mirror of
https://github.com/microsoft/qlib.git
synced 2026-07-05 12:00:58 +08:00
388 lines
12 KiB
Python
Executable File
388 lines
12 KiB
Python
Executable File
# Copyright (c) Microsoft Corporation.
|
|
# Licensed under the MIT License.
|
|
|
|
|
|
from __future__ import division
|
|
from __future__ import print_function
|
|
|
|
import os
|
|
import numpy as np
|
|
import pandas as pd
|
|
import copy
|
|
from ...utils import create_save_path
|
|
from ...log import get_module_logger
|
|
|
|
import torch
|
|
import torch.nn as nn
|
|
import torch.optim as optim
|
|
|
|
from ...model.base import Model
|
|
from ...data.dataset import DatasetH
|
|
from ...data.dataset.handler import DataHandlerLP
|
|
|
|
|
|
class GAT(Model):
|
|
"""GAT Model
|
|
|
|
Parameters
|
|
----------
|
|
lr : float
|
|
learning rate
|
|
d_feat : int
|
|
input dimensions for each time step
|
|
metric : str
|
|
the evaluate metric used in early stop
|
|
optimizer : str
|
|
optimizer name
|
|
GPU : str
|
|
the GPU ID(s) used for training
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
d_feat=6,
|
|
hidden_size=64,
|
|
num_layers=2,
|
|
dropout=0.0,
|
|
n_epochs=200,
|
|
lr=0.001,
|
|
metric="",
|
|
early_stop=20,
|
|
loss="mse",
|
|
base_model="GRU",
|
|
with_pretrain=True,
|
|
optimizer="adam",
|
|
GPU="0",
|
|
seed=0,
|
|
**kwargs
|
|
):
|
|
# Set logger.
|
|
self.logger = get_module_logger("GAT")
|
|
self.logger.info("GAT pytorch version...")
|
|
|
|
# set hyper-parameters.
|
|
self.d_feat = d_feat
|
|
self.hidden_size = hidden_size
|
|
self.num_layers = num_layers
|
|
self.dropout = dropout
|
|
self.n_epochs = n_epochs
|
|
self.lr = lr
|
|
self.metric = metric
|
|
self.early_stop = early_stop
|
|
self.optimizer = optimizer.lower()
|
|
self.loss = loss
|
|
self.base_model = base_model
|
|
self.with_pretrain = with_pretrain
|
|
self.visible_GPU = GPU
|
|
self.use_gpu = torch.cuda.is_available()
|
|
self.seed = seed
|
|
|
|
self.logger.info(
|
|
"GAT parameters setting:"
|
|
"\nd_feat : {}"
|
|
"\nhidden_size : {}"
|
|
"\nnum_layers : {}"
|
|
"\ndropout : {}"
|
|
"\nn_epochs : {}"
|
|
"\nlr : {}"
|
|
"\nmetric : {}"
|
|
"\nearly_stop : {}"
|
|
"\noptimizer : {}"
|
|
"\nloss_type : {}"
|
|
"\nbase_model : {}"
|
|
"\nwith_pretrain : {}"
|
|
"\nvisible_GPU : {}"
|
|
"\nuse_GPU : {}"
|
|
"\nseed : {}".format(
|
|
d_feat,
|
|
hidden_size,
|
|
num_layers,
|
|
dropout,
|
|
n_epochs,
|
|
lr,
|
|
metric,
|
|
early_stop,
|
|
optimizer.lower(),
|
|
loss,
|
|
base_model,
|
|
with_pretrain,
|
|
GPU,
|
|
self.use_gpu,
|
|
seed,
|
|
)
|
|
)
|
|
|
|
self.GAT_model = GATModel(
|
|
d_feat=self.d_feat,
|
|
hidden_size=self.hidden_size,
|
|
num_layers=self.num_layers,
|
|
dropout=self.dropout,
|
|
base_model=self.base_model,
|
|
)
|
|
if optimizer.lower() == "adam":
|
|
self.train_optimizer = optim.Adam(self.GAT_model.parameters(), lr=self.lr)
|
|
elif optimizer.lower() == "gd":
|
|
self.train_optimizer = optim.SGD(self.GAT_model.parameters(), lr=self.lr)
|
|
else:
|
|
raise NotImplementedError("optimizer {} is not supported!".format(optimizer))
|
|
|
|
self._fitted = False
|
|
if self.use_gpu:
|
|
self.GAT_model.cuda()
|
|
# set the visible GPU
|
|
if self.visible_GPU:
|
|
os.environ["CUDA_VISIBLE_DEVICES"] = self.visible_GPU
|
|
|
|
def mse(self, pred, label):
|
|
loss = (pred - label) ** 2
|
|
return torch.mean(loss)
|
|
|
|
def loss_fn(self, pred, label):
|
|
mask = ~torch.isnan(label)
|
|
|
|
if self.loss == "mse":
|
|
return self.mse(pred[mask], label[mask])
|
|
|
|
raise ValueError("unknown loss `%s`" % self.loss)
|
|
|
|
def metric_fn(self, pred, label):
|
|
|
|
mask = torch.isfinite(label)
|
|
|
|
if self.metric == "" or self.metric == "loss": # use loss
|
|
return -self.loss_fn(pred[mask], label[mask])
|
|
|
|
raise ValueError("unknown metric `%s`" % self.metric)
|
|
|
|
def get_daily_inter(self, df, shuffle=False):
|
|
# organize the train data into daily inter as daily batches
|
|
daily_count = df.groupby(level=0).size().values
|
|
daily_index = np.roll(np.cumsum(daily_count), 1)
|
|
daily_index[0] = 0
|
|
if shuffle:
|
|
# shuffle the daily inter data
|
|
daily_shuffle = list(zip(daily_index, daily_count))
|
|
np.random.shuffle(daily_shuffle)
|
|
daily_index, daily_count = zip(*daily_shuffle)
|
|
return daily_index, daily_count
|
|
|
|
def train_epoch(self, x_train, y_train):
|
|
|
|
x_train_values = x_train.values
|
|
y_train_values = np.squeeze(y_train.values)
|
|
self.GAT_model.train()
|
|
|
|
# organize the train data into daily inter as daily batches
|
|
daily_index, daily_count = self.get_daily_inter(x_train, shuffle=True)
|
|
|
|
for idx, count in zip(daily_index, daily_count):
|
|
batch = slice(idx, idx + count)
|
|
feature = torch.from_numpy(x_train_values[batch]).float()
|
|
label = torch.from_numpy(y_train_values[batch]).float()
|
|
|
|
if self.use_gpu:
|
|
feature = feature.cuda()
|
|
label = label.cuda()
|
|
|
|
pred = self.GAT_model(feature)
|
|
loss = self.loss_fn(pred, label)
|
|
|
|
self.train_optimizer.zero_grad()
|
|
loss.backward()
|
|
torch.nn.utils.clip_grad_value_(self.GAT_model.parameters(), 3.0)
|
|
self.train_optimizer.step()
|
|
|
|
def test_epoch(self, data_x, data_y):
|
|
|
|
# prepare training data
|
|
x_values = data_x.values
|
|
y_values = np.squeeze(data_y.values)
|
|
|
|
self.GAT_model.eval()
|
|
|
|
scores = []
|
|
losses = []
|
|
|
|
# organize the test data into daily inter as daily batches
|
|
daily_index, daily_count = self.get_daily_inter(data_x, shuffle=False)
|
|
|
|
for idx, count in zip(daily_index, daily_count):
|
|
batch = slice(idx, idx + count)
|
|
feature = torch.from_numpy(x_values[batch]).float()
|
|
label = torch.from_numpy(y_values[batch]).float()
|
|
|
|
if self.use_gpu:
|
|
feature = feature.cuda()
|
|
label = label.cuda()
|
|
|
|
pred = self.GAT_model(feature)
|
|
loss = self.loss_fn(pred, label)
|
|
losses.append(loss.item())
|
|
|
|
score = self.metric_fn(pred, label)
|
|
scores.append(score.item())
|
|
|
|
return np.mean(losses), np.mean(scores)
|
|
|
|
def fit(
|
|
self,
|
|
dataset: DatasetH,
|
|
evals_result=dict(),
|
|
verbose=True,
|
|
save_path=None,
|
|
):
|
|
|
|
df_train, df_valid, df_test = dataset.prepare(
|
|
["train", "valid", "test"], 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"]
|
|
|
|
if save_path == None:
|
|
save_path = create_save_path(save_path)
|
|
stop_steps = 0
|
|
best_score = -np.inf
|
|
best_epoch = 0
|
|
evals_result["train"] = []
|
|
evals_result["valid"] = []
|
|
|
|
# load pretrained base_model
|
|
if self.with_pretrain:
|
|
self.logger.info("Loading pretrained model...")
|
|
if self.base_model == "LSTM":
|
|
from ...contrib.model.pytorch_lstm import LSTMModel
|
|
|
|
pretrained_model = LSTMModel()
|
|
pretrained_model.load_state_dict(torch.load("benchmarks/LSTM/model_lstm_csi300.pkl"))
|
|
elif self.base_model == "GRU":
|
|
from ...contrib.model.pytorch_gru import GRUModel
|
|
|
|
pretrained_model = GRUModel()
|
|
pretrained_model.load_state_dict(torch.load("benchmarks/GRU/model_gru_csi300.pkl"))
|
|
model_dict = self.GAT_model.state_dict()
|
|
pretrained_dict = {k: v for k, v in pretrained_model.state_dict().items() if k in model_dict}
|
|
model_dict.update(pretrained_dict)
|
|
self.GAT_model.load_state_dict(model_dict)
|
|
self.logger.info("Loading pretrained model Done...")
|
|
|
|
# train
|
|
self.logger.info("training...")
|
|
self._fitted = True
|
|
# return
|
|
|
|
for step in range(self.n_epochs):
|
|
self.logger.info("Epoch%d:", step)
|
|
self.logger.info("training...")
|
|
self.train_epoch(x_train, y_train)
|
|
self.logger.info("evaluating...")
|
|
train_loss, train_score = self.test_epoch(x_train, y_train)
|
|
val_loss, val_score = self.test_epoch(x_valid, y_valid)
|
|
self.logger.info("train %.6f, valid %.6f" % (train_score, val_score))
|
|
evals_result["train"].append(train_score)
|
|
evals_result["valid"].append(val_score)
|
|
|
|
if val_score > best_score:
|
|
best_score = val_score
|
|
stop_steps = 0
|
|
best_epoch = step
|
|
best_param = copy.deepcopy(self.GAT_model.state_dict())
|
|
else:
|
|
stop_steps += 1
|
|
if stop_steps >= self.early_stop:
|
|
self.logger.info("early stop")
|
|
break
|
|
|
|
self.logger.info("best score: %.6lf @ %d" % (best_score, best_epoch))
|
|
self.GAT_model.load_state_dict(best_param)
|
|
torch.save(best_param, save_path)
|
|
|
|
if self.use_gpu:
|
|
torch.cuda.empty_cache()
|
|
|
|
def predict(self, dataset):
|
|
if not self._fitted:
|
|
raise ValueError("model is not fitted yet!")
|
|
|
|
x_test = dataset.prepare("test", col_set="feature")
|
|
index = x_test.index
|
|
self.GAT_model.eval()
|
|
x_values = x_test.values
|
|
preds = []
|
|
|
|
# organize the data into daily inter as daily batches
|
|
daily_index, daily_count = self.get_daily_inter(x_test, shuffle=False)
|
|
|
|
for idx, count in zip(daily_index, daily_count):
|
|
batch = slice(idx, idx + count)
|
|
x_batch = torch.from_numpy(x_values[batch]).float()
|
|
|
|
if self.use_gpu:
|
|
x_batch = x_batch.cuda()
|
|
|
|
with torch.no_grad():
|
|
if self.use_gpu:
|
|
pred = self.GAT_model(x_batch).detach().cpu().numpy()
|
|
else:
|
|
pred = self.GAT_model(x_batch).detach().numpy()
|
|
|
|
preds.append(pred)
|
|
|
|
return pd.Series(np.concatenate(preds), index=index)
|
|
|
|
|
|
class GATModel(nn.Module):
|
|
def __init__(self, d_feat=6, hidden_size=64, num_layers=2, dropout=0.0, base_model="GRU"):
|
|
super().__init__()
|
|
|
|
if base_model == "GRU":
|
|
self.rnn = nn.GRU(
|
|
input_size=d_feat,
|
|
hidden_size=hidden_size,
|
|
num_layers=num_layers,
|
|
batch_first=True,
|
|
dropout=dropout,
|
|
)
|
|
elif base_model == "LSTM":
|
|
self.rnn = nn.LSTM(
|
|
input_size=d_feat,
|
|
hidden_size=hidden_size,
|
|
num_layers=num_layers,
|
|
batch_first=True,
|
|
dropout=dropout,
|
|
)
|
|
else:
|
|
raise ValueError("unknown base model name `%s`" % base_model)
|
|
|
|
self.hidden_size = hidden_size
|
|
self.bn1 = nn.BatchNorm1d(num_features=hidden_size, track_running_stats=False)
|
|
self.fc = nn.Linear(hidden_size, hidden_size)
|
|
self.bn2 = nn.BatchNorm1d(num_features=hidden_size, track_running_stats=False)
|
|
self.fc_out = nn.Linear(hidden_size, 1)
|
|
self.leaky_relu = nn.LeakyReLU()
|
|
self.softmax = nn.Softmax(dim=1)
|
|
self.d_feat = d_feat
|
|
|
|
def cal_convariance(self, x, y): # the 2nd dimension of x and y are the same
|
|
e_x = torch.mean(x, dim=1).reshape(-1, 1)
|
|
e_y = torch.mean(y, dim=1).reshape(-1, 1)
|
|
e_x_e_y = e_x.mm(torch.t(e_y))
|
|
x_extend = x.reshape(x.shape[0], 1, x.shape[1]).repeat(1, y.shape[0], 1)
|
|
y_extend = y.reshape(1, y.shape[0], y.shape[1]).repeat(x.shape[0], 1, 1)
|
|
e_xy = torch.mean(x_extend * y_extend, dim=2)
|
|
return e_xy - e_x_e_y
|
|
|
|
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]
|
|
out, _ = self.rnn(x)
|
|
hidden = out[:, -1, :]
|
|
hidden = self.bn1(hidden)
|
|
gamma = self.cal_convariance(hidden, hidden)
|
|
output = gamma.mm(hidden)
|
|
output = self.fc(output)
|
|
output = self.bn2(output)
|
|
output = self.leaky_relu(output)
|
|
return self.fc_out(output).squeeze()
|