def step3(records, radius=parameters.gridding_radius, year_begin=1880):
"""Step 3 of the GISS processing.
*records* should be a generator that yields each station.
"""
# Most of the metadata here used to be synthesized in step2.py and
# copied from the first yielded record. Now we synthesize here
# instead.
last_year = giss_data.get_ghcn_last_year()
year_begin = giss_data.BASE_YEAR
# Compute total number of months in a fixed length record.
monm = 12 * (last_year - year_begin + 1)
meta = giss_data.SubboxMetaData(mo1=None,
kq=1,
mavg=6,
monm=monm,
monm4=monm + 7,
yrbeg=year_begin,
missing_flag=9999,
precipitation_flag=9999,
title='GHCN V2 Temperatures (.1 C)')
units = '(C)'
title = "%20.20s ANOM %-4s CR %4dKM %s-present" % (meta.title, units,
radius, year_begin)
meta.mo1 = 1
meta.title = title.ljust(80)
box_source = iter_subbox_grid(records, monm, year_begin, radius)
yield meta
for box in box_source:
yield box
def step3(records, radius=parameters.gridding_radius, year_begin=1880):
"""Step 3 of the GISS processing.
*records* should be a generator that yields each station.
"""
# Most of the metadata here used to be synthesized in step2.py and
# copied from the first yielded record. Now we synthesize here
# instead.
last_year = giss_data.get_ghcn_last_year()
year_begin = giss_data.BASE_YEAR
# Compute total number of months in a fixed length record.
monm = 12 * (last_year - year_begin + 1)
meta = giss_data.SubboxMetaData(mo1=None, kq=1, mavg=6, monm=monm,
monm4=monm + 7, yrbeg=year_begin, missing_flag=9999,
precipitation_flag=9999,
title='GHCN V2 Temperatures (.1 C)')
units = '(C)'
title = "%20.20s ANOM %-4s CR %4dKM %s-present" % (meta.title,
units, radius, year_begin)
meta.mo1 = 1
meta.title = title.ljust(80)
box_source = iter_subbox_grid(records, monm, year_begin, radius)
yield meta
for box in box_source:
yield box
def urban_adjustments(anomaly_stream):
"""Takes an iterator of station records and applies an adjustment
to urban stations to compensate for urban temperature effects.
Returns an iterator of station records. Rural stations are passed
unchanged. Urban stations which cannot be adjusted are discarded.
The adjustment follows a linear or two-part linear fit to the
difference in annual anomalies between the urban station and the
combined set of nearby rural stations. The linear fit is to allow
for a linear effect at the urban station. The two-part linear fit
is to allow for a model of urban effect which starts or stops at
some point during the time series.
The algorithm is essentially as follows:
For each urban station:
1. Find all the rural stations within a fixed radius;
2. Combine the annual anomaly series for those rural stations, in
order of valid-data count;
3. Calculate a two-part linear fit for the difference between
the urban annual anomalies and this combined rural annual anomaly;
4. If this fit is satisfactory, apply it; otherwise apply a linear fit.
If there are not enough nearby rural stations, or the combined
rural record does not have enough overlap with the urban
record, try a second time for this urban station, with a
larger radius. If there is still not enough data, discard the
urban station.
"""
last_year = giss_data.get_ghcn_last_year()
first_year = 1880
iyoff = giss_data.BASE_YEAR - 1
iyrm = last_year - iyoff
rural_stations = []
urban_stations = {}
pi180 = math.pi / 180.0
all = []
for record in anomaly_stream:
station = record.station
all.append(record)
record.urban_adjustment = None
annual_anomaly(record)
if record.anomalies is None:
continue
length = len(record.anomalies)
d = Struct()
d.anomalies = record.anomalies
d.cslat = math.cos(station.lat * pi180)
d.snlat = math.sin(station.lat * pi180)
d.cslon = math.cos(station.lon * pi180)
d.snlon = math.sin(station.lon * pi180)
d.id = record.uid
d.first_year = record.first - iyoff
d.last_year = d.first_year + length - 1
d.station = station
d.record = record
if is_rural(station):
rural_stations.append(d)
else:
urban_stations[record] = d
# Sort the rural stations according to the length of the time record
# (ignoring gaps).
for st in rural_stations:
st.recLen = len([v for v in st.anomalies if valid(v)])
rural_stations.sort(key=lambda s:s.recLen)
rural_stations.reverse()
# Combine time series for rural stations around each urban station
for record in all:
us = urban_stations.get(record, None)
if us is None:
# Just remove leading/trailing invalid values for rural stations.
record.strip_invalid()
record.begin = record.first
record.end = record.last
yield record
continue
iyu1 = us.first_year + iyoff - 1 # subtract 1 for a possible partial yr
iyu2 = us.last_year + iyoff + 1 # add 1 for partial year
usingFullRadius = False
dropStation = False
needNewNeighbours = True
while True:
if needNewNeighbours:
if usingFullRadius:
radius = parameters.urban_adjustment_full_radius
else:
radius = parameters.urban_adjustment_full_radius / 2
neighbors = get_neighbours(us, rural_stations, radius)
if not neighbors:
if usingFullRadius:
dropStation = True
break
usingFullRadius = True
needNewNeighbours = True
continue
counts, urban_series, combined = combine_neighbors(
us, iyrm, iyoff, neighbors)
iy1 = 1
needNewNeighbours = False
points, quorate_count, first, last = prepare_series(
iy1, iyrm, combined, urban_series, counts, iyoff)
if quorate_count < parameters.urban_adjustment_min_years:
if usingFullRadius:
dropStation = True
break
usingFullRadius = True
needNewNeighbours = True
continue
if quorate_count >= (parameters.urban_adjustment_proportion_good
* (last - first + 0.9)):
break
# Not enough good years for the given range. Try to save
# cases in which the gaps are in the early part, by
# dropping that part and going around to prepare_series
# again.
iy1 = int(last - (quorate_count - 1) /
parameters.urban_adjustment_proportion_good)
if iy1 < first + 1:
iy1 = first + 1 # avoid infinite loop
if dropStation:
continue
fit = getfit(points)
# find extended range
iyxtnd = int(round(quorate_count /
parameters.urban_adjustment_proportion_good)
- (last - first + 1))
n1x = first + iyoff
n2x = last + iyoff
if iyxtnd < 0:
sys.exit('impossible')
if iyxtnd > 0:
lxend = iyu2 - (last + iyoff)
if iyxtnd <= lxend:
n2x = n2x + lxend
else:
n1x = n1x - (iyxtnd - lxend)
if n1x < iyu1:
n1x = iyu1
n2x = iyu2
series = record.series
# adjust
m1 = record.rel_first_month + record.good_start_idx
m2 = record.rel_first_month + record.good_end_idx - 1
offset = record.good_start_idx # index of first valid month
a, b = adjust(first_year, record, series, fit, n1x, n2x,
first + iyoff, last + iyoff, m1, m2, offset)
# a and b are numbers of new first and last valid months
aa = a - m1
bb = b - a + 1
record.set_series(a-1 + first_year * 12 + 1,
series[aa + offset:aa + offset + bb])
record.begin = ((a-1) / 12) + first_year
record.first = record.begin
record.end = ((b-1) / 12) + first_year
record.last = record.last_year
yield record
def urban_adjustments(anomaly_stream):
"""Takes an iterator of station records and applies an adjustment
to urban stations to compensate for urban temperature effects.
Returns an iterator of station records. Rural stations are passed
unchanged. Urban stations which cannot be adjusted are discarded.
The adjustment follows a linear or two-part linear fit to the
difference in annual anomalies between the urban station and the
combined set of nearby rural stations. The linear fit is to allow
for a linear effect at the urban station. The two-part linear fit
is to allow for a model of urban effect which starts or stops at
some point during the time series.
The algorithm is essentially as follows:
For each urban station:
1. Find all the rural stations within a fixed radius;
2. Combine the annual anomaly series for those rural stations, in
order of valid-data count;
3. Calculate a two-part linear fit for the difference between
the urban annual anomalies and this combined rural annual anomaly;
4. If this fit is satisfactory, apply it; otherwise apply a linear fit.
If there are not enough nearby rural stations, or the combined
rural record does not have enough overlap with the urban
record, try a second time for this urban station, with a
larger radius. If there is still not enough data, discard the
urban station.
"""
last_year = giss_data.get_ghcn_last_year()
first_year = 1880
iyoff = giss_data.BASE_YEAR - 1
iyrm = last_year - iyoff
rural_stations = []
urban_stations = {}
pi180 = math.pi / 180.0
all = []
for record in anomaly_stream:
station = record.station
all.append(record)
record.urban_adjustment = None
annual_anomaly(record)
if record.anomalies is None:
continue
length = len(record.anomalies)
d = Struct()
d.anomalies = record.anomalies
d.cslat = math.cos(station.lat * pi180)
d.snlat = math.sin(station.lat * pi180)
d.cslon = math.cos(station.lon * pi180)
d.snlon = math.sin(station.lon * pi180)
d.id = record.uid
d.first_year = record.first - iyoff
d.last_year = d.first_year + length - 1
d.station = station
d.record = record
if is_rural(station):
rural_stations.append(d)
else:
urban_stations[record] = d
# Sort the rural stations according to the length of the time record
# (ignoring gaps).
for st in rural_stations:
st.recLen = len([v for v in st.anomalies if valid(v)])
rural_stations.sort(key=lambda s: s.recLen)
rural_stations.reverse()
# Combine time series for rural stations around each urban station
for record in all:
us = urban_stations.get(record, None)
if us is None:
# Just remove leading/trailing invalid values for rural stations.
record.strip_invalid()
record.begin = record.first
record.end = record.last
yield record
continue
iyu1 = us.first_year + iyoff - 1 # subtract 1 for a possible partial yr
iyu2 = us.last_year + iyoff + 1 # add 1 for partial year
usingFullRadius = False
dropStation = False
needNewNeighbours = True
while True:
if needNewNeighbours:
if usingFullRadius:
radius = parameters.urban_adjustment_full_radius
else:
radius = parameters.urban_adjustment_full_radius / 2
neighbors = get_neighbours(us, rural_stations, radius)
if not neighbors:
if usingFullRadius:
dropStation = True
break
usingFullRadius = True
needNewNeighbours = True
continue
counts, urban_series, combined = combine_neighbors(
us, iyrm, iyoff, neighbors)
iy1 = 1
needNewNeighbours = False
points, quorate_count, first, last = prepare_series(
iy1, iyrm, combined, urban_series, counts, iyoff)
if quorate_count < parameters.urban_adjustment_min_years:
if usingFullRadius:
dropStation = True
break
usingFullRadius = True
needNewNeighbours = True
continue
if quorate_count >= (parameters.urban_adjustment_proportion_good *
(last - first + 0.9)):
break
# Not enough good years for the given range. Try to save
# cases in which the gaps are in the early part, by
# dropping that part and going around to prepare_series
# again.
iy1 = int(last - (quorate_count - 1) /
parameters.urban_adjustment_proportion_good)
if iy1 < first + 1:
iy1 = first + 1 # avoid infinite loop
if dropStation:
continue
fit = getfit(points)
# find extended range
iyxtnd = int(
round(quorate_count /
parameters.urban_adjustment_proportion_good) -
(last - first + 1))
n1x = first + iyoff
n2x = last + iyoff
if iyxtnd < 0:
sys.exit('impossible')
if iyxtnd > 0:
lxend = iyu2 - (last + iyoff)
if iyxtnd <= lxend:
n2x = n2x + lxend
else:
n1x = n1x - (iyxtnd - lxend)
if n1x < iyu1:
n1x = iyu1
n2x = iyu2
series = record.series
# adjust
m1 = record.rel_first_month + record.good_start_idx
m2 = record.rel_first_month + record.good_end_idx - 1
offset = record.good_start_idx # index of first valid month
a, b = adjust(first_year, record, series, fit, n1x, n2x, first + iyoff,
last + iyoff, m1, m2, offset)
# a and b are numbers of new first and last valid months
aa = a - m1
bb = b - a + 1
record.set_series(a - 1 + first_year * 12 + 1,
series[aa + offset:aa + offset + bb])
record.begin = ((a - 1) / 12) + first_year
record.first = record.begin
record.end = ((b - 1) / 12) + first_year
record.last = record.last_year
yield record