From 8318aebb06789e17df00491adf2a4e55d22e7556 Mon Sep 17 00:00:00 2001
From: D-X-Y <280835372@qq.com>
Date: Sun, 7 Mar 2021 09:52:30 +0000
Subject: [PATCH] Add DoubleEnsemble

---
 ...rkflow_config_doubleensemble_Alpha360.yaml | 97 +++++++++++++++++++
 exps/trading/baselines.py                     |  3 +
 2 files changed, 100 insertions(+)
 create mode 100644 configs/qlib/workflow_config_doubleensemble_Alpha360.yaml

diff --git a/configs/qlib/workflow_config_doubleensemble_Alpha360.yaml b/configs/qlib/workflow_config_doubleensemble_Alpha360.yaml
new file mode 100644
index 0000000..8885a3d
--- /dev/null
+++ b/configs/qlib/workflow_config_doubleensemble_Alpha360.yaml
@@ -0,0 +1,97 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market all
+benchmark: &benchmark SH000300
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+    infer_processors: []
+    learn_processors:
+        - class: DropnaLabel
+        - class: CSRankNorm
+          kwargs:
+              fields_group: label
+    label: ["Ref($close, -2) / Ref($close, -1) - 1"]
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy.strategy
+        kwargs:
+            topk: 50
+            n_drop: 5
+    backtest:
+        verbose: False
+        limit_threshold: 0.095
+        account: 100000000
+        benchmark: *benchmark
+        deal_price: close
+        open_cost: 0.0005
+        close_cost: 0.0015
+        min_cost: 5
+task:
+    model:
+        class: DEnsembleModel
+        module_path: qlib.contrib.model.double_ensemble
+        kwargs:
+            base_model: "gbm"
+            loss: mse
+            num_models: 6
+            enable_sr: True
+            enable_fs: True
+            alpha1: 1
+            alpha2: 1
+            bins_sr: 10
+            bins_fs: 5
+            decay: 0.5
+            sample_ratios:
+                - 0.8
+                - 0.7
+                - 0.6
+                - 0.5
+                - 0.4
+            sub_weights:
+                - 1
+                - 0.2
+                - 0.2
+                - 0.2
+                - 0.2
+                - 0.2
+            epochs: 136
+            colsample_bytree: 0.8879
+            learning_rate: 0.0421
+            subsample: 0.8789
+            lambda_l1: 205.6999
+            lambda_l2: 580.9768
+            max_depth: 8
+            num_leaves: 210
+            num_threads: 20
+            verbosity: -1
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: Alpha360
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record:
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+            ana_long_short: False
+            ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+            config: *port_analysis_config
diff --git a/exps/trading/baselines.py b/exps/trading/baselines.py
index b91d085..679aede 100644
--- a/exps/trading/baselines.py
+++ b/exps/trading/baselines.py
@@ -8,6 +8,7 @@
 # python exps/trading/baselines.py --alg SFM        #
 # python exps/trading/baselines.py --alg XGBoost    #
 # python exps/trading/baselines.py --alg LightGBM   #
+# python exps/trading/baselines.py --alg DoubleE    #
 #####################################################
 import sys
 import argparse
@@ -46,6 +47,8 @@ def retrieve_configs():
     alg2names["LightGBM"] = "workflow_config_lightgbm_Alpha360.yaml"
     # State Frequency Memory (SFM): Stock Price Prediction via Discovering Multi-Frequency Trading Patterns, KDD-2017
     alg2names["SFM"] = "workflow_config_sfm_Alpha360.yaml"
+    # DoubleEnsemble: A New Ensemble Method Based on Sample Reweighting and Feature Selection for Financial Data Analysis, https://arxiv.org/pdf/2010.01265.pdf
+    alg2names["DoubleE"] = "workflow_config_doubleensemble_Alpha360.yaml"
 
     # find the yaml paths
     alg2paths = OrderedDict()