Merge branch 'main' of 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/CatBoost/workflow_config_catboost.yaml

@@ -36,7 +36,7 @@ task:
             num_leaves: 100
             thread_count: 20
             grow_policy: Lossguide
-            boostrap_type: Poisson
+            bootstrap_type: Poisson
     dataset:
         class: DatasetH
         module_path: qlib.data.dataset

examples/benchmarks/GATs/README.md

@@ -1,4 +1,4 @@
-#GATs
+# GATs
 * Graph Attention Networks(GATs) leverage masked self-attentional layers on graph-structured data. The nodes in stacked layers have different weights and they are able to attend over their
 neighborhoods’ features, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront.
 * This code used in Qlib is implemented with PyTorch by ourselves.

examples/benchmarks/HATS/README.md

@@ -1,11 +1,11 @@
-##Requirement
+## Requirement
 
 * pandas==1.1.2
 * numpy==1.17.4
 * scikit_learn==0.23.2
 * torch==1.7.0
 
-##HATS
+## HATS
 
 * HATS is a a hierarchical attention network for stock prediction which uses relational data for stock market prediction. HATS selectively aggregates information
 on different relation types and adds the information to the representations of each company. HATS is used as a relational modeling module with initialized node representations.Furthermore, HATS

examples/benchmarks/SFM/workflow_config_sfm.yaml

@@ -31,21 +31,21 @@ task:
         kwargs:
             d_feat: 6
             hidden_size: 64
-            output_dim: 1
-            freq_dim: 15
+            output_dim: 32
+            freq_dim: 25
             dropout_W: 0.5
             dropout_U: 0.5
-            n_epochs: 10
+            n_epochs: 20
             lr: 1e-3
-            batch_size: 800
+            batch_size: 1600
             early_stop: 20
             eval_steps: 5
             loss: mse
             lr_decay: 0.96
             lr_decay_steps: 100
-            optimizer: gd
+            optimizer: adam
             GPU: 1
-            seed: 0
+            seed: 710
     dataset:
         class: DatasetH
         module_path: qlib.data.dataset
@@ -70,4 +70,4 @@ task:
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs: 
-            config: *port_analysis_config
+            config: *port_analysis_config

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.
+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/benchmarks/TabNet/workflow_config_tabnet.yaml

@@ -44,7 +44,7 @@ task:
         module_path: qlib.data.dataset
         kwargs:
             handler:
-                class: Alpha158
+                class: ALPHA360_Denoise
                 module_path: qlib.contrib.data.handler
                 kwargs: *data_handler_config
             segments:

examples/benchmarks/XGBoost/workflow_config_xgboost.yaml

@@ -29,18 +29,15 @@ task:
         class: XGBModel
         module_path: qlib.contrib.model.xgboost
         kwargs:
-            objective: reg:linear
-            n_estimators: 5000
-            colsample_bytree: 0.85
-            learning_rate: 0.0421
-            subsample: 0.8789
-            max_depth: 8
-            num_leaves: 210
-            num_threads: 20
-            missing: -1
-            min_child_weight: 1
+            eval_metric: rmse
+            colsample_bytree: 0.5
+            eta: 0.2
+            gamma: 0.55
+            max_depth: 2
+            min_child_weight: 1.0
+            n_estimators: 647
+            subsample: 0.8
             nthread: 4
-            tree_method: hist
     dataset:
         class: DatasetH
         module_path: qlib.data.dataset

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_alstm.py

@@ -7,20 +7,14 @@ from pathlib import Path
 import qlib
 import pandas as pd
 from qlib.config import REG_CN
-from qlib.contrib.model.pytorch_alstm import ALSTM
-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__":
 
     # use default data
@@ -73,7 +67,7 @@ if __name__ == "__main__":
                 "metric": "IC",
                 "loss": "mse",
                 "seed": 0,
-                "GPU": 0,
+                "GPU": "0",
                 "rnn_type": "GRU",
             },
         },
@@ -97,7 +91,6 @@ if __name__ == "__main__":
         # "record": ['SignalRecord', 'SigAnaRecord', 'PortAnaRecord'],
     }
 
-    # model = train_model(task)
     model = init_instance_by_config(task["model"])
     dataset = init_instance_by_config(task["dataset"])
     model.fit(dataset)

examples/workflow_by_code_gats.py

@@ -7,19 +7,15 @@ 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_hats.py

@@ -3,24 +3,17 @@
 
 import sys
 from pathlib import Path
-
 import qlib
 import pandas as pd
 from qlib.config import REG_CN
-from qlib.contrib.model.pytorch_hats import HATS
-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__":
 
     # use default data
@@ -30,7 +23,7 @@ if __name__ == "__main__":
         sys.path.append(str(Path(__file__).resolve().parent.parent.joinpath("scripts")))
         from get_data import GetData
 
-        GetData().qlib_data_cn(target_dir=provider_uri)
+        GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
 
     qlib.init(provider_uri=provider_uri, region=REG_CN)
 
@@ -74,7 +67,7 @@ if __name__ == "__main__":
                 "loss": "mse",
                 "base_model": "LSTM",
                 "seed": 0,
-                "GPU": 0,
+                "GPU": "0",
             },
         },
         "dataset": {
@@ -97,7 +90,6 @@ if __name__ == "__main__":
         # "record": ['SignalRecord', 'SigAnaRecord', 'PortAnaRecord'],
     }
 
-    # model = train_model(task)
     model = init_instance_by_config(task["model"])
     dataset = init_instance_by_config(task["dataset"])
     model.fit(dataset, save_path="benchmarks/HATS/model_hat.pkl")

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,
             },
         },