Merge pull request #319 from Derek-Wds/main

Update Filter doc

docs/component/data.rst

@@ -218,6 +218,25 @@ Filter
     - `cross-sectional features filter` \: rule_expression = '$rank($close)<10'
     - `time-sequence features filter`: rule_expression = '$Ref($close, 3)>100'
 
+Here is a simple example showing how to use filter in a basic ``Qlib`` workflow configuration file:
+
+.. code-block:: yaml
+
+    filter: &filter
+        filter_type: ExpressionDFilter
+        rule_expression: "Ref($close, -2) / Ref($close, -1) > 1"
+        filter_start_time: 2010-01-01
+        filter_end_time: 2010-01-07
+        keep: False
+
+    data_handler_config: &data_handler_config
+        start_time: 2010-01-01
+        end_time: 2021-01-22
+        fit_start_time: 2010-01-01
+        fit_end_time: 2015-12-31
+        instruments: *market
+        filter_pipe: [*filter]
+
 To know more about ``Filter``, please refer to `Filter API <../reference/api.html#module-qlib.data.filter>`_.
 
 Reference

qlib/data/dataset/__init__.py

@@ -413,7 +413,7 @@ class TSDataSampler:
         # 1) for better performance, use the last nan line for padding the lost date
         # 2) In case of precision problems. We use np.float64. # TODO: I'm not sure if whether np.float64 will result in
         # precision problems. It will not cause any problems in my tests at least
-        indices = np.nan_to_num(indices.astype(np.float64), nan=self.nan_idx).astype(np.int)
+        indices = np.nan_to_num(indices.astype(np.float64), nan=self.nan_idx).astype(int)
 
         data = self.data_arr[indices]
         if isinstance(idx, mtit):

qlib/utils/__init__.py

@@ -64,7 +64,7 @@ def np_ffill(arr: np.array):
     arr : np.array
         Input numpy 1D array
     """
-    mask = np.isnan(arr.astype(np.float))  # np.isnan only works on np.float
+    mask = np.isnan(arr.astype(float))  # np.isnan only works on np.float
     # get fill index
     idx = np.where(~mask, np.arange(mask.shape[0]), 0)
     np.maximum.accumulate(idx, out=idx)