update docs and code

.gitignore

@@ -2,9 +2,12 @@
 __pycache__/
 
 *.pyc
+*.so
 *.ipynb
 .ipynb_checkpoints
 _build
+build/
+dist/
 
 
 *.pkl
@@ -16,6 +19,9 @@ _build
 .nvimrc
 .vscode
 
+qlib/data/_libs/expanding.cpp
+qlib/data/_libs/rolling.cpp
+examples/estimator/estimator_example/
 
 *.egg-info/
 

docs/component/backtest.rst

@@ -20,16 +20,16 @@ Example
 ===========================
 
 Users need to generate a prediction score(a pandas DataFrame) with MultiIndex<instrument, datetime> and a `score` column. And users need to assign a strategy used in backtest, if strategy is not assigned,
-a `TopkAmountStrategy` strategy with `(topk=20, buffer_margin=150, risk_degree=0.95, limit_threshold=0.0095)` will be used.
-If ``Strategy`` module is not user's interested part, `TopkAmountStrategy` is enough. 
+a `TopkDropoutStrategy` strategy with `(topk=50, n_drop=5, risk_degree=0.95, limit_threshold=0.0095)` will be used.
+If ``Strategy`` module is not user's interested part, `TopkDropoutStrategy` is enough. 
 
 The simple example with default strategy is as follows.
 
 .. code-block:: python
 
     from qlib.contrib.evaluate import backtest
     # pred_score is the prediction score
-    report, positions = backtest(pred_score, topk=50, margin=0.5, verbose=False, limit_threshold=0.0095)
+    report, positions = backtest(pred_score, topk=50, n_drop=0.5, verbose=False, limit_threshold=0.0095)
 
 To know more about backtesting with specific strategy, please refer to `Strategy <strategy.html>`_.
 

docs/component/estimator.rst

@@ -71,10 +71,10 @@ First, Write a simple configuration file as following,
         test_start_date: 2017-01-01
         test_end_date: 2020-08-01
     strategy:
-      class: TopkAmountStrategy
+      class: TopkDropoutStrategy
       args:
         topk: 50
-        buffer_margin: 230
+        n_drop: 5
     backtest:
       normal_backtest_args:
         verbose: False
@@ -473,13 +473,13 @@ Users can specify strategy through a config file, for example:
 .. code-block:: YAML
 
     strategy :
-        class: TopkAmountStrategy
+        class: TopkDropoutStrategy
         args:
             topk: 50
-            buffer_margin: 300
+            n_drop: 5
 
 - `class`
-    The strategy class, str type, should be a subclass of `qlib.contrib.strategy.strategy.BaseStrategy`. The default value is `TopkAmountStrategy`.
+    The strategy class, str type, should be a subclass of `qlib.contrib.strategy.strategy.BaseStrategy`. The default value is `TopkDropoutStrategy`.
 
 - `module_path`
     The module location, str type, absolute url is also supported, and absolute path is also supported, indicates the location of the policy class implementation.
@@ -488,10 +488,10 @@ Users can specify strategy through a config file, for example:
     Parameters used for ``Trainer`` initialization.
 
     - `topk`    
-        A threshold for buying rank, integer type, determines the threshold for the topk-margin strategy buy rank. The default value is 30.
+        The number of stocks in the portfolio
 
-    - `margin`    
-        The sell buffer threshold, integer type, determines the buffer threshold, those who are outside the margin will be sold. The default value is 350.
+    - `n_drop`    
+        Number of stocks to be replaced in each trading date
 
 Custom Strategy
 ^^^^^^^^^^^^^^^^^^^

docs/component/strategy.rst

@@ -54,37 +54,7 @@ Users can inherit `WeightStrategyBase` and implement the inteface `generate_targ
 Implemented Strategy
 ====================
 
-Qlib provides several implemented strategy classes, such as `TopkWeightStrategy`, `TopkAmountStrategy` and `TopkDropoutStrategy`.
-
-TopkWeightStrategy
-------------------
-`TopkWeightStrategy` is a subclass of `WeightStrategyBase` and implements the interface `generate_target_weight_position`.
-
-The implemented interface `generate_target_weight_position` adopts the ``Topk-Margin`` algorithm to calculate the target position, it ensures that the weight of each stock is as even as possible.
-
-.. note:: 
-    ``Topk-Margin`` algorithm: 
-
-    - `Topk`: The number of stocks held
-    - `margin`: Rank threshold of prediction score 
-
-
-    Currently, the number of held stocks is `Topk`.
-    On each trading day, the held stocks with the rank of prediction score outside the threshold `margin` will be sold, and the same number of unheld stocks with best prediction score will be bought. 
-
-    .. image:: ../_static/img/topk_margin.png
-        :alt: Topk-Margin
-
-
-
-
-TopkAmountStrategy
-------------------
-`TopkAmountStrategy` is a subclass of `BaseStrategy` and implement the interface `generate_order_list` whose process is as follows.
-
-- Adopt the the ``Topk-Margin`` algorithm to calculate the target amount of each stock
-- Generate the order list from the target amount
-
+Qlib provides several implemented strategy classes `TopkDropoutStrategy`.
 
 
 TopkDropoutStrategy
@@ -115,11 +85,11 @@ Usage & Example
 
 .. code-block:: python
 
-    from qlib.contrib.strategy.strategy import TopkAmountStrategy
+    from qlib.contrib.strategy.strategy import TopkDropoutStrategy
     from qlib.contrib.evaluate import backtest
     STRATEGY_CONFIG = {
         "topk": 50,
-        "buffer_margin": 230,
+        "n_drop": 5,
     }
     BACKTEST_CONFIG = {
         "verbose": False,
@@ -131,7 +101,7 @@ Usage & Example
 
     # use default strategy
     # custom Strategy, refer to: TODO: Strategy API url
-    strategy = TopkAmountStrategy(**STRATEGY_CONFIG)
+    strategy = TopkDropoutStrategy(**STRATEGY_CONFIG)
 
     # pred_score is the prediction score output by Model
     report_normal, positions_normal = backtest(

docs/hidden/online.rst

@@ -254,11 +254,11 @@ Followings are two examples for a TopkAmountStrategy
 .. code-block:: YAML
 
     strategy:
-        class: TopkAmountStrategy
+        class: TopkDropoutStrategy
         module_path: qlib.contrib.strategy.strategy
         args:
             topk: 100
-            buffer_margin: 300
+            n_drop: 10
 
 Generated files
 ------------------

examples/estimator/estimator_config.yaml

@@ -33,10 +33,10 @@ trainer:
     test_start_date: 2017-01-01
     test_end_date: 2020-08-01
 strategy:
-  class: TopkAmountStrategy
+  class: TopkDropoutStrategy
   args:
     topk: 50
-    buffer_margin: 230
+    n_drop: 5
 backtest:
   normal_backtest_args:
     verbose: False
@@ -52,3 +52,4 @@ qlib_data:
   # when testing, please modify the following parameters according to the specific environment
   provider_uri: "~/.qlib/qlib_data/cn_data"
   region: "cn"
+  redis_port: 4312

examples/estimator/estimator_config_dnn.yaml

@@ -34,10 +34,10 @@ trainer:
     test_start_date: 2017-01-01
     test_end_date: 2020-08-01
 strategy:
-  class: TopkAmountStrategy
+  class: TopkDropoutStrategy
   args:
     topk: 50
-    buffer_margin: 230
+    n_drop: 5
 backtest:
   normal_backtest_args:
     verbose: False

examples/train_and_backtest.py

@@ -9,7 +9,7 @@
 from qlib.config import REG_CN
 from qlib.contrib.model.gbdt import LGBModel
 from qlib.contrib.estimator.handler import QLibDataHandlerClose
-from qlib.contrib.strategy.strategy import TopkAmountStrategy
+from qlib.contrib.strategy.strategy import TopkDropoutStrategy
 from qlib.contrib.evaluate import (
     backtest as normal_backtest,
     risk_analysis,
@@ -90,7 +90,7 @@
     ###################################
     STRATEGY_CONFIG = {
         "topk": 50,
-        "buffer_margin": 230,
+        "n_drop": 5,
     }
     BACKTEST_CONFIG = {
         "verbose": False,
@@ -105,7 +105,7 @@
 
     # use default strategy
     # custom Strategy, refer to: TODO: Strategy API url
-    strategy = TopkAmountStrategy(**STRATEGY_CONFIG)
+    strategy = TopkDropoutStrategy(**STRATEGY_CONFIG)
     report_normal, positions_normal = normal_backtest(pred_score, strategy=strategy, **BACKTEST_CONFIG)
 
     ###################################

examples/train_backtest_analyze.ipynb

@@ -14,7 +14,7 @@
     "from qlib.config import REG_CN\n",
     "from qlib.contrib.model.gbdt import LGBModel\n",
     "from qlib.contrib.estimator.handler import QLibDataHandlerClose\n",
-    "from qlib.contrib.strategy.strategy import TopkAmountStrategy\n",
+    "from qlib.contrib.strategy.strategy import TopkDropoutStrategy\n",
     "from qlib.contrib.evaluate import (\n",
     "    backtest as normal_backtest,\n",
     "    risk_analysis,\n",
@@ -135,7 +135,7 @@
     "###################################\n",
     "STRATEGY_CONFIG = {\n",
     "    \"topk\": 50,\n",
-    "    \"buffer_margin\": 230,\n",
+    "    \"n_drop\": 5",
     "}\n",
     "BACKTEST_CONFIG = {\n",
     "    \"verbose\": False,\n",
@@ -151,7 +151,7 @@
     "\n",
     "# use default strategy\n",
     "# custom Strategy, refer to: TODO: Strategy api url\n",
-    "strategy = TopkAmountStrategy(**STRATEGY_CONFIG)\n",
+    "strategy = TopkDropoutStrategy(**STRATEGY_CONFIG)\n",
     "report_normal, positions_normal = normal_backtest(pred_score, strategy=strategy, **BACKTEST_CONFIG)\n"
    ]
   },