def whichbox(boxes, cell):
"""Return the box in *boxes* that contains (the centre of the)
*cell*.
"""
lat, lon = eqarea.centre(cell)
for box in boxes:
s, n, w, e = box
if s <= lat < n and w <= lon < e:
return box
def whichbox(boxes, cell):
"""Return the box in *boxes* that contains (the centre of the)
*cell*.
"""
lat,lon = eqarea.centre(cell)
for box in boxes:
s,n,w,e = box
if s <= lat < n and w <= lon < e:
return box
def __init__(self, series, **k):
super(SubboxRecord, self).__init__()
self.__dict__.update(k)
# Synthesize a uid attribute if necessary, based on the box's
# centre.
if not hasattr(self, 'uid'):
if hasattr(self, 'box'):
import eqarea
lat,lon = eqarea.centre(self.box)
self.uid = "%+05.1f%+06.1fC" % (lat,lon)
self.set_series(series)
def __init__(self, series, **k):
super(SubboxRecord, self).__init__()
self.__dict__.update(k)
# Synthesize a uid attribute if necessary, based on the box's
# centre.
if not hasattr(self, 'uid'):
if hasattr(self, 'box'):
import eqarea
lat, lon = eqarea.centre(self.box)
self.uid = "%+05.1f%+06.1fC" % (lat, lon)
self.set_series(series)
def boxuid(box, celltype='QXQ'):
"""Synthesize a uid attribute based on the box's centre. *box* is a
4-tuple of the boxes bounds: (south, north, west, east).
There are 2 sorts of 12 character string returned:
+NN.N+EEE.EQ
QXQ@+NN-EEET
The first is used when the width of the box is less than 10
degrees; the second otherwise. This is the distinction of cells
versus boxes.
*celltype* is used to determine either the last character (1st form,
above) or the first 3 characters (2nd form, above). In the 1st
form, the first character of celltype determines the last character.
"""
import eqarea
lat,lon = eqarea.centre(box)
_,_,w,e = box
if e - w < 10:
return "%+05.1f%+06.1f%s" % (lat, lon, celltype[0])
else:
return "%s@%+03.0f%+04.0fT" % (celltype[:3], lat, lon)
def boxuid(box, celltype='QXQ'):
"""Synthesize a uid attribute based on the box's centre. *box* is a
4-tuple of the boxes bounds: (south, north, west, east).
There are 2 sorts of 12 character string returned:
+NN.N+EEE.EQ
QXQ@+NN-EEET
The first is used when the width of the box is less than 10
degrees; the second otherwise. This is the distinction of cells
versus boxes.
*celltype* is used to determine either the last character (1st form,
above) or the first 3 characters (2nd form, above). In the 1st
form, the first character of celltype determines the last character.
"""
import eqarea
lat, lon = eqarea.centre(box)
_, _, w, e = box
if e - w < 10:
return "%+05.1f%+06.1f%s" % (lat, lon, celltype[0])
else:
return "%s@%+03.0f%+04.0fT" % (celltype[:3], lat, lon)
def iter_subbox_grid(station_records, max_months, first_year, radius):
"""Convert the input *station_records*, into a gridded anomaly
dataset which is returned as an iterator.
*max_months* is the maximum number of months in any station
record. *first_year* is the first year in the dataset. *radius*
is the combining radius in kilometres.
"""
station_records = list(station_records)
log = sys.stdout
# Critical radius as an angle of arc
arc = radius / earth.radius
arcdeg = arc * 180 / math.pi
regions = list(eqarea.gridsub())
for region in regions:
box, subboxes = region[0], list(region[1])
# Extend box, by half a box east and west and by arc north
# and south.
extent = [
box[0] - arcdeg, box[1] + arcdeg, box[2] - 0.5 * (box[3] - box[2]),
box[3] + 0.5 * (box[3] - box[2])
]
if box[0] <= -90 or box[1] >= 90:
# polar
extent[2] = -180.0
extent[3] = +180.0
region_records = list(inbox(station_records, *extent))
# Descending sort by number of good records
# TODO: Switch to using Python's sort method here, although it
# will change the results.
sort(region_records, lambda x, y: y.good_count - x.good_count)
# Count how many cells are empty
n_empty_cells = 0
# Used to generate the "subbox at" rows in the log.
lastcentre = (None, None)
for subbox in subboxes:
# Select and weight stations
centre = eqarea.centre(subbox)
log.write("\rsubbox at %+05.1f%+06.1f (%d empty)" %
(centre + (n_empty_cells, )))
log.flush()
lastcentre = centre
# Of possible station records for this region, filter for those
# from stations within radius of subbox centre.
incircle_records = list(incircle(region_records, arc, *centre))
# Combine data.
subbox_series = [MISSING] * max_months
if len(incircle_records) == 0:
box_obj = giss_data.SubboxRecord(subbox_series,
box=list(subbox),
stations=0,
station_months=0,
d=MISSING)
n_empty_cells += 1
yield box_obj
continue
# Initialise data with first station
record = incircle_records[0]
total_good_months = record.good_count
total_stations = 1
max_weight = record.weight
offset = record.rel_first_month - 1
a = record.series # just a temporary
subbox_series[offset:offset + len(a)] = a
weight = [0.0] * max_months
for i in range(len(a)):
if valid(a[i]):
weight[i + offset] = record.weight
# Add in the remaining stations
for record in incircle_records[1:]:
# TODO: A StationMethod method to produce a padded data series
# would be good here. Hence we could just do:
# new = record.padded_series(max_months)
new = [MISSING] * max_months
aa, bb = record.rel_first_month, record.rel_last_month
new[aa - 1:bb] = record.series
station_months = series.combine(
subbox_series, weight, new, record.weight,
record.rel_first_year, record.rel_last_year + 1,
parameters.gridding_min_overlap)
total_good_months += station_months
if station_months == 0:
continue
total_stations += 1
if max_weight < record.weight:
max_weight = record.weight
series.anomalize(subbox_series,
parameters.gridding_reference_period, first_year)
box_obj = giss_data.SubboxRecord(subbox_series,
n=max_months,
box=list(subbox),
stations=total_stations,
station_months=total_good_months,
d=radius * (1 - max_weight))
yield box_obj
plural_suffix = 's'
if n_empty_cells == 1:
plural_suffix = ''
log.write(
'\rRegion (%+03.0f/%+03.0f S/N %+04.0f/%+04.0f W/E): %d empty cell%s.\n'
% (tuple(box) + (n_empty_cells, plural_suffix)))
log.write("\n")
def iter_subbox_grid(station_records, max_months, first_year, radius):
"""Convert the input *station_records*, into a gridded anomaly
dataset which is returned as an iterator.
*max_months* is the maximum number of months in any station
record. *first_year* is the first year in the dataset. *radius*
is the combining radius in kilometres.
"""
# Clear Climate Code
import earth # required for radius.
# Convert to list because we re-use it for each box (region).
station_records = list(station_records)
# Descending sort by number of good records.
# TODO: Switch to using Python's sort method here, although it
# will change the results.
sort(station_records, lambda x,y: y.good_count - x.good_count)
# A dribble of progress messages.
dribble = sys.stdout
# Critical radius as an angle of arc
arc = radius / earth.radius
arcdeg = arc * 180 / math.pi
regions = list(eqarea.gridsub())
for region in regions:
box, subboxes = region[0], list(region[1])
# Count how many cells are empty
n_empty_cells = 0
for subbox in subboxes:
# Select and weight stations
centre = eqarea.centre(subbox)
dribble.write("\rsubbox at %+05.1f%+06.1f (%d empty)" % (
centre + (n_empty_cells,)))
dribble.flush()
# Determine the contributing stations to this grid cell.
contributors = list(incircle(station_records, arc, *centre))
# Combine data.
subbox_series = [MISSING] * max_months
if not contributors:
box_obj = giss_data.Series(series=subbox_series,
box=list(subbox), stations=0, station_months=0,
d=MISSING)
n_empty_cells += 1
yield box_obj
continue
# Initialise series and weight arrays with first station.
record,wt = contributors[0]
total_good_months = record.good_count
total_stations = 1
offset = record.rel_first_month - 1
a = record.series # just a temporary
subbox_series[offset:offset + len(a)] = a
max_weight = wt
weight = [wt*valid(v) for v in subbox_series]
# For logging, keep a list of stations that contributed.
# Each item in this list is a triple (in list form, so that
# it can be converted to JSON easily) of [id12, weight,
# months]. *id12* is the 12 character station identifier;
# *weight* (a float) is the weight (computed based on
# distance) of the station's series; *months* is a 12 digit
# string that records whether each of the 12 months is used.
# '0' in position *i* indicates that the month was not used,
# a '1' indicates that is was used. January is position 0.
l = [any(valid(v) for v in subbox_series[i::12])
for i in range(12)]
s = ''.join('01'[x] for x in l)
contributed = [[record.uid,wt,s]]
# Add in the remaining stations
for record,wt in contributors[1:]:
# TODO: A method to produce a padded data series
# would be good here. Hence we could just do:
# new = record.padded_series(max_months)
new = [MISSING] * max_months
aa, bb = record.rel_first_month, record.rel_last_month
new[aa - 1:bb] = record.series
station_months = series.combine(
subbox_series, weight, new, wt,
parameters.gridding_min_overlap)
n_good_months = sum(station_months)
total_good_months += n_good_months
if n_good_months == 0:
contributed.append([record.uid, 0.0, '0'*12])
continue
total_stations += 1
s = ''.join('01'[bool(x)] for x in station_months)
contributed.append([record.uid,wt,s])
max_weight = max(max_weight, wt)
series.anomalize(subbox_series,
parameters.gridding_reference_period, first_year)
box_obj = giss_data.Series(series=subbox_series, n=max_months,
box=list(subbox), stations=total_stations,
station_months=total_good_months,
d=radius*(1-max_weight))
log.write("%s stations %s\n" % (box_obj.uid,
asjson(contributed)))
yield box_obj
plural_suffix = 's'
if n_empty_cells == 1:
plural_suffix = ''
dribble.write(
'\rRegion (%+03.0f/%+03.0f S/N %+04.0f/%+04.0f W/E): %d empty cell%s.\n' %
(tuple(box) + (n_empty_cells,plural_suffix)))
dribble.write("\n")
def iter_subbox_grid(station_records, max_months, first_year, radius):
"""Convert the input *station_records*, into a gridded anomaly
dataset which is returned as an iterator.
*max_months* is the maximum number of months in any station
record. *first_year* is the first year in the dataset. *radius*
is the combining radius in kilometres.
"""
station_records = list(station_records)
log = sys.stdout
# Critical radius as an angle of arc
arc = radius / earth.radius
arcdeg = arc * 180 / math.pi
regions = list(eqarea.gridsub())
for region in regions:
box, subboxes = region[0], list(region[1])
# Extend box, by half a box east and west and by arc north
# and south.
extent = [box[0] - arcdeg,
box[1] + arcdeg,
box[2] - 0.5 * (box[3] - box[2]),
box[3] + 0.5 * (box[3] - box[2])]
if box[0] <= -90 or box[1] >= 90:
# polar
extent[2] = -180.0
extent[3] = +180.0
region_records = list(inbox(station_records, *extent))
# Descending sort by number of good records
# TODO: Switch to using Python's sort method here, although it
# will change the results.
sort(region_records, lambda x,y: y.good_count - x.good_count)
# Count how many cells are empty
n_empty_cells = 0
# Used to generate the "subbox at" rows in the log.
lastcentre = (None, None)
for subbox in subboxes:
# Select and weight stations
centre = eqarea.centre(subbox)
log.write("\rsubbox at %+05.1f%+06.1f (%d empty)" % (
centre + (n_empty_cells,)))
log.flush()
lastcentre = centre
# Of possible station records for this region, filter for those
# from stations within radius of subbox centre.
incircle_records = list(incircle(region_records, arc, *centre))
# Combine data.
subbox_series = [MISSING] * max_months
if len(incircle_records) == 0:
box_obj = giss_data.SubboxRecord(subbox_series,
box=list(subbox), stations=0, station_months=0,
d=MISSING)
n_empty_cells += 1
yield box_obj
continue
# Initialise data with first station
record = incircle_records[0]
total_good_months = record.good_count
total_stations = 1
max_weight = record.weight
offset = record.rel_first_month - 1
a = record.series # just a temporary
subbox_series[offset:offset + len(a)] = a
weight = [0.0] * max_months
for i in range(len(a)):
if valid(a[i]):
weight[i + offset] = record.weight
# Add in the remaining stations
for record in incircle_records[1:]:
# TODO: A StationMethod method to produce a padded data series
# would be good here. Hence we could just do:
# new = record.padded_series(max_months)
new = [MISSING] * max_months
aa, bb = record.rel_first_month, record.rel_last_month
new[aa - 1:bb] = record.series
station_months = series.combine(
subbox_series, weight, new, record.weight,
record.rel_first_year, record.rel_last_year + 1,
parameters.gridding_min_overlap)
total_good_months += station_months
if station_months == 0:
continue
total_stations += 1
if max_weight < record.weight:
max_weight = record.weight
series.anomalize(subbox_series,
parameters.gridding_reference_period, first_year)
box_obj = giss_data.SubboxRecord(subbox_series, n=max_months,
box=list(subbox), stations=total_stations,
station_months=total_good_months,
d=radius*(1-max_weight))
yield box_obj
plural_suffix = 's'
if n_empty_cells == 1:
plural_suffix = ''
log.write(
'\rRegion (%+03.0f/%+03.0f S/N %+04.0f/%+04.0f W/E): %d empty cell%s.\n' %
(tuple(box) + (n_empty_cells,plural_suffix)))
log.write("\n")
def iter_subbox_grid(station_records, max_months, first_year, radius):
"""Convert the input *station_records*, into a gridded anomaly
dataset which is returned as an iterator.
*max_months* is the maximum number of months in any station
record. *first_year* is the first year in the dataset. *radius*
is the combining radius in kilometres.
"""
# Clear Climate Code
import earth # required for radius.
# Convert to list because we re-use it for each box (region).
station_records = list(station_records)
# Descending sort by number of good records.
# TODO: Switch to using Python's sort method here, although it
# will change the results.
sort(station_records, lambda x, y: y.good_count - x.good_count)
# A dribble of progress messages.
dribble = sys.stdout
# Critical radius as an angle of arc
arc = radius / earth.radius
arcdeg = arc * 180 / math.pi
regions = list(eqarea.gridsub())
for region in regions:
box, subboxes = region[0], list(region[1])
# Count how many cells are empty
n_empty_cells = 0
for subbox in subboxes:
# Select and weight stations
centre = eqarea.centre(subbox)
dribble.write("\rsubbox at %+05.1f%+06.1f (%d empty)" %
(centre + (n_empty_cells, )))
dribble.flush()
# Determine the contributing stations to this grid cell.
contributors = list(incircle(station_records, arc, *centre))
# Combine data.
subbox_series = [MISSING] * max_months
if not contributors:
box_obj = giss_data.Series(series=subbox_series,
box=list(subbox),
stations=0,
station_months=0,
d=MISSING)
n_empty_cells += 1
yield box_obj
continue
# Initialise series and weight arrays with first station.
record, wt = contributors[0]
total_good_months = record.good_count
total_stations = 1
offset = record.rel_first_month - 1
a = record.series # just a temporary
subbox_series[offset:offset + len(a)] = a
max_weight = wt
weight = [wt * valid(v) for v in subbox_series]
# For logging, keep a list of stations that contributed.
# Each item in this list is a triple (in list form, so that
# it can be converted to JSON easily) of [id12, weight,
# months]. *id12* is the 12 character station identifier;
# *weight* (a float) is the weight (computed based on
# distance) of the station's series; *months* is a 12 digit
# string that records whether each of the 12 months is used.
# '0' in position *i* indicates that the month was not used,
# a '1' indicates that is was used. January is position 0.
l = [
any(valid(v) for v in subbox_series[i::12]) for i in range(12)
]
s = ''.join('01'[x] for x in l)
contributed = [[record.uid, wt, s]]
# Add in the remaining stations
for record, wt in contributors[1:]:
# TODO: A method to produce a padded data series
# would be good here. Hence we could just do:
# new = record.padded_series(max_months)
new = [MISSING] * max_months
aa, bb = record.rel_first_month, record.rel_last_month
new[aa - 1:bb] = record.series
station_months = series.combine(
subbox_series, weight, new, wt,
parameters.gridding_min_overlap)
n_good_months = sum(station_months)
total_good_months += n_good_months
if n_good_months == 0:
contributed.append([record.uid, 0.0, '0' * 12])
continue
total_stations += 1
s = ''.join('01'[bool(x)] for x in station_months)
contributed.append([record.uid, wt, s])
max_weight = max(max_weight, wt)
series.anomalize(subbox_series,
parameters.gridding_reference_period, first_year)
box_obj = giss_data.Series(series=subbox_series,
n=max_months,
box=list(subbox),
stations=total_stations,
station_months=total_good_months,
d=radius * (1 - max_weight))
log.write("%s stations %s\n" % (box_obj.uid, asjson(contributed)))
yield box_obj
plural_suffix = 's'
if n_empty_cells == 1:
plural_suffix = ''
dribble.write(
'\rRegion (%+03.0f/%+03.0f S/N %+04.0f/%+04.0f W/E): %d empty cell%s.\n'
% (tuple(box) + (n_empty_cells, plural_suffix)))
dribble.write("\n")
