print "Target data subsampling loop"
for i in range(len(percs)):
n_trg_perc = np.int(n_trg * percs[i])
p_trg = trg[:, inds[:n_trg_perc]].copy()
p_trg_labels = trg_labels[inds[:n_trg_perc]].copy()
# 4. MTL/DA mixing parameter loop
res_desc = list()
for m in range(len(methods)):
print(
'Running experiment {0} of {1}: Train target data of repetition {2} - {3} source cells, {4} genes, '
'{5} target cells and the {6}th method'.format(
exp_counter, num_exps, r + 1, n_src[s], genes,
n_trg_perc, m + 1))
#plt.subplot(len(percs), len(methods), plot_cnt)
source_nmf.cell_filter_list = list()
source_nmf.gene_filter_list = list()
# source data is already filtered and transformed ...
source_nmf.add_cell_filter(
lambda x: np.arange(x.shape[1]).tolist())
source_nmf.add_gene_filter(
lambda x: np.arange(x.shape[0]).tolist())
source_nmf.set_data_transformation(lambda x: x)
desc, target_nmf, trg_lbls_pred, mixed_data = methods[m](
source_nmf,
p_trg.copy(),
p_trg_labels.copy(),
n_trg_cluster=num_cluster)
res_desc.append(desc)
print "Evaluation of target results"
accs_desc = list()
trg_labels[trg_clustering.remain_cell_inds], trg_clustering.cluster_labels)
print ' -ARI: ', accs[4, j, i]
# --------------------------------------------------
# 5. SAVE RESULTS
# --------------------------------------------------
trg_clustering.cell_filter_list = None
trg_clustering.gene_filter_list = None
trg_clustering.data_transf = None
if arguments.method is 'SC3':
trg_clustering.dists_list = None
trg_clustering.dimred_list = None
trg_clustering.intermediate_clustering_list = None
if src_clustering is not None:
src_clustering.cell_filter_list = None
src_clustering.gene_filter_list = None
src_clustering.data_transf = None
print('\nSaving data structures and results to file with prefix \'{0}_m{1}_c{2}\'.'.format(arguments.fout, mix, trg_k))
np.savez('{0}_m{1}_c{2}.npz'.format(arguments.fout, mix, trg_k), src=src_clustering, trg=trg_clustering, args=arguments)
np.savetxt('{0}_m{1}_c{2}.labels.tsv'.format(arguments.fout, mix, trg_k),
(trg_clustering.cluster_labels, trg_clustering.remain_cell_inds), fmt='%u', delimiter='\t')
# --------------------------------------------------
# 6. SUMMARIZE RESULTS
# --------------------------------------------------
print 'Mixtures:', mixtures
print 'Cluster:', num_cluster
plt.figure(0)
for i in range(accs.shape[0]):
plt.subplot(2, 3, i+1)
metric='spearman')
print ' -KTA (linear) : ', accs[0, i]
print ' -Silhouette (euc) : ', accs[1, i]
print ' -Silhouette (pear): ', accs[2, i]
print ' -Silhouette (spea): ', accs[3, i]
if labels is not None:
print('\nSupervised evaluation:')
accs[4, i] = metrics.adjusted_rand_score(labels[nmf.remain_cell_inds],
nmf.cluster_labels)
print ' -ARI: ', accs[4, i]
# --------------------------------------------------
# 3.3. SAVE RESULTS
# --------------------------------------------------
nmf.cell_filter_list = None
nmf.gene_filter_list = None
nmf.data_transf = None
print(
'\nSaving data structures and results to file with prefix \'{0}_c{1}\'.'
.format(arguments.fout, k))
np.savez('{0}_c{1}.npz'.format(arguments.fout, k), src=nmf, args=arguments)
np.savetxt('{0}_c{1}_labels.tsv'.format(arguments.fout, k),
(nmf.cluster_labels, nmf.remain_cell_inds),
fmt='%u',
delimiter='\t')
# --------------------------------------------------
# 3.4. T-SNE PLOT
# --------------------------------------------------
if arguments.tsne:
model = TSNE(n_components=2,
