Newer
Older
# coding=utf-8
import iris
import iris.coord_categorisation
import iris.analysis
import iris.exceptions
import numpy as np
from earthdiagnostics.diagnostic import Diagnostic, DiagnosticOption, DiagnosticDomainOption, \
DiagnosticFrequencyOption, DiagnosticVariableOption
from earthdiagnostics.frequency import Frequencies
from earthdiagnostics.utils import TempFile, Utils
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
class TimeMean(Diagnostic):
"""
Base class for all time mean diagnostics
:param data_manager: data management object
:type data_manager: DataManager
:param startdate: startdate
:type startdate: str
:param member: member number
:type member: int
:param chunk: chunk's number
:type chunk: int
:param variable: variable's name
:type variable: str
:param domain: variable's domain
:type domain: ModelingRealm
:param frequency: original frequency
:type frequency: str
:param grid: original data grid
:type grid: str
"""
def __init__(self, data_manager, startdate, member, chunk, domain, variable, frequency, grid):
Diagnostic.__init__(self, data_manager)
self.startdate = startdate
self.member = member
self.chunk = chunk
self.variable = variable
self.domain = domain
self.frequency = frequency
self.grid = grid
self._target_frequency = None
self.mean_file = None
def __str__(self):
return 'Calculate {0._target_frequency} mean Startdate: {0.startdate} Member: {0.member} Chunk: {0.chunk} ' \
'Variable: {0.domain}:{0.variable} Original frequency: {0.frequency} Grid: {0.grid}'.format(self)
def __hash__(self):
return hash(str(self))
def __eq__(self, other):
if self._different_type(other):
return False
return self.startdate == other.startdate and self.member == other.member and self.chunk == other.chunk and \
self.domain == other.domain and self.variable == other.variable and self.frequency == other.frequency and \
self.grid == other.grid and self._target_frequency == other._target_frequency
@classmethod
def _process_options(cls, diags, options):
options_available = (DiagnosticDomainOption(),
DiagnosticVariableOption(diags.data_manager.config.var_manager),
DiagnosticFrequencyOption(),
DiagnosticOption('grid', ''))
options = cls.process_options(options, options_available)
return options
@classmethod
def generate_jobs(cls, diags, options):
"""
Create a job for each chunk to compute the diagnostic
:param diags: Diagnostics manager class
:type diags: Diags
:param options: variable, domain, frequency=day, grid=''
:type options: list[str]
:return:
"""
options = cls._process_options(diags, options)
job_list = list()
for startdate, member, chunk in diags.config.experiment.get_chunk_list():
job_list.append(cls(diags.data_manager, startdate, member, chunk,
options['domain'], options['variable'], options['frequency'], options['grid']))
return job_list
def request_data(self):
"""Request data required by the diagnostic"""
self.variable_file = self.request_chunk(self.domain, self.variable, self.startdate, self.member, self.chunk,
frequency=self.frequency, grid=self.grid)
def compute_mean(self, cube):
cube: iris.cube.Cube
Returns
-------
iris.cube.Cube
raise NotImplementedError()
def compute(self):
"""Run the diagnostic"""
temp = TempFile.get()
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
cube = iris.load_cube(self.variable_file.local_file)
time_centered = [coord for coord in cube.coords() if coord.var_name == 'time_centered']
if time_centered:
cube.remove_coord(time_centered[0])
iris.coord_categorisation.add_day_of_month(cube, 'time')
iris.coord_categorisation.add_month_number(cube, 'time')
iris.coord_categorisation.add_year(cube, 'time')
cube = self.compute_mean(cube)
cube.remove_coord('day_of_month')
cube.remove_coord('month_number')
cube.remove_coord('year')
try:
region_coord = cube.coord('region')
cube.remove_coord(region_coord)
except iris.exceptions.CoordinateNotFoundError:
region_coord = None
iris.FUTURE.netcdf_no_unlimited = True
iris.save(cube, temp)
if region_coord:
handler = Utils.open_cdf(temp)
region = handler.createVariable('region', str, ('dim0',))
region.standard_name = region_coord.standard_name
region[...] = region_coord.points.astype(np.dtype(str))
handler.variables[self.variable].coordinates += ' region'
handler.close()
self.mean_file.set_local_file(temp)
class DailyMean(TimeMean):
"""
Calculates daily mean for a given variable
:param data_manager: data management object
:type data_manager: DataManager
:param startdate: startdate
:type startdate: str
:param member: member number
:type member: int
:param chunk: chunk's number
:type chunk: int
:param variable: variable's name
:type variable: str
:param domain: variable's domain
:type domain: ModelingRealm
:param frequency: original frequency
:type frequency: str
:param grid: original data grid
:type grid: str
"""
alias = 'daymean'
"Diagnostic alias for the configuration file"
def __init__(self, data_manager, startdate, member, chunk, domain, variable, frequency, grid):
TimeMean.__init__(self, data_manager, startdate, member, chunk, domain, variable, frequency, grid)
self._target_frequency = 'daily'
def compute_mean(self, cube):
cube: iris.cube.Cube
Returns
-------
iris.cube.Cube
return cube.aggregated_by(['day_of_month', 'month_number', 'year'], iris.analysis.MEAN)
def declare_data_generated(self):
"""Declare data to be generated by the diagnostic"""
self.mean_file = self.declare_chunk(self.domain, self.variable, self.startdate, self.member, self.chunk,
frequency=Frequencies.daily, grid=self.grid)
class MonthlyMean(TimeMean):
"""
Calculates monthly mean for a given variable
:param data_manager: data management object
:type data_manager: DataManager
:param startdate: startdate
:type startdate: str
:param member: member number
:type member: int
:param chunk: chunk's number
:type chunk: int
:param variable: variable's name
:type variable: str
:param domain: variable's domain
:type domain: ModelingRealm
:param frequency: original frequency
:type frequency: str
:param grid: original data grid
:type grid: str
"""
alias = 'monmean'
"Diagnostic alias for the configuration file"
def __init__(self, data_manager, startdate, member, chunk, domain, variable, frequency, grid):
TimeMean.__init__(self, data_manager, startdate, member, chunk, domain, variable, frequency, grid)
self._target_frequency = 'monthly'
def compute_mean(self, cube):
cube: iris.cube.Cube
Returns
-------
iris.cube.Cube
return cube.aggregated_by(['month_number', 'year'], iris.analysis.MEAN)
def declare_data_generated(self):
"""Declare data to be generated by the diagnostic"""
self.mean_file = self.declare_chunk(self.domain, self.variable, self.startdate, self.member, self.chunk,
frequency=Frequencies.monthly, grid=self.grid)
class YearlyMean(TimeMean):
"""
Calculates monthly mean for a given variable
:param data_manager: data management object
:type data_manager: DataManager
:param startdate: startdate
:type startdate: str
:param member: member number
:type member: int
:param chunk: chunk's number
:type chunk: int
:param variable: variable's name
:type variable: str
:param domain: variable's domain
:type domain: ModelingRealm
:param frequency: original frequency
:type frequency: str
:param grid: original data grid
:type grid: str
"""
alias = 'yearmean'
"Diagnostic alias for the configuration file"
def __init__(self, data_manager, startdate, member, chunk, domain, variable, frequency, grid):
TimeMean.__init__(self, data_manager, startdate, member, chunk, domain, variable, frequency, grid)
self._target_frequency = 'yearly'
def compute_mean(self, cube):
cube: iris.cube.Cube
Returns
-------
iris.cube.Cube
return cube.aggregated_by(['year'], iris.analysis.MEAN)
def declare_data_generated(self):
"""Declare data to be generated by the diagnostic"""
self.mean_file = self.declare_chunk(self.domain, self.variable, self.startdate, self.member, self.chunk,
frequency=Frequencies.yearly, grid=self.grid)