Debug MacOS CI

* Fixed pandas FutureWarning

`FutureWarning: Passing a set as an indexer is deprecated and will raise in a future version. Use a list instead.`

* fixed another pandas FutureWarning

```
scripts/data_collector/index.py:228: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  new_df = new_df.append(_tmp_df, sort=False)
```

* fixed more pandas futurewarnings

.github/workflows/test_macos.yml

@@ -34,25 +34,10 @@ jobs:
         python -m black qlib -l 120 --check --diff
     # Test Qlib installed with pip
 
-    - name: Check Qlib with flake8
-        run: |
-          pip install --upgrade pip
-          pip install flake8
-          cd ..
-          flake8 --ignore=E501,F541,E266,E402,W503,E731,E203 qlib
-
     - name: Install Qlib with pip
       run: |
           python -m pip install numpy==1.19.5
           python -m pip install pyqlib --ignore-installed ruamel.yaml numpy
-    - name: Make html with sphnix
-      run: |
-        pip install -U sphinx
-        pip install sphinx_rtd_theme readthedocs_sphinx_ext
-        pip install --exists-action=w --no-cache-dir -r docs/requirements.txt 
-        cd docs 
-        sphinx-build -b html . build
-        cd ..
     - name: Install Lightgbm for MacOS
       run: |
         /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Microsoft/qlib/main/.github/brew_install.sh)"
@@ -64,8 +49,7 @@ jobs:
         brew install libomp.rb
     - name: Test data downloads
       run: |
-        python scripts/get_data.py qlib_data --name qlib_data_simple --target_dir ~/.qlib/qlib_data/cn_data_simple --interval 1d --region cn
+        python scripts/get_data.py qlib_data --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
-        python -c "import os; userpath=os.path.expanduser('~'); os.rename(userpath + '/.qlib/qlib_data/cn_data_simple', userpath + '/.qlib/qlib_data/cn_data')"
     - name: Test workflow by config (install from pip)
       run: |
         python qlib/workflow/cli.py examples/benchmarks/LightGBM/workflow_config_lightgbm_Alpha158.yaml

docs/component/data.rst

@@ -437,7 +437,7 @@ Dataset
 
 The ``Dataset`` module in ``Qlib`` aims to prepare data for model training and inferencing.
 
-The motivation of this module is that we want to maximize the flexibility of of different models to handle data that are suitable for themselves. This module gives the model the flexibility to process their data in an unique way. For instance, models such as ``GBDT`` may work well on data that contains `nan` or `None` value, while neural networks such as ``MLP`` will break down on such data. 
+The motivation of this module is that we want to maximize the flexibility of different models to handle data that are suitable for themselves. This module gives the model the flexibility to process their data in an unique way. For instance, models such as ``GBDT`` may work well on data that contains `nan` or `None` value, while neural networks such as ``MLP`` will break down on such data. 
 
 If user's model need process its data in a different way, user could implement his own ``Dataset`` class. If the model's
 data processing is not special, ``DatasetH`` can be used directly.

docs/component/workflow.rst

@@ -233,7 +233,7 @@ The meaning of each field is as follows:
 Dataset Section
 ~~~~~~~~~~~~~~~~~~~~
 
-The `dataset` field describes the parameters for the ``Dataset`` module in ``Qlib`` as well those for the module ``DataHandler``. For more information about the ``Dataset`` module, please refer to `Qlib Model <../component/data.html#dataset>`_.
+The `dataset` field describes the parameters for the ``Dataset`` module in ``Qlib`` as well those for the module ``DataHandler``. For more information about the ``Dataset`` module, please refer to `Qlib Data <../component/data.html#dataset>`_.
 
 The keywords arguments configuration of the ``DataHandler`` is as follows:
 
@@ -248,7 +248,7 @@ The keywords arguments configuration of the ``DataHandler`` is as follows:
 
 Users can refer to the document of `DataHandler <../component/data.html#datahandler>`_ for more information about the meaning of each field in the configuration.
 
-Here is the configuration for the ``Dataset`` module which will take care of data preprossing and slicing during the training and testing phase.
+Here is the configuration for the ``Dataset`` module which will take care of data preprocessing and slicing during the training and testing phase.
 
 .. code-block:: YAML
 

qlib/__init__.py

@@ -2,7 +2,7 @@
 # Licensed under the MIT License.
 from pathlib import Path
 
-__version__ = "0.8.5"
+__version__ = "0.8.5.99"
 __version__bak = __version__  # This version is backup for QlibConfig.reset_qlib_version
 import os
 from typing import Union

qlib/contrib/eva/alpha.py

@@ -123,7 +123,7 @@ def pred_autocorr(pred: pd.Series, lag=1, inst_col="instrument", date_col="datet
     """
     if isinstance(pred, pd.DataFrame):
         pred = pred.iloc[:, 0]
-        get_module_logger("pred_autocorr").warning("Only the first column in {pred.columns} of `pred` is kept")
+        get_module_logger("pred_autocorr").warning(f"Only the first column in {pred.columns} of `pred` is kept")
     pred_ustk = pred.sort_index().unstack(inst_col)
     corr_s = {}
     for (idx, cur), (_, prev) in zip(pred_ustk.iterrows(), pred_ustk.shift(lag).iterrows()):

qlib/contrib/report/analysis_position/parse_position.py

@@ -68,9 +68,9 @@ def parse_position(position: dict = None) -> pd.DataFrame:
             if not _trading_day_sell_df.empty:
                 _trading_day_sell_df["status"] = -1
                 _trading_day_sell_df["date"] = _trading_date
-                _trading_day_df = _trading_day_df.append(_trading_day_sell_df, sort=False)
+                _trading_day_df = pd.concat([_trading_day_df, _trading_day_sell_df], sort=False)
 
-        result_df = result_df.append(_trading_day_df, sort=True)
+        result_df = pd.concat([result_df, _trading_day_df], sort=True)
 
         previous_data = dict(
             date=_trading_date,

qlib/contrib/report/analysis_position/risk_analysis.py

@@ -85,7 +85,7 @@ def _get_monthly_risk_analysis_with_report(report_normal_df: pd.DataFrame) -> pd
             # _m_report_long_short,
             pd.Timestamp(year=gp_m[0], month=gp_m[1], day=month_days),
         )
-        _monthly_df = _monthly_df.append(_temp_df, sort=False)
+        _monthly_df = pd.concat([_monthly_df, _temp_df], sort=False)
 
     return _monthly_df
 

scripts/data_collector/base.py

@@ -170,7 +170,7 @@ class BaseCollector(abc.ABC):
         df["symbol"] = symbol
         if instrument_path.exists():
             _old_df = pd.read_csv(instrument_path)
-            df = _old_df.append(df, sort=False)
+            df = pd.concat([_old_df, df], sort=False)
         df.to_csv(instrument_path, index=False)
 
     def cache_small_data(self, symbol, df):

scripts/data_collector/index.py

@@ -225,7 +225,7 @@ class IndexBase:
                 ] = _row.date
             else:
                 _tmp_df = pd.DataFrame([[_row.symbol, self.bench_start_date, _row.date]], columns=instruments_columns)
-                new_df = new_df.append(_tmp_df, sort=False)
+                new_df = pd.concat([new_df, _tmp_df], sort=False)
 
         inst_df = new_df.loc[:, instruments_columns]
         _inst_prefix = self.INST_PREFIX.strip()

scripts/data_collector/yahoo/collector.py

@@ -245,7 +245,7 @@ class YahooCollectorCN1d(YahooCollectorCN):
             _path = self.save_dir.joinpath(f"sh{_index_code}.csv")
             if _path.exists():
                 _old_df = pd.read_csv(_path)
-                df = _old_df.append(df, sort=False)
+                df = pd.concat([_old_df, df], sort=False)
             df.to_csv(_path, index=False)
             time.sleep(5)
 
@@ -404,7 +404,7 @@ class YahooNormalize(BaseNormalize):
                 .index
             )
         df.sort_index(inplace=True)
-        df.loc[(df["volume"] <= 0) | np.isnan(df["volume"]), set(df.columns) - {symbol_field_name}] = np.nan
+        df.loc[(df["volume"] <= 0) | np.isnan(df["volume"]), list(set(df.columns) - {symbol_field_name})] = np.nan
 
         change_series = YahooNormalize.calc_change(df, last_close)
         # NOTE: The data obtained by Yahoo finance sometimes has exceptions