yaml

@@ -0,0 +1,150 @@
+# PR-I — Seventh real factor evaluation: VALLEY-RELATIVE VWAP.
+#
+# Reproduces the THIRD factor of the Kaiyuan market-microstructure series #27 (开源证券
+# 《高频成交量的峰、岭、谷信息——市场微观结构研究系列（27）》, reportId 4957417, §4) — the
+# "量谷相对加权价格因子" — as a first-class ValleyRelativeVwapFactor and runs it through the
+# FROZEN StandardFactorEvaluator on REAL cached A-share data. CACHE-ONLY: the minute read
+# is provably live-call-free; daily / universe / covariate endpoints go through the
+# read-through cache (warm -> 0 gap fetches).
+#
+# SAME MACHINE as PR-F / PR-H, DIFFERENT FAMILY. The minute classification is REUSED from
+# data/clean/intraday_volume_prv.py (not re-implemented): PIT-truncate each day at 14:50,
+# classify every visible minute against its SAME-SLOT strictly-prior 20-day baseline
+# (ERUPTIVE if vol > mu + sigma, else a VALLEY 量谷). Where PR-F counted the PEAKS and PR-H
+# measured their TIMING -- both null results -- this factor prices the VALLEYS: the daily
+# ratio (valley VWAP) / (whole visible day VWAP), averaged over the trailing 20 VALID days.
+# Because the classification is shared verbatim, a different verdict here cannot be an
+# artefact of a differently-implemented taxonomy.
+#
+# PINNED choices (disclosed on the factor spec):
+#   (1) each VWAP uses the aggregation identity sum(p*v)/sum(v) == sum(amount)/sum(volume),
+#       i.e. the day's REAL volume-weighted price rather than a close approximation;
+#   (2) bars with non-finite or non-positive volume OR amount are dropped from BOTH sums;
+#       the guard runs at the summation step only, so PR-F's same-slot baseline -- and
+#       therefore volume_peak_count / peak_interval_kurtosis -- is bit-identical;
+#   (3) RAW (unadjusted) prices are correct here: the adjustment factor is constant within
+#       a day and cancels exactly in the ratio (same reasoning as PR-D amplitude / I5b);
+#   (4) DEVIATION FROM THE REPORT, disclosed and NOT silently equated: our day VWAP spans
+#       the PIT-VISIBLE window 09:31-14:50 only, while the report uses the FULL day.
+#       Reading the closing auction would be lookahead at our 14:50 decision time;
+#   (5) a day is VALID iff it has >= 100 classifiable bars AND >= 20 TRADABLE valley bars
+#       (counted AFTER the positive-trade guard) AND positive volume in both denominators;
+#       NaN below 10 valid days in the trailing window (honest missing).
+#
+# Pre-registered sign = +1 (report full-market RankIC +8.69% / RankICIR 4.44, long-short
+# 25.35%/yr, IR 3.04, monthly win rate 79.7% -- the strongest factor in the report; CSI500
+# sub-domain long-short 9.94% / IR 1.26, the closest comparable to this cell). NOTE the
+# report is a MONTHLY, market-cap + industry neutral FULL-MARKET series on Wind data --
+# our eval cell is CSI500 daily with industry + size neutral, so those numbers are a LOOSE
+# reference only and are NOT written in as expected values. Raw minute volume (cached
+# as-is) has split-day magnitude jumps that pollute the 20-day sigma; the report (Wind)
+# does not adjust for this either, so it is disclosed and NOT corrected.
+#
+# Eval CELL is IDENTICAL to PR-C / PR-D / PR-E / PR-F / PR-G / PR-H: universe = CSI500
+# (000905.SH), PIT membership; window = 2021-07-01 .. 2026-06-30 (the project's
+# minute-coverage window); daily rebalance; OOS split 2024-01-01; book =
+# value_ep/value_bp/volatility_20; fee 0.001. The ONLY substantive difference is the
+# subject factor, which is minute-derived and computed by the runner from the intraday
+# cache -- it is NOT a config-listed daily factor. Because the cell matches PR-F / PR-H
+# exactly, this run is directly comparable to its siblings. The evaluator runs TWICE (see
+# qt/eval_valley_relative_vwap.py): once with NO book (Incremental NOT_ASSESSED) and once
+# with the confirmed book -- which matters more than usual here, since a relative PRICE
+# LEVEL is a plausible cousin of a value signal and the with-book run is what says whether
+# this is a genuinely new bet.
+
+project:
+  name: quantitative_trading_pr_i_valley_relative_vwap
+  timezone: Asia/Shanghai
+data:
+  source: tushare
+  freq: D
+  start: '2021-07-01'
+  end: '2026-06-30'
+  external_secret_file: /home/shaofl/Projects/financial_projects/.config.json
+  tushare_token_key: tushare.token
+  output_name: valley_relative_vwap_daily
+  cache:
+    enabled: true
+    root_dir: artifacts/cache/tushare/v1
+    refresh_recent_days: 14
+    refresh_dimension_days: 30
+    force_refresh: []
+universe:
+  type: index
+  index_code: 000905.SH
+  symbols: []
+  min_listing_days: 60
+  filters:
+    missing_close: true
+    suspended: false
+    st: false
+    limit_up_down: false
+# factors = the confirmed BOOK used for the Incremental axis (value + low-vol). The
+# SUBJECT factor (valley_relative_vwap_20) is minute-derived and computed by the runner
+# from the intraday cache -- it is NOT a config-listed daily factor.
+factors:
+- name: value_ep
+  enabled: true
+- name: value_bp
+  enabled: true
+- name: volatility_20
+  enabled: true
+  params:
+    window: 20
+    price_col: close
+processing:
+  drop_missing: true
+  standardize:
+    enabled: true
+    method: zscore
+  # winsorize is a P0 no-op in this codebase; the EvalConfig declares winsorize=None
+  # accordingly (nothing is clipped), so the report never overstates preprocessing.
+  winsorize:
+    enabled: false
+    method: mad
+    n: 3.0
+  # Industry + market-cap neutralization (SW-L1), matching the report's neutral column
+  # and the EvalConfig neutralization declaration.
+  neutralize:
+    enabled: true
+    industry_col: industry
+    size_col: market_cap
+    industry_level: L1
+alpha:
+  model: equal_weight
+  params: {}
+portfolio:
+  # Required by the schema but unused: this runner evaluates a factor, it does not
+  # build/execute a portfolio.
+  constructor: topn_equal_weight
+  top_n: 50
+  long_only: true
+  max_weight: null
+  turnover_cap: null
+backtest:
+  # Required by the schema but unused (no backtest is run). The EvalConfig uses a DAILY
+  # rebalance (contract default), independent of this field.
+  initial_nav: 1.0
+  rebalance: monthly
+  event_order: close_to_next_period
+  cash_return: 0.0
+cost:
+  fee_rate: 0.001
+  slippage_rate: 0.0
+  turnover_formula: l1
+analytics:
+  forward_return_periods:
+  - 1
+  quantiles: 5
+  benchmark: null
+# OOS split (window midpoint) so the OOS section runs and the Predictive axis can be
+# assessed (sign consistency across both holdout subperiods).
+oos:
+  split_date: '2024-01-01'
+output:
+  root_dir: artifacts
+  data_dir: artifacts/data
+  factor_dir: artifacts/factors
+  report_dir: artifacts/reports
+  log_dir: artifacts/logs
+  overwrite: true