File: _api.py

package info (click to toggle)
python-rosettasciio 0.7.1-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 144,644 kB
  • sloc: python: 36,638; xml: 2,582; makefile: 20; ansic: 4
file content (220 lines) | stat: -rw-r--r-- 6,636 bytes parent folder | download
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
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
# -*- coding: utf-8 -*-
# Copyright 2007-2023 The HyperSpy developers
#
# This file is part of RosettaSciIO.
#
# RosettaSciIO is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# RosettaSciIO is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with RosettaSciIO. If not, see <https://www.gnu.org/licenses/#GPL>.

import logging
import os

import numpy as np

from rsciio._docstrings import FILENAME_DOC, LAZY_UNSUPPORTED_DOC, RETURNS_DOC

_logger = logging.getLogger(__name__)


try:
    from netCDF4 import Dataset as netcdf_file_reader

    netcdf_reader = "netCDF4"
except Exception:
    try:
        from scipy.io import netcdf_file as netcdf_file_reader

        netcdf_reader = "scipy"
    except Exception:
        netcdf_reader = None


attrib2netcdf = {
    "energyorigin": "energy_origin",
    "energyscale": "energy_scale",
    "energyunits": "energy_units",
    "xorigin": "x_origin",
    "xscale": "x_scale",
    "xunits": "x_units",
    "yorigin": "y_origin",
    "yscale": "y_scale",
    "yunits": "y_units",
    "zorigin": "z_origin",
    "zscale": "z_scale",
    "zunits": "z_units",
    "exposure": "exposure",
    "title": "title",
    "binning": "binning",
    "readout_frequency": "readout_frequency",
    "ccd_height": "ccd_height",
    "blanking": "blanking",
}

acquisition2netcdf = {
    "exposure": "exposure",
    "binning": "binning",
    "readout_frequency": "readout_frequency",
    "ccd_height": "ccd_height",
    "blanking": "blanking",
    "gain": "gain",
    "pppc": "pppc",
}

treatments2netcdf = {
    "dark_current": "dark_current",
    "readout": "readout",
}


def file_reader(filename, lazy=False):
    """
    Read netCDF ``.nc`` files saved using the HyperSpy predecessor EELSlab.

    Parameters
    ----------
    %s
    %s

    %s
    """
    if netcdf_reader is None:
        raise ImportError(
            "No netCDF library installed. "
            "To read EELSLab netcdf files install "
            "one of the following packages:"
            "netCDF4 or scipy."
        )

    if lazy is not False:
        raise NotImplementedError("Lazy loading is not supported.")

    ncfile = netcdf_file_reader(filename, "r")

    if (
        hasattr(ncfile, "file_format_version")
        and ncfile.file_format_version == "EELSLab 0.1"
    ):
        dictionary = nc_hyperspy_reader_0dot1(ncfile, filename)
    else:
        ncfile.close()
        raise IOError("Unsupported netCDF file")

    return (dictionary,)


file_reader.__doc__ %= (FILENAME_DOC, LAZY_UNSUPPORTED_DOC, RETURNS_DOC)


def nc_hyperspy_reader_0dot1(ncfile, filename):
    calibration_dict, acquisition_dict, treatments_dict = {}, {}, {}
    dc = ncfile.variables["data_cube"]
    data = dc[:]
    if "history" in calibration_dict:
        calibration_dict["history"] = eval(ncfile.history)
    for attrib in attrib2netcdf.items():
        if hasattr(dc, attrib[1]):
            value = eval("dc." + attrib[1])
            if isinstance(value, np.ndarray):
                calibration_dict[attrib[0]] = value[0]
            else:
                calibration_dict[attrib[0]] = value
        else:
            _logger.warning(
                "Warning: the attribute '%s' is not defined in " "the file '%s'",
                attrib[0],
                filename,
            )
    for attrib in acquisition2netcdf.items():
        if hasattr(dc, attrib[1]):
            value = eval("dc." + attrib[1])
            if isinstance(value, np.ndarray):
                acquisition_dict[attrib[0]] = value[0]
            else:
                acquisition_dict[attrib[0]] = value
        else:
            _logger.warning(
                "Warning: the attribute '%s' is not defined in " "the file '%s'",
                attrib[0],
                filename,
            )
    for attrib in treatments2netcdf.items():
        if hasattr(dc, attrib[1]):
            treatments_dict[attrib[0]] = eval("dc." + attrib[1])
        else:
            _logger.warning(
                "Warning: the attribute '%s' is not defined in " "the file '%s'",
                attrib[0],
                filename,
            )
    original_metadata = {
        "record_by": ncfile.type,
        "calibration": calibration_dict,
        "acquisition": acquisition_dict,
        "treatments": treatments_dict,
    }
    ncfile.close()
    # Now we'll map some parameters
    record_by = "image" if original_metadata["record_by"] == "image" else "spectrum"
    if record_by == "image":
        dim = len(data.shape)
        names = ["Z", "Y", "X"][3 - dim :]
        scaleskeys = ["zscale", "yscale", "xscale"]
        originskeys = ["zorigin", "yorigin", "xorigin"]
        unitskeys = ["zunits", "yunits", "xunits"]
        navigate = [True, False, False]

    elif record_by == "spectrum":
        dim = len(data.shape)
        names = ["Y", "X", "Energy"][3 - dim :]
        scaleskeys = ["yscale", "xscale", "energyscale"]
        originskeys = ["yorigin", "xorigin", "energyorigin"]
        unitskeys = ["yunits", "xunits", "energyunits"]
        navigate = [True, True, False]

    # The images are recorded in the Fortran order
    data = data.T.copy()
    try:
        scales = [calibration_dict[key] for key in scaleskeys[3 - dim :]]
    except KeyError:
        scales = [1, 1, 1][3 - dim :]
    try:
        origins = [calibration_dict[key] for key in originskeys[3 - dim :]]
    except KeyError:
        origins = [0, 0, 0][3 - dim :]
    try:
        units = [calibration_dict[key] for key in unitskeys[3 - dim :]]
    except KeyError:
        units = ["", "", ""]
    axes = [
        {
            "size": int(data.shape[i]),
            "index_in_array": i,
            "name": names[i],
            "scale": scales[i],
            "offset": origins[i],
            "units": units[i],
            "navigate": navigate[i],
        }
        for i in range(dim)
    ]
    metadata = {"General": {}, "Signal": {}}
    metadata["General"]["original_filename"] = os.path.split(filename)[1]
    metadata["General"]["signal_type"] = ""
    dictionary = {
        "data": data,
        "axes": axes,
        "metadata": metadata,
        "original_metadata": original_metadata,
    }

    return dictionary