1 |
|
---|
2 |
""" |
---|
3 |
Classes to handle processed sodar data samples. |
---|
4 |
|
---|
5 |
A list of sample data. |
---|
6 |
|
---|
7 |
A list of dictionaries, each with an item for header and body data. |
---|
8 |
|
---|
9 |
A list of dictionaries of sample data, each with a two items: |
---|
10 |
a header dictionary, and |
---|
11 |
a body list of alitude dictionaries. |
---|
12 |
""" |
---|
13 |
|
---|
14 |
__author__ = 'Chris Calloway' |
---|
15 |
__email__ = 'cbc@unc.edu' |
---|
16 |
__copyright__ = 'Copyright 2007 UNC-CH Department of Marine Science' |
---|
17 |
__license__ = 'GPL2' |
---|
18 |
|
---|
19 |
import rawData |
---|
20 |
import numpy as n |
---|
21 |
import datetime |
---|
22 |
|
---|
23 |
class ProcessedData(list): |
---|
24 |
|
---|
25 |
"""Processed daily sodar file data. |
---|
26 |
|
---|
27 |
A list of rawData.Sample deep copies. |
---|
28 |
""" |
---|
29 |
|
---|
30 |
def __init__(self, data): |
---|
31 |
"""Prepare raw sodar daily data for analysis.""" |
---|
32 |
super(ProcessedData, self).__init__() |
---|
33 |
self.extend([sample.data() for sample in data]) |
---|
34 |
self._normalize() |
---|
35 |
|
---|
36 |
def _normalize(self): |
---|
37 |
"""Clean up data for analysis.""" |
---|
38 |
self._convert() |
---|
39 |
self._stamp() |
---|
40 |
self._sampleInterval() |
---|
41 |
|
---|
42 |
self._minimumAltitude() |
---|
43 |
self._maximumAltitude() |
---|
44 |
|
---|
45 |
|
---|
46 |
|
---|
47 |
|
---|
48 |
|
---|
49 |
|
---|
50 |
|
---|
51 |
|
---|
52 |
|
---|
53 |
|
---|
54 |
def _convert(self): |
---|
55 |
"""Convert data to numbers and correct for invalid values.""" |
---|
56 |
INVALID = "-9999" |
---|
57 |
for sample in self: |
---|
58 |
|
---|
59 |
for key,value in sample['header'].items(): |
---|
60 |
try: |
---|
61 |
if value == INVALID: |
---|
62 |
raise ValueError |
---|
63 |
sample['header'][key] = int(value) |
---|
64 |
except (ValueError, TypeError): |
---|
65 |
sample['header'][key] = n.NaN |
---|
66 |
|
---|
67 |
for altitude in sample['body']: |
---|
68 |
for key,value in altitude.items(): |
---|
69 |
try: |
---|
70 |
if value == INVALID: |
---|
71 |
raise ValueError |
---|
72 |
altitude[key] = float(value) |
---|
73 |
except (ValueError, TypeError): |
---|
74 |
altitude[key] = n.NaN |
---|
75 |
|
---|
76 |
def _stamp(self): |
---|
77 |
"""Add a datetime stamp item to each sample.""" |
---|
78 |
for sample in self: |
---|
79 |
try: |
---|
80 |
header = sample['header'] |
---|
81 |
sample['stamp'] = datetime.datetime(header['YEAR'], |
---|
82 |
header['MONTH'], |
---|
83 |
header['DAY'], |
---|
84 |
header['HOUR'], |
---|
85 |
header['MIN']) |
---|
86 |
except (KeyError, TypeError): |
---|
87 |
sample['stamp'] = datetime.datetime.min |
---|
88 |
|
---|
89 |
def _sampleInterval(self): |
---|
90 |
"""Add a sample interval attribute.""" |
---|
91 |
intervals = zip([sample['stamp'] for sample in self[:-1]], |
---|
92 |
[sample['stamp'] for sample in self[1:]]) |
---|
93 |
intervals = [interval[1] - interval[0] for interval in intervals] |
---|
94 |
intervals = [interval for interval in intervals if interval] |
---|
95 |
intervals = [interval for interval in intervals |
---|
96 |
if interval != datetime.datetime.min] |
---|
97 |
try: |
---|
98 |
self.interval = min(intervals) |
---|
99 |
except ValueError: |
---|
100 |
self.interval = datetime.datetime.min |
---|
101 |
|
---|
102 |
def _minimumAltitude(self): |
---|
103 |
"""Add an overall minimum altitude attribute.""" |
---|
104 |
accumulator = {} |
---|
105 |
for sample in self: |
---|
106 |
minalt = sample['body'][0]['ALT'] |
---|
107 |
sample['header']['minalt'] = minalt |
---|
108 |
if minalt is not n.NaN: |
---|
109 |
if minalt in accumulator: |
---|
110 |
accumulator[minalt] += 1 |
---|
111 |
else: |
---|
112 |
accumulator[minalt] = 1 |
---|
113 |
maxVotes = max(accumulator.values()) |
---|
114 |
for key,value in accumulator.items(): |
---|
115 |
if value == maxVotes: |
---|
116 |
self.minimumAltitude = key |
---|
117 |
break |
---|
118 |
self.minimumAltitude = getattr(self, |
---|
119 |
'minimumAltitude', |
---|
120 |
n.NaN) |
---|
121 |
|
---|
122 |
|
---|
123 |
def _maximumAltitude(self): |
---|
124 |
"""Add an overall maximum altitude attribute.""" |
---|
125 |
accumulator = {} |
---|
126 |
for sample in self: |
---|
127 |
maxalt = sample['body'][-1]['ALT'] |
---|
128 |
sample['header']['maxalt'] = maxalt |
---|
129 |
if maxalt is not n.NaN: |
---|
130 |
if maxalt in accumulator: |
---|
131 |
accumulator[maxalt] += 1 |
---|
132 |
else: |
---|
133 |
accumulator[maxalt] = 1 |
---|
134 |
maxVotes = max(accumulator.values()) |
---|
135 |
for key,value in accumulator.items(): |
---|
136 |
if value == maxVotes: |
---|
137 |
self.maximumAltitude = key |
---|
138 |
break |
---|
139 |
self.maximumAltitude = getattr(self, |
---|
140 |
'maximumAltitude', |
---|
141 |
n.NaN) |
---|
142 |
def _main(): |
---|
143 |
"""Process as script from command line.""" |
---|
144 |
import urllib2 |
---|
145 |
try: |
---|
146 |
rawDataHandle = urllib2.urlopen('http://nemo.isis.unc.edu/'\ |
---|
147 |
'data/nccoos/level0/dukeforest/sodar/'\ |
---|
148 |
'store/2007-06/20070601.dat') |
---|
149 |
rawDataString = rawDataHandle.read() |
---|
150 |
except: |
---|
151 |
raise IOError("Failure to read raw test data") |
---|
152 |
rawDataObject = rawData.RawData(rawDataString) |
---|
153 |
processedDataObject = ProcessedData(rawDataObject) |
---|
154 |
|
---|
155 |
if __name__ == "__main__": |
---|
156 |
_main() |
---|