modify the default value of exists_skip in the GetData.qlib_data parameter to False

Author: zhupr

examples/highfreq/workflow.py

@@ -85,7 +85,7 @@ def _init_qlib(self):
         # use yahoo_cn_1min data
         QLIB_INIT_CONFIG = {**HIGH_FREQ_CONFIG, **self.SPEC_CONF}
         provider_uri = QLIB_INIT_CONFIG.get("provider_uri")
-        GetData().qlib_data(target_dir=provider_uri, interval="1min", region=REG_CN)
+        GetData().qlib_data(target_dir=provider_uri, interval="1min", region=REG_CN, exists_skip=True)
         qlib.init(**QLIB_INIT_CONFIG)
 
     def _prepare_calender_cache(self):

examples/hyperparameter/LightGBM/hyperparameter_158.py

@@ -37,7 +37,7 @@ def objective(trial):
 if __name__ == "__main__":
 
     provider_uri = "~/.qlib/qlib_data/cn_data"
-    GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
+    GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
     qlib.init(provider_uri=provider_uri, region="cn")
 
     dataset = init_instance_by_config(CSI300_DATASET_CONFIG)

examples/hyperparameter/LightGBM/hyperparameter_360.py

@@ -40,7 +40,7 @@ def objective(trial):
 if __name__ == "__main__":
 
     provider_uri = "~/.qlib/qlib_data/cn_data"
-    GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
+    GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
     qlib.init(provider_uri=provider_uri, region=REG_CN)
 
     dataset = init_instance_by_config(DATASET_CONFIG)

examples/model_interpreter/feature.py

@@ -14,7 +14,7 @@
 
     # use default data
     provider_uri = "~/.qlib/qlib_data/cn_data"  # target_dir
-    GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
+    GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
 
     qlib.init(provider_uri=provider_uri, region=REG_CN)
 

examples/rolling_process_data/workflow.py

@@ -23,7 +23,7 @@ def _init_qlib(self):
         """initialize qlib"""
         # use yahoo_cn_1min data
         provider_uri = "~/.qlib/qlib_data/cn_data"  # target_dir
-        GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
+        GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
         qlib.init(provider_uri=provider_uri, region=REG_CN)
 
     def _dump_pre_handler(self, path):

examples/run_all_model.py

@@ -37,7 +37,7 @@
     },
 }
 
-GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
+GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
 qlib.init(provider_uri=provider_uri, region=REG_CN, exp_manager=exp_manager)
 
 # decorator to check the arguments

examples/workflow_by_code.py

@@ -14,7 +14,7 @@
 
     # use default data
     provider_uri = "~/.qlib/qlib_data/cn_data"  # target_dir
-    GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
+    GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
     qlib.init(provider_uri=provider_uri, region=REG_CN)
 
     port_analysis_config = {

qlib/tests/__init__.py

@@ -19,5 +19,6 @@ def setUpClass(cls) -> None:
             interval="1d",
             target_dir=cls.provider_uri,
             delete_old=False,
+            exists_skip=True,
         )
         init(provider_uri=cls.provider_uri, region=REG_CN, **cls._setup_kwargs)

qlib/tests/data.py

@@ -113,7 +113,7 @@ def qlib_data(
         interval="1d",
         region="cn",
         delete_old=True,
-        exists_skip=True,
+        exists_skip=False,
     ):
         """download cn qlib data from remote
 
@@ -132,7 +132,7 @@ def qlib_data(
         delete_old: bool
             delete an existing directory, by default True
         exists_skip: bool
-            exists skip, by default True
+            exists skip, by default False
 
         Examples
         ---------
@@ -145,6 +145,10 @@ def qlib_data(
 
         """
         if exists_skip and exists_qlib_data(target_dir):
+            logger.warning(
+                f"Data already exists: {target_dir}, the data download will be skipped\n"
+                f"\tIf downloading is required: `exists_skip=False` or `change target_dir`"
+            )
             return
 
         qlib_version = ".".join(re.findall(r"(\d+)\.+", qlib.__version__))

tests/test_get_data.py

@@ -34,7 +34,9 @@ def tearDownClass(cls) -> None:
 
     def test_0_qlib_data(self):
 
-        GetData().qlib_data(name="qlib_data_simple", target_dir=QLIB_DIR, region="cn", interval="1d", delete_old=False)
+        GetData().qlib_data(
+            name="qlib_data_simple", target_dir=QLIB_DIR, region="cn", interval="1d", delete_old=False, exists_skip=True
+        )
         df = D.features(D.instruments("csi300"), self.FIELDS)
         self.assertListEqual(list(df.columns), self.FIELDS, "get qlib data failed")
         self.assertFalse(df.dropna().empty, "get qlib data failed")