Mercurial > repos > ecology > xarray_select

comparison timeseries.py @ 4:b393815e4cb7 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyecology/tools-ecology/tree/master/tools/data_manipulation/xarray/ commit fd8ad4d97db7b1fd3876ff63e14280474e06fdf7
author ecology
date Sun, 31 Jul 2022 21:20:41 +0000
parents
children
comparison
equal deleted inserted replaced
3:bf595d613af4 4:b393815e4cb7
1 #!/usr/bin/env python3
2 #
3 #
4 # usage: netCDF_timeseries.py [-h] [--output output.png]
5 # [--save timeseries.tabular]
6 # [--config config-file]
7 # [-v]
8 # input varname
9 # positional arguments:
10 # input input filename with geographical coordinates (netCDF
11 # format)
12 # varname Specify which variable to extract (case sensitive)
13 #
14 # optional arguments:
15 # -h, --help show this help message and exit
16 # --output output.png filename to store image (png format)
17 # --save timeseries.tabular filename to store timeseries (tabular format)
18 # --config config file extract parameters
19 # -v, --verbose switch on verbose mode
20 #
21 import argparse
22 import ast
23 import warnings
24
25 import cftime # noqa: F401
26
27 import matplotlib as mpl
28 mpl.use('Agg')
29
30 import matplotlib.pyplot as plt # noqa: I202,E402
31 from matplotlib.dates import DateFormatter # noqa: I202,E402
32
33 import xarray as xr # noqa: I202,E402
34
35
36 class TimeSeries ():
37 def __init__(self, input, varname, output, save, verbose=False,
38 config_file=""):
39
40 li = list(input.split(","))
41 if len(li) > 1:
42 self.input = li
43 else:
44 self.input = input
45
46 self.varname = varname
47 self.xylim_supported = True
48 if output == "" or output is None:
49 self.output = "Timeseries.png"
50 else:
51 self.output = output
52 if save == "" or save is None:
53 self.save = "Timeseries.tabular"
54 else:
55 self.save = save
56 self.verbose = verbose
57 self.time_start_value = ""
58 self.time_end_value = ""
59 self.lon_value = ""
60 self.lat_value = ""
61 self.lat_name = 'lat'
62 self.lon_name = 'lon'
63 self.time_name = 'time'
64 self.title = ''
65 self.xlabel = ''
66 self.ylabel = ''
67 self.format_date = ''
68 if config_file != "" and config_file is not None:
69 with open(config_file) as f:
70 sdict = ''.join(
71 f.read().replace("\n", "").split('{')[1].split('}')[0]
72 )
73 tmp = ast.literal_eval('{' + sdict.strip() + '}')
74 for key in tmp:
75 if key == 'time_start_value':
76 self.time_start_value = tmp[key]
77 if key == 'time_end_value':
78 self.time_end_value = tmp[key]
79 if key == 'lon_value':
80 self.lon_value = tmp[key]
81 if key == 'lat_value':
82 self.lat_value = tmp[key]
83 if key == 'lon_name':
84 self.lon_name = tmp[key]
85 if key == 'lat_name':
86 self.lat_name = tmp[key]
87 if key == 'time_name':
88 self.time_name = tmp[key]
89 if key == 'title':
90 self.title = tmp[key]
91 if key == 'xlabel':
92 self.xlabel = tmp[key]
93 if key == 'ylabel':
94 self.ylabel = tmp[key]
95 if key == 'format_date':
96 self.format_date = tmp[key]
97 self.format_date = self.format_date.replace('X', '%')
98
99 if type(self.input) is list:
100 self.dset = xr.open_mfdataset(self.input, use_cftime=True)
101 else:
102 self.dset = xr.open_dataset(self.input, use_cftime=True)
103
104 if verbose:
105 print("input: ", self.input)
106 print("varname: ", self.varname)
107 if self.time_start_value:
108 print("time_start_value: ", self.time_start_value)
109 if self.time_end_value:
110 print("time_end_value: ", self.time_end_value)
111 print("output: ", self.output)
112 if self.lon_value:
113 print(self.lon_name, self.lon_value)
114 if self.lat_value:
115 print(self.lat_name, self.lat_value)
116
117 def plot(self):
118 if self.lon_value:
119 lon_c = float(self.lon_value)
120 if self.lat_value:
121 lat_c = float(self.lat_value)
122 if self.lat_value and self.lon_value:
123 self.df = self.dset.sel({self.lat_name: lat_c,
124 self.lon_name: lon_c},
125 method='nearest')
126 else:
127 self.df = self.dset
128 if self.time_start_value or self.time_end_value:
129 self.df = self.df.sel({self.time_name: slice(self.time_start_value,
130 self.time_end_value)})
131 # Saving the time series into a tabular
132 self.df = self.df[self.varname].squeeze().to_dataframe()
133 self.df.dropna().to_csv(self.save, sep='\t')
134 # Plot the time series into png image
135 fig = plt.figure(figsize=(15, 5))
136 ax = plt.subplot(111)
137 self.df[self.varname].plot(ax=ax)
138 if self.title:
139 plt.title(self.title)
140 if self.xlabel:
141 plt.xlabel(self.xlabel)
142 if self.ylabel:
143 plt.ylabel(self.ylabel)
144 if self.format_date:
145 ax.xaxis.set_major_formatter(DateFormatter(self.format_date))
146 fig.tight_layout()
147 fig.savefig(self.output)
148
149
150 if __name__ == '__main__':
151 warnings.filterwarnings("ignore")
152 parser = argparse.ArgumentParser()
153 parser.add_argument(
154 'input',
155 help='input filename with geographical coordinates (netCDF format)'
156 )
157 parser.add_argument(
158 'varname',
159 help='Specify which variable to plot (case sensitive)'
160 )
161 parser.add_argument(
162 '--output',
163 help='output filename to store resulting image (png format)'
164 )
165 parser.add_argument(
166 '--save',
167 help='save resulting tabular file (tabular format) into filename'
168 )
169 parser.add_argument(
170 '--config',
171 help='pass timeseries parameters via a config file'
172 )
173 parser.add_argument(
174 "-v", "--verbose",
175 help="switch on verbose mode",
176 action="store_true")
177 args = parser.parse_args()
178
179 dset = TimeSeries(input=args.input, varname=args.varname,
180 output=args.output, save=args.save, verbose=args.verbose,
181 config_file=args.config)
182 dset.plot()