iicd/autodl-projects
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update Q models

Browse Source
This commit is contained in:
D-X-Y 2021-03-03 13:57:48 +00:00
parent 0591fcbb10
commit ead6ae0842
7 changed files with 227 additions and 160 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@ -129,3 +129,4 @@ TEMP-L.sh
# Visual Studio Code
.vscode
mlruns
outputs

94
exps/trading/workflow_test.py
View File

@ -1,94 +0,0 @@
#####################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019.01 #
#####################################################
# Refer to:
# - https://github.com/microsoft/qlib/blob/main/examples/workflow_by_code.ipynb
# - https://github.com/microsoft/qlib/blob/main/examples/workflow_by_code.py
# python exps/trading/workflow_test.py
#####################################################
import sys, site
from pathlib import Path
lib_dir = (Path(__file__).parent / '..' / '..' / 'lib').resolve()
if str(lib_dir) not in sys.path: sys.path.insert(0, str(lib_dir))
import qlib
import pandas as pd
from qlib.config import REG_CN
from qlib.contrib.model.gbdt import LGBModel
from qlib.contrib.data.handler import Alpha158
from qlib.contrib.strategy.strategy import TopkDropoutStrategy
from qlib.contrib.evaluate import (
backtest as normal_backtest,
risk_analysis,
)
from qlib.utils import exists_qlib_data, init_instance_by_config
from qlib.workflow import R
from qlib.workflow.record_temp import SignalRecord, PortAnaRecord
from qlib.utils import flatten_dict
# use default data
# NOTE: need to download data from remote: python scripts/get_data.py qlib_data_cn --target_dir ~/.qlib/qlib_data/cn_data
provider_uri = "~/.qlib/qlib_data/cn_data" # target_dir
if not exists_qlib_data(provider_uri):
print(f"Qlib data is not found in {provider_uri}")
sys.path.append(str(scripts_dir))
from get_data import GetData
GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
qlib.init(provider_uri=provider_uri, region=REG_CN)
market = "csi300"
benchmark = "SH000300"
###################################
# train model
###################################
data_handler_config = {
"start_time": "2008-01-01",
"end_time": "2020-08-01",
"fit_start_time": "2008-01-01",
"fit_end_time": "2014-12-31",
"instruments": market,
}
task = {
"model": {
"class": "QuantTransformer",
"module_path": "trade_models",
"kwargs": {
"loss": "mse",
"GPU": "0",
"metric": "loss",
},
},
"dataset": {
"class": "DatasetH",
"module_path": "qlib.data.dataset",
"kwargs": {
"handler": {
"class": "Alpha158",
"module_path": "qlib.contrib.data.handler",
"kwargs": data_handler_config,
},
"segments": {
"train": ("2008-01-01", "2014-12-31"),
"valid": ("2015-01-01", "2016-12-31"),
"test": ("2017-01-01", "2020-08-01"),
},
},
},
}
# model initiaiton
model = init_instance_by_config(task["model"])
dataset = init_instance_by_config(task["dataset"])
# start exp to train model
with R.start(experiment_name="train_model"):
R.log_params(**flatten_dict(task))
model.fit(dataset)
R.save_objects(trained_model=model)
rid = R.get_recorder().id

100
exps/trading/workflow_tt.py Normal file
View File

@ -0,0 +1,100 @@
#####################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019.01 #
#####################################################
# Refer to:
# - https://github.com/microsoft/qlib/blob/main/examples/workflow_by_code.ipynb
# - https://github.com/microsoft/qlib/blob/main/examples/workflow_by_code.py
# python exps/trading/workflow_tt.py
#####################################################
import sys, site, argparse
from pathlib import Path
lib_dir = (Path(__file__).parent / ".." / ".." / "lib").resolve()
if str(lib_dir) not in sys.path:
sys.path.insert(0, str(lib_dir))
import qlib
from qlib.config import C
import pandas as pd
from qlib.config import REG_CN
from qlib.contrib.model.gbdt import LGBModel
from qlib.contrib.data.handler import Alpha158
from qlib.contrib.strategy.strategy import TopkDropoutStrategy
from qlib.contrib.evaluate import (
backtest as normal_backtest,
risk_analysis,
)
from qlib.utils import exists_qlib_data, init_instance_by_config
from qlib.workflow import R
from qlib.workflow.record_temp import SignalRecord, PortAnaRecord
from qlib.utils import flatten_dict
def main(xargs):
dataset_config = {
"class": "DatasetH",
"module_path": "qlib.data.dataset",
"kwargs": {
"handler": {
"class": "Alpha360",
"module_path": "qlib.contrib.data.handler",
"kwargs": {
"start_time": "2008-01-01",
"end_time": "2020-08-01",
"fit_start_time": "2008-01-01",
"fit_end_time": "2014-12-31",
"instruments": xargs.market,
"infer_processors": [
{"class": "RobustZScoreNorm", "kwargs": {"fields_group": "feature", "clip_outlier": True}},
{"class": "Fillna", "kwargs": {"fields_group": "feature"}},
],
"learn_processors": [
{"class": "DropnaLabel"},
{"class": "CSRankNorm", "kwargs": {"fields_group": "label"}},
],
"label": ["Ref($close, -2) / Ref($close, -1) - 1"],
},
},
"segments": {
"train": ("2008-01-01", "2014-12-31"),
"valid": ("2015-01-01", "2016-12-31"),
"test": ("2017-01-01", "2020-08-01"),
},
},
}
model_config = {
"class": "QuantTransformer",
"module_path": "trade_models",
"kwargs": {
"loss": "mse",
"GPU": "0",
"metric": "loss",
},
}
task = {"model": model_config, "dataset": dataset_config}
model = init_instance_by_config(model_config)
dataset = init_instance_by_config(dataset_config)
# start exp to train model
with R.start(experiment_name="train_tt_model"):
R.log_params(**flatten_dict(task))
model.fit(dataset)
R.save_objects(trained_model=model)
rid = R.get_recorder().id
if __name__ == "__main__":
parser = argparse.ArgumentParser("Vanilla Transformable Transformer")
parser.add_argument("--save_dir", type=str, default="./outputs/tt-ml-runs", help="The checkpoint directory.")
parser.add_argument("--market", type=str, default="csi300", help="The market indicator.")
args = parser.parse_args()
provider_uri = "~/.qlib/qlib_data/cn_data" # target_dir
exp_manager = C.exp_manager
exp_manager["kwargs"]["uri"] = "file:{:}".format(Path(args.save_dir).resolve())
qlib.init(provider_uri=provider_uri, region=REG_CN, exp_manager=exp_manager)
main(args)

2
lib/layers/__init__.py
View File

@ -1,2 +1,4 @@
from .drop import DropBlock2d, DropPath
from .weight_init import trunc_normal_
from .positional_embedding import PositionalEncoder

29
lib/layers/positional_embedding.py Normal file
View File

@ -0,0 +1,29 @@
import torch
import torch.nn as nn
import math
class PositionalEncoder(nn.Module):
# Attention Is All You Need: https://arxiv.org/pdf/1706.03762.pdf
def __init__(self, d_model, max_seq_len):
super(PositionalEncoder, self).__init__()
self.d_model = d_model
# create constant 'pe' matrix with values dependant on
# pos and i
pe = torch.zeros(max_seq_len, d_model)
for pos in range(max_seq_len):
for i in range(0, d_model):
div = 10000 ** ((i // 2) * 2 / d_model)
value = pos / div
if i % 2 == 0:
pe[pos, i] = math.sin(value)
else:
pe[pos, i] = math.cos(value)
pe = pe.unsqueeze(0)
self.register_buffer('pe', pe)
def forward(self, x):
batch, seq, fdim = x.shape[:3]
embeddings = self.pe[:, :seq, :fdim]
return x + embeddings

75
lib/trade_models/quant_transformer.py
View File

@ -1,7 +1,6 @@
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
##################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2021 #
##################################################
from __future__ import division
from __future__ import print_function
@ -26,7 +25,7 @@ import torch
import torch.nn as nn
import torch.optim as optim
from layers import DropPath, trunc_normal_
import layers as xlayers
from qlib.model.base import Model
from qlib.data.dataset import DatasetH
@ -182,7 +181,6 @@ class QuantTransformer(Model):
losses = []
indices = np.arange(len(x_values))
import pdb; pdb.set_trace()
for i in range(len(indices))[:: self.batch_size]:
@ -261,6 +259,7 @@ class QuantTransformer(Model):
torch.cuda.empty_cache()
def predict(self, dataset):
if not self.fitted:
raise ValueError("model is not fitted yet!")
@ -294,9 +293,9 @@ class QuantTransformer(Model):
# Real Model
class Mlp(nn.Module):
class MLP(nn.Module):
def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
super().__init__()
super(MLP, self).__init__()
out_features = out_features or in_features
hidden_features = hidden_features or in_features
self.fc1 = nn.Linear(in_features, hidden_features)
@ -314,8 +313,9 @@ class Mlp(nn.Module):
class Attention(nn.Module):
def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0.):
super().__init__()
super(Attention, self).__init__()
self.num_heads = num_heads
head_dim = dim // num_heads
# NOTE scale factor was wrong in my original version, can set manually to be compat with prev weights
@ -345,15 +345,15 @@ class Block(nn.Module):
def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0.,
drop_path=0., act_layer=nn.GELU, norm_layer=nn.LayerNorm):
super().__init__()
super(Block, self).__init__()
self.norm1 = norm_layer(dim)
self.attn = Attention(
dim, num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale, attn_drop=attn_drop, proj_drop=drop)
# NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
self.drop_path = xlayers.DropPath(drop_path) if drop_path > 0. else nn.Identity()
self.norm2 = norm_layer(dim)
mlp_hidden_dim = int(dim * mlp_ratio)
self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
self.mlp = MLP(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
def forward(self, x):
x = x + self.drop_path(self.attn(self.norm1(x)))
@ -365,19 +365,18 @@ class SimpleEmbed(nn.Module):
def __init__(self, d_feat, embed_dim):
super(SimpleEmbed, self).__init__()
self.d_feat = d_feat
self.proj = nn.Linear(d_feat, embed_dim)
def forward(self, x):
import pdb; pdb.set_trace()
B, C, H, W = x.shape
# FIXME look at relaxing size constraints
assert H == self.img_size[0] and W == self.img_size[1], \
f"Input image size ({H}*{W}) doesn't match model ({self.img_size[0]}*{self.img_size[1]})."
x = self.proj(x).flatten(2).transpose(1, 2)
return x
x = x.reshape(len(x), self.d_feat, -1) # [N, F*T] -> [N, F, T]
x = x.permute(0, 2, 1) # [N, F, T] -> [N, T, F]
out = self.proj(x)
return out
class TransformerModel(nn.Module):
def __init__(self,
d_feat: int,
embed_dim: int = 64,
@ -408,11 +407,9 @@ class TransformerModel(nn.Module):
self.input_embed = SimpleEmbed(d_feat, embed_dim=embed_dim)
"""
self.cls_token = nn.Parameter(torch.zeros(1, 1, embed_dim))
self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + 1, embed_dim))
self.pos_embed = xlayers.PositionalEncoder(d_model=embed_dim, max_seq_len=65)
self.pos_drop = nn.Dropout(p=drop_rate)
"""
dpr = [x.item() for x in torch.linspace(0, drop_path_rate, depth)] # stochastic depth decay rule
self.blocks = nn.ModuleList([
@ -425,15 +422,12 @@ class TransformerModel(nn.Module):
# regression head
self.head = nn.Linear(self.num_features, 1)
"""
trunc_normal_(self.pos_embed, std=.02)
trunc_normal_(self.cls_token, std=.02)
"""
xlayers.trunc_normal_(self.cls_token, std=.02)
self.apply(self._init_weights)
def _init_weights(self, m):
if isinstance(m, nn.Linear):
trunc_normal_(m.weight, std=.02)
xlayers.trunc_normal_(m.weight, std=.02)
if isinstance(m, nn.Linear) and m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.LayerNorm):
@ -441,21 +435,22 @@ class TransformerModel(nn.Module):
nn.init.constant_(m.weight, 1.0)
def forward_features(self, x):
B = x.shape[0]
x = self.input_embed(x)
batch, flatten_size = x.shape
feats = self.input_embed(x) # batch * 60 * 64
cls_tokens = self.cls_token.expand(B, -1, -1) # stole cls_tokens impl from Phil Wang, thanks
x = torch.cat((cls_tokens, x), dim=1)
x = x + self.pos_embed
x = self.pos_drop(x)
cls_tokens = self.cls_token.expand(batch, -1, -1) # stole cls_tokens impl from Phil Wang, thanks
feats_w_ct = torch.cat((cls_tokens, feats), dim=1)
feats_w_tp = self.pos_embed(feats_w_ct)
feats_w_tp = self.pos_drop(feats_w_tp)
for blk in self.blocks:
x = blk(x)
xfeats = feats_w_tp
for block in self.blocks:
xfeats = block(xfeats)
x = self.norm(x)[:, 0]
return x
xfeats = self.norm(xfeats)[:, 0]
return xfeats
def forward(self, x):
x = self.forward_features(x)
x = self.head(x)
return x
feats = self.forward_features(x)
predicts = self.head(feats).squeeze(-1)
return predicts

86
notebooks/Q/workflow-demo.py
View File

@ -1,41 +1,75 @@
import os
import sys
import qlib
import ruamel.yaml as yaml
import pprint
import numpy as np
import pandas as pd
from pathlib import Path
import qlib
from qlib import config as qconfig
from qlib.utils import init_instance_by_config
from qlib.workflow import R
from qlib.data.dataset import DatasetH
from qlib.data.dataset.handler import DataHandlerLP
qlib.init(provider_uri='~/.qlib/qlib_data/cn_data', region=qconfig.REG_CN)
qlib.init(provider_uri="~/.qlib/qlib_data/cn_data", region=qconfig.REG_CN)
dataset_config = {
"class": "DatasetH",
"module_path": "qlib.data.dataset",
"class": "DatasetH",
"module_path": "qlib.data.dataset",
"kwargs": {
"handler": {
"class": "Alpha360",
"module_path": "qlib.contrib.data.handler",
"kwargs": {
"handler": {
"class": "Alpha158",
"module_path": "qlib.contrib.data.handler",
"kwargs": {
"start_time": "2008-01-01",
"end_time": "2020-08-01",
"fit_start_time": "2008-01-01",
"fit_end_time": "2014-12-31",
"instruments": "csi300",
},
},
"segments": {
"train": ("2008-01-01", "2014-12-31"),
"valid": ("2015-01-01", "2016-12-31"),
"test": ("2017-01-01", "2020-08-01"),
},
"start_time": "2008-01-01",
"end_time": "2020-08-01",
"fit_start_time": "2008-01-01",
"fit_end_time": "2014-12-31",
"instruments": "csi300",
"infer_processors": [
{"class": "RobustZScoreNorm", "kwargs": {"fields_group": "feature", "clip_outlier": True}},
{"class": "Fillna", "kwargs": {"fields_group": "feature"}},
],
"learn_processors": [
{"class": "DropnaLabel"},
{"class": "CSRankNorm", "kwargs": {"fields_group": "label"}},
],
"label": ["Ref($close, -2) / Ref($close, -1) - 1"]
},
}
},
"segments": {
"train": ("2008-01-01", "2014-12-31"),
"valid": ("2015-01-01", "2016-12-31"),
"test": ("2017-01-01", "2020-08-01"),
},
},
}
if __name__ == "__main__":
dataset = init_instance_by_config(dataset_config)
pprint.pprint(dataset_config)
pprint.pprint(dataset)
import pdb; pdb.set_trace()
print('Complete')
qlib_root_dir = (Path(__file__).parent / '..' / '..' / '.latent-data' / 'qlib').resolve()
demo_yaml_path = qlib_root_dir / 'examples' / 'benchmarks' / 'GRU' / 'workflow_config_gru_Alpha360.yaml'
print('Demo-workflow-yaml: {:}'.format(demo_yaml_path))
with open(demo_yaml_path, 'r') as fp:
config = yaml.safe_load(fp)
pprint.pprint(config['task']['dataset'])
dataset = init_instance_by_config(dataset_config)
pprint.pprint(dataset_config)
pprint.pprint(dataset)
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"]
import pdb
pdb.set_trace()
print("Complete")