Normal mod

examples/benchmarks_dynamic/DDG-DA/workflow.py

@@ -1,5 +1,6 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.
+import os
 from pathlib import Path
 from typing import Union
 
@@ -35,6 +36,10 @@ def __init__(self, conf_path: Union[str, Path] = DEFAULT_CONF, horizon=20, **kwa
 
 
 if __name__ == "__main__":
-    GetData().qlib_data(exists_skip=True)
-    auto_init()
+    kwargs = {}
+    if os.environ.get("PROVIDER_URI", "") == "":
+        GetData().qlib_data(exists_skip=True)
+    else:
+        kwargs["provider_uri"] = os.environ["PROVIDER_URI"]
+    auto_init(**kwargs)
     fire.Fire(DDGDABench)

examples/benchmarks_dynamic/baseline/rolling_benchmark.py

@@ -1,5 +1,6 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.
+import os
 from pathlib import Path
 from typing import Union
 
@@ -31,6 +32,10 @@ def __init__(self, conf_path: Union[str, Path] = DEFAULT_CONF, horizon=20, **kwa
 
 
 if __name__ == "__main__":
-    GetData().qlib_data(exists_skip=True)
-    auto_init()
+    kwargs = {}
+    if os.environ.get("PROVIDER_URI", "") == "":
+        GetData().qlib_data(exists_skip=True)
+    else:
+        kwargs["provider_uri"] = os.environ["PROVIDER_URI"]
+    auto_init(**kwargs)
     fire.Fire(RollingBenchmark)

qlib/contrib/meta/data_selection/dataset.py

@@ -243,7 +243,7 @@ def __init__(
         trunc_days: int = None,
         rolling_ext_days: int = 0,
         exp_name: Union[str, InternalData],
-        segments: Union[Dict[Text, Tuple], float],
+        segments: Union[Dict[Text, Tuple], float, str],
         hist_step_n: int = 10,
         task_mode: str = MetaTask.PROC_MODE_FULL,
         fill_method: str = "max",
@@ -271,12 +271,16 @@ def __init__(
             - str: the name of the experiment to store the performance of data
             - InternalData: a prepared internal data
         segments: Union[Dict[Text, Tuple], float]
-            the segments to divide data
-            both left and right
+            if the segment is a Dict
+                the segments to divide data
+                both left and right are included
             if segments is a float:
                 the float represents the percentage of data for training
+            if segments is a string:
+                it will try its best to put its data in training and ensure that the date `segments` is in the test set
         hist_step_n: int
             length of historical steps for the meta infomation
+            Number of steps of the data similarity information
         task_mode : str
             Please refer to the docs of MetaTask
         """
@@ -383,10 +387,30 @@ def _prepare_seg(self, segment: Text) -> List[MetaTask]:
         if isinstance(self.segments, float):
             train_task_n = int(len(self.meta_task_l) * self.segments)
             if segment == "train":
-                return self.meta_task_l[:train_task_n]
+                train_tasks = self.meta_task_l[:train_task_n]
+                get_module_logger("MetaDatasetDS").info(f"The first train meta task: {train_tasks[0]}")   
+                return train_tasks
             elif segment == "test":
-                return self.meta_task_l[train_task_n:]
+                test_tasks = self.meta_task_l[train_task_n:]
+                get_module_logger("MetaDatasetDS").info(f"The first test meta task: {test_tasks[0]}")   
+                return test_tasks
             else:
                 raise NotImplementedError(f"This type of input is not supported")
+        elif isinstance(self.segments, str):
+            train_tasks = []
+            test_tasks = []
+            for t in self.meta_task_l:
+                test_end = t.task["dataset"]["kwargs"]["segments"]["test"][1]
+                if test_end is None or pd.Timestamp(test_end) < pd.Timestamp(self.segments):
+                    train_tasks.append(t)
+                else:
+                    test_tasks.append(t)
+            get_module_logger("MetaDatasetDS").info(f"The first train meta task: {train_tasks[0]}")   
+            get_module_logger("MetaDatasetDS").info(f"The first test meta task: {test_tasks[0]}")   
+            if segment == "train":
+                return train_tasks
+            elif segment == "test":
+                return test_tasks
+            raise NotImplementedError(f"This type of input is not supported")
         else:
             raise NotImplementedError(f"This type of input is not supported")

qlib/contrib/meta/data_selection/model.py

@@ -53,7 +53,12 @@ def __init__(
         max_epoch=100,
         seed=43,
         alpha=0.0,
+        loss_skip_thresh=50,
     ):
+        """
+        loss_skip_size: int
+            The number of threshold to skip the loss calculation for each day.
+        """
         self.step = step
         self.hist_step_n = hist_step_n
         self.clip_method = clip_method
@@ -63,6 +68,7 @@ def __init__(
         self.max_epoch = max_epoch
         self.fitted = False
         self.alpha = alpha
+        self.loss_skip_thresh = loss_skip_thresh
         torch.manual_seed(seed)
 
     def run_epoch(self, phase, task_list, epoch, opt, loss_l, ignore_weight=False):
@@ -88,12 +94,14 @@ def run_epoch(self, phase, task_list, epoch, opt, loss_l, ignore_weight=False):
                 criterion = nn.MSELoss()
                 loss = criterion(pred, meta_input["y_test"])
             elif self.criterion == "ic_loss":
-                criterion = ICLoss()
+                criterion = ICLoss(self.loss_skip_thresh)
                 try:
-                    loss = criterion(pred, meta_input["y_test"], meta_input["test_idx"], skip_size=50)
+                    loss = criterion(pred, meta_input["y_test"], meta_input["test_idx"])
                 except ValueError as e:
                     get_module_logger("MetaModelDS").warning(f"Exception `{e}` when calculating IC loss")
                     continue
+            else:
+                raise ValueError(f"Unknown criterion: {self.criterion}")
 
             assert not np.isnan(loss.detach().item()), "NaN loss!"
 

qlib/contrib/meta/data_selection/utils.py

@@ -10,7 +10,11 @@
 
 
 class ICLoss(nn.Module):
-    def forward(self, pred, y, idx, skip_size=50):
+    def __init__(self, skip_size=50):
+        super().__init__()
+        self.skip_size = skip_size
+
+    def forward(self, pred, y, idx):
         """forward.
         FIXME:
         - Some times it will be a slightly different from the result from `pandas.corr()`
@@ -33,7 +37,7 @@ def forward(self, pred, y, idx, skip_size=50):
         skip_n = 0
         for start_i, end_i in zip(diff_point, diff_point[1:]):
             pred_focus = pred[start_i:end_i]  # TODO: just for fake
-            if pred_focus.shape[0] < skip_size:
+            if pred_focus.shape[0] < self.skip_size:
                 # skip some days which have very small amount of stock.
                 skip_n += 1
                 continue
@@ -50,6 +54,7 @@ def forward(self, pred, y, idx, skip_size=50):
             )
             ic_all += ic_day
         if len(diff_point) - 1 - skip_n <= 0:
+            __import__('ipdb').set_trace()
             raise ValueError("No enough data for calculating IC")
         if skip_n > 0:
             get_module_logger("ICLoss").info(

qlib/contrib/model/linear.py

@@ -63,6 +63,7 @@ def fit(self, dataset: DatasetH, reweighter: Reweighter = None):
                 df_train = pd.concat([df_train, df_valid])
             except KeyError:
                 get_module_logger("LinearModel").info("include_valid=True, but valid does not exist")
+        df_train = df_train.dropna()
         if df_train.empty:
             raise ValueError("Empty data from dataset, please check your dataset config.")
         if reweighter is not None: