trg_labels = np.zeros((n_trg, len(methods)))
trg_labels_reps = np.zeros((n_trg, len(methods), reps))
# Use perfect number of latent states for nmf and sc3
src_lbl_set = np.unique(src_labels)
n_trg_cluster = num_cluster
n_src_cluster = src_lbl_set.size
## Train source once
source_nmf = NmfClustering_initW(data_source,
np.arange(data_source.shape[0]),
num_cluster=n_src_cluster,
labels=src_labels)
source_nmf.apply(k=n_src_cluster,
alpha=nmf_alpha,
l1=nmf_l1,
max_iter=nmf_max_iter,
rel_err=nmf_rel_err)
## Calculate ARIs and KTAs
source_aris = metrics.adjusted_rand_score(
src_labels[source_nmf.remain_cell_inds], source_nmf.cluster_labels)
print('SOURCE ARI = ', source_aris)
# Multiple replications loop
# MTL/DA mixing parameter loop
for r in range(reps):
res_desc = list()
for m in range(len(methods)):
print((
'Running experiment {0} of {1}: Train target data - {2} source cells, {3} genes, {4} target cells and the {5}th method, rep = {6}'
nmf_labels.add_gene_filter(gene_filter_fun)
nmf_labels.set_data_transformation(data_transf_fun)
nmf_labels.apply(k=k, alpha=arguments.nmf_alpha, l1=arguments.nmf_l1, max_iter=arguments.nmf_max_iter, rel_err=arguments.nmf_rel_err)
labels = nmf_labels.cluster_labels
# Use perfect number of latent states for nmf and sc3
src_labels = np.array(labels, dtype=np.int)
src_lbl_set = np.unique(src_labels)
k_now = src_lbl_set.size
nmf = None
nmf = NmfClustering_initW(data, gene_ids, labels=labels, num_cluster=k_now)
nmf.add_cell_filter(cell_filter_fun)
nmf.add_gene_filter(gene_filter_fun)
nmf.set_data_transformation(data_transf_fun)
nmf.apply(k=k_now, alpha=arguments.nmf_alpha, l1=arguments.nmf_l1, max_iter=arguments.nmf_max_iter, rel_err=arguments.nmf_rel_err)
# --------------------------------------------------
# 3.2. EVALUATE CLUSTER ASSIGNMENT
# --------------------------------------------------
print('\nUnsupervised evaluation:')
accs[0, i] = unsupervised_acc_kta(nmf.pp_data, nmf.cluster_labels, kernel='linear')
print ' -KTA (linear) : ', accs[0, i]
print('\nSupervised evaluation:')
accs[1, i] = metrics.adjusted_rand_score(labels[nmf.remain_cell_inds], nmf.cluster_labels)
print ' -ARI: ', accs[1, i]
# --------------------------------------------------
# 3.3. SAVE RESULTS
# --------------------------------------------------
nmf.cell_filter_list = None