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
170
171
172
173
174
175
176
177
178
179
|
from numpy import array as numpy_array
from numpy import reshape as numpy_reshape
from numpy.ma import masked as numpy_ma_masked
from numpy.ma import resize as numpy_ma_resize
from numpy.ma import where as numpy_ma_where
from operator import mul
from .functions import _open_netcdf_file, _close_netcdf_file
from ..data.filearray import FileArray
# ====================================================================
#
# NetCDFFileArray object
#
# ====================================================================
class NetCDFFileArray(FileArray):
'''
A sub-array stored in a netCDF file.
**Initialization**
:Parameters:
file : str
The netCDF file name in normalized, absolute form.
dtype : numpy.dtype
The numpy data type of the data array.
ndim : int
Number of dimensions in the data array.
shape : tuple
The data array's dimension sizes.
size : int
Number of elements in the data array.
ncvar : str, optional
The netCDF variable name containing the data array. Must be
set if *varid* is not set.
varid : int, optional
The netCDF ID of the variable containing the data array. Must
be set if *ncvar* is not set. Ignored if *ncvar* is set.
:Examples:
>>> import netCDF4
>>> import os
>>> nc = netCDF4.Dataset('file.nc', 'r')
>>> v = nc.variable['tas']
>>> a = NetCDFFileArray(file=os.path.abspath('file.nc'), ncvar='tas',
dtype=v.dtype, ndim=v.ndim, shape=v.shape, size=v.size)
'''
def __getitem__(self, indices):
'''
x.__getitem__(indices) <==> x[indices]
Returns a numpy array.
'''
nc = self.open()
ncvar = getattr(self, 'ncvar', None)
if ncvar is not None:
# Get the variable by name
array = nc.variables[ncvar][indices]
else:
# Get the variable by netCDF ID
varid = self.varid
for value in nc.variables.itervalues():
if value._varid == varid:
array = value[indices]
break
#--- End: if
if not self.ndim:
# Hmm netCDF4 has a thing for making scalar size 1 , 1d
array = array.squeeze()
# ------------------------------------------------------------
# If approriate, collapse (by concatenation) the outermost
# (fastest varying) dimension of string valued array into
# memory. E.g. [['a','b','c']] becomes ['abc']
# ------------------------------------------------------------
if array.dtype.kind == 'S' and array.ndim > self.ndim:
strlen = array.shape[-1]
new_shape = array.shape[0:-1]
new_size = long(reduce(mul, new_shape, 1))
array = numpy_ma_resize(array, (new_size, strlen))
array = array.filled(fill_value='')
array = numpy_array([''.join(x).rstrip() for x in array],
dtype='S%d' % strlen)
array = array.reshape(new_shape)
array = numpy_ma_where(array=='', numpy_ma_masked, array)
#--- End: if
return array
#--- End: def
def __str__(self):
'''
x.__str__() <==> str(x)
'''
name = getattr(self, 'ncvar', None)
if name is None:
name = self.varid
return "%s%s in %s" % (name, self.shape, self.file)
#--- End: def
def close(self):
'''
Close the file containing the data array.
If the file is not open then no action is taken.
:Returns:
None
:Examples:
>>> f.close()
'''
_close_netcdf_file(self.file)
#--- End: def
@property
def file_pointer(self):
'''
'''
offset = getattr(self, 'ncvar', None)
if offset is None:
offset = self.varid
return (self.file, offset)
#--- End: def
def open(self):
'''
Return a `netCDF4.Dataset` object for the file containing the data
array.
:Returns:
out : netCDF4.Dataset
:Examples:
>>> f.open()
<netCDF4.Dataset at 0x115a4d0>
'''
return _open_netcdf_file(self.file, 'r')
#--- End: def
#--- End: class
|
