Newer
Older
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
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import ipdb
import glob
from datetime import datetime, timedelta
import pytz
from multiprocessing import Pool
from os.path import join, splitext
from modules.datapipeline import datetime_to_ms
def get_flist(f_glob):
f_list = sorted(glob.glob(f_glob, recursive=True))
return f_list
def load_only_imu(f):
try:
df = pd.read_json(f, lines=True, compression='gzip')
except EOFError:
df = pd.read_json(splitext(f)[0], lines=True)
if df.empty: return
data_df = pd.DataFrame(df['data'].tolist())
df = pd.concat([df.drop('data', axis=1), data_df], axis=1)
mask = pd.isna(df['accelerometer'])
na_inds = df.loc[mask, :].index.values
not_na_inds = df.loc[~mask, :].index.values
df_na = df.drop(index=not_na_inds)
df_not_na = df.drop(index=na_inds)
return df_not_na
def get_mean_fs(df):
time = df['timestamp'].values
diff = time[1:] - time[:-1]
fs = 1/np.mean(diff)
print(max(diff))
print(min(diff))
plt.plot(diff)
plt.show()
return fs
def fname_fs(f):
imu_df = load_only_imu(f)
if imu_df is None: return
fs = get_mean_fs(imu_df)
return f, fs
def imu_start_end_time(hdr_fname, data_fname):
imu_hdr = pd.read_json(hdr_fname, orient='index')
imu_hdr = imu_hdr.to_dict().pop(0)
imu_df = load_only_imu(data_fname)
iso_tz = imu_hdr['created']
tzinfo = pytz.timezone(imu_hdr['timezone'])
# adjust for UTC
start_time = datetime.fromisoformat(iso_tz[:-1]) + timedelta(hours=11)
imu_times = imu_df['timestamp'].values
imu_datetimes = [start_time + timedelta(seconds=val) \
for val in imu_times]
nbins = len(imu_times)
est_end = datetime.fromtimestamp(imu_datetimes[0].timestamp() + nbins*(1/120))
print("endtime: {0}\testimate: {1}".format(imu_datetimes[-1],
est_end))
return imu_datetimes[0], imu_datetimes[-1]
def str_to_datetime(time_in):
fmt ="%d/%m/%Y %H:%M:%S.%f"
dstr = datetime.strptime(time_in, fmt)
return dstr
def harness_start_end_time(fname, fs=100):
df = pd.read_csv(fname)
t0 = str_to_datetime(df['Time'].iloc[0])
t1 = str_to_datetime(df['Time'].iloc[-1])
nbins = len(df)
est_end = datetime.fromtimestamp(t0.timestamp() + nbins*(1/fs))
print("endtime: {0}\testimate: {1}".format(t1,
est_end))
return t0, t1
if __name__ == '__main__':
data_dir = '/data/rqchia/aria_walk/Data/test-rest'
f_glob = join(data_dir, '**', 'imudata.gz')
h_glob = join(data_dir, '**', 'recording.g3')
data_fname = glob.glob(f_glob)[0]
hdr_fname = glob.glob(h_glob)[0]
t0, t1 = imu_start_end_time(hdr_fname, data_fname)
a_glob = join(data_dir, '**', '*_Accel.csv')
b_glob = join(data_dir, '**', '*_Breathing.csv')
s_glob = join(data_dir, '**', '*_SummaryEnhanced.csv')
a_fname = glob.glob(a_glob)[0]
a0, a1 = harness_start_end_time(a_fname, fs=100)
b_fname = glob.glob(b_glob)[0]
b0, b1 = harness_start_end_time(b_fname, fs=25)
s_fname = glob.glob(s_glob)[0]
s0, s1 = harness_start_end_time(s_fname, fs=1)
print(f"imu {t0}\t{t1}\n"
f"acc {a0}\t{a1}\n"
f"bre {b0}\t{b1}\n"
f"sum {s0}\t{s1}\n")
# flist = get_flist(f_glob)
# tmp = []
# tmp = fname_fs(flist[0])
# # with Pool(10) as p:
# # tmp = p.map(fname_fs, flist)
# df = pd.DataFrame(tmp, columns=['fname', 'fs'])
# df.dropna(inplace=True)
# mask = df['fs'] > 10
# df = df[mask]
# print(df)