mirror of
https://github.com/microsoft/qlib.git
synced 2026-07-07 04:50:56 +08:00
be4646b4b7
* Intermediate version * Fix yaml template & Successfully run rolling * Be compatible with benchmark * Get same results with previous linear model * Black formatting * Update black * Update the placeholder mechanism * Update CI * Update CI * Upgrade Black * Fix CI and simplify code * Fix CI * Move the data processing caching mechanism into utils. * Adjusting DDG-DA * Organize import
86 lines
3.0 KiB
Python
Executable File
86 lines
3.0 KiB
Python
Executable File
# Copyright (c) Microsoft Corporation.
|
|
# Licensed under the MIT License.
|
|
|
|
import numpy as np
|
|
import pandas as pd
|
|
import xgboost as xgb
|
|
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 ...data.dataset.weight import Reweighter
|
|
|
|
|
|
class XGBModel(Model, FeatureInt):
|
|
"""XGBModel Model"""
|
|
|
|
def __init__(self, **kwargs):
|
|
self._params = {}
|
|
self._params.update(kwargs)
|
|
self.model = None
|
|
|
|
def fit(
|
|
self,
|
|
dataset: DatasetH,
|
|
num_boost_round=1000,
|
|
early_stopping_rounds=50,
|
|
verbose_eval=20,
|
|
evals_result=dict(),
|
|
reweighter=None,
|
|
**kwargs
|
|
):
|
|
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_valid["feature"], df_valid["label"]
|
|
|
|
# Lightgbm need 1D array as its label
|
|
if y_train.values.ndim == 2 and y_train.values.shape[1] == 1:
|
|
y_train_1d, y_valid_1d = np.squeeze(y_train.values), np.squeeze(y_valid.values)
|
|
else:
|
|
raise ValueError("XGBoost doesn't support multi-label training")
|
|
|
|
if reweighter is None:
|
|
w_train = None
|
|
w_valid = None
|
|
elif isinstance(reweighter, Reweighter):
|
|
w_train = reweighter.reweight(df_train)
|
|
w_valid = reweighter.reweight(df_valid)
|
|
else:
|
|
raise ValueError("Unsupported reweighter type.")
|
|
|
|
dtrain = xgb.DMatrix(x_train.values, label=y_train_1d, weight=w_train)
|
|
dvalid = xgb.DMatrix(x_valid.values, label=y_valid_1d, weight=w_valid)
|
|
self.model = xgb.train(
|
|
self._params,
|
|
dtrain=dtrain,
|
|
num_boost_round=num_boost_round,
|
|
evals=[(dtrain, "train"), (dvalid, "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: DatasetH, segment: Union[Text, slice] = "test"):
|
|
if self.model is None:
|
|
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)), 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)
|