add test/config.py

examples/workflow_by_code.py

@@ -1,82 +1,22 @@
 #  Copyright (c) Microsoft Corporation.
 #  Licensed under the MIT License.
 
-import sys
-from pathlib import Path
-
 import qlib
-import pandas as pd
 from qlib.config import REG_CN
-from qlib.contrib.model.gbdt import LGBModel
-from qlib.contrib.data.handler import Alpha158
-from qlib.contrib.strategy.strategy import TopkDropoutStrategy
-from qlib.contrib.evaluate import (
-    backtest as normal_backtest,
-    risk_analysis,
-)
-from qlib.utils import exists_qlib_data, init_instance_by_config, flatten_dict
+from qlib.utils import init_instance_by_config, flatten_dict
 from qlib.workflow import R
 from qlib.workflow.record_temp import SignalRecord, PortAnaRecord
 from qlib.tests.data import GetData
+from qlib.tests.config import CSI300_BENCH, CSI300_GBDT_TASK
+
 
 if __name__ == "__main__":
 
     # use default data
     provider_uri = "~/.qlib/qlib_data/cn_data"  # target_dir
-    if not exists_qlib_data(provider_uri):
-        print(f"Qlib data is not found in {provider_uri}")
-        GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
-
+    GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
     qlib.init(provider_uri=provider_uri, region=REG_CN)
 
-    market = "csi300"
-    benchmark = "SH000300"
-
-    ###################################
-    # train model
-    ###################################
-    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,
-    }
-
-    task = {
-        "model": {
-            "class": "LGBModel",
-            "module_path": "qlib.contrib.model.gbdt",
-            "kwargs": {
-                "loss": "mse",
-                "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,
-            },
-        },
-        "dataset": {
-            "class": "DatasetH",
-            "module_path": "qlib.data.dataset",
-            "kwargs": {
-                "handler": {
-                    "class": "Alpha158",
-                    "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"),
-                },
-            },
-        },
-    }
-
     port_analysis_config = {
         "strategy": {
             "class": "TopkDropoutStrategy",
@@ -90,7 +30,7 @@ if __name__ == "__main__":
             "verbose": False,
             "limit_threshold": 0.095,
             "account": 100000000,
-            "benchmark": benchmark,
+            "benchmark": CSI300_BENCH,
             "deal_price": "close",
             "open_cost": 0.0005,
             "close_cost": 0.0015,
@@ -100,8 +40,8 @@ if __name__ == "__main__":
     }
 
     # model initialization
-    model = init_instance_by_config(task["model"])
-    dataset = init_instance_by_config(task["dataset"])
+    model = init_instance_by_config(CSI300_GBDT_TASK["model"])
+    dataset = init_instance_by_config(CSI300_GBDT_TASK["dataset"])
 
     # NOTE: This line is optional
     # It demonstrates that the dataset can be used standalone.
@@ -110,7 +50,7 @@ if __name__ == "__main__":
 
     # start exp
     with R.start(experiment_name="workflow"):
-        R.log_params(**flatten_dict(task))
+        R.log_params(**flatten_dict(CSI300_GBDT_TASK))
         model.fit(dataset)
         R.save_objects(**{"params.pkl": model})