Merge branch 'main' of https://github.com/you-n-g/qlib into main

examples/benchmarks/ALSTM/README.md

@@ -0,0 +1,10 @@
+# ALSTM
+
+- ALSTM contains a temporal attentive aggregation layer based on normal LSTM.
+
+- The code used in Qlib is a pyTorch implementation of Code: https://github.com/fulifeng/Adv-ALSTM
+
+- Paper: A dual-stage attention-based recurrent neural network for time series prediction.
+
+  https://www.ijcai.org/Proceedings/2017/0366.pdf
+

examples/benchmarks/TFT/README.md

@@ -5,8 +5,10 @@
 **GitHub**: https://github.com/google-research/google-research/tree/master/tft
 
 ## Run the Workflow
-Users can follow the ``workflow_by_code_tft.py`` to run the benchmark. Please be **aware** that this script can only support Python 3.5 - 3.8.
+Users can follow the ``workflow_by_code_tft.py`` to run the benchmark. 
 
 ### Notes
-1. The model must run in GPU, or an error will be raised.
-2. New datasets should be registered in ``data_formatters``, for detail please visit the source.
+1. Please be **aware** that this script can only support `Python 3.5 - 3.8`.
+2. If the CUDA version on your machine is not 10.0, please remember to run the following commands `conda install anaconda cudatoolkit=10.0` and `conda install cudnn` on your machine.
+3. The model must run in GPU, or an error will be raised.
+4. New datasets should be registered in ``data_formatters``, for detail please visit the source.

examples/run_all_model.py

@@ -10,6 +10,7 @@ import shutil
 import tempfile
 import statistics
 from pathlib import Path
+from operator import xor
 from subprocess import Popen, PIPE
 from threading import Thread
 from pprint import pprint
@@ -174,11 +175,22 @@ def cal_mean_std(results) -> dict:
 
 
 # function to get all the folders benchmark folder
-def get_all_folders() -> dict:
+def get_all_folders(models, exclude) -> dict:
     folders = dict()
+    if isinstance(models, str):
+        model_list = models.split(",")
+        models = [m.lower().strip("[ ]") for m in model_list]
+    elif isinstance(models, list):
+        models = [m.lower() for m in models]
+    elif models is None:
+        models = [f.name.lower() for f in os.scandir("benchmarks")]
+    else:
+        raise ValueError("Input models type is not supported. Please provide str or list without space.")
     for f in os.scandir("benchmarks"):
-        path = Path("benchmarks") / f.name
-        folders[f.name] = str(path.resolve())
+        add = xor(bool(f.name.lower() in models), bool(exclude))
+        if add:
+            path = Path("benchmarks") / f.name
+            folders[f.name] = str(path.resolve())
     return folders
 
 
@@ -225,13 +237,44 @@ def gen_and_save_md_table(metrics):
 
 
 # function to run the all the models
-def run(times=1):
+def run(times=1, models=None, exclude=False):
     """
     Please be aware that this function can only work under Linux. MacOS and Windows will be supported in the future.
     Any PR to enhance this method is highly welcomed.
+
+    Parameters:
+    -----------
+    times : int
+        determines how many times the model should be running.
+    models : str or list
+        determines the specific model or list of models to run or exclude.
+    exclude : boolean
+        determines whether the model being used is excluded or included.
+
+    Usage:
+    -------
+    Here are some use cases of the function in the bash:
+
+    .. code-block:: bash
+
+        # Case 1 - run all models multiple times
+        python run_all_model.py 3
+
+        # Case 2 - run specific models multiple times
+        python run_all_model.py 3 dnn
+
+        # Case 3 - run other models except those are given as arguments for multiple times
+        python run_all_model.py 3 [dnn,tft,lstm] True
+
+        # Case 4 - run specific models for one time
+        python run_all_model.py --models=[dnn,lightgbm]
+
+        # Case 5 - run other models except those are given as aruments for one time
+        python run_all_model.py --models=[dnn,tft,sfm] --exclude=True
+
     """
     # get all folders
-    folders = get_all_folders()
+    folders = get_all_folders(models, exclude)
     # set up
     compatible = True
     if sys.version_info < (3, 3):

examples/workflow_by_code_gats.py

@@ -7,19 +7,16 @@ from pathlib import Path
 import qlib
 import pandas as pd
 from qlib.config import REG_CN
-from qlib.contrib.model.pytorch_gats import GAT
-from qlib.contrib.data.handler import ALPHA360_Denoise
+
 from qlib.contrib.strategy.strategy import TopkDropoutStrategy
 from qlib.contrib.evaluate import (
     backtest as normal_backtest,
     risk_analysis,
 )
 from qlib.utils import exists_qlib_data
-
-# from qlib.model.learner import train_model
 from qlib.utils import init_instance_by_config
 
-import pickle
+
 
 if __name__ == "__main__":
 

examples/workflow_by_code_sfm.py

@@ -71,21 +71,22 @@ if __name__ == "__main__":
             "module_path": "qlib.contrib.model.pytorch_sfm",
             "kwargs": {
                 "d_feat": 6,
-                "hidden_size": 32,
-                "output_dim": 16,
+                "hidden_size": 64,
+                "output_dim": 32,
                 "freq_dim": 25,
                 "dropout_W": 0.5,
                 "dropout_U": 0.5,
-                "n_epochs": 200,
+                "n_epochs": 15,
                 "lr": 1e-3,
-                "batch_size": 200,
+                "metric": "", 
+                "batch_size": 1600,
                 "early_stop": 20,
                 "eval_steps": 5,
                 "loss": "mse",
                 "lr_decay": 0.96,
                 "lr_decay_steps": 100,
                 "optimizer": "adam",
-                "GPU": 1,
+                "GPU": 3,
                 "seed": 710,
             },
         },