liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-16 17:12:20 +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

43
qlib/contrib/model/pytorch_alstm_ts.py
View File

@@ -22,6 +22,8 @@ from .pytorch_utils import count_parameters
from ...model.base import Model
from ...data.dataset import DatasetH, TSDatasetH
from ...data.dataset.handler import DataHandlerLP
from ...model.utils import ConcatDataset
from ...data.dataset.weight import Reweighter
class ALSTM(Model):
@@ -139,15 +141,18 @@ class ALSTM(Model):
def use_gpu(self):
return self.device != torch.device("cpu")
def mse(self, pred, label):
loss = (pred - label) ** 2
def mse(self, pred, label, weight):
loss = weight * (pred - label) ** 2
return torch.mean(loss)
def loss_fn(self, pred, label):
def loss_fn(self, pred, label, weight=None):
mask = ~torch.isnan(label)
if weight is None:
weight = torch.ones_like(label)
if self.loss == "mse":
return self.mse(pred[mask], label[mask])
return self.mse(pred[mask], label[mask], weight[mask])
raise ValueError("unknown loss `%s`" % self.loss)
@@ -164,12 +169,12 @@ class ALSTM(Model):
self.ALSTM_model.train()
for data in data_loader:
for (data, weight) in data_loader:
feature = data[:, :, 0:-1].to(self.device)
label = data[:, -1, -1].to(self.device)
pred = self.ALSTM_model(feature.float())
loss = self.loss_fn(pred, label)
loss = self.loss_fn(pred, label, weight.to(self.device))
self.train_optimizer.zero_grad()
loss.backward()
@@ -183,7 +188,7 @@ class ALSTM(Model):
scores = []
losses = []
for data in data_loader:
for (data, weight) in data_loader:
feature = data[:, :, 0:-1].to(self.device)
# feature[torch.isnan(feature)] = 0
@@ -191,7 +196,7 @@ class ALSTM(Model):
with torch.no_grad():
pred = self.ALSTM_model(feature.float())
loss = self.loss_fn(pred, label)
loss = self.loss_fn(pred, label, weight.to(self.device))
losses.append(loss.item())
score = self.metric_fn(pred, label)
@@ -204,6 +209,7 @@ class ALSTM(Model):
dataset,
evals_result=dict(),
save_path=None,
reweighter=None,
):
dl_train = dataset.prepare("train", col_set=["feature", "label"], data_key=DataHandlerLP.DK_L)
dl_valid = dataset.prepare("valid", col_set=["feature", "label"], data_key=DataHandlerLP.DK_L)
@@ -213,11 +219,28 @@ class ALSTM(Model):
dl_train.config(fillna_type="ffill+bfill") # process nan brought by dataloader
dl_valid.config(fillna_type="ffill+bfill") # process nan brought by dataloader
if reweighter is None:
wl_train = np.ones(len(dl_train))
wl_valid = np.ones(len(dl_valid))
elif isinstance(reweighter, Reweighter):
wl_train = reweighter.reweight(dl_train)
wl_valid = reweighter.reweight(dl_valid)
else:
raise ValueError("Unsupported reweighter type.")
train_loader = DataLoader(
dl_train, batch_size=self.batch_size, shuffle=True, num_workers=self.n_jobs, drop_last=True
ConcatDataset(dl_train, wl_train),
batch_size=self.batch_size,
shuffle=True,
num_workers=self.n_jobs,
drop_last=True,
)
valid_loader = DataLoader(
dl_valid, batch_size=self.batch_size, shuffle=False, num_workers=self.n_jobs, drop_last=True
ConcatDataset(dl_valid, wl_valid),
batch_size=self.batch_size,
shuffle=False,
num_workers=self.n_jobs,
drop_last=True,
)
save_path = get_or_create_path(save_path)