book: scaffold + ch00 (execution trail as spine) — evidence exp 8-31, round 3

2026-08-18 22:35:23 +00:00
commit c93424e76c
83 changed files with 17676 additions and 0 deletions
@@ -0,0 +1,113 @@
+# -----------------------------------------------------------------------------
+# RankIC early-stop workflow — minimal example wiring the custom model.
+#
+# model_rank_gbdt.py must be importable: copy it (or symlink) into
+# tac_qlib/contrib/model/ and sync to /opt/venv site-packages (see SKILL.md
+# "Installed package copy" gotcha). Then run:
+#
+#   rd_run_workflow config_path=examples/workflow_rankic.yaml \
+#       experiment_name=tac-rd-rankic
+# -----------------------------------------------------------------------------
+{%- set LAKE = TAC_LAKE_DIR %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs: { lake_root: "{{ LAKE }}", market: US }
+
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-rankic" }
+
+task:
+    model:
+        # Custom model — see examples/model_rank_gbdt.py (RankICLGBModel):
+        # per-day query groups + feval=rankic + metric='None' so early-stopping
+        # tracks mean per-day Spearman instead of l2.
+        class: RankICLGBModel
+        module_path: tac_qlib.contrib.model.rank_gbdt
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 15
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l1: 0.0
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            seed: 2026
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: AAPL,MSFT,QQQ,IVV,SMH,TLT
+                    start_time: 2026-03-01
+                    end_time: 2026-08-06
+                    fit_start_time: 2026-03-01
+                    fit_end_time: 2026-05-31
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    infer_processors:
+                        - { class: DropAllNaN, kwargs: {} }
+                        - { class: ProcessInf, kwargs: {} }
+                        - { class: CSRankNorm, kwargs: {} }
+                        - { class: ZScoreNorm, kwargs: {} }
+                        - { class: Fillna, kwargs: {} }
+            segments:
+                train: [2026-03-01, 2026-05-31]
+                valid: [2026-06-01, 2026-06-30]
+                test:  [2026-07-01, 2026-08-06]
+
+    record:
+        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: { ana_long_short: true, ann_scaler: 252 }
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: TopkDropoutStrategy
+                      module_path: qlib.contrib.strategy
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 2
+                          n_drop: 1
+                          only_tradable: true
+                          risk_degree: 0.95
+                  backtest:
+                      start_time: 2026-07-01
+                      end_time: 2026-08-06
+                      account: 1000000
+                      benchmark: QQQ
+                      exchange_kwargs:
+                          codes: AAPL,MSFT,QQQ,IVV,SMH,TLT
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d