add test and mod doc

CHANGES.rst

@@ -150,3 +150,11 @@ Version 0.4.6
 - Some bugs are fixed
     - The default config in `Version 0.4.5` is not friendly to daily frequency data.
     - Backtest error in TopkWeightStrategy when `WithInteract=True`.
+
+
+Version 0.5.0
+--------------------
+- First opensource version
+    - Refine the docs, code
+    - Add baselines
+    - public data crawler

docs/component/data.rst

@@ -65,7 +65,7 @@ After conversion, users can find their Qlib format data in the directory `~/.qli
 
 .. note::
 
-    The arguments of `--include_fields` should correspond with the columns names of CSV files. The columns names of dataset provided by ``Qlib`` includes open,close,high,low,volume,factor.
+    The arguments of `--include_fields` should correspond with the columns names of CSV files. The columns names of dataset provided by ``Qlib`` should include open, close, high, low, volume and factor at least.
     
     - `open`
         The opening price
@@ -80,6 +80,7 @@ After conversion, users can find their Qlib format data in the directory `~/.qli
     - `factor`
         The Restoration factor
 
+    In the convention of `Qlib` data processing, `open, close, high, low, volume, money and factor` will be set to NaN if the stock is suspended. 
 
 China-Stock Mode & US-Stock Mode
 --------------------------------

qlib/config.py

@@ -120,7 +120,7 @@ _default_client_config = {
 _default_region_config = {
     REG_CN: {
         "trade_unit": 100,
-        "limit_threshold": 0.1,
+        "limit_threshold": 0.099,
         "deal_price": "vwap",
     },
     REG_US: {

qlib/contrib/backtest/exchange.py

@@ -149,7 +149,7 @@ class Exchange:
         self.quote = quote_df.to_dict("index")
 
     def _update_limit(self, buy_limit, sell_limit):
-        self.quote["limit"] = ~self.quote["$change"].between(-sell_limit, buy_limit)
+        self.quote["limit"] = ~self.quote["$change"].between(-sell_limit, buy_limit, inclusive=False)
 
     def check_stock_limit(self, stock_id, trade_date):
         """Parameter

tests/dataset_tests/README.md

@@ -0,0 +1,2 @@
+# About dataset tests
+This tests is for testing the prepared dataset from Yahoo

tests/dataset_tests/test_dataset.py

@@ -0,0 +1,32 @@
+
+import qlib
+from qlib.data import D
+from qlib.config import REG_CN
+import unittest
+import numpy as np
+
+
+class TestDataset(unittest.TestCase):
+
+    def setUp(self):
+        provider_uri = "~/.qlib/qlib_data/cn_data"  # target_dir
+        qlib.init(provider_uri=provider_uri, region=REG_CN)
+
+    def testCSI300(self):
+        close_p = D.features(D.instruments('csi300'), ['$close'])
+        size = close_p.groupby('datetime').size()
+        cnt = close_p.groupby('datetime').count()
+
+        print(size.describe(percentiles=np.arange(0.1, 0.9, 0.1)))
+        print(cnt.describe(percentiles=np.arange(0.1, 0.9, 0.1)))
+        # TODO: assert
+
+    def testClose(self):
+        close_p = D.features(D.instruments('csi300'), ['Ref($close, 1)/$close - 1'])
+        print(close_p.describe(percentiles=np.arange(0.1, 0.9, 0.1)))
+        # TODO: assert
+
+
+if __name__ == '__main__':
+    unittest.main()
+