liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-15 08:46:56 +08:00
Code Activity

add finetune example & fix serial bug

Browse Source
This commit is contained in:
Young
2020-11-16 13:11:39 +00:00
parent 3e04ded750
commit 90d41e4022
5 changed files with 203 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files

84
qlib/contrib/model/gbdt.py
View File

@@ -5,56 +5,54 @@ import numpy as np
import pandas as pd
import lightgbm as lgb
from ...model.base import Model
from ...model.base import ModelFT
from ...data.dataset import DatasetH
from ...data.dataset.handler import DataHandlerLP
class LGBModel(Model):
class LGBModel(ModelFT):
"""LightGBM Model"""
def __init__(self, loss="mse", **kwargs):
if loss not in {"mse", "binary"}:
raise NotImplementedError
self._params = {"objective": loss}
self._params.update(kwargs)
self.params = {"objective": loss}
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
)
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_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)
y_train, y_valid = np.squeeze(y_train.values), np.squeeze(y_valid.values)
else:
raise ValueError("LightGBM doesn't support multi-label training")
dtrain = lgb.Dataset(x_train.values, label=y_train_1d)
dvalid = lgb.Dataset(x_valid.values, label=y_valid_1d)
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
)
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]
@@ -63,3 +61,25 @@ class LGBModel(Model):
raise ValueError("model is not fitted yet!")
x_test = dataset.prepare("test", col_set="feature")
return pd.Series(self.model.predict(np.squeeze(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
"""
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)