Repository navigation
Expand file tree
/
Copy pathdata.py
More file actions
167 lines (143 loc) · 5.92 KB
/
Copy pathdata.py
File metadata and controls
167 lines (143 loc) · 5.92 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
import re
import qlib
import shutil
import zipfile
import requests
import datetime
from tqdm import tqdm
from pathlib import Path
from loguru import logger
class GetData:
DATASET_VERSION = "v1"
REMOTE_URL = "http://fintech.msra.cn/stock_data/downloads"
QLIB_DATA_NAME = "{dataset_name}_{region}_{interval}_{qlib_version}.zip"
def __init__(self, delete_zip_file=False):
"""
Parameters
----------
delete_zip_file : bool, optional
Whether to delete the zip file, value from True or False, by default False
"""
self.delete_zip_file = delete_zip_file
def normalize_dataset_version(self, dataset_version: str = None):
if dataset_version is None:
dataset_version = self.DATASET_VERSION
return dataset_version
def merge_remote_url(self, file_name: str, dataset_version: str = None):
return f"{self.REMOTE_URL}/{self.normalize_dataset_version(dataset_version)}/{file_name}"
def _download_data(
self, file_name: str, target_dir: [Path, str], delete_old: bool = True, dataset_version: str = None
):
target_dir = Path(target_dir).expanduser()
target_dir.mkdir(exist_ok=True, parents=True)
# saved file name
_target_file_name = datetime.datetime.now().strftime("%Y%m%d%H%M%S") + "_" + file_name
target_path = target_dir.joinpath(_target_file_name)
url = self.merge_remote_url(file_name, dataset_version)
resp = requests.get(url, stream=True)
if resp.status_code != 200:
raise requests.exceptions.HTTPError()
chunk_size = 1024
logger.warning(
f"The data for the example is collected from Yahoo Finance. Please be aware that the quality of the data might not be perfect. (You can refer to the original data source: https://finance.yahoo.com/lookup.)"
)
logger.info(f"{file_name} downloading......")
with tqdm(total=int(resp.headers.get("Content-Length", 0))) as p_bar:
with target_path.open("wb") as fp:
for chunk in resp.iter_content(chunk_size=chunk_size):
fp.write(chunk)
p_bar.update(chunk_size)
self._unzip(target_path, target_dir, delete_old)
if self.delete_zip_file:
target_path.unlink()
def check_dataset(self, file_name: str, dataset_version: str = None):
url = self.merge_remote_url(file_name, dataset_version)
resp = requests.get(url, stream=True)
status = True
if resp.status_code == 404:
status = False
return status
@staticmethod
def _unzip(file_path: Path, target_dir: Path, delete_old: bool = True):
if delete_old:
logger.warning(
f"will delete the old qlib data directory(features, instruments, calendars, features_cache, dataset_cache): {target_dir}"
)
GetData._delete_qlib_data(target_dir)
logger.info(f"{file_path} unzipping......")
with zipfile.ZipFile(str(file_path.resolve()), "r") as zp:
for _file in tqdm(zp.namelist()):
zp.extract(_file, str(target_dir.resolve()))
@staticmethod
def _delete_qlib_data(file_dir: Path):
logger.info(f"delete {file_dir}")
rm_dirs = []
for _name in ["features", "calendars", "instruments", "features_cache", "dataset_cache"]:
_p = file_dir.joinpath(_name)
if _p.exists():
rm_dirs.append(str(_p.resolve()))
if rm_dirs:
flag = input(
f"Will be deleted: "
f"\n\t{rm_dirs}"
f"\nIf you do not need to delete {file_dir}, please change the <--target_dir>"
f"\nAre you sure you want to delete, yes(Y/y), no (N/n):"
)
if str(flag) not in ["Y", "y"]:
exit()
for _p in rm_dirs:
logger.warning(f"delete: {_p}")
shutil.rmtree(_p)
def qlib_data(
self,
name="qlib_data",
target_dir="~/.qlib/qlib_data/cn_data",
version=None,
interval="1d",
region="cn",
delete_old=True,
):
"""download cn qlib data from remote
Parameters
----------
target_dir: str
data save directory
name: str
dataset name, value from [qlib_data, qlib_data_simple], by default qlib_data
version: str
data version, value from [v1, ...], by default None(use script to specify version)
interval: str
data freq, value from [1d], by default 1d
region: str
data region, value from [cn, us], by default cn
delete_old: bool
delete an existing directory, by default True
Examples
---------
python get_data.py qlib_data --name qlib_data --target_dir ~/.qlib/qlib_data/cn_data --interval 1d --region cn
-------
"""
qlib_version = ".".join(re.findall(r"(\d+)\.+", qlib.__version__))
def _get_file_name(v):
return self.QLIB_DATA_NAME.format(
dataset_name=name, region=region.lower(), interval=interval.lower(), qlib_version=v
)
file_name = _get_file_name(qlib_version)
if not self.check_dataset(file_name, version):
file_name = _get_file_name("latest")
self._download_data(file_name.lower(), target_dir, delete_old, dataset_version=version)
def csv_data_cn(self, target_dir="~/.qlib/csv_data/cn_data"):
"""download cn csv data from remote
Parameters
----------
target_dir: str
data save directory
Examples
---------
python get_data.py csv_data_cn --target_dir ~/.qlib/csv_data/cn_data
-------
"""
file_name = "csv_data_cn.zip"
self._download_data(file_name, target_dir)