Merge pull request #358 from javaThonc/high_freq_demp

update high freq demo

examples/benchmarks/README.md

@@ -17,6 +17,7 @@ The numbers shown below demonstrate the performance of the entire `workflow` of
 | ALSTM (Yao Qin, et al.) | Alpha360 | 0.0493±0.01 | 0.3778±0.06| 0.0585±0.00 | 0.4606±0.04 | 0.0513±0.03 | 0.6727±0.38| -0.1085±0.02 |
 | GATs (Petar Velickovic, et al.) | Alpha360 | 0.0475±0.00 | 0.3515±0.02| 0.0592±0.00 | 0.4585±0.01 | 0.0876±0.02 | 1.1513±0.27| -0.0795±0.02 |
 | DoubleEnsemble (Chuheng Zhang, et al.) | Alpha360 | 0.0407±0.00| 0.3053±0.00 | 0.0490±0.00 | 0.3840±0.00 | 0.0380±0.02 | 0.5000±0.21 | -0.0984±0.02 |
+| TabNet (Sercan O. Arik, et al.)| Alpha360 | 0.0192±0.00 | 0.1401±0.00| 0.0291±0.00 | 0.2163±0.00 | -0.0258±0.00 | -0.2961±0.00| -0.1429±0.00 |
 
 ## Alpha158 dataset
 | Model Name | Dataset | IC | ICIR | Rank IC | Rank ICIR | Annualized Return | Information Ratio | Max Drawdown |
@@ -32,6 +33,7 @@ The numbers shown below demonstrate the performance of the entire `workflow` of
 | ALSTM (Yao Qin, et al.) | Alpha158 (with selected 20 features) | 0.0385±0.01 | 0.3022±0.06| 0.0478±0.00 | 0.3874±0.04 | 0.0486±0.03 | 0.7141±0.45| -0.1088±0.03 |
 | GATs (Petar Velickovic, et al.) | Alpha158 (with selected 20 features) | 0.0349±0.00 | 0.2511±0.01| 0.0457±0.00 | 0.3537±0.01 | 0.0578±0.02 | 0.8221±0.25| -0.0824±0.02 |
 | DoubleEnsemble (Chuheng Zhang, et al.) | Alpha158 | 0.0544±0.00 | 0.4338±0.01 | 0.0523±0.00 | 0.4257±0.01 | 0.1253±0.01 | 1.4105±0.14 | -0.0902±0.01 |
+| TabNet (Sercan O. Arik, et al.)| Alpha158 | 0.0383±0.00 | 0.3414±0.00| 0.0388±0.00 | 0.3460±0.00 | 0.0226±0.00 | 0.2652±0.00| -0.1072±0.00 |
 
 - The selected 20 features are based on the feature importance of a lightgbm-based model.
 - The base model of DoubleEnsemble is LGBM.

examples/highfreq/README.md

@@ -25,4 +25,11 @@ The example is given in `workflow.py`, users can run the code as follows.
 Run the example by running the following command:
 ```bash
     python workflow.py dump_and_load_dataset
-```
+```
+
+## Benchmarks Performance
+### Signal Test
+Here are the results of signal test for benchmark models. We will keep updating benchmark models in future.
+| Model Name | Dataset | IC | ICIR | Rank IC | Rank ICIR | Long precision| Short Precision | Long-Short Average Return | Long-Short Average Sharpe |
+|---|---|---|---|---|---|---|---|---|---|
+| LightGBM | Alpha158 | 0.3042±0.00 | 1.5372±0.00| 0.3117±0.00 | 1.6258±0.00 | 0.6720±0.00 | 0.6870±0.00 | 0.000769±0.00 | 1.0190±0.00 |

examples/highfreq/workflow_config_High_Freq_Tree_Alpha158.yaml

@@ -0,0 +1,65 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data_1min"
+    region: cn
+market: &market 'csi300'
+start_time: &start_time "2020-09-15 00:00:00"
+end_time: &end_time "2021-01-18 16:00:00"
+train_end_time: &train_end_time "2020-11-15 16:00:00"
+valid_start_time: &valid_start_time "2020-11-16 00:00:00"
+valid_end_time: &valid_end_time "2020-11-30 16:00:00"
+test_start_time: &test_start_time "2020-12-01 00:00:00"
+data_handler_config: &data_handler_config
+    start_time: *start_time
+    end_time: *end_time
+    fit_start_time: *start_time
+    fit_end_time: *train_end_time
+    instruments: *market
+    freq: '1min'
+    infer_processors:
+        - class: 'RobustZScoreNorm'
+          kwargs:
+              fields_group: 'feature'
+              clip_outlier: false
+        - class: "Fillna"
+          kwargs:
+              fields_group: 'feature'
+    learn_processors:
+        - class: 'DropnaLabel'
+        - class: 'CSRankNorm'
+          kwargs:
+              fields_group: 'label'
+    label: ["Ref($close, -2) / Ref($close, -1) - 1"]
+    
+task:
+    model:
+        class: "HFLGBModel"
+        module_path: "qlib.contrib.model.highfreq_gdbt_model"
+        kwargs:
+            objective: 'binary'
+            metric: ['binary_logloss','auc']
+            verbosity: -1
+            learning_rate: 0.01
+            max_depth: 8
+            num_leaves: 150
+            lambda_l1: 1.5
+            lambda_l2: 1
+            num_threads: 20
+    dataset:
+        class: "DatasetH"
+        module_path: "qlib.data.dataset"
+        kwargs:
+            handler:
+                class: "Alpha158"
+                module_path: "qlib.contrib.data.handler"
+                kwargs: *data_handler_config
+            segments:
+                train: [*start_time, *train_end_time]
+                valid: [*train_end_time, *valid_end_time]
+                test: [*test_start_time, *end_time]
+    record: 
+        - class: "SignalRecord"
+          module_path: "qlib.workflow.record_temp"
+          kwargs: {}
+        - class: "HFSignalRecord"
+          module_path: "qlib.workflow.record_temp"
+          kwargs: {}