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

examples/benchmarks/ALSTM/requirements.txt

@@ -0,0 +1,4 @@
+numpy==1.17.4
+pandas==1.1.2
+scikit_learn==0.23.2
+torch==1.7.0

examples/benchmarks/ALSTM/workflow_config_alstm.yaml

@@ -0,0 +1,69 @@
+provider_uri: "~/.qlib/qlib_data/cn_data"
+region: cn
+market: &market csi300
+benchmark: &benchmark SH000300
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy.strategy
+        kwargs:
+            topk: 50
+            n_drop: 5
+    backtest:
+        verbose: False
+        limit_threshold: 0.095
+        account: 100000000
+        benchmark: *benchmark
+        deal_price: close
+        open_cost: 0.0005
+        close_cost: 0.0015
+        min_cost: 5
+task:
+    model:
+        class: ALSTM
+        module_path: qlib.contrib.model.pytorch_alstm
+        kwargs:
+            d_feat: 6
+            hidden_size: 64
+            num_layers: 2
+            dropout: 0.0
+            n_epochs: 200
+            lr: 1e-3
+            early_stop: 20
+            batch_size: 800
+            metric: IC
+            loss: mse
+            seed: 0
+            GPU: 0
+            rnn_type: GRU
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: ALPHA360_Denoise
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            ana_long_short: False
+            ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            config: *port_analysis_config

examples/benchmarks/CatBoost/README.md

@@ -0,0 +1,3 @@
+# CatBoost
+* Code: [https://github.com/catboost/catboost](https://github.com/catboost/catboost)
+* Paper: CatBoost: unbiased boosting with categorical features. [https://proceedings.neurips.cc/paper/2018/file/14491b756b3a51daac41c24863285549-Paper.pdf](https://proceedings.neurips.cc/paper/2018/file/14491b756b3a51daac41c24863285549-Paper.pdf).

examples/benchmarks/DNN/workflow_config_dnn.yaml

@@ -30,7 +30,7 @@ task:
         module_path: qlib.contrib.model.pytorch_nn
         kwargs:
             loss: mse
-            input_dim: 360
+            input_dim: 158
             output_dim: 1
             lr: 0.002
             lr_decay: 0.96

examples/benchmarks/GATs/workflow_config_gats.yaml

@@ -37,9 +37,10 @@ task:
             lr: 1e-3
             early_stop: 20
             batch_size: 800
-            metric: IC
+            metric: loss
             loss: mse
-            base_model: GRU
+            base_model: LSTM
+            with_pretrain: True
             seed: 0
             GPU: 0
     dataset:

examples/benchmarks/HATS/requirements.txt

@@ -0,0 +1,4 @@
+pandas==1.1.2
+numpy==1.17.4
+scikit_learn==0.23.2
+torch==1.7.0

examples/benchmarks/HATS/worflow_config_hats.yaml

@@ -0,0 +1,64 @@
+provider_uri: "~/.qlib/qlib_data/cn_data"
+region: cn
+market: &market csi300
+benchmark: &benchmark SH000300
+data_handler_config: &data_handler_config
+    start_time: 2008-01-01
+    end_time: 2020-08-01
+    fit_start_time: 2008-01-01
+    fit_end_time: 2014-12-31
+    instruments: *market
+port_analysis_config: &port_analysis_config
+    strategy:
+        class: TopkDropoutStrategy
+        module_path: qlib.contrib.strategy.strategy
+        kwargs:
+            topk: 50
+            n_drop: 5
+    backtest:
+        verbose: False
+        limit_threshold: 0.095
+        account: 100000000
+        benchmark: *benchmark
+        deal_price: close
+        open_cost: 0.0005
+        close_cost: 0.0015
+        min_cost: 5
+task:
+    model:
+        class: HATS
+        module_path: qlib.contrib.model.pytorch_gats
+        kwargs:
+            d_feat: 6
+            hidden_size: 64
+            num_layers: 2
+            dropout: 0.6
+            n_epochs: 200
+            lr: 1e-3
+            early_stop: 20
+            batch_size: 800
+            metric: IC
+            loss: mse
+            base_model: GRU
+            seed: 0
+            GPU: 0
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: ALPHA360_Denoise
+                module_path: qlib.contrib.data.handler
+                kwargs: *data_handler_config
+            segments:
+                train: [2008-01-01, 2014-12-31]
+                valid: [2015-01-01, 2016-12-31]
+                test: [2017-01-01, 2020-08-01]
+    record: 
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: 
+            config: *port_analysis_config

examples/benchmarks/LightGBM/README.md

@@ -0,0 +1,4 @@
+# LightGBM
+* Code: [https://github.com/microsoft/LightGBM](https://github.com/microsoft/LightGBM)
+* Paper: LightGBM: A Highly Efficient Gradient Boosting
+Decision Tree. [https://proceedings.neurips.cc/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf](https://proceedings.neurips.cc/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf).

examples/benchmarks/SFM/README.md

@@ -0,0 +1,4 @@
+# State-Frequency-Memory
+- State Frequency Memory (SFM) is a novel recurrent network that uses Discrete Fourier Transform (DFT) to decompose the hidden states of memory cells and capture the multi-frequency trading patterns from past market data to make stock price predictions. 
+- The code used in Qlib is a pyTorch implementation of SFM (Zhang, L., Aggarwal, C., & Qi, G. J. (2017,)).
+- Paper: Stock Price Prediction via Discovering Multi-Frequency Trading Patterns. https://www.cs.ucf.edu/~gqi/publications/kdd2017_stock.pdf.

examples/benchmarks/TabNet/README.md

@@ -0,0 +1,4 @@
+# TabNet
+* TabNet is a novel high-performance and interpretable canonical deep tabular data learning architectur. TabNet uses sequential attention to choose which features to reason from at each decision step, enabling interpretability and more effcient learning as the learning capacity is used for the most salient features.
+* The code used in Qlib is a pyTorch implementation of Tabnet (Arik, S. O., & Pfister, T. (2019). [https://github.com/dreamquark-ai/tabnet](https://github.com/dreamquark-ai/tabnet)
+* Paper: TabNet: Attentive Interpretable Tabular Learning. [https://arxiv.org/pdf/1908.07442.pdf](https://arxiv.org/pdf/1908.07442.pdf).

examples/benchmarks/XGBoost/README.md

@@ -0,0 +1,3 @@
+# XGBoost
+* Code: [https://github.com/dmlc/xgboost](https://github.com/dmlc/xgboost)
+* Paper: XGBoost: A Scalable Tree Boosting System. [https://dl.acm.org/doi/pdf/10.1145/2939672.2939785](https://dl.acm.org/doi/pdf/10.1145/2939672.2939785).

examples/workflow_by_code_alstm.py

@@ -0,0 +1,145 @@
+#  Copyright (c) Microsoft Corporation.
+#  Licensed under the MIT License.
+
+import sys
+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
+    provider_uri = "~/.qlib/qlib_data/cn_data"  # target_dir
+    if not exists_qlib_data(provider_uri):
+        print(f"Qlib data is not found in {provider_uri}")
+        sys.path.append(str(Path(__file__).resolve().parent.parent.joinpath("scripts")))
+        from get_data import GetData
+
+        GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
+
+    qlib.init(provider_uri=provider_uri, region=REG_CN)
+
+    MARKET = "csi300"
+    BENCHMARK = "SH000300"
+
+    ###################################
+    # train model
+    ###################################
+    DATA_HANDLER_CONFIG = {
+        "start_time": "2008-01-01",
+        "end_time": "2020-08-01",
+        "fit_start_time": "2008-01-01",
+        "fit_end_time": "2014-12-31",
+        "instruments": MARKET,
+    }
+
+    TRAINER_CONFIG = {
+        "train_start_time": "2008-01-01",
+        "train_end_time": "2014-12-31",
+        "validate_start_time": "2015-01-01",
+        "validate_end_time": "2016-12-31",
+        "test_start_time": "2017-01-01",
+        "test_end_time": "2020-08-01",
+    }
+
+    task = {
+        "model": {
+            "class": "ALSTM",
+            "module_path": "qlib.contrib.model.pytorch_alstm",
+            "kwargs": {
+                "d_feat": 6,
+                "hidden_size": 64,
+                "num_layers": 2,
+                "dropout": 0.0,
+                "n_epochs": 200,
+                "lr": 1e-3,
+                "early_stop": 20,
+                "batch_size": 800,
+                "metric": "IC",
+                "loss": "mse",
+                "seed": 0,
+                "GPU": 0,
+                "rnn_type": "GRU",
+            },
+        },
+        "dataset": {
+            "class": "DatasetH",
+            "module_path": "qlib.data.dataset",
+            "kwargs": {
+                "handler": {
+                    "class": "ALPHA360_Denoise",
+                    "module_path": "qlib.contrib.data.handler",
+                    "kwargs": DATA_HANDLER_CONFIG,
+                },
+                "segments": {
+                    "train": ("2008-01-01", "2014-12-31"),
+                    "valid": ("2015-01-01", "2016-12-31"),
+                    "test": ("2017-01-01", "2020-08-01"),
+                },
+            },
+        }
+        # You shoud record the data in specific sequence
+        # "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)
+
+    pred_score = model.predict(dataset)
+
+    # save pred_score to file
+    pred_score_path = Path("~/tmp/qlib/pred_score.pkl").expanduser()
+    pred_score_path.parent.mkdir(exist_ok=True, parents=True)
+    pred_score.to_pickle(pred_score_path)
+
+    ###################################
+    # backtest
+    ###################################
+    STRATEGY_CONFIG = {
+        "topk": 50,
+        "n_drop": 5,
+    }
+    BACKTEST_CONFIG = {
+        "verbose": False,
+        "limit_threshold": 0.095,
+        "account": 100000000,
+        "benchmark": BENCHMARK,
+        "deal_price": "close",
+        "open_cost": 0.0005,
+        "close_cost": 0.0015,
+        "min_cost": 5,
+    }
+
+    # use default strategy
+    # custom Strategy, refer to: TODO: Strategy API url
+    strategy = TopkDropoutStrategy(**STRATEGY_CONFIG)
+    report_normal, positions_normal = normal_backtest(pred_score, strategy=strategy, **BACKTEST_CONFIG)
+
+    ###################################
+    # analyze
+    # If need a more detailed analysis, refer to: examples/train_and_bakctest.ipynb
+    ###################################
+    analysis = dict()
+    analysis["excess_return_without_cost"] = risk_analysis(report_normal["return"] - report_normal["bench"])
+    analysis["excess_return_with_cost"] = risk_analysis(
+        report_normal["return"] - report_normal["bench"] - report_normal["cost"]
+    )
+    analysis_df = pd.concat(analysis)  # type: pd.DataFrame
+    print(analysis_df)

examples/workflow_by_code_gats.py

@@ -70,9 +70,10 @@ if __name__ == "__main__":
                 "lr": 1e-3,
                 "early_stop": 20,
                 "batch_size": 800,
-                "metric": "IC",
+                "metric": "loss",
                 "loss": "mse",
-                "base_model": "GRU",
+                "base_model": "LSTM",
+                "with_pretrain": True,
                 "seed": 0,
                 "GPU": 0,
             },

examples/workflow_by_code_hats.py

@@ -0,0 +1,145 @@
+#  Copyright (c) Microsoft Corporation.
+#  Licensed under the MIT License.
+
+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
+    provider_uri = "~/.qlib/qlib_data/cn_data"  # target_dir
+    if not exists_qlib_data(provider_uri):
+        print(f"Qlib data is not found in {provider_uri}")
+        sys.path.append(str(Path(__file__).resolve().parent.parent.joinpath("scripts")))
+        from get_data import GetData
+
+        GetData().qlib_data_cn(target_dir=provider_uri)
+
+    qlib.init(provider_uri=provider_uri, region=REG_CN)
+
+    MARKET = "csi300"
+    BENCHMARK = "SH000300"
+
+    ###################################
+    # train model
+    ###################################
+    DATA_HANDLER_CONFIG = {
+        "start_time": "2008-01-01",
+        "end_time": "2020-08-01",
+        "fit_start_time": "2008-01-01",
+        "fit_end_time": "2014-12-31",
+        "instruments": MARKET,
+    }
+
+    TRAINER_CONFIG = {
+        "train_start_time": "2008-01-01",
+        "train_end_time": "2014-12-31",
+        "validate_start_time": "2015-01-01",
+        "validate_end_time": "2016-12-31",
+        "test_start_time": "2017-01-01",
+        "test_end_time": "2020-08-01",
+    }
+
+    task = {
+        "model": {
+            "class": "HATS",
+            "module_path": "qlib.contrib.model.pytorch_hats",
+            "kwargs": {
+                "d_feat": 6,
+                "hidden_size": 64,
+                "num_layers": 2,
+                "dropout": 0.6,
+                "n_epochs": 200,
+                "lr": 1e-3,
+                "early_stop": 20,
+                "batch_size": 800,
+                "metric": "IC",
+                "loss": "mse",
+                "base_model": "LSTM",
+                "seed": 0,
+                "GPU": 0,
+            },
+        },
+        "dataset": {
+            "class": "DatasetH",
+            "module_path": "qlib.data.dataset",
+            "kwargs": {
+                "handler": {
+                    "class": "ALPHA360_Denoise",
+                    "module_path": "qlib.contrib.data.handler",
+                    "kwargs": DATA_HANDLER_CONFIG,
+                },
+                "segments": {
+                    "train": ("2008-01-01", "2014-12-31"),
+                    "valid": ("2015-01-01", "2016-12-31"),
+                    "test": ("2017-01-01", "2020-08-01"),
+                },
+            },
+        }
+        # You shoud record the data in specific sequence
+        # "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")
+
+    pred_score = model.predict(dataset)
+
+    # save pred_score to file
+    pred_score_path = Path("~/tmp/qlib/pred_score.pkl").expanduser()
+    pred_score_path.parent.mkdir(exist_ok=True, parents=True)
+    pred_score.to_pickle(pred_score_path)
+
+    ###################################
+    # backtest
+    ###################################
+    STRATEGY_CONFIG = {
+        "topk": 50,
+        "n_drop": 5,
+    }
+    BACKTEST_CONFIG = {
+        "verbose": False,
+        "limit_threshold": 0.095,
+        "account": 100000000,
+        "benchmark": BENCHMARK,
+        "deal_price": "close",
+        "open_cost": 0.0005,
+        "close_cost": 0.0015,
+        "min_cost": 5,
+    }
+
+    # use default strategy
+    # custom Strategy, refer to: TODO: Strategy API url
+    strategy = TopkDropoutStrategy(**STRATEGY_CONFIG)
+    report_normal, positions_normal = normal_backtest(pred_score, strategy=strategy, **BACKTEST_CONFIG)
+
+    ###################################
+    # analyze
+    # If need a more detailed analysis, refer to: examples/train_and_bakctest.ipynb
+    ###################################
+    analysis = dict()
+    analysis["excess_return_without_cost"] = risk_analysis(report_normal["return"] - report_normal["bench"])
+    analysis["excess_return_with_cost"] = risk_analysis(
+        report_normal["return"] - report_normal["bench"] - report_normal["cost"]
+    )
+    analysis_df = pd.concat(analysis)  # type: pd.DataFrame
+    print(analysis_df)