Merge remote-tracking branch 'microsoft/main' into online_srv

qlib/contrib/backtest/backtest.py

@@ -15,7 +15,8 @@ LOG = get_module_logger("backtest")
 
 
 def backtest(pred, strategy, executor, trade_exchange, shift, verbose, account, benchmark, return_order):
-    """Parameters
+    """
+    Parameters
     ----------
     pred : pandas.DataFrame
         predict should has <datetime, instrument> index and one `score` column
@@ -124,7 +125,9 @@ def backtest(pred, strategy, executor, trade_exchange, shift, verbose, account,
 
 
 def update_account(trade_account, trade_info, trade_exchange, trade_date):
-    """Update the account and strategy
+    """
+    Update the account and strategy
+
     Parameters
     ----------
     trade_account : Account()

qlib/contrib/backtest/position.py

@@ -128,7 +128,7 @@ class Position:
         return self.position["cash"]
 
     def get_stock_amount_dict(self):
-        """generate stock amount dict {stock_id : amount of stock} """
+        """generate stock amount dict {stock_id : amount of stock}"""
         d = {}
         stock_list = self.get_stock_list()
         for stock_code in stock_list:

qlib/contrib/eva/alpha.py

@@ -8,6 +8,59 @@ import pandas as pd
 from typing import Tuple
 
 
+def calc_long_short_prec(
+    pred: pd.Series, label: pd.Series, date_col="datetime", quantile: float = 0.2, dropna=False, is_alpha=False
+) -> Tuple[pd.Series, pd.Series]:
+    """
+    calculate the precision for long and short operation
+
+
+    :param pred/label: index is **pd.MultiIndex**, index name is **[datetime, instruments]**; columns names is **[score]**.
+
+            .. code-block:: python
+                                                  score
+                datetime            instrument
+                2020-12-01 09:30:00 SH600068    0.553634
+                                    SH600195    0.550017
+                                    SH600276    0.540321
+                                    SH600584    0.517297
+                                    SH600715    0.544674
+    label :
+        label
+    date_col :
+        date_col
+
+    Returns
+    -------
+    (pd.Series, pd.Series)
+        long precision and short precision in time level
+    """
+    if is_alpha:
+        label = label - label.mean(level=date_col)
+    if int(1 / quantile) >= len(label.index.get_level_values(1).unique()):
+        raise ValueError("Need more instruments to calculate precision")
+
+    df = pd.DataFrame({"pred": pred, "label": label})
+    if dropna:
+        df.dropna(inplace=True)
+
+    group = df.groupby(level=date_col)
+
+    N = lambda x: int(len(x) * quantile)
+    # find the top/low quantile of prediction and treat them as long and short target
+    long = group.apply(lambda x: x.nlargest(N(x), columns="pred").label).reset_index(level=0, drop=True)
+    short = group.apply(lambda x: x.nsmallest(N(x), columns="pred").label).reset_index(level=0, drop=True)
+
+    groupll = long.groupby(date_col)
+    l_dom = groupll.apply(lambda x: x > 0)
+    l_c = groupll.count()
+
+    groups = short.groupby(date_col)
+    s_dom = groups.apply(lambda x: x < 0)
+    s_c = groups.count()
+    return (l_dom.groupby(date_col).sum() / l_c), (s_dom.groupby(date_col).sum() / s_c)
+
+
 def calc_ic(pred: pd.Series, label: pd.Series, date_col="datetime", dropna=False) -> Tuple[pd.Series, pd.Series]:
     """calc_ic.
 

qlib/contrib/model/highfreq_gdbt_model.py

@@ -0,0 +1,157 @@
+# Copyright (c) Microsoft Corporation.
+# Licensed under the MIT License.
+
+import numpy as np
+import pandas as pd
+import lightgbm as lgb
+
+from qlib.model.base import ModelFT
+from qlib.data.dataset import DatasetH
+from qlib.data.dataset.handler import DataHandlerLP
+import warnings
+
+
+class HFLGBModel(ModelFT):
+    """LightGBM Model for high frequency prediction"""
+
+    def __init__(self, loss="mse", **kwargs):
+        if loss not in {"mse", "binary"}:
+            raise NotImplementedError
+        self.params = {"objective": loss, "verbosity": -1}
+        self.params.update(kwargs)
+        self.model = None
+
+    def _cal_signal_metrics(self, y_test, l_cut, r_cut):
+        """
+        Calcaute the signal metrics by daily level
+        """
+        up_pre, down_pre = [], []
+        up_alpha_ll, down_alpha_ll = [], []
+        for date in y_test.index.get_level_values(0).unique():
+            df_res = y_test.loc[date].sort_values("pred")
+            if int(l_cut * len(df_res)) < 10:
+                warnings.warn("Warning: threhold is too low or instruments number is not enough")
+                continue
+            top = df_res.iloc[: int(l_cut * len(df_res))]
+            bottom = df_res.iloc[int(r_cut * len(df_res)) :]
+
+            down_precision = len(top[top[top.columns[0]] < 0]) / (len(top))
+            up_precision = len(bottom[bottom[top.columns[0]] > 0]) / (len(bottom))
+
+            down_alpha = top[top.columns[0]].mean()
+            up_alpha = bottom[bottom.columns[0]].mean()
+
+            up_pre.append(up_precision)
+            down_pre.append(down_precision)
+            up_alpha_ll.append(up_alpha)
+            down_alpha_ll.append(down_alpha)
+
+        return (
+            np.array(up_pre).mean(),
+            np.array(down_pre).mean(),
+            np.array(up_alpha_ll).mean(),
+            np.array(down_alpha_ll).mean(),
+        )
+
+    def hf_signal_test(self, dataset: DatasetH, threhold=0.2):
+        """
+        Test the sigal in high frequency test set
+        """
+        if self.model == None:
+            raise ValueError("Model hasn't been trained yet")
+        df_test = dataset.prepare("test", col_set=["feature", "label"], data_key=DataHandlerLP.DK_I)
+        df_test.dropna(inplace=True)
+        x_test, y_test = df_test["feature"], df_test["label"]
+        # Convert label into alpha
+        y_test[y_test.columns[0]] = y_test[y_test.columns[0]] - y_test[y_test.columns[0]].mean(level=0)
+
+        res = pd.Series(self.model.predict(x_test.values), index=x_test.index)
+        y_test["pred"] = res
+
+        up_p, down_p, up_a, down_a = self._cal_signal_metrics(y_test, threhold, 1 - threhold)
+        print("===============================")
+        print("High frequency signal test")
+        print("===============================")
+        print("Test set precision: ")
+        print("Positive precision: {}, Negative precision: {}".format(up_p, down_p))
+        print("Test Alpha Average in test set: ")
+        print("Positive average alpha: {}, Negative average alpha: {}".format(up_a, down_a))
+
+    def _prepare_data(self, dataset: DatasetH):
+        df_train, df_valid = dataset.prepare(
+            ["train", "valid"], col_set=["feature", "label"], data_key=DataHandlerLP.DK_L
+        )
+
+        x_train, y_train = df_train["feature"], df_train["label"]
+        x_valid, y_valid = df_train["feature"], df_valid["label"]
+        if y_train.values.ndim == 2 and y_train.values.shape[1] == 1:
+            l_name = df_train["label"].columns[0]
+            # Convert label into alpha
+            df_train["label"][l_name] = df_train["label"][l_name] - df_train["label"][l_name].mean(level=0)
+            df_valid["label"][l_name] = df_valid["label"][l_name] - df_valid["label"][l_name].mean(level=0)
+            mapping_fn = lambda x: 0 if x < 0 else 1
+            df_train["label_c"] = df_train["label"][l_name].apply(mapping_fn)
+            df_valid["label_c"] = df_valid["label"][l_name].apply(mapping_fn)
+            x_train, y_train = df_train["feature"], df_train["label_c"].values
+            x_valid, y_valid = df_valid["feature"], df_valid["label_c"].values
+        else:
+            raise ValueError("LightGBM doesn't support multi-label training")
+
+        dtrain = lgb.Dataset(x_train.values, label=y_train)
+        dvalid = lgb.Dataset(x_valid.values, label=y_valid)
+        return dtrain, dvalid
+
+    def fit(
+        self,
+        dataset: DatasetH,
+        num_boost_round=1000,
+        early_stopping_rounds=50,
+        verbose_eval=20,
+        evals_result=dict(),
+        **kwargs
+    ):
+        dtrain, dvalid = self._prepare_data(dataset)
+        self.model = lgb.train(
+            self.params,
+            dtrain,
+            num_boost_round=num_boost_round,
+            valid_sets=[dtrain, dvalid],
+            valid_names=["train", "valid"],
+            early_stopping_rounds=early_stopping_rounds,
+            verbose_eval=verbose_eval,
+            evals_result=evals_result,
+            **kwargs
+        )
+        evals_result["train"] = list(evals_result["train"].values())[0]
+        evals_result["valid"] = list(evals_result["valid"].values())[0]
+
+    def predict(self, dataset):
+        if self.model is None:
+            raise ValueError("model is not fitted yet!")
+        x_test = dataset.prepare("test", col_set="feature", data_key=DataHandlerLP.DK_I)
+        return pd.Series(self.model.predict(x_test.values), index=x_test.index)
+
+    def finetune(self, dataset: DatasetH, num_boost_round=10, verbose_eval=20):
+        """
+        finetune model
+
+        Parameters
+        ----------
+        dataset : DatasetH
+            dataset for finetuning
+        num_boost_round : int
+            number of round to finetune model
+        verbose_eval : int
+            verbose level
+        """
+        # Based on existing model and finetune by train more rounds
+        dtrain, _ = self._prepare_data(dataset)
+        self.model = lgb.train(
+            self.params,
+            dtrain,
+            num_boost_round=num_boost_round,
+            init_model=self.model,
+            valid_sets=[dtrain],
+            valid_names=["train"],
+            verbose_eval=verbose_eval,
+        )

qlib/contrib/report/analysis_position/cumulative_return.py

@@ -214,7 +214,7 @@ def cumulative_return_graph(
                 features_df = D.features(D.instruments('csi500'), ['Ref($close, -1)/$close - 1'], pred_df_dates.min(), pred_df_dates.max())
                 features_df.columns = ['label']
 
-                qcr.cumulative_return_graph(positions, report_normal_df, features_df)
+                qcr.analysis_position.cumulative_return_graph(positions, report_normal_df, features_df)
 
 
         Graph desc:

qlib/contrib/report/analysis_position/rank_label.py

@@ -94,7 +94,7 @@ def rank_label_graph(
                 features_df = D.features(D.instruments('csi500'), ['Ref($close, -1)/$close-1'], pred_df_dates.min(), pred_df_dates.max())
                 features_df.columns = ['label']
 
-                qcr.rank_label_graph(positions, features_df, pred_df_dates.min(), pred_df_dates.max())
+                qcr.analysis_position.rank_label_graph(positions, features_df, pred_df_dates.min(), pred_df_dates.max())
 
 
     :param position: position data; **qlib.contrib.backtest.backtest.backtest** result.

qlib/contrib/report/analysis_position/report.py

@@ -186,7 +186,7 @@ def report_graph(report_df: pd.DataFrame, show_notebook: bool = True) -> [list,
 
                 report_normal_df, _ = backtest(pred_df, strategy, **bparas)
 
-                qcr.report_graph(report_normal_df)
+                qcr.analysis_position.report_graph(report_normal_df)
 
     :param report_df: **df.index.name** must be **date**, **df.columns** must contain **return**, **turnover**, **cost**, **bench**.
 

qlib/contrib/report/graph.py

@@ -18,7 +18,7 @@ from ...utils import get_module_by_module_path
 
 
 class BaseGraph:
-    """"""
+    """ """
 
     _name = None
 

qlib/contrib/workflow/record_temp.py

@@ -1,10 +1,11 @@
 #  Copyright (c) Microsoft Corporation.
 #  Licensed under the MIT License.
 
+import logging
 import pandas as pd
+import numpy as np
 from sklearn.metrics import mean_squared_error
 from typing import Dict, Text, Any
-import numpy as np
 
 from ...contrib.eva.alpha import calc_ic
 from ...workflow.record_temp import RecordTemp
@@ -12,7 +13,7 @@ from ...workflow.record_temp import SignalRecord
 from ...data import dataset as qlib_dataset
 from ...log import get_module_logger
 
-logger = get_module_logger("workflow", "INFO")
+logger = get_module_logger("workflow", logging.INFO)
 
 
 class MultiSegRecord(RecordTemp):