def bootcorr( self, ntim = 1000, corrconf = 0.95, bootconf = 0.9, debug = False, quick = False ): from numpy import meshgrid, zeros, ma, isnan, linspace from atmos_ocean_data import vcorr, sig_test corrlevel = 1 - corrconf fieldData = self.sst.data clim_data = self.clim_data corr_grid = vcorr(X = fieldData, y = clim_data) n_yrs = len(clim_data) p_value = sig_test(corr_grid, n_yrs) #Mask insignificant gridpoints corr_grid = ma.masked_array(corr_grid, ~(p_value < corrlevel)) #Mask land corr_grid = ma.masked_array(corr_grid, isnan(corr_grid)) #Mask northern/southern ocean corr_grid.mask[self.sst.lat > 60] = True corr_grid.mask[self.sst.lat < -30] = True nlat = len(self.sst.lat) nlon = len(self.sst.lon) if quick: self.corr_grid = corr_grid self.n_pre_grid = nlat * nlon - corr_grid.mask.sum() if self.n_pre_grid == 0: self.flags['noSST'] = True else: self.flags['noSST'] = False return ###INITIALIZE A NEW CORR GRID#### count = np.zeros((nlat,nlon)) dat = clim_data.copy() for boot in xrange(ntim): ###SHUFFLE THE YEARS AND CREATE THE BOOT DATA### idx = np.random.randint(0, len(dat) - 1, len(dat)) boot_fieldData = np.zeros((len(idx), nlat, nlon)) boot_fieldData[:] = fieldData[idx] boot_climData = np.zeros((len(idx))) boot_climData = dat[idx] boot_corr_grid = vcorr(X = boot_fieldData, y = boot_climData) p_value = sig_test(boot_corr_grid, n_yrs) count[p_value <= corrlevel] += 1 if debug: print 'Count max is %i' % count.max() ###CREATE MASKED ARRAY USING THE COUNT AND BOOTCONF ATTRIBUTES corr_grid = np.ma.masked_array(corr_grid, count < bootconf * ntim) self.corr_grid = corr_grid self.n_pre_grid = nlat * nlon - corr_grid.mask.sum() if self.n_pre_grid == 0: self.flags['noSST'] = True else: self.flags['noSST'] = False return
def bootcorr(self, n = 100, fig = None, ax = None, field = 'sst', \ phase = 'allyears', corrconf = 0.9, bootconf = 0.9, cbloc = 'bottom',\ quick = False, debug = False, monte = False): from numpy import meshgrid, zeros, ma, isnan, linspace import time from random import sample if field == 'sst': fieldData = self.sst[phase] if field == 'slp': fieldData = self.slp[phase] clim_data = self.clim_data[phase] corrlevel = 1 - corrconf corr_grid = vcorr(X = fieldData, y = clim_data) n_yrs = len(clim_data) p_value = sig_test(corr_grid, n_yrs) #Mask insignificant gridpoints corr_grid = ma.masked_array(corr_grid, ~(p_value < corrlevel)) #Mask land corr_grid = ma.masked_array(corr_grid, isnan(corr_grid)) #Mask northern/southern ocean corr_grid.mask[self.lat[field] > 60] = True corr_grid.mask[self.lat[field] < -30] = True ###SAVE THE MASK TO FILTER THE BOOTSTRAP mask = corr_grid.mask if quick: self.corr_grid[field][phase] = corr_grid return ###SET UP INDICES FOR FIELD DATA### ###INITIALIZE A NEW CORR GRID#### nlat = fieldData.shape[1] nlon = fieldData.shape[2] count = np.zeros((nlat,nlon)) ntim = n dat = clim_data mask = corr_grid.mask if debug: print 'Starting %s' % phase for boot in xrange(ntim): if debug: print 'starting round %i' % boot ###SHUFFLE THE YEARS AND CREATE THE BOOT DATA### idx = np.random.randint(0, len(dat) - 1, len(dat)) bootdata = np.zeros((len(idx), nlat, nlon)) bootdata[:] = fieldData[idx] bootvar = np.zeros((len(idx))) bootvar = dat[idx] corr_grid_boot = vcorr(X = bootdata, y = bootvar) n_yrs = len(bootvar) p_value = sig_test(corr_grid_boot, n_yrs) count[p_value <= corrlevel] += 1 if debug: print 'Count max is %i' % count.max() # for lon, lat in zip(xx[~mask], yy[~mask]): # c, p = corr(bootdata[:,lat,lon], bootvar) # if p <= corrlevel: # count[lat,lon] += 1 ###GET THE ACTUAL CORRELATION AGAIN #_Mask insignificant values ###CREATE MASKED ARRAY USING THE COUNT AND BOOTCONF ATTRIBUTES corr_grid = np.ma.masked_array(corr_grid, count < bootconf * ntim) self.corr_grid[field][phase] = corr_grid if monte: n_phase = len(clim_data) n_total = len(self.clim_data['allyears']) count = np.zeros((nlat, nlon)) field = self.sst[phase] for t in xrange(100): #print 'Starting monte round %i' % t idx = sample(xrange(n_total), n_phase) var = self.clim_data['allyears'][idx] for lon, lat in zip(xx[~mask], yy[~mask]): r, p = corr(var, field[:,lat,lon]) if p <= (1 - corrconf): #print 'Entering while loop for grid %i, %i' % (i, j) x = 0 c2 = 0 while x < 100: #print 'Monte round %i' % x idx2 = np.random.randint(0, n_phase-1, n_phase) x += 1 r, p = corr(var[idx2], field[idx2,lat,lon]) if p <= (1 - corrconf): c2 += 1 if c2 >= 80: count[lat,lon] += 1 print 'Count max is %.0f' % (count.max()) self.monte_count[phase] = count.max() self.monte_grid[phase] = np.ma.masked_array(data = count, \ mask = self.corr_grid['sst'][phase].mask) return
