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

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.
+1. Please be **aware** that this script can only support `Python 3.5 - 3.8`.
-2. New datasets should be registered in ``data_formatters``, for detail please visit the source.
+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
+        add = xor(bool(f.name.lower() in models), bool(exclude))
-        folders[f.name] = str(path.resolve())
+        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):

qlib/contrib/data/handler.py

@@ -10,6 +10,28 @@ from inspect import getfullargspec
 import copy
 
 
+def check_transform_proc(proc_l, fit_start_time, fit_end_time):
+    new_l = []
+    for p in proc_l:
+        if not isinstance(p, Processor):
+            klass, pkwargs = get_cls_kwargs(p, processor_module)
+            args = getfullargspec(klass).args
+            if "fit_start_time" in args and "fit_end_time" in args:
+                assert (
+                    fit_start_time is not None and fit_end_time is not None
+                ), "Make sure `fit_start_time` and `fit_end_time` are not None."
+                pkwargs.update(
+                    {
+                        "fit_start_time": fit_start_time,
+                        "fit_end_time": fit_end_time,
+                    }
+                )
+            new_l.append({"class": klass.__name__, "kwargs": pkwargs})
+        else:
+            new_l.append(p)
+    return new_l
+
+
 class ALPHA360_Denoise(DataHandlerLP):
     def __init__(self, instruments="csi500", start_time=None, end_time=None, fit_start_time=None, fit_end_time=None):
         data_loader = {
@@ -83,8 +105,31 @@ class ALPHA360_Denoise(DataHandlerLP):
         return fields, names
 
 
+_DEFAULT_LEARN_PROCESSORS = [
+    {"class": "DropnaLabel"},
+    {"class": "CSZScoreNorm", "kwargs": {"fields_group": "label"}},
+]
+_DEFAULT_INFER_PROCESSORS = [
+    {"class": "ProcessInf", "kwargs": {}},
+    {"class": "ZScoreNorm", "kwargs": {}},
+    {"class": "Fillna", "kwargs": {}},
+]
+
+
 class ALPHA360(DataHandlerLP):
-    def __init__(self, instruments="csi500", start_time=None, end_time=None, fit_start_time=None, fit_end_time=None):
+    def __init__(
+        self,
+        instruments="csi500",
+        start_time=None,
+        end_time=None,
+        infer_processors=_DEFAULT_INFER_PROCESSORS,
+        learn_processors=_DEFAULT_LEARN_PROCESSORS,
+        fit_start_time=None,
+        fit_end_time=None,
+    ):
+        infer_processors = check_transform_proc(infer_processors, fit_start_time, fit_end_time)
+        learn_processors = check_transform_proc(learn_processors, fit_start_time, fit_end_time)
+
         data_loader = {
             "class": "QlibDataLoader",
             "kwargs": {
@@ -95,16 +140,6 @@ class ALPHA360(DataHandlerLP):
             },
         }
 
-        learn_processors = [
-            {"class": "DropnaLabel", "kwargs": {"fields_group": "label"}},
-            {"class": "CSZScoreNorm", "kwargs": {"fields_group": "label"}},
-        ]
-        infer_processors = [
-            {"class": "ProcessInf", "kwargs": {}},
-            {"class": "ZscoreNorm", "kwargs": {"fit_start_time": fit_start_time, "fit_end_time": fit_end_time}},
-            {"class": "Fillna", "kwargs": {}},
-        ]
-
         super().__init__(
             instruments,
             start_time,
@@ -168,33 +203,12 @@ class Alpha158(DataHandlerLP):
         start_time=None,
         end_time=None,
         infer_processors=[],
-        learn_processors=["DropnaLabel", {"class": "CSZScoreNorm", "kwargs": {"fields_group": "label"}}],
+        learn_processors=_DEFAULT_LEARN_PROCESSORS,
         fit_start_time=None,
         fit_end_time=None,
     ):
-        def check_transform_proc(proc_l):
+        infer_processors = check_transform_proc(infer_processors, fit_start_time, fit_end_time)
-            new_l = []
+        learn_processors = check_transform_proc(learn_processors, fit_start_time, fit_end_time)
-            for p in proc_l:
-                if not isinstance(p, Processor):
-                    klass, pkwargs = get_cls_kwargs(p, processor_module)
-                    args = getfullargspec(klass).args
-                    if "fit_start_time" in args and "fit_end_time" in args:
-                        assert (
-                            fit_start_time is not None and fit_end_time is not None
-                        ), "Make sure `fit_start_time` and `fit_end_time` are not None."
-                        pkwargs.update(
-                            {
-                                "fit_start_time": fit_start_time,
-                                "fit_end_time": fit_end_time,
-                            }
-                        )
-                    new_l.append({"class": klass.__name__, "kwargs": pkwargs})
-                else:
-                    new_l.append(p)
-            return new_l
-
-        infer_processors = check_transform_proc(infer_processors)
-        learn_processors = check_transform_proc(learn_processors)
 
         data_loader = {
             "class": "QlibDataLoader",

qlib/contrib/model/pytorch_gru.py

@@ -28,14 +28,10 @@ class GRU(Model):
 
     Parameters
     ----------
-    input_dim : int
+    d_feat : int
-        input dimension
+        input dimension for each time step
-    output_dim : int
+    metric: str
-        output dimension
+        the evaluate metric used in early stop
-    layers : tuple
-        layer sizes
-    lr : float
-        learning rate
     optimizer : str
         optimizer name
     GPU : str
@@ -112,10 +108,6 @@ class GRU(Model):
             )
         )
 
-        if loss not in {"mse", "binary"}:
-            raise NotImplementedError("loss {} is not supported!".format(loss))
-        self._scorer = mean_squared_error if loss == "mse" else roc_auc_score
-
         self.gru_model = GRUModel(
             d_feat=self.d_feat, hidden_size=self.hidden_size, num_layers=self.num_layers, dropout=self.dropout
         )
@@ -251,7 +243,6 @@ class GRU(Model):
         # train
         self.logger.info("training...")
         self._fitted = True
-        # return
 
         for step in range(self.n_epochs):
             self.logger.info("Epoch%d:", step)

qlib/contrib/model/pytorch_lstm.py

@@ -28,14 +28,10 @@ class LSTM(Model):
 
     Parameters
     ----------
-    input_dim : int
+    d_feat : int
-        input dimension
+        input dimension for each time step
-    output_dim : int
+    metric: str
-        output dimension
+        the evaluate metric used in early stop
-    layers : tuple
-        layer sizes
-    lr : float
-        learning rate
     optimizer : str
         optimizer name
     GPU : str
@@ -112,10 +108,6 @@ class LSTM(Model):
             )
         )
 
-        if loss not in {"mse", "binary"}:
-            raise NotImplementedError("loss {} is not supported!".format(loss))
-        self._scorer = mean_squared_error if loss == "mse" else roc_auc_score
-
         self.lstm_model = LSTMModel(
             d_feat=self.d_feat, hidden_size=self.hidden_size, num_layers=self.num_layers, dropout=self.dropout
         )
@@ -251,7 +243,6 @@ class LSTM(Model):
         # train
         self.logger.info("training...")
         self._fitted = True
-        # return
 
         for step in range(self.n_epochs):
             self.logger.info("Epoch%d:", step)

qlib/data/dataset/processor.py

@@ -166,7 +166,9 @@ class MinMaxNorm(Processor):
         return df
 
 
-class ZscoreNorm(Processor):
+class ZScoreNorm(Processor):
+    """ZScore Normalization"""
+
     def __init__(self, fit_start_time, fit_end_time, fields_group=None):
         self.fit_start_time = fit_start_time
         self.fit_end_time = fit_end_time
@@ -193,6 +195,42 @@ class ZscoreNorm(Processor):
         return df
 
 
+class RobustZScoreNorm(Processor):
+    """Robust ZScore Normalization
+
+    Use robust statistics for Z-Score normalization:
+        mean(x) = median(x)
+        std(x) = MAD(x) * 1.4826
+
+    Reference:
+        https://en.wikipedia.org/wiki/Median_absolute_deviation.
+    """
+
+    def __init__(self, fit_start_time, fit_end_time, fields_group=None, clip_outlier=True):
+        self.fit_start_time = fit_start_time
+        self.fit_end_time = fit_end_time
+        self.fields_group = fields_group
+        self.clip_outlier = clip_outlier
+
+    def fit(self, df):
+        df = fetch_df_by_index(df, slice(self.fit_start_time, self.fit_end_time), level="datetime")
+        self.cols = get_group_columns(df, self.fields_group)
+        X = df[self.cols].values
+        self.mean_train = np.nanmedian(X, axis=0)
+        self.std_train = np.nanmedian(np.abs(X - self.mean_train), axis=0)
+        self.std_train += EPS
+        self.std_train *= 1.4826
+
+    def __call__(self, df):
+        X = df[self.cols]
+        X -= self.mean_train
+        X /= self.std_train
+        df[self.cols] = X
+        if self.clip_outlier:
+            df.clip(-3, 3, inplace=True)
+        return df
+
+
 class CSZScoreNorm(Processor):
     """Cross Sectional ZScore Normalization"""
 

qlib/workflow/cli.py

@@ -27,9 +27,9 @@ def sys_config(config, config_path):
     Parameters
     ----------
     config : dict
-        configuration of the workflow
+        configuration of the workflow.
     config_path : str
-        configuration of the path
+        configuration of the path.
     """
     sys_config = config.get("sys", {})