release-0.5.0 (#1)

* init commit

* change the version number

* rich the docs&fix cache docs

* update index readme

* Modify cache class name

* Modify sharpe to information_ratio

* Modify Group- to Group

* add the description of graphical results & fix the backtest docs

* fix docs in details

* update docs

* Update introduction.rst

* Update README.md

* Update introduction.rst

* Update introduction.rst

* Update introduction.rst

* Update installation.rst

* Update installation.rst

* Update initialization.rst

* Update getdata.rst

* Update integration.rst

* Update initialization.rst

* Update getdata.rst

* Update estimator.rst

Modify some typos.

* Update README.md

Modify the typos.

* Update initialization.rst

* Update data.rst

* Update report.rst

* Update estimator.rst

* Update cumulative_return.py

* Update model.rst

* Update rank_label.py

* Update cumulative_return.py

* Update strategy.rst

* Update getdata.rst

* Update backtest.rst

* Update integration.rst

* Update getdata.rst

* Update introduction.rst

* Update introduction.rst

* Update README.md

* Update report.rst

* Update integration.rst

Fix typos

* Update installation.rst

Fix typos

* Update getdata.rst

* Update initialization.rst

Fix typos.

* add quick start docs&fix detials

* fix estimator docs & fix strategy docs

* fix the cahce in data.rst

* update documents

* Fix Corr && Rsquare

* fix data retrival example to csi300 & fix a data bug

* fix filter bug

* Fix data collector

* Modift model args

* add the log & fix README.md\quick.rst

* add enviroment depend & add intoduction of qlib-server online mode

* fix image center fomat & set log_only of docs is True

* fix README.md format

* update data preparation & readme logo image

* get_data support version

* Modify analysis names

* Modify analysis graph

* update report.rst & data.rst

* commmit estimator for merge

* minimal requirements

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update READEME.md

* Update READEME.md

* update estimator

* Fix doc urls

* fix get_data.py docstring

* update test_get_data.py

* Upate docs

* Upate docs

* Upate docs

Co-authored-by: bxdd <bxddream@gmail.com>
Co-authored-by: zhupr <zhu.pengrong@foxmail.com>
Co-authored-by: Wendi Li <wendili.academic@qq.com>
Co-authored-by: Dingsu Wang <dingsu.wang@gmail.com>
Co-authored-by: bxdd <45119470+bxdd@users.noreply.github.com>
Co-authored-by: cslwqxx <cslwqxx@users.noreply.github.com>

qlib/contrib/report/__init__.py

@@ -1,7 +1,7 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.
 
-GRAPH_NAME_LISt = [
+GRAPH_NAME_LIST = [
     "analysis_position.report_graph",
     "analysis_position.score_ic_graph",
     "analysis_position.cumulative_return_graph",

qlib/contrib/report/analysis_model/analysis_model_performance.py

@@ -35,7 +35,7 @@ def _group_return(
     # Group
     t_df = pd.DataFrame(
         {
-            "Group-%d"
+            "Group%d"
             % (i + 1): pred_label_drop.groupby(level="datetime")["label"].apply(
                 lambda x: x[len(x) // N * i : len(x) // N * (i + 1)].mean()
             )
@@ -45,11 +45,11 @@ def _group_return(
     t_df.index = pd.to_datetime(t_df.index)
 
     # Long-Short
-    t_df["long-short"] = t_df["Group-1"] - t_df["Group-%d" % N]
+    t_df["long-short"] = t_df["Group1"] - t_df["Group%d" % N]
 
     # Long-Average
     t_df["long-average"] = (
-        t_df["Group-1"] - pred_label.groupby(level="datetime")["label"].mean()
+        t_df["Group1"] - pred_label.groupby(level="datetime")["label"].mean()
     )
 
     t_df = t_df.dropna(how="all")  # for days which does not contain label

qlib/contrib/report/analysis_position/cumulative_return.py

@@ -228,11 +228,11 @@ def cumulative_return_graph(
         Graph desc:
             - Axis X: Trading day
             - Axis Y:
-            - Above axis Y: (((Ref($close, -1)/$close - 1) * weight).sum() / weight.sum()).cumsum()
+            - Above axis Y: `(((Ref($close, -1)/$close - 1) * weight).sum() / weight.sum()).cumsum()`
             - Below axis Y: Daily weight sum
-            - In the sell graph, y < 0 stands for profit; in other cases, y > 0 stands for profit.
-            - In the buy_minus_sell graph, the y value of the weight graph at the bottom is buy_weight + sell_weight.
-            - In each graph, the red line in the histogram on the right represents the average.
+            - In the **sell** graph, `y < 0` stands for profit; in other cases, `y > 0` stands for profit.
+            - In the **buy_minus_sell** graph, the **y** value of the **weight** graph at the bottom is `buy_weight + sell_weight`.
+            - In each graph, the **red line** in the histogram on the right represents the average.
 
     :param position: position data
     :param report_normal:
@@ -250,7 +250,7 @@ def cumulative_return_graph(
 
 
     :param label_data: `D.features` result; index is `pd.MultiIndex`, index name is [`instrument`, `datetime`]; columns names is [`label`].
-    **The ``label`` T is the change from T to T+1**, it is recommended to use ``close``, example: D.features(D.instruments('csi500'), ['Ref($close, -1)/$close-1'])
+    **The label T is the change from T to T+1**, it is recommended to use ``close``, example: `D.features(D.instruments('csi500'), ['Ref($close, -1)/$close-1'])`
 
 
             .. code-block:: python

qlib/contrib/report/analysis_position/rank_label.py

@@ -99,7 +99,7 @@ def rank_label_graph(
 
     :param position: position data; **qlib.contrib.backtest.backtest.backtest** result
     :param label_data: **D.features** result; index is **pd.MultiIndex**, index name is **[instrument, datetime]**; columns names is **[label]**.
-    **The ``label`` T is the change from T to T+1**, it is recommended to use ``close``, example: D.features(D.instruments('csi500'), ['Ref($close, -1)/$close-1'])
+    **The label T is the change from T to T+1**, it is recommended to use ``close``, example: `D.features(D.instruments('csi500'), ['Ref($close, -1)/$close-1'])`
 
 
             .. code-block:: python

qlib/contrib/report/analysis_position/risk_analysis.py

@@ -32,10 +32,10 @@ def _get_risk_analysis_data_with_report(
     #     analysis["pred_long_short"] = risk_analysis(report_long_short_df["long_short"])
 
     if not report_normal_df.empty:
-        analysis["sub_bench"] = risk_analysis(
+        analysis["excess_return_without_cost"] = risk_analysis(
             report_normal_df["return"] - report_normal_df["bench"]
         )
-        analysis["sub_cost"] = risk_analysis(
+        analysis["excess_return_with_cost"] = risk_analysis(
             report_normal_df["return"]
             - report_normal_df["bench"]
             - report_normal_df["cost"]
@@ -97,7 +97,7 @@ def _get_monthly_risk_analysis_with_report(report_normal_df: pd.DataFrame) -> pd
 
 
 def _get_monthly_analysis_with_feature(
-    monthly_df: pd.DataFrame, feature: str = "annual"
+    monthly_df: pd.DataFrame, feature: str = "annualized_return"
 ) -> pd.DataFrame:
     """
 
@@ -156,7 +156,7 @@ def _get_monthly_risk_analysis_figure(report_normal_df: pd.DataFrame) -> Iterabl
         # report_long_short_df=report_long_short_df,
     )
 
-    for _feature in ["annual", "mdd", "sharpe", "std"]:
+    for _feature in ["annualized_return", "max_drawdown", "information_ratio", "std"]:
         _temp_df = _get_monthly_analysis_with_feature(_monthly_df, _feature)
         yield ScatterGraph(
             _temp_df,
@@ -200,8 +200,8 @@ def risk_analysis_graph(
                 # analysis['pred_long'] = risk_analysis(report_long_short_df['long'])
                 # analysis['pred_short'] = risk_analysis(report_long_short_df['short'])
                 # analysis['pred_long_short'] = risk_analysis(report_long_short_df['long_short'])
-                analysis['sub_bench'] = risk_analysis(report_normal_df['return'] - report_normal_df['bench'])
-                analysis['sub_cost'] = risk_analysis(report_normal_df['return'] - report_normal_df['bench'] - report_normal_df['cost'])
+                analysis['excess_return_without_cost'] = risk_analysis(report_normal_df['return'] - report_normal_df['bench'])
+                analysis['excess_return_with_cost'] = risk_analysis(report_normal_df['return'] - report_normal_df['bench'] - report_normal_df['cost'])
                 analysis_df = pd.concat(analysis)
 
                 analysis_position.risk_analysis_graph(analysis_df, report_normal_df)
@@ -213,17 +213,17 @@ def risk_analysis_graph(
 
             .. code-block:: python
 
-                                    risk
-                sub_bench mean    0.000662
-                          std     0.004487
-                          annual  0.166720
-                          sharpe  2.340526
-                          mdd    -0.080516
-                sub_cost  mean    0.000577
-                          std     0.004482
-                          annual  0.145392
-                          sharpe  2.043494
-                          mdd    -0.083584
+                                                                  risk
+                excess_return_without_cost mean               0.000692
+                                           std                0.005374
+                                           annualized_return  0.174495
+                                           information_ratio  2.045576
+                                           max_drawdown      -0.079103
+                excess_return_with_cost    mean               0.000499
+                                           std                0.005372
+                                           annualized_return  0.125625
+                                           information_ratio  1.473152
+                                           max_drawdown      -0.088263
 
 
     :param report_normal_df: **df.index.name** must be **date**, df.columns must contain **return**, **turnover**, **cost**, **bench**