Merge pull request #416 from zhupr/configurable_dataset

Add configurable dataset to examples

examples/benchmarks/LightGBM/workflow_config_lightgbm_configurable_dataset.yaml

@@ -0,0 +1,81 @@
+qlib_init:
+    provider_uri: "~/.qlib/qlib_data/cn_data"
+    region: cn
+market: &market csi300
+benchmark: &benchmark SH000300
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    instruments: *market
+    data_loader:
+        class: QlibDataLoader
+        kwargs:
+            config:
+                feature:
+                    - ["Resi($close, 15)/$close", "Std(Abs($close/Ref($close, 1)-1)*$volume, 5)/(Mean(Abs($close/Ref($close, 1)-1)*$volume, 5)+1e-12)", "Rsquare($close, 5)", "($high-$low)/$open", "Rsquare($close, 10)", "Corr($close, Log($volume+1), 5)", "Corr($close/Ref($close,1), Log($volume/Ref($volume, 1)+1), 5)", "Corr($close, Log($volume+1), 10)", "Rsquare($close, 20)", "Corr($close/Ref($close,1), Log($volume/Ref($volume, 1)+1), 60)", "Corr($close/Ref($close,1), Log($volume/Ref($volume, 1)+1), 10)", "Corr($close, Log($volume+1), 20)", "(Less($open, $close)-$low)/$open"]
+                    - ["RESI5", "WVMA5", "RSQR5", "KLEN", "RSQR10", "CORR5", "CORD5", "CORR10", "RSQR20", "CORD60", "CORD10", "CORR20", "KLOW"]
+                label:
+                    - ["Ref($close, -2)/Ref($close, -1) - 1"]
+                    - ["LABEL0"]
+            freq: day
+
+    learn_processors:
+        - class: DropnaLabel
+        - class: CSZScoreNorm
+          kwargs:
+            fields_group: label
+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: LGBModel
+        module_path: qlib.contrib.model.gbdt
+        kwargs:
+            loss: mse
+            colsample_bytree: 0.8879
+            learning_rate: 0.2
+            subsample: 0.8789
+            lambda_l1: 205.6999
+            lambda_l2: 580.9768
+            max_depth: 8
+            num_leaves: 210
+            num_threads: 20
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: DataHandlerLP
+                module_path: qlib.data.dataset.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

qlib/data/dataset/handler.py

@@ -58,7 +58,7 @@ class DataHandler(Serializable):
         instruments=None,
         start_time=None,
         end_time=None,
-        data_loader: Tuple[dict, str, DataLoader] = None,
+        data_loader: Union[dict, str, DataLoader] = None,
         init_data=True,
         fetch_orig=True,
     ):
@@ -71,7 +71,7 @@ class DataHandler(Serializable):
             start_time of the original data.
         end_time :
             end_time of the original data.
-        data_loader : Tuple[dict, str, DataLoader]
+        data_loader : Union[dict, str, DataLoader]
             data loader to load the data.
         init_data :
             intialize the original data in the constructor.
@@ -282,7 +282,7 @@ class DataHandlerLP(DataHandler):
         instruments=None,
         start_time=None,
         end_time=None,
-        data_loader: Tuple[dict, str, DataLoader] = None,
+        data_loader: Union[dict, str, DataLoader] = None,
         infer_processors=[],
         learn_processors=[],
         process_type=PTYPE_A,