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
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
168
169
from typing import Dict, Union, List
from datetime import timedelta
import numpy as np
from obspy import UTCDateTime
from pydantic import BaseModel, Field, validator
from enum import Enum
class Flag(BaseModel):
"""
Base class for flagging features in magnetic timeseries data.
Flag example:
```
automatic_flag = Metadata(
created_by='ex_algorithm',
start_time=UTCDateTime('2023-01-01T03:05:10'),
end_time=UTCDateTime('2023-01-01T03:05:11'),
network='NT',
station='BOU',
channel='BEH',
category=MetadataCategory.FLAG,
comment="spike detected",
priority=1,
data_valid=False,
metadata= ArtificialDisturbance{
"description": "Spike in magnetic field strength",
"field_work": false,
"corrected": false,
"artificial_disturbance_type": ArtificialDisturbanceType.SPIKE,
"source": "Lightning".
"deviation": None,
}
)
```
"""
description: str = Field(..., description="Description of the flag")
field_work: bool = Field(..., description="Flag signaling field work")
corrected: int = Field(..., description="Corrected ID for processing stage")
# Should there be an attribute for data quality or is data_valid above enough?
class ArtificialDisturbanceType(str, Enum):
SPIKES = "SPIKES"
OFFSET = "OFFSET"
ARTIFICIAL_DISTURBANCES = "ARTIFICIAL_DISTURBANCES"
class ArtificialDisturbance(Flag):
"""
This class is used to flag artificial disturbances.
Artificial disturbances consist of the following types:
SPIKES = Single data points that are outliers in the timeseries.
OFFSET = A relatively constant shift or deviation in the baseline magnetic field.
ARTIFICIAL_DISTURBANCES = A catch-all for a continuous period of unwanted variations, may include multiple spikes, offsets and/or gaps.
Attributes
----------
artificial_disturbance_type:ArtificialDisturbanceType
The type of artificial disturbance(s).
source: str
Source of the disturbance if known or suspected.
deviation: float
Deviation of an offset in nt.
spikes: np.ndarray
NumPy array of timestamps as UTCDateTime. Can be a single spike or many spikes.
"""
artificial_disturbance_type: ArtificialDisturbanceType
deviation: float = None
source: str = None
spikes: np.ndarray = None
class Gap(Flag):
"""
This class is used to flag gaps in data.
A gap is a period where data is missing or not recorded.
Attributes
----------
cause: str
Cause of gap, e.g., network outage.
handling: str
How the gap is being handled, e.g., backfilled.
"""
cause: str = None
handling: str = None
class EventType(str, Enum):
GEOMAGNETIC_STORM = "GEOMAGNETIC_STORM"
GEOMAGNETIC_SUBSTORM = "GEOMAGNETIC_SUBSTORM"
EARTHQUAKE = "EARTHQUAKE"
OTHER = "OTHER"
class Event(Flag):
"""
This class is used to flag an event of interest such as a geomagnetic storm or earthquake.
Attributes
----------
event_type : EventType
The type of event.
scale : str
Geomagnetic storm scale or Richter scale magnitude.
index : int
Planetary K-index, DST index or some other index.
url : str
A url related to the event. Could be NOAA SWPC, USGS Earthquakes page or another site.
"""
event_type: EventType
index: int = None
scale: str = None
url: str = None
# More example usage:
timestamps_array = np.array(
[
UTCDateTime("2023-11-16T12:00:0"),
UTCDateTime("2023-11-16T12:01:10"),
UTCDateTime("2023-11-16T12:02:30"),
]
)
spikes_data = {
"starttime": "2023-11-16 12:00:00",
"endtime": "2023-11-16 12:02:30",
"description": "Spikes description",
"field_work": False,
"corrected": 32265,
"disturbance_type": ArtificialDisturbanceType.SPIKES,
"source": "processing",
"spikes": timestamps_array,
}
offset_data = {
"description": "Offset description",
"field_work": False,
"corrected": 47999,
"disturbance_type": ArtificialDisturbanceType.OFFSET,
"source": "Bin change",
"deviation": 10.0,
}
geomagnetic_storm_data = {
"description": "Geomagnetic storm",
"field_work": False,
"corrected": 36999,
"event_type": EventType.GEOMAGNETIC_STORM,
"scale": "G3",
"index": 7,
"url": "https://www.swpc.noaa.gov/products/planetary-k-index",
}
spike_instance = ArtificialDisturbance(**spikes_data)
offset_instance = ArtificialDisturbance(**offset_data)
print(spike_instance.dict())
print(offset_instance.dict())