elif 'ServerNotFoundError' in e.args[0] or \
'Unable to find the server' in e.args[0] or \
'getaddrinfo failed' in e.args[0] or \
'connection attempt failed' in e.args[0]:
log.lprint('Waiting 30 secs...'.format(str(wait)))
time.sleep(wait)
continue
else:
continue
# all extracted dictionaries to file
if not Handler(OUTFILE).file_exists():
Handler.write_to_csv(temp_dicts,
header=True,
append=False,
outfile=OUTFILE)
else:
Handler.write_to_csv(temp_dicts,
header=False,
append=True,
outfile=OUTFILE)
time2 = datetime.datetime.now()
log.lprint(
'Time taken for site {s} ({ii} of {nn}): {t} seconds'.format(
s=str(temp_dicts[0]['site']),
ii=str(site_count + 1),
nn=str(n_samp),
if len(num_list) > 1:
md_vec = [md_vec[x] for x in num_list]
# find all MD values that as less than cutoff percentile
loc = list(i for i, x in enumerate(md_vec)
if (x <= np.percentile(md_vec, md_cutoff) and x != np.nan))
out_samples += list(binned_samp_dicts[i] for i in loc)
else:
out_samples += binned_samp_dicts
else:
Opt.cprint('Too few samples for cleaning')
out_samples += binned_samp_dicts
Opt.cprint('After Mahalanobis dist removal of all samp above {} percentile: {}'.format(str(md_cutoff),
str(len(out_samples))))
else:
out_samples = out_list
Handler.write_to_csv(out_samples, outfile)
Opt.cprint('Done!')
res3 = ax1.hist(out_decid_frac_list,
color='#FFA500',
edgecolor='black',
bins=int(nbins))
# save plot
fig3.savefig(outdir + '/sample_distribution_plot_v{}.png'.format(version), bbox_inches='tight')
'''
out_samp_index = list(range(len(out_decid_frac_samp)))
np.random.shuffle(out_samp_index)
out_decid_frac_samp = list(out_decid_frac_samp[i] for i in out_samp_index)
# write csv file
Handler.write_to_csv(out_decid_frac_samp, outfile)
# write shp file---------
attribute_types = {'site': 'str', 'year': 'int', 'decid_frac': 'float'}
trn_data = list()
print('Total {} sites'.format(str(len(out_decid_frac_samp))))
ntrn = int((trn_perc * len(out_decid_frac_samp)) / 100.0)
nval = len(out_decid_frac_samp) - ntrn
# randomly select training samples based on number
trn_sites = Sublist(range(len(out_decid_frac_samp))).random_selection(ntrn)
# get the rest of samples as validation samples