mirror of
https://github.com/microsoft/qlib.git
synced 2026-07-05 20:11:08 +08:00
72 lines
2.5 KiB
Python
Executable File
72 lines
2.5 KiB
Python
Executable File
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
import numpy as np
|
|
import pandas as pd
|
|
import xgboost as xgb
|
|
|
|
from ...model.base import Model
|
|
from ...data.dataset import DatasetH
|
|
from ...data.dataset.handler import DataHandlerLP
|
|
|
|
|
|
class XGBModel(Model):
|
|
"""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(),
|
|
**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")
|
|
|
|
dtrain = xgb.DMatrix(x_train.values, label=y_train_1d)
|
|
dvalid = xgb.DMatrix(x_valid.values, label=y_valid_1d)
|
|
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):
|
|
if self.model is None:
|
|
raise ValueError("model is not fitted yet!")
|
|
x_test = dataset.prepare("test", col_set="feature")
|
|
return pd.Series(self.model.predict(xgb.DMatrix(x_test.values)), index=x_test.index)
|