Add Qlib notebook tutorial (#1037)

* Add Qlib notebook tutorial

* Update tutorial

README.md

@@ -386,6 +386,8 @@ Dataset plays a very important role in Quant. Here is a list of the datasets bui
 Your PR to build new Quant dataset is highly welcomed.
 
 # More About Qlib
+If you want to have a quick glance at the most frequently used components of qlib, you can try notebooks [here](examples/tutorial/).
+
 The detailed documents are organized in [docs](docs/).
 [Sphinx](http://www.sphinx-doc.org) and the readthedocs theme is required to build the documentation in html formats. 
 ```bash
@@ -471,8 +473,10 @@ If you don't know how to start to contribute, you can refer to the following exa
 | Models |  [Implement a new model](https://github.com/microsoft/qlib/pull/689) | 
 
 [Good first issues](https://github.com/microsoft/qlib/labels/good%20first%20issue) are labelled to indicate that they are easy to start your contributions.
+
+You can find some impefect implementation in Qlib by  `rg 'TODO|FIXME' qlib`
  
-If you would like to become one of Qlib's maintainers to contribute more (e.g. help merge PR, triage issues), please contact us by email([qlib@microsoft.com](mailto:qlib@microsoft.com)).  We are glad to help you to set the right permission.
+If you would like to become one of Qlib's maintainers to contribute more (e.g. help merge PR, triage issues), please contact us by email([qlib@microsoft.com](mailto:qlib@microsoft.com)).  We are glad to help to upgrade your permission.
 
 ## Licence
 Most contributions require you to agree to a

examples/workflow_by_code.ipynb

@@ -256,7 +256,6 @@
     "recorder = R.get_recorder(recorder_id=ba_rid, experiment_name=\"backtest_analysis\")\n",
     "print(recorder)\n",
     "pred_df = recorder.load_object(\"pred.pkl\")\n",
-    "pred_df_dates = pred_df.index.get_level_values(level='datetime')\n",
     "report_normal_df = recorder.load_object(\"portfolio_analysis/report_normal_1day.pkl\")\n",
     "positions = recorder.load_object(\"portfolio_analysis/positions_normal_1day.pkl\")\n",
     "analysis_df = recorder.load_object(\"portfolio_analysis/port_analysis_1day.pkl\")"

qlib/contrib/model/__init__.py

@@ -10,17 +10,19 @@ try:
     from .gbdt import LGBModel
 except ModuleNotFoundError:
     DEnsembleModel, LGBModel = None, None
-    print("Please install necessary libs for DEnsembleModel and LGBModel, such as lightgbm.")
+    print(
+        "ModuleNotFoundError. DEnsembleModel and LGBModel are skipped. (optional: maybe installing lightgbm can fix it.)"
+    )
 try:
     from .xgboost import XGBModel
 except ModuleNotFoundError:
     XGBModel = None
-    print("Please install necessary libs for XGBModel, such as xgboost.")
+    print("ModuleNotFoundError. XGBModel is skipped(optional: maybe installing xgboost can fix it).")
 try:
     from .linear import LinearModel
 except ModuleNotFoundError:
     LinearModel = None
-    print("Please install necessary libs for LinearModel, such as scipy and sklearn.")
+    print("ModuleNotFoundError. LinearModel is skipped(optional: maybe installing scipy and sklearn can fix it).")
 # import pytorch models
 try:
     from .pytorch_alstm import ALSTM
@@ -36,6 +38,6 @@ try:
     pytorch_classes = (ALSTM, GATs, GRU, LSTM, DNNModelPytorch, TabnetModel, SFM_Model, TCN, ADD)
 except ModuleNotFoundError:
     pytorch_classes = ()
-    print("Please install necessary libs for PyTorch models.")
+    print("ModuleNotFoundError.  PyTorch models are skipped (optional: maybe installing pytorch can fix it).")
 
 all_model_classes = (CatBoostModel, DEnsembleModel, LGBModel, XGBModel, LinearModel) + pytorch_classes

qlib/data/dataset/__init__.py

@@ -199,6 +199,9 @@ class DatasetH(Dataset):
 
         col_set : str
             The col_set will be passed to self.handler when fetching data.
+            TODO: make it automatic:
+                - select DK_I for test data
+                - select DK_L for training data.
         data_key : str
             The data to fetch:  DK_*
             Default is DK_I, which indicate fetching data for **inference**.

qlib/workflow/cli.py

@@ -43,6 +43,11 @@ def sys_config(config, config_path):
 
 # workflow handler function
 def workflow(config_path, experiment_name="workflow", uri_folder="mlruns"):
+    """
+    This is a Qlib CLI entrance.
+    User can run the whole Quant research workflow defined by a configure file
+    - the code is located here ``qlib/workflow/cli.py`
+    """
     with open(config_path) as fp:
         config = yaml.safe_load(fp)
 

scripts/data_collector/pit/requirements.txt

@@ -6,4 +6,5 @@ pandas
 lxml
 loguru
 baostock
-yahooquery
+yahooquery
+beautifulsoup4