liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-13 07:46:53 +08:00
Code Activity

Fix processor bug and format

Browse Source
This commit is contained in:
Jactus
2020-11-11 14:24:04 +08:00
parent e2d89f44fb
commit 52c0c4b7a8
8 changed files with 114 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files

58
qlib/contrib/data/handler.py
View File

@@ -8,15 +8,9 @@ from ...data.dataset import processor as processor_module
from ...log import TimeInspector
import copy
class ALPHA360(DataHandlerLP):
def __init__(
self,
instruments="csi500",
start_time=None,
end_time=None,
fit_start_time=None,
fit_end_time=None
):
def __init__(self, instruments="csi500", start_time=None, end_time=None, fit_start_time=None, fit_end_time=None):
data_loader = {
"class": "QlibDataLoader",
"kwargs": {
@@ -28,22 +22,22 @@ class ALPHA360(DataHandlerLP):
}
learn_processors = [
{"class": "DropnaLabel", "kwargs": {'group': 'label'}},
{"class": "CSZScoreNorm", "kwargs": {"fields_group": "label"}},
{"class": "DropnaLabel", "kwargs": {"group": "label"}},
{"class": "CSZScoreNorm", "kwargs": {"fields_group": "label"}},
]
infer_processors = [
{"class": "ProcessInf", "kwargs": {}},
{"class": "ZscoreNorm", "kwargs": {"fit_start_time": fit_start_time, "fit_end_time": fit_end_time}},
{"class": "Fillna", "kwargs": {}},
{"class": "ProcessInf", "kwargs": {}},
{"class": "ZscoreNorm", "kwargs": {"fit_start_time": fit_start_time, "fit_end_time": fit_end_time}},
{"class": "Fillna", "kwargs": {}},
]
super().__init__(
instruments,
start_time,
end_time,
data_loader=data_loader,
learn_processors=learn_processors,
infer_processors=infer_processors
instruments,
start_time,
end_time,
data_loader=data_loader,
learn_processors=learn_processors,
infer_processors=infer_processors,
)
def get_label_config(self):
@@ -54,19 +48,19 @@ class ALPHA360(DataHandlerLP):
fields = []
names = []
for i in range(59,0,-1):
fields += ["Ref($close, %d)/$close"%(i)]
names += ["CLOSE%d"%(i)]
fields += ["Ref($open, %d)/$close"%(i)]
names += ["OPEN%d"%(i)]
fields += ["Ref($high, %d)/$close"%(i)]
names += ["HIGH%d"%(i)]
fields += ["Ref($low, %d)/$close"%(i)]
names += ["LOW%d"%(i)]
fields += ["Ref($vwap, %d)/$close"%(i)]
names += ["VWAP%d"%(i)]
fields += ["Ref($volume, %d)/$volume"%(i)]
names += ["VOLUME%d"%(i)]
for i in range(59, 0, -1):
fields += ["Ref($close, %d)/$close" % (i)]
names += ["CLOSE%d" % (i)]
fields += ["Ref($open, %d)/$close" % (i)]
names += ["OPEN%d" % (i)]
fields += ["Ref($high, %d)/$close" % (i)]
names += ["HIGH%d" % (i)]
fields += ["Ref($low, %d)/$close" % (i)]
names += ["LOW%d" % (i)]
fields += ["Ref($vwap, %d)/$close" % (i)]
names += ["VWAP%d" % (i)]
fields += ["Ref($volume, %d)/$volume" % (i)]
names += ["VOLUME%d" % (i)]
fields += ["$close/$close"]
fields += ["$open/$close"]

14
qlib/contrib/model/pytorch_gru.py
View File

@@ -22,6 +22,7 @@ from ...model.base import Model
from ...data.dataset import DatasetH
from ...data.dataset.handler import DataHandlerLP
class GRU(Model):
"""GRU Model
@@ -127,7 +128,9 @@ class GRU(Model):
raise NotImplementedError("loss {} is not supported!".format(loss))
self._scorer = mean_squared_error if loss == "mse" else roc_auc_score
self.gru_model = GRUModel(d_feat=self.d_feat, hidden_size=self.hidden_size, num_layers=self.num_layers, dropout=self.dropout)
self.gru_model = GRUModel(
d_feat=self.d_feat, hidden_size=self.hidden_size, num_layers=self.num_layers, dropout=self.dropout
)
if optimizer.lower() == "adam":
self.train_optimizer = optim.Adam(self.gru_model.parameters(), lr=self.lr)
elif optimizer.lower() == "gd":
@@ -262,7 +265,7 @@ class GRU(Model):
def get_loss(self, pred, target, loss_type):
if loss_type == "mse":
sqr_loss = (pred - target)**2
sqr_loss = (pred - target) ** 2
loss = sqr_loss.mean()
return loss
elif loss_type == "binary":
@@ -307,6 +310,7 @@ class GRU(Model):
self.gru_model.load_state_dict(torch.load(_model_path))
self._fitted = True
class AverageMeter(object):
"""Computes and stores the average and current value"""
@@ -327,7 +331,6 @@ class AverageMeter(object):
class GRUModel(nn.Module):
def __init__(self, d_feat=6, hidden_size=64, num_layers=2, dropout=0.0):
super().__init__()
@@ -344,8 +347,7 @@ class GRUModel(nn.Module):
def forward(self, x):
# x: [N, F*T]
x = x.reshape(len(x), self.d_feat, -1) # [N, F, T]
x = x.permute(0, 2, 1) # [N, T, F]
x = x.reshape(len(x), self.d_feat, -1) # [N, F, T]
x = x.permute(0, 2, 1) # [N, T, F]
out, _ = self.rnn(x)
return self.fc_out(out[:, -1, :]).squeeze()

4
qlib/contrib/model/xgboost.py
View File

@@ -41,14 +41,14 @@ class XGBModel(Model):
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')],
evals=[(dtrain, "train"), (dvalid, "valid")],
early_stopping_rounds=early_stopping_rounds,
verbose_eval=verbose_eval,
evals_result=evals_result,