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
|
"""
Fetch the LIGO BigDog time-domain dataset
"""
import os
from io import BytesIO
from gzip import GzipFile
import numpy as np
from . import get_data_home
from .tools import download_with_progress_bar
DATA_URL_LARGE = ('https://github.com/astroML/astroML-data/raw/main/datasets/'
'hoft.968653908-968655956.H1.dat.gz')
LOCAL_FILE_LARGE = 'LIGO_large.npy'
DATA_URL = 'http://www.ligo.org/science/GW100916/HLV-strain.txt'
LOCAL_FILE = 'LIGO_bigdog.npy'
def fetch_LIGO_large(data_home=None, download_if_missing=True):
"""Loader for LIGO large dataset
Parameters
----------
data_home : optional, default=None
Specify another download and cache folder for the datasets. By default
all astroML data is stored in '~/astroML_data'.
download_if_missing : optional, default=True
If False, raise a IOError if the data is not locally available
instead of trying to download the data from the source site.
Returns
-------
data : ndarray
dt : float
data represents ~2000s of amplitude data from LIGO hanford;
dt is the time spacing between measurements in seconds.
"""
data_home = get_data_home(data_home)
local_file = os.path.join(data_home, LOCAL_FILE_LARGE)
if os.path.exists(local_file):
data = np.load(local_file)
else:
if not download_if_missing:
raise IOError('data not present on disk. '
'set download_if_missing=True to download')
print("downloading LIGO bigdog data from %s to %s"
% (DATA_URL_LARGE, local_file))
zipped_buf = download_with_progress_bar(DATA_URL_LARGE,
return_buffer=True)
gzf = GzipFile(fileobj=zipped_buf, mode='rb')
print("uncompressing file...")
extracted_buf = BytesIO(gzf.read())
data = np.loadtxt(extracted_buf)
np.save(local_file, data)
return data, 1. / 4096
def fetch_LIGO_bigdog(data_home=None, download_if_missing=True):
"""Loader for LIGO bigdog event
Parameters
----------
data_home : optional, default=None
Specify another download and cache folder for the datasets. By default
all astroML data is stored in '~/astroML_data'.
download_if_missing : optional, default=True
If False, raise a IOError if the data is not locally available
instead of trying to download the data from the source site.
Returns
-------
data : record array
The data is 10 seconds of measurements from three sites, along with
the time of each measurement.
Examples
--------
>>> from astroML.datasets import fetch_LIGO_bigdog
>>> data = fetch_LIGO_bigdog() # doctest: +IGNORE_OUTPUT +REMOTE_DATA
>>> print(data.dtype.names) # doctest: +REMOTE_DATA
('t', 'Hanford', 'Livingston', 'Virgo')
>>> print(data['t'][:3]) # doctest: +REMOTE_DATA
[ 0.00000000e+00 6.10400000e-05 1.22070000e-04]
>>> print(data['Hanford'][:3]) # doctest: +REMOTE_DATA
[ 1.26329846e-17 1.26846778e-17 1.19187381e-17]
"""
data_home = get_data_home(data_home)
local_file = os.path.join(data_home, LOCAL_FILE)
if os.path.exists(local_file):
data = np.load(local_file)
else:
if not download_if_missing:
raise IOError('data not present on disk. '
'set download_if_missing=True to download')
print("downloading LIGO bigdog data from %s to %s"
% (DATA_URL, local_file))
buffer = download_with_progress_bar(DATA_URL, return_buffer=True)
data = np.loadtxt(buffer, skiprows=2,
dtype=[('t', 'f8'),
('Hanford', 'f8'),
('Livingston', 'f8'),
('Virgo', 'f8')])
np.save(local_file, data)
return data
|
