def analyze_zN(z, outdir, vg, skip_umap=False):
zdim = z.shape[1]
# Principal component analysis
log('Perfoming principal component analysis...')
pc, pca = analysis.run_pca(z)
start, end = np.percentile(pc[:,0],(5,95))
z_pc1 = analysis.get_pc_traj(pca, z.shape[1], 10, 1, start, end)
start, end = np.percentile(pc[:,1],(5,95))
z_pc2 = analysis.get_pc_traj(pca, z.shape[1], 10, 2, start, end)
# kmeans clustering
log('K-means clustering...')
K = 20
kmeans_labels, centers = analysis.cluster_kmeans(z, K)
centers, centers_ind = analysis.get_nearest_point(z, centers)
if not os.path.exists(f'{outdir}/kmeans20'):
os.mkdir(f'{outdir}/kmeans20')
utils.save_pkl(kmeans_labels, f'{outdir}/kmeans20/labels.pkl')
np.savetxt(f'{outdir}/kmeans20/centers.txt', centers)
np.savetxt(f'{outdir}/kmeans20/centers_ind.txt', centers_ind, fmt='%d')
# Generate volumes
log('Generating volumes...')
vg.gen_volumes(f'{outdir}/pc1', z_pc1)
vg.gen_volumes(f'{outdir}/pc2', z_pc2)
vg.gen_volumes(f'{outdir}/kmeans20', centers)
# UMAP -- slow step
if zdim > 2 and not skip_umap:
log('Running UMAP...')
umap_emb = analysis.run_umap(z)
utils.save_pkl(umap_emb, f'{outdir}/umap.pkl')
# Make some plots
log('Generating plots...')
plt.figure(1)
plt.scatter(pc[:,0], pc[:,1], alpha=.1, s=2)
plt.xlabel('PC1')
plt.ylabel('PC2')
plt.savefig(f'{outdir}/z_pca.png')
if zdim > 2 and not skip_umap:
plt.figure(2)
plt.scatter(umap_emb[:,0], umap_emb[:,1], alpha=.1, s=2)
plt.xlabel('UMAP1')
plt.ylabel('UMAP2')
plt.savefig(f'{outdir}/umap.png')
analysis.plot_by_cluster(pc[:,0], pc[:,1], K, kmeans_labels, centers_ind=centers_ind, annotate=True)
plt.xlabel('PC1')
plt.ylabel('PC2')
plt.savefig(f'{outdir}/kmeans20/z_pca.png')
if zdim > 2 and not skip_umap:
analysis.plot_by_cluster(umap_emb[:,0], umap_emb[:,1], K, kmeans_labels, centers_ind=centers_ind, annotate=True)
plt.xlabel('UMAP1')
plt.ylabel('UMAP2')
plt.savefig(f'{outdir}/kmeans20/umap.png')
def generate_volumes(z, outdir, vg, K):
# kmeans clustering
log('Sketching distribution...')
kmeans_labels, centers = analysis.cluster_kmeans(z,
K,
on_data=True,
reorder=True)
centers, centers_ind = analysis.get_nearest_point(z, centers)
if not os.path.exists(f'{outdir}/kmeans{K}'):
os.mkdir(f'{outdir}/kmeans{K}')
utils.save_pkl(kmeans_labels, f'{outdir}/kmeans{K}/labels.pkl')
np.savetxt(f'{outdir}/kmeans{K}/centers.txt', centers)
np.savetxt(f'{outdir}/kmeans{K}/centers_ind.txt', centers_ind, fmt='%d')
log('Generating volumes...')
vg.gen_volumes(f'{outdir}/kmeans{K}', centers)
def main(args):
fig, ax = plt.subplots()
print(args)
z = pickle.load(open(args.input, 'rb'))
if args.stride:
z = z[::args.stride]
print('{} points'.format(len(z)))
# k-means clustering
labels, centers = analysis.cluster_kmeans(z,
args.k,
on_data=args.on_data,
reorder=args.reorder)
# use the nearest data point instead of cluster centroid
if args.on_data:
centers_zi = cdist(centers, z).argmin(axis=1)
print(centers_zi)
centers_z = z[centers_zi]
centers = centers_z
if args.out_k_ind:
np.savetxt(args.out_k_ind, centers_zi, fmt='%d')
if args.o:
with open(args.o, 'wb') as f:
pickle.dump(labels, f)
if args.out_k:
np.savetxt(args.out_k, centers)
# dimensionality reduction for viz
pca = PCA(z.shape[1])
pca.fit(z)
print('PCA explained variance ratio:')
print(pca.explained_variance_ratio_)
pc = pca.transform(z)
for i in range(args.k):
ii = np.where(labels == i)
pc_sub = pc[ii]
plt.scatter(pc_sub[:, 0],
pc_sub[:, 1],
s=2,
alpha=0.1,
label='cluster {}'.format(i))
c = pca.transform(centers)
plt.scatter(c[:, 0], c[:, 1], c='k')
for i in range(args.k):
ax.annotate(str(i), c[i, 0:2])
xx, yy = 0, 1
plt.xlabel('PC{} ({:3f})'.format(xx + 1,
pca.explained_variance_ratio_[xx]))
plt.ylabel('PC{} ({:3f})'.format(yy + 1,
pca.explained_variance_ratio_[yy]))
if args.out_png:
plt.savefig(args.out_png)
else:
plt.show()
def analyze_zN(z, outdir, vg, skip_umap=False, num_pcs=2, num_ksamples=20):
zdim = z.shape[1]
# Principal component analysis
log('Perfoming principal component analysis...')
pc, pca = analysis.run_pca(z)
log('Generating volumes...')
for i in range(num_pcs):
start, end = np.percentile(pc[:, i], (5, 95))
z_pc = analysis.get_pc_traj(pca, z.shape[1], 10, i + 1, start, end)
vg.gen_volumes(f'{outdir}/pc{i+1}', z_pc)
# kmeans clustering
log('K-means clustering...')
K = num_ksamples
kmeans_labels, centers = analysis.cluster_kmeans(z, K)
centers, centers_ind = analysis.get_nearest_point(z, centers)
if not os.path.exists(f'{outdir}/kmeans{K}'):
os.mkdir(f'{outdir}/kmeans{K}')
utils.save_pkl(kmeans_labels, f'{outdir}/kmeans{K}/labels.pkl')
np.savetxt(f'{outdir}/kmeans{K}/centers.txt', centers)
np.savetxt(f'{outdir}/kmeans{K}/centers_ind.txt', centers_ind, fmt='%d')
log('Generating volumes...')
vg.gen_volumes(f'{outdir}/kmeans{K}', centers)
# UMAP -- slow step
if zdim > 2 and not skip_umap:
log('Running UMAP...')
umap_emb = analysis.run_umap(z)
utils.save_pkl(umap_emb, f'{outdir}/umap.pkl')
# Make some plots
log('Generating plots...')
plt.figure(1)
g = sns.jointplot(x=pc[:, 0], y=pc[:, 1], alpha=.1, s=2)
g.set_axis_labels('PC1', 'PC2')
plt.tight_layout()
plt.savefig(f'{outdir}/z_pca.png')
plt.figure(2)
g = sns.jointplot(x=pc[:, 0], y=pc[:, 1], kind='hex')
g.set_axis_labels('PC1', 'PC2')
plt.tight_layout()
plt.savefig(f'{outdir}/z_pca_hexbin.png')
if zdim > 2 and not skip_umap:
plt.figure(3)
g = sns.jointplot(x=umap_emb[:, 0], y=umap_emb[:, 1], alpha=.1, s=2)
g.set_axis_labels('UMAP1', 'UMAP2')
plt.tight_layout()
plt.savefig(f'{outdir}/umap.png')
plt.figure(4)
g = sns.jointplot(x=umap_emb[:, 0], y=umap_emb[:, 1], kind='hex')
g.set_axis_labels('UMAP1', 'UMAP2')
plt.tight_layout()
plt.savefig(f'{outdir}/umap_hexbin.png')
analysis.scatter_annotate(pc[:, 0],
pc[:, 1],
centers_ind=centers_ind,
annotate=True)
plt.xlabel('PC1')
plt.ylabel('PC2')
plt.savefig(f'{outdir}/kmeans{K}/z_pca.png')
g = analysis.scatter_annotate_hex(pc[:, 0],
pc[:, 1],
centers_ind=centers_ind,
annotate=True)
g.set_axis_labels('PC1', 'PC2')
plt.tight_layout()
plt.savefig(f'{outdir}/kmeans{K}/z_pca_hex.png')
if zdim > 2 and not skip_umap:
analysis.scatter_annotate(umap_emb[:, 0],
umap_emb[:, 1],
centers_ind=centers_ind,
annotate=True)
plt.xlabel('UMAP1')
plt.ylabel('UMAP2')
plt.savefig(f'{outdir}/kmeans{K}/umap.png')
g = analysis.scatter_annotate_hex(umap_emb[:, 0],
umap_emb[:, 1],
centers_ind=centers_ind,
annotate=True)
g.set_axis_labels('UMAP1', 'UMAP2')
plt.tight_layout()
plt.savefig(f'{outdir}/kmeans{K}/umap_hex.png')
for i in range(num_pcs):
if not skip_umap:
analysis.scatter_color(umap_emb[:, 0],
umap_emb[:, 1],
pc[:, i],
label=f'PC{i+1}')
plt.xlabel('UMAP1')
plt.ylabel('UMAP2')
plt.tight_layout()
plt.savefig(f'{outdir}/pc{i+1}/umap.png')