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

Merge pull request #314 from D-X-Y/fshare

Browse Source 
(1) Fix /0 bug in double_ensemble, (2) remove _default_uri for R/expm, (3) support model size in pytorch models
This commit is contained in:
you-n-g
2021-03-11 20:51:16 +08:00
committed by GitHub
parent 0054a4db2a 0ef7c8e0e6
commit e8beaa5257
23 changed files with 185 additions and 70 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
qlib/contrib/model/double_ensemble.py
View File

@@ -184,7 +184,7 @@ class DEnsembleModel(Model):
/ M
)
loss_feat = self.get_loss(y_train.values.squeeze(), pred.values)
g.loc[i_f, "g_value"] = np.mean(loss_feat - loss_values) / np.std(loss_feat - loss_values)
g.loc[i_f, "g_value"] = np.mean(loss_feat - loss_values) / (np.std(loss_feat - loss_values) + 1e-7)
x_train_tmp.loc[:, feat] = x_train.loc[:, feat].copy()
# one column in train features is all-nan # if g['g_value'].isna().any()

11
qlib/contrib/model/pytorch_alstm.py
View File

@@ -23,6 +23,7 @@ import torch
import torch.nn as nn
import torch.optim as optim
from .pytorch_utils import count_parameters
from ...model.base import Model
from ...data.dataset import DatasetH
from ...data.dataset.handler import DataHandlerLP
@@ -39,8 +40,8 @@ class ALSTM(Model):
the evaluate metric used in early stop
optimizer : str
optimizer name
GPU : str
the GPU ID(s) used for training
GPU : int
the GPU ID used for training
"""
def __init__(
@@ -76,7 +77,7 @@ class ALSTM(Model):
self.early_stop = early_stop
self.optimizer = optimizer.lower()
self.loss = loss
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu")
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() and GPU >= 0 else "cpu")
self.use_gpu = torch.cuda.is_available()
self.seed = seed
@@ -123,6 +124,9 @@ class ALSTM(Model):
num_layers=self.num_layers,
dropout=self.dropout,
)
self.logger.info("model:\n{:}".format(self.ALSTM_model))
self.logger.info("model size: {:.4f} MB".format(count_parameters(self.ALSTM_model)))
if optimizer.lower() == "adam":
self.train_optimizer = optim.Adam(self.ALSTM_model.parameters(), lr=self.lr)
elif optimizer.lower() == "gd":
@@ -214,7 +218,6 @@ class ALSTM(Model):
self,
dataset: DatasetH,
evals_result=dict(),
verbose=True,
save_path=None,
):

13
qlib/contrib/model/pytorch_alstm_ts.py
View File

@@ -24,6 +24,7 @@ import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
from .pytorch_utils import count_parameters
from ...model.base import Model
from ...data.dataset import DatasetH, TSDatasetH
from ...data.dataset.handler import DataHandlerLP
@@ -40,8 +41,8 @@ class ALSTM(Model):
the evaluate metric used in early stop
optimizer : str
optimizer name
GPU : str
the GPU ID(s) used for training
GPU : int
the GPU ID used for training
"""
def __init__(
@@ -78,7 +79,7 @@ class ALSTM(Model):
self.early_stop = early_stop
self.optimizer = optimizer.lower()
self.loss = loss
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu")
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() and GPU >= 0 else "cpu")
self.n_jobs = n_jobs
self.use_gpu = torch.cuda.is_available()
self.seed = seed
@@ -127,7 +128,10 @@ class ALSTM(Model):
hidden_size=self.hidden_size,
num_layers=self.num_layers,
dropout=self.dropout,
).to(self.device)
)
self.logger.info("model:\n{:}".format(self.ALSTM_model))
self.logger.info("model size: {:.4f} MB".format(count_parameters(self.ALSTM_model)))
if optimizer.lower() == "adam":
self.train_optimizer = optim.Adam(self.ALSTM_model.parameters(), lr=self.lr)
elif optimizer.lower() == "gd":
@@ -201,7 +205,6 @@ class ALSTM(Model):
self,
dataset,
evals_result=dict(),
verbose=True,
save_path=None,
):
dl_train = dataset.prepare("train", col_set=["feature", "label"], data_key=DataHandlerLP.DK_L)

11
qlib/contrib/model/pytorch_gats.py
View File

@@ -22,6 +22,7 @@ import torch
import torch.nn as nn
import torch.optim as optim
from .pytorch_utils import count_parameters
from ...model.base import Model
from ...data.dataset import DatasetH
from ...data.dataset.handler import DataHandlerLP
@@ -42,8 +43,8 @@ class GATs(Model):
the evaluate metric used in early stop
optimizer : str
optimizer name
GPU : str
the GPU ID(s) used for training
GPU : int
the GPU ID used for training
"""
def __init__(
@@ -83,7 +84,7 @@ class GATs(Model):
self.base_model = base_model
self.with_pretrain = with_pretrain
self.model_path = model_path
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu")
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() and GPU >= 0 else "cpu")
self.use_gpu = torch.cuda.is_available()
self.seed = seed
@@ -135,6 +136,9 @@ class GATs(Model):
dropout=self.dropout,
base_model=self.base_model,
)
self.logger.info("model:\n{:}".format(self.GAT_model))
self.logger.info("model size: {:.4f} MB".format(count_parameters(self.GAT_model)))
if optimizer.lower() == "adam":
self.train_optimizer = optim.Adam(self.GAT_model.parameters(), lr=self.lr)
elif optimizer.lower() == "gd":
@@ -232,7 +236,6 @@ class GATs(Model):
self,
dataset: DatasetH,
evals_result=dict(),
verbose=True,
save_path=None,
):

11
qlib/contrib/model/pytorch_gats_ts.py
View File

@@ -24,6 +24,7 @@ import torch.optim as optim
from torch.utils.data import DataLoader
from torch.utils.data import Sampler
from .pytorch_utils import count_parameters
from ...model.base import Model
from ...data.dataset import DatasetH
from ...data.dataset.handler import DataHandlerLP
@@ -62,8 +63,8 @@ class GATs(Model):
the evaluate metric used in early stop
optimizer : str
optimizer name
GPU : str
the GPU ID(s) used for training
GPU : int
the GPU ID used for training
"""
def __init__(
@@ -104,7 +105,7 @@ class GATs(Model):
self.base_model = base_model
self.with_pretrain = with_pretrain
self.model_path = model_path
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu")
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() and GPU >= 0 else "cpu")
self.n_jobs = n_jobs
self.use_gpu = torch.cuda.is_available()
self.seed = seed
@@ -157,6 +158,9 @@ class GATs(Model):
dropout=self.dropout,
base_model=self.base_model,
)
self.logger.info("model:\n{:}".format(self.GAT_model))
self.logger.info("model size: {:.4f} MB".format(count_parameters(self.GAT_model)))
if optimizer.lower() == "adam":
self.train_optimizer = optim.Adam(self.GAT_model.parameters(), lr=self.lr)
elif optimizer.lower() == "gd":
@@ -245,7 +249,6 @@ class GATs(Model):
self,
dataset,
evals_result=dict(),
verbose=True,
save_path=None,
):

7
qlib/contrib/model/pytorch_gru.py
View File

@@ -23,6 +23,7 @@ import torch
import torch.nn as nn
import torch.optim as optim
from .pytorch_utils import count_parameters
from ...model.base import Model
from ...data.dataset import DatasetH
from ...data.dataset.handler import DataHandlerLP
@@ -76,7 +77,7 @@ class GRU(Model):
self.early_stop = early_stop
self.optimizer = optimizer.lower()
self.loss = loss
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu")
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() and GPU >= 0 else "cpu")
self.use_gpu = torch.cuda.is_available()
self.seed = seed
@@ -123,6 +124,9 @@ class GRU(Model):
num_layers=self.num_layers,
dropout=self.dropout,
)
self.logger.info("model:\n{:}".format(self.gru_model))
self.logger.info("model size: {:.4f} MB".format(count_parameters(self.gru_model)))
if optimizer.lower() == "adam":
self.train_optimizer = optim.Adam(self.gru_model.parameters(), lr=self.lr)
elif optimizer.lower() == "gd":
@@ -214,7 +218,6 @@ class GRU(Model):
self,
dataset: DatasetH,
evals_result=dict(),
verbose=True,
save_path=None,
):

9
qlib/contrib/model/pytorch_gru_ts.py
View File

@@ -24,6 +24,7 @@ import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
from .pytorch_utils import count_parameters
from ...model.base import Model
from ...data.dataset import DatasetH, TSDatasetH
from ...data.dataset.handler import DataHandlerLP
@@ -78,7 +79,7 @@ class GRU(Model):
self.early_stop = early_stop
self.optimizer = optimizer.lower()
self.loss = loss
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu")
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() and GPU >= 0 else "cpu")
self.n_jobs = n_jobs
self.use_gpu = torch.cuda.is_available()
self.seed = seed
@@ -127,7 +128,10 @@ class GRU(Model):
hidden_size=self.hidden_size,
num_layers=self.num_layers,
dropout=self.dropout,
).to(self.device)
)
self.logger.info("model:\n{:}".format(self.gru_model))
self.logger.info("model size: {:.4f} MB".format(count_parameters(self.gru_model)))
if optimizer.lower() == "adam":
self.train_optimizer = optim.Adam(self.GRU_model.parameters(), lr=self.lr)
elif optimizer.lower() == "gd":
@@ -201,7 +205,6 @@ class GRU(Model):
self,
dataset,
evals_result=dict(),
verbose=True,
save_path=None,
):
dl_train = dataset.prepare("train", col_set=["feature", "label"], data_key=DataHandlerLP.DK_L)

3
qlib/contrib/model/pytorch_lstm.py
View File

@@ -76,7 +76,7 @@ class LSTM(Model):
self.early_stop = early_stop
self.optimizer = optimizer.lower()
self.loss = loss
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu")
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() and GPU >= 0 else "cpu")
self.use_gpu = torch.cuda.is_available()
self.seed = seed
@@ -214,7 +214,6 @@ class LSTM(Model):
self,
dataset: DatasetH,
evals_result=dict(),
verbose=True,
save_path=None,
):

3
qlib/contrib/model/pytorch_lstm_ts.py
View File

@@ -78,7 +78,7 @@ class LSTM(Model):
self.early_stop = early_stop
self.optimizer = optimizer.lower()
self.loss = loss
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu")
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() and GPU >= 0 else "cpu")
self.n_jobs = n_jobs
self.use_gpu = torch.cuda.is_available()
self.seed = seed
@@ -201,7 +201,6 @@ class LSTM(Model):
self,
dataset,
evals_result=dict(),
verbose=True,
save_path=None,
):
dl_train = dataset.prepare("train", col_set=["feature", "label"], data_key=DataHandlerLP.DK_L)

10
qlib/contrib/model/pytorch_nn.py
View File

@@ -15,6 +15,7 @@ import torch
import torch.nn as nn
import torch.optim as optim
from .pytorch_utils import count_parameters
from ...model.base import Model
from ...data.dataset import DatasetH
from ...data.dataset.handler import DataHandlerLP
@@ -42,8 +43,8 @@ class DNNModelPytorch(Model):
learning rate decay steps
optimizer : str
optimizer name
GPU : str
the GPU ID(s) used for training
GPU : int
the GPU ID used for training
"""
def __init__(
@@ -80,7 +81,7 @@ class DNNModelPytorch(Model):
self.lr_decay_steps = lr_decay_steps
self.optimizer = optimizer.lower()
self.loss_type = loss
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu")
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() and GPU >= 0 else "cpu")
self.use_GPU = torch.cuda.is_available()
self.seed = seed
self.weight_decay = weight_decay
@@ -129,6 +130,9 @@ class DNNModelPytorch(Model):
self._scorer = mean_squared_error if loss == "mse" else roc_auc_score
self.dnn_model = Net(input_dim, output_dim, layers, loss=self.loss_type)
self.logger.info("model:\n{:}".format(self.dnn_model))
self.logger.info("model size: {:.4f} MB".format(count_parameters(self.dnn_model)))
if optimizer.lower() == "adam":
self.train_optimizer = optim.Adam(self.dnn_model.parameters(), lr=self.lr, weight_decay=self.weight_decay)
elif optimizer.lower() == "gd":

13
qlib/contrib/model/pytorch_sfm.py
View File

@@ -23,6 +23,7 @@ import torch.nn as nn
import torch.nn.init as init
import torch.optim as optim
from .pytorch_utils import count_parameters
from ...model.base import Model
from ...data.dataset import DatasetH
from ...data.dataset.handler import DataHandlerLP
@@ -196,8 +197,8 @@ class SFM(Model):
learning rate
optimizer : str
optimizer name
GPU : str
the GPU ID(s) used for training
GPU : int
the GPU ID used for training
"""
def __init__(
@@ -216,7 +217,7 @@ class SFM(Model):
eval_steps=5,
loss="mse",
optimizer="gd",
GPU="0",
GPU=0,
seed=None,
**kwargs
):
@@ -239,7 +240,7 @@ class SFM(Model):
self.eval_steps = eval_steps
self.optimizer = optimizer.lower()
self.loss = loss
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu")
self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() and GPU >= 0 else "cpu")
self.use_gpu = torch.cuda.is_available()
self.seed = seed
@@ -295,6 +296,9 @@ class SFM(Model):
dropout_U=self.dropout_U,
device=self.device,
)
self.logger.info("model:\n{:}".format(self.sfm_model))
self.logger.info("model size: {:.4f} MB".format(count_parameters(self.sfm_model)))
if optimizer.lower() == "adam":
self.train_optimizer = optim.Adam(self.sfm_model.parameters(), lr=self.lr)
elif optimizer.lower() == "gd":
@@ -365,7 +369,6 @@ class SFM(Model):
self,
dataset: DatasetH,
evals_result=dict(),
verbose=True,
save_path=None,
):

8
qlib/contrib/model/pytorch_tabnet.py
View File

@@ -23,6 +23,7 @@ import torch.optim as optim
import torch.nn.functional as F
from torch.autograd import Function
from .pytorch_utils import count_parameters
from ...model.base import Model
from ...data.dataset import DatasetH
from ...data.dataset.handler import DataHandlerLP
@@ -49,7 +50,7 @@ class TabnetModel(Model):
loss="mse",
metric="",
early_stop=20,
GPU="1",
GPU=0,
pretrain_loss="custom",
ps=0.3,
lr=0.01,
@@ -75,7 +76,7 @@ class TabnetModel(Model):
self.n_epochs = n_epochs
self.logger = get_module_logger("TabNet")
self.pretrain_n_epochs = pretrain_n_epochs
self.device = "cuda:%s" % (GPU) if torch.cuda.is_available() else "cpu"
self.device = "cuda:%s" % (GPU) if torch.cuda.is_available() and GPU >= 0 else "cpu"
self.loss = loss
self.metric = metric
self.early_stop = early_stop
@@ -98,6 +99,8 @@ class TabnetModel(Model):
self.tabnet_decoder = TabNet_Decoder(self.out_dim, self.d_feat, n_shared, n_ind, vbs, n_steps, self.device).to(
self.device
)
self.logger.info("model:\n{:}\n{:}".format(self.tabnet_model, self.tabnet_decoder))
self.logger.info("model size: {:.4f} MB".format(count_parameters([self.tabnet_model, self.tabnet_decoder])))
if optimizer.lower() == "adam":
self.pretrain_optimizer = optim.Adam(
@@ -159,7 +162,6 @@ class TabnetModel(Model):
self,
dataset: DatasetH,
evals_result=dict(),
verbose=True,
save_path=None,
):
if self.pretrain:

37
qlib/contrib/model/pytorch_utils.py Normal file
View File

@@ -0,0 +1,37 @@
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
import torch.nn as nn
def count_parameters(models_or_parameters, unit="m"):
"""
This function is to obtain the storage size unit of a (or multiple) models.
Parameters
----------
models_or_parameters : PyTorch model(s) or a list of parameters.
unit : the storage size unit.
Returns
-------
The number of parameters of the given model(s) or parameters.
"""
if isinstance(models_or_parameters, nn.Module):
counts = sum(v.numel() for v in models_or_parameters.parameters())
elif isinstance(models_or_parameters, nn.Parameter):
counts = models_or_parameters.numel()
elif isinstance(models_or_parameters, (list, tuple)):
return sum(count_parameters(x, unit) for x in models_or_parameters)
else:
counts = sum(v.numel() for v in models_or_parameters)
unit = unit.lower()
if unit == "kb" or unit == "k":
counts /= 2 ** 10
elif unit == "mb" or unit == "m":
counts /= 2 ** 20
elif unit == "gb" or unit == "g":
counts /= 2 ** 30
elif unit is not None:
raise ValueError("Unknow unit: {:}".format(unit))
return counts