def plot_clustering_heatmap(clust_object, folder, figsize=(15.5, 9.5)):
"""Hierarchical clustering heatmap"""
plt.figure(41, figsize=figsize)
# colInds = plotHColCluster(ds[s].cyDf, method='complete', metric='pearson-signed', col_labels=ds[s].labels, col_dmat=ds[s].dmatDf)
colInds = plotHColCluster(clust_object.cyDf,
method='complete',
metric='pearson-signed',
col_labels=clust_object.labels,
figsize=figsize,
save_path=os.path.join(
folder, '%s_hierchical_clust_heatmap.png' %
clust_object.name))
# filename = "".join([FIG_PATH, p, "_bar_median_responses_clusters_", str(i[0]), "_",str(i[1]), ".png"])
# f.savefig(filename, dpi=200)
# plot correlation matrix of HA and NA clustering on Shanghai
# for p in ['SHA_ha', 'SHA_na']:
# col_ind = np.argsort(clusters[p])
# f = plt.figure()
# ax_matrix = f.add_axes([0.3,0.1,0.6,0.6])
# my_norm = mpl.colors.Normalize(vmin=0.4, vmax=1)
# im = ax_matrix.matshow(dMat[p][colInd,:][:,colInd].T,aspect='auto', origin='upper', cmap=cm.RdBu_r,norm=my_norm)
# ax_matrix.set_xticks([])
# c_inds = []
# c_inds = [len(np.where(clusters[p]==i)[0]) for i in np.arange(1,num_clusters+1)]
# ax_matrix.set_yticks(np.cumsum(c_inds)[:-1])
# ax_matrix.set_xticks(np.cumsum(c_inds)[:-1])
# # Plot colorbar.
# ax_color = f.add_axes([0.91,0.1,0.02,0.6])
# plt.colorbar(im, cax=ax_color)
# plot correlation matrix with dendrogram overlayed:
for p, s in zip(['SHA_ha', 'SHA_na'], ['H7', 'N9']):
colInd = hcp.plotHColCluster(arr_df[post_inds][ind_dict[p]].T,method='complete', metric='spearman',titleStr=s,vRange=(0, 1))
#, \col_labels=arr_df[post_inds].group)
f = gcf()
filename = "".join([FIG_PATH + p + "postBoost_clustering_matrix_and_dendrogram"])
f.savefig(filename, dpi=200)
# filename = "".join([FIG_PATH, p, "_bar_median_responses_clusters_", str(i[0]), "_",str(i[1]), ".png"])
# f.savefig(filename, dpi=200)
# plot correlation matrix of HA and NA clustering on Shanghai
# for p in ['SHA_ha', 'SHA_na']:
# col_ind = np.argsort(clusters[p])
# f = plt.figure()
# ax_matrix = f.add_axes([0.3,0.1,0.6,0.6])
# my_norm = mpl.colors.Normalize(vmin=0.4, vmax=1)
# im = ax_matrix.matshow(dMat[p][colInd,:][:,colInd].T,aspect='auto', origin='upper', cmap=cm.RdBu_r,norm=my_norm)
# ax_matrix.set_xticks([])
# c_inds = []
# c_inds = [len(np.where(clusters[p]==i)[0]) for i in np.arange(1,num_clusters+1)]
# ax_matrix.set_yticks(np.cumsum(c_inds)[:-1])
# ax_matrix.set_xticks(np.cumsum(c_inds)[:-1])
# # Plot colorbar.
# ax_color = f.add_axes([0.91,0.1,0.02,0.6])
# plt.colorbar(im, cax=ax_color)
# plot correlation matrix with dendrogram overlayed:
for p in ["SHA_ha", "SHA_na"]:
colInd = hcp.plotHColCluster(arr_df[ind_dict[p]].T, method="complete", metric="spearman", titleStr=p, vRange=(0, 1))
# , \col_labels=arr_df[post_inds].group)
f = plt.gcf()
filename = "".join([FIG_PATH + p + "postBoost_clustering_matrix_and_dendrogram"])
f.savefig(filename, dpi=200)
# Output clustering results
if do_recalculate:
for cyto_object in cyto_modules.values():
cyplot.plotMeanCorr(
cyto_object.withMean,
cyto_object.meanS.name,
cyList=sorted(cyto_object.cyDf.columns),
figsize=(10, 6),
save_path=os.path.join(
args.paths['correlation_figures'],
'%s_cy_mean_correlation.png' % cyto_object.name))
plotHColCluster(cyto_object.cyDf,
method='complete',
metric='pearson-signed',
figsize=(10, 6),
save_path=os.path.join(
args.paths['correlation_figures'],
'%s_correlation_heatmap.png' % cyto_object.name))
cytomod.io.write_modules(cyto_object, args.paths['clustering_info'])
cytomod.io.plot_modules(cyto_object,
args.paths['clustering_figures'],
heatmap_figsize=(10, 6))
########### ------------ Associations ------------- ###########
# standardize numeric covariates
if args.covariates != []:
standardizeFunc = lambda col: (col - np.nanmean(col)) / np.nanstd(col)
def plot_modules(clust_object, folder):
'''Plot cytomod object modules information'''
"""Hierarchical clustering heatmap"""
plt.figure(41, figsize=(15.5, 9.5))
# colInds = plotHColCluster(ds[s].cyDf, method='complete', metric='pearson-signed', col_labels=ds[s].labels, col_dmat=ds[s].dmatDf)
colInds = plotHColCluster(clust_object.cyDf,
method='complete',
metric='pearson-signed',
col_labels=clust_object.labels,
save_path=os.path.join(
folder, '%s_hierchical_clust_heatmap.png' %
clust_object.name))
# plt.figure(41).savefig(os.path.join(folder, '%s_hierchical_clust_heatmap.png' % clust_object.name))
"""Heatmaps of pairwise reliability"""
plt.figure(43, figsize=(15.5, 9.5))
colInds = cyplot.plotHierClust(1 - clust_object.pwrel,
clust_object.Z,
labels=clust_object.labels,
titleStr='Pairwise reliability (%s)' %
clust_object.name.replace('_', ' '),
vRange=(0, 1))
plt.figure(43).savefig(os.path.join(folder,
'%s_pwrel.png' % clust_object.name),
dpi=300)
"""color_label_legend"""
plt.figure(48, figsize=(3, 3))
plt.clf()
axh = plt.subplot(1, 1, 1)
colorLegend(palettable.colorbrewer.qualitative.Set3_6.mpl_colors,
['%s' % s for s in clust_object.modDf.columns],
loc=10)
axh.spines['right'].set_color('none')
axh.spines['left'].set_color('none')
axh.spines['top'].set_color('none')
axh.spines['bottom'].set_color('none')
axh.set_xticks([])
axh.set_yticks([])
axh.set_facecolor('white')
plt.figure(48).savefig(os.path.join(folder, 'color_label_legend.png'),
dpi=300)
"""Plot intra-module correlation"""
plt.figure(50, figsize=(15, 9))
for lab in list(
cy.labels2modules(clust_object.labels,
clust_object.dropped).keys()):
cyplot.plotModuleCorr(clust_object.cyDf,
clust_object.labels,
lab,
dropped=clust_object.dropped)
plt.figure(50).savefig(os.path.join(
folder, '%s_mod_corr_%s.png' % (clust_object.name, lab)),
dpi=300)
"""Cytokine embedding"""
plt.figure(901, figsize=(13, 9.7))
cyplot.plotModuleEmbedding(clust_object.dmatDf,
clust_object.labels,
method='kpca')
colors = palettable.colorbrewer.get_map(
'Set1', 'qualitative', len(np.unique(clust_object.labels))).mpl_colors
colorLegend(colors, [
'%s%1.0f' % (clust_object.sampleStr, i)
for i in np.unique(clust_object.labels)
],
loc='lower left')
plt.figure(901).savefig(os.path.join(folder,
'%sembed.png' % clust_object.name),
dpi=300)
