'affinity': 'jaccard',
'linkage': 'average'
})
# xr_temp = xrclustered.sel(longitude=
# np.arange(232., 295., .25)).sel(latitude=np.arange(25, 50, .25)).copy()
fig = plot_maps.plot_labels(xrclustered,
wspace=.04,
hspace=-.35,
cbar_vert=.09,
col_dim='q',
row_dim='n_clusters')
f_name = 'clustering_dendogram_{}'.format(xrclustered.attrs['hash'])
path_fig = os.path.join(path_outmain, f_name + '.pdf')
plt.savefig(path_fig, bbox_inches='tight') # dpi auto 600
cl.store_netcdf(xrclustered.to_dataset(name='xrclustered'),
filepath=os.path.join(rg.path_outmain, f_name + '.nc'))
print('hash', xrclustered.attrs['hash'])
print(f'{round(time()-t0, 2)}')
#%%
# =============================================================================
# Clustering correlation Hierarchical Agglomerative Clustering
# =============================================================================
# from time import time
# t0 = time()
# xrclustered, results = cl.correlation_clustering(var_filename, mask=xr_mask,
# kwrgs_load={'tfreq':tfreq,
# 'seldates':('06-01', '08-31'),
# 'selbox':selbox},
# clustermethodkey='AgglomerativeClustering',
'col_dim': 'tfreq',
'x_ticks': np.arange(240, 300, 20),
'y_ticks': np.arange(0, 61, 10)
})
f_name = 'clustering_dendogram_{}'.format(xrclustered.attrs['hash']) + '.pdf'
path_fig = os.path.join(rg.path_outmain, f_name)
fig.savefig(path_fig, bbox_inches='tight') # dpi auto 600
#%%
if region != 'init':
# try:
# ds_cl_ts = core_pp.get_selbox(ds_cl['xrclusteredall'].sel(q=q, n_clusters=c),
# selbox)
# ds_new = cl.spatial_mean_clusters(var_filename,
# ds_cl_ts,
# selbox=selbox)
# ds_new['xrclusteredall'] = xrclustered
# f_name = 'q{}_nc{}'.format(int(q), int(c))
# except:
ds_cl_ts = core_pp.get_selbox(
ds_cl['xrclusteredall'].sel(tfreq=t, n_clusters=c), selbox)
ds_new = cl.spatial_mean_clusters(var_filename, ds_cl_ts, selbox=selbox)
ds_new['xrclusteredall'] = xrclustered
f_name = 'tf{}_nc{}'.format(int(t), int(c))
filepath = os.path.join(rg.path_outmain, f_name)
cl.store_netcdf(ds_new,
filepath=filepath,
append_hash='dendo_' + xrclustered.attrs['hash'])
TVpath = filepath + '_' + 'dendo_' + xrclustered.attrs['hash'] + '.nc'
ds_avail.plot(vmin=30)
ds_avail.min()
ds_std = (ds_raw - ds_raw.mean(dim='time')) / ds_raw.std(dim='time')
linkage = 'ward'
c = 2
xrclustered = xrclusteredall.sel(linkage=linkage, n_clusters=c)
ds = cl.spatial_mean_clusters(ds_std, xrclustered)
df = ds.ts.to_dataframe().pivot_table(index='time', columns='cluster')['ts']
f_name = 'linkage_{}_nc{}'.format(linkage, int(c))
filepath = os.path.join(path_outmain, f_name)
cl.store_netcdf(ds,
filepath=filepath,
append_hash='dendo_' + xrclustered.attrs['hash'])
#%% Soy bean USDA
raw_filename = '/Users/semvijverberg/Dropbox/VIDI_Coumou/Paper3_Sem/GDHY_MIRCA2000_Soy/USDA/usda_soy.nc'
selbox = [250, 290, 28, 50]
ds = core_pp.import_ds_lazy(raw_filename, var='variable',
selbox=selbox).rename({'z': 'time'})
ds.name = 'Soy_Yield'
ds['time'] = pd.to_datetime([f'{y+1949}-01-01' for y in ds.time.values])
ds.attrs['dataset'] = 'USDA'
ds.attrs['planting_months'] = 'May/June'
ds.attrs['harvest_months'] = 'October'
