liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-11 23:06:58 +08:00
Code Activity

DDG-DA paper code (#743)

Browse Source 
* Merge data selection to main

* Update trainer for reweighter

* Typos fixed.

* update data selection interface

* successfully run exp after refactor some interface

* data selection share handler &  trainer

* fix meta model time series bug

* fix online workflow set_uri bug

* fix set_uri bug

* updawte ds docs and delay trainer bug

* docs

* resume reweighter

* add reweighting result

* fix qlib model import

* make recorder more friendly

* fix experiment workflow bug

* commit for merging master incase of conflictions

* Successful run DDG-DA with a single command

* remove unused code

* asdd more docs

* Update README.md

* Update & fix some bugs.

* Update configuration & remove debug functions

* Update README.md

* Modfify horizon from code rather than yaml

* Update performance in README.md

* fix part comments

* Remove unfinished TCTS.

* Fix some details.

* Update meta docs

* Update README.md of the benchmarks_dynamic

* Update README.md files

* Add README.md to the rolling_benchmark baseline.

* Refine the docs and link

* Rename README.md in benchmarks_dynamic.

* Remove comments.

* auto download data

Co-authored-by: wendili-cs <wendili.academic@qq.com>
Co-authored-by: demon143 <785696300@qq.com>
This commit is contained in:
you-n-g
2022-01-10 16:52:37 +08:00
committed by GitHub
parent 184ce34a34
commit cf35562e84
52 changed files with 2441 additions and 456 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
qlib/contrib/model/linear.py
View File

@@ -4,6 +4,7 @@
import numpy as np
import pandas as pd
from typing import Text, Union
from qlib.data.dataset.weight import Reweighter
from scipy.optimize import nnls
from sklearn.linear_model import LinearRegression, Ridge, Lasso
@@ -49,33 +50,40 @@ class LinearModel(Model):
self.coef_ = None
def fit(self, dataset: DatasetH):
def fit(self, dataset: DatasetH, reweighter: Reweighter = None):
df_train = dataset.prepare("train", col_set=["feature", "label"], data_key=DataHandlerLP.DK_L)
if df_train.empty:
raise ValueError("Empty data from dataset, please check your dataset config.")
if reweighter is not None:
w: pd.Series = reweighter.reweight(df_train)
w = w.values
else:
w = None
X, y = df_train["feature"].values, np.squeeze(df_train["label"].values)
if self.estimator in [self.OLS, self.RIDGE, self.LASSO]:
self._fit(X, y)
self._fit(X, y, w)
elif self.estimator == self.NNLS:
self._fit_nnls(X, y)
self._fit_nnls(X, y, w)
else:
raise ValueError(f"unknown estimator `{self.estimator}`")
return self
def _fit(self, X, y):
def _fit(self, X, y, w):
if self.estimator == self.OLS:
model = LinearRegression(fit_intercept=self.fit_intercept, copy_X=False)
else:
model = {self.RIDGE: Ridge, self.LASSO: Lasso}[self.estimator](
alpha=self.alpha, fit_intercept=self.fit_intercept, copy_X=False
)
model.fit(X, y)
model.fit(X, y, sample_weight=w)
self.coef_ = model.coef_
self.intercept_ = model.intercept_
def _fit_nnls(self, X, y):
def _fit_nnls(self, X, y, w=None):
if w is not None:
raise NotImplementedError("TODO: support nnls with weight") # TODO
if self.fit_intercept:
X = np.c_[X, np.ones(len(X))] # NOTE: mem copy
coef = nnls(X, y)[0]