add get_feature_importance to model interpret

examples/model_interpreter.py

@@ -0,0 +1,81 @@
+#  Copyright (c) Microsoft Corporation.
+#  Licensed under the MIT License.
+
+
+import qlib
+from qlib.config import REG_CN
+
+from qlib.utils import exists_qlib_data, init_instance_by_config
+from qlib.tests.data import GetData
+
+market = "csi300"
+benchmark = "SH000300"
+
+###################################
+# 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,
+}
+
+task = {
+    "model": {
+        "class": "LGBModel",
+        "module_path": "qlib.contrib.model.gbdt",
+        "kwargs": {
+            "loss": "mse",
+            "colsample_bytree": 0.8879,
+            "learning_rate": 0.0421,
+            "subsample": 0.8789,
+            "lambda_l1": 205.6999,
+            "lambda_l2": 580.9768,
+            "max_depth": 8,
+            "num_leaves": 210,
+            "num_threads": 20,
+        },
+    },
+    "dataset": {
+        "class": "DatasetH",
+        "module_path": "qlib.data.dataset",
+        "kwargs": {
+            "handler": {
+                "class": "Alpha158",
+                "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"),
+            },
+        },
+    },
+}
+
+
+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}")
+        GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
+
+    qlib.init(provider_uri=provider_uri, region=REG_CN)
+
+    ###################################
+    # train model
+    ###################################
+    # model initialization
+    model = init_instance_by_config(task["model"])
+    dataset = init_instance_by_config(task["dataset"])
+    model.fit(dataset)
+
+    # get model feature importance
+    feature_importance = model.get_feature_importance()
+    print("feature importance:")
+    print(feature_importance)

qlib/contrib/model/catboost_model.py

@@ -10,9 +10,10 @@ from catboost.utils import get_gpu_device_count
 from ...model.base import Model
 from ...data.dataset import DatasetH
 from ...data.dataset.handler import DataHandlerLP
+from ...model.interpret.base import FeatureInt
 
 
-class CatBoostModel(Model):
+class CatBoostModel(Model, FeatureInt):
     """CatBoost Model"""
 
     def __init__(self, loss="RMSE", **kwargs):
@@ -69,6 +70,18 @@ class CatBoostModel(Model):
         x_test = dataset.prepare(segment, col_set="feature", data_key=DataHandlerLP.DK_I)
         return pd.Series(self.model.predict(x_test.values), index=x_test.index)
 
+    def get_feature_importance(self, *args, **kwargs) -> pd.Series:
+        """get feature importance
+
+        Notes
+        -----
+            parameters references:
+            https://catboost.ai/docs/concepts/python-reference_catboost_get_feature_importance.html#python-reference_catboost_get_feature_importance
+        """
+        return pd.Series(
+            data=self.model.get_feature_importance(*args, **kwargs), index=self.model.feature_names_
+        ).sort_values(ascending=False)
+
 
 if __name__ == "__main__":
     cat = CatBoostModel()

qlib/contrib/model/double_ensemble.py

@@ -8,10 +8,11 @@ from typing import Text, Union
 from ...model.base import Model
 from ...data.dataset import DatasetH
 from ...data.dataset.handler import DataHandlerLP
+from ...model.interpret.base import FeatureInt
 from ...log import get_module_logger
 
 
-class DEnsembleModel(Model):
+class DEnsembleModel(Model, FeatureInt):
     """Double Ensemble Model"""
 
     def __init__(
@@ -121,8 +122,8 @@ class DEnsembleModel(Model):
         else:
             raise ValueError("LightGBM doesn't support multi-label training")
 
-        dtrain = lgb.Dataset(x_train.values, label=y_train, weight=weights)
+        dtrain = lgb.Dataset(x_train, label=y_train, weight=weights)
-        dvalid = lgb.Dataset(x_valid.values, label=y_valid)
+        dvalid = lgb.Dataset(x_valid, label=y_valid)
         return dtrain, dvalid
 
     def sample_reweight(self, loss_curve, loss_values, k_th):
@@ -203,8 +204,8 @@ class DEnsembleModel(Model):
         for i_b, b in enumerate(sorted_bins):
             b_feat = features[g["bins"] == b]
             num_feat = int(np.ceil(self.sample_ratios[i_b] * len(b_feat)))
-            res_feat = res_feat + np.random.choice(b_feat, size=num_feat).tolist()
+            res_feat = res_feat + np.random.choice(b_feat, size=num_feat, replace=False).tolist()
-        return pd.Index(res_feat)
+        return pd.Index(set(res_feat))
 
     def get_loss(self, label, pred):
         if self.loss == "mse":
@@ -249,3 +250,16 @@ class DEnsembleModel(Model):
         x_data, y_data = df_data["feature"].loc[:, features], df_data["label"]
         pred_sub = pd.Series(submodel.predict(x_data.values), index=x_data.index)
         return pred_sub
+
+    def get_feature_importance(self, *args, **kwargs) -> pd.Series:
+        """get feature importance
+
+        Notes
+        -----
+            parameters reference:
+            https://lightgbm.readthedocs.io/en/latest/pythonapi/lightgbm.Booster.html?highlight=feature_importance#lightgbm.Booster.feature_importance
+        """
+        res = []
+        for _model, _weight in zip(self.ensemble, self.sub_weights):
+            res.append(pd.Series(_model.feature_importance(*args, **kwargs), index=_model.feature_name()) * _weight)
+        return pd.concat(res, axis=1, sort=False).sum(axis=1).sort_values(ascending=False)

qlib/contrib/model/gbdt.py

@@ -8,9 +8,10 @@ from typing import Text, Union
 from ...model.base import ModelFT
 from ...data.dataset import DatasetH
 from ...data.dataset.handler import DataHandlerLP
+from ...model.interpret.base import LightGBMFInt
 
 
-class LGBModel(ModelFT):
+class LGBModel(ModelFT, LightGBMFInt):
     """LightGBM Model"""
 
     def __init__(self, loss="mse", **kwargs):
@@ -33,8 +34,8 @@ class LGBModel(ModelFT):
         else:
             raise ValueError("LightGBM doesn't support multi-label training")
 
-        dtrain = lgb.Dataset(x_train.values, label=y_train)
+        dtrain = lgb.Dataset(x_train, label=y_train)
-        dvalid = lgb.Dataset(x_valid.values, label=y_valid)
+        dvalid = lgb.Dataset(x_valid, label=y_valid)
         return dtrain, dvalid
 
     def fit(

qlib/contrib/model/highfreq_gdbt_model.py

@@ -1,17 +1,18 @@
 # Copyright (c) Microsoft Corporation.
 # Licensed under the MIT License.
 
+import warnings
 import numpy as np
 import pandas as pd
 import lightgbm as lgb
 
-from qlib.model.base import ModelFT
+from ...model.base import ModelFT
-from qlib.data.dataset import DatasetH
+from ...data.dataset import DatasetH
-from qlib.data.dataset.handler import DataHandlerLP
+from ...data.dataset.handler import DataHandlerLP
-import warnings
+from ...model.interpret.base import LightGBMFInt
 
 
-class HFLGBModel(ModelFT):
+class HFLGBModel(ModelFT, LightGBMFInt):
     """LightGBM Model for high frequency prediction"""
 
     def __init__(self, loss="mse", **kwargs):
@@ -97,8 +98,8 @@ class HFLGBModel(ModelFT):
         else:
             raise ValueError("LightGBM doesn't support multi-label training")
 
-        dtrain = lgb.Dataset(x_train.values, label=y_train)
+        dtrain = lgb.Dataset(x_train, label=y_train)
-        dvalid = lgb.Dataset(x_valid.values, label=y_valid)
+        dvalid = lgb.Dataset(x_valid, label=y_valid)
         return dtrain, dvalid
 
     def fit(

qlib/contrib/model/xgboost.py

@@ -8,9 +8,10 @@ from typing import Text, Union
 from ...model.base import Model
 from ...data.dataset import DatasetH
 from ...data.dataset.handler import DataHandlerLP
+from ...model.interpret.base import FeatureInt
 
 
-class XGBModel(Model):
+class XGBModel(Model, FeatureInt):
     """XGBModel Model"""
 
     def __init__(self, **kwargs):
@@ -42,8 +43,8 @@ class XGBModel(Model):
         else:
             raise ValueError("XGBoost doesn't support multi-label training")
 
-        dtrain = xgb.DMatrix(x_train.values, label=y_train_1d)
+        dtrain = xgb.DMatrix(x_train, label=y_train_1d)
-        dvalid = xgb.DMatrix(x_valid.values, label=y_valid_1d)
+        dvalid = xgb.DMatrix(x_valid, label=y_valid_1d)
         self.model = xgb.train(
             self._params,
             dtrain=dtrain,
@@ -62,3 +63,13 @@ class XGBModel(Model):
             raise ValueError("model is not fitted yet!")
         x_test = dataset.prepare(segment, col_set="feature", data_key=DataHandlerLP.DK_I)
         return pd.Series(self.model.predict(xgb.DMatrix(x_test.values)), index=x_test.index)
+
+    def get_feature_importance(self, *args, **kwargs) -> pd.Series:
+        """get feature importance
+
+        Notes
+        -------
+            parameters reference:
+                https://xgboost.readthedocs.io/en/latest/python/python_api.html#xgboost.Booster.get_score
+        """
+        return pd.Series(self.model.get_score(*args, **kwargs)).sort_values(ascending=False)

qlib/model/interpret/base.py

@@ -0,0 +1,33 @@
+#  Copyright (c) Microsoft Corporation.
+#  Licensed under the MIT License.
+
+"""
+Interfaces to interpret models
+"""
+
+import pandas as pd
+from abc import abstractmethod
+
+
+class FeatureInt:
+    """Feature (Int)erpreter"""
+
+    @abstractmethod
+    def get_feature_importance(self) -> pd.Series:
+        ...
+
+
+class LightGBMFInt(FeatureInt):
+    """LightGBM (F)eature (Int)erpreter"""
+
+    def get_feature_importance(self, *args, **kwargs) -> pd.Series:
+        """get feature importance
+
+        Notes
+        -----
+            parameters reference:
+            https://lightgbm.readthedocs.io/en/latest/pythonapi/lightgbm.Booster.html?highlight=feature_importance#lightgbm.Booster.feature_importance
+        """
+        return pd.Series(self.model.feature_importance(*args, **kwargs), index=self.model.feature_name()).sort_values(
+            ascending=False
+        )