def regress_data(alldata, indname='onset', axis=0):
data = alldata['data_latlon']
var_sector = alldata['var_sector']
index = alldata[indname]
print('Computing regressions')
reg_data = xray.Dataset()
for nm in data.data_vars:
print(nm)
reg = atm.regress_field(data[nm], index, axis)
for nm2 in reg.data_vars:
reg_data[nm + '_' + nm2] = reg[nm2]
reg_sector = atm.regress_field(var_sector, index, axis)
reg_out = {'latlon' : reg_data, 'sector' : reg_sector}
return reg_out
with xray.open_dataset(ptsfile) as index_pts:
index_pts.load()
for nm in index_pts.data_vars:
if pts_xroll is not None:
index_pts[nm] = atm.rolling_mean(index_pts[nm], pts_xroll, axis=-1,
center=True)
if pts_yroll is not None:
index_pts[nm] = atm.rolling_mean(index_pts[nm], pts_yroll, axis=-2,
center=True)
# Regression of gridpoint indices onto large-scale index
print('Regression of gridpoint indices onto large-scale index')
pts_reg, pts_mask = {}, {}
for nm in index_pts.data_vars:
ind = index[nm].sel(year=index_pts['year'])
pts_reg[nm] = atm.regress_field(index_pts[nm], ind, axis=0)
pts_reg[nm]['pts_mask'] = (pts_reg[nm]['p'] >= 0.05)
# Mask out grid points where CHP index is ill-defined
def applymask(ds, mask_in):
for nm in ds.data_vars:
mask = atm.biggify(mask_in, ds[nm], tile=True)
vals = np.ma.masked_array(ds[nm], mask=mask).filled(np.nan)
ds[nm].values = vals
return ds
if ptsmaskfile is not None:
fracmin = 0.5
day1 = atm.mmdd_to_jday(6, 1)
day2 = atm.mmdd_to_jday(9, 30)
with xray.open_dataset(ptsmaskfile) as ds:
data = collections.OrderedDict()
for nm in datafiles:
var, onset, retreat = utils.load_dailyrel(datafiles[nm])
data[nm] = var
# ----------------------------------------------------------------------
# Test atm.regress_field
day = -60
# 1-d timeseries
var = data['U200'].sel(dayrel=day)
ts = atm.mean_over_geobox(var, 10, 30, 60, 100)
ts_reg = atm.Linreg(onset, ts)
ts_reg2 = atm.regress_field(ts, onset)
print(ts_reg.r, ts_reg2.r.values)
print(ts_reg.slope, ts_reg2.m.values)
print(ts_reg.p, ts_reg2.p.values)
# x-y data
regdays = [-60, -30, 0, 30, 60]
plotdays = [-60, -30]
clev_r = np.arange(-1.0, 1.01, 0.05)
for nm in varnms:
print(nm)
var = data[nm].sel(dayrel=regdays)
reg_daily = atm.regress_field(var, onset, axis=0)
for day in plotdays:
reg = reg_daily.sel(dayrel=day)
title = '%s day %d vs. Onset ' % (var.name, day)
data = collections.OrderedDict()
for nm in datafiles:
var, onset, retreat = utils.load_dailyrel(datafiles[nm])
data[nm] = var
# ----------------------------------------------------------------------
# Test atm.regress_field
day = -60
# 1-d timeseries
var = data['U200'].sel(dayrel=day)
ts = atm.mean_over_geobox(var, 10, 30, 60, 100)
ts_reg = atm.Linreg(onset, ts)
ts_reg2 = atm.regress_field(ts, onset)
print(ts_reg.r, ts_reg2.r.values)
print(ts_reg.slope, ts_reg2.m.values)
print(ts_reg.p, ts_reg2.p.values)
# x-y data
regdays = [-60, -30, 0, 30, 60]
plotdays = [-60, -30]
clev_r = np.arange(-1.0, 1.01, 0.05)
for nm in varnms:
print(nm)
var = data[nm].sel(dayrel=regdays)
reg_daily = atm.regress_field(var, onset, axis=0)
for day in plotdays:
reg = reg_daily.sel(dayrel=day)
title = '%s day %d vs. Onset ' % (var.name, day)
