feat(factors): reproduce volume peak-minute-count factor (PR-F, weak-positive Reject)

config/phase_f_volume_peak_count.yaml

@@ -0,0 +1,128 @@
+# PR-F — Fourth real factor evaluation: volume-peak-minute count.
+#
+# Reproduces 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) flagship "量峰分钟数因子" as a
+# first-class VolumePeakCountFactor 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).
+#
+# The subject factor works DIRECTLY on the 1min cache (no coarser resample): PIT-truncate
+# each day at 14:50, classify every visible minute against its SAME-SLOT strictly-prior
+# 20-day baseline (eruptive if vol > μ + σ else mild), mark the eruptive minutes whose
+# both 1-minute same-session neighbours are mild as PEAKS (ridge / session-boundary /
+# unclassifiable-neighbour minutes are not peaks), and count the peak minutes over the
+# trailing 20 VALID trading days (a day is valid iff it has >= 100 classifiable bars;
+# NaN below 10 valid days). Pre-registered sign = +1 (report IC positive: full-market
+# RankIC +10.62% / RankICIR 4.36, CSI500 sub-domain long-short +14.96%/yr). NOTE the
+# report is a MONTHLY, market-cap + industry neutral series on Wind data -- our eval cell
+# is CSI500 daily with industry + size neutral, so those numbers are a LOOSE reference
+# only. Raw minute volume (cached as-is) has split-day magnitude jumps that pollute the
+# 20-day σ; 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: 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. The evaluator runs TWICE (see qt/eval_volume_peak_count.py): once with NO book
+# (Incremental NOT_ASSESSED) and once with the confirmed book to measure whether the
+# volume-peak-count factor adds alpha BEYOND value / low-vol.
+
+project:
+  name: quantitative_trading_pr_f_volume_peak_count
+  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: volume_peak_count_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 (volume_peak_count_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