survival_fpath = args.survival_fpath
duration_col = args.duration_col
event_col = args.event_col
# setup directories
log_dir = make_and_get_dir(results_dir, 'log')
fitting_dir = make_and_get_dir(results_dir, 'model_fitting')
model_sel_dir = make_and_get_dir(results_dir, 'model_selection')
opt_diag_dir = make_and_get_dir(results_dir, 'opt_diagnostics')
clust_interpret_dir = make_and_get_dir(results_dir, 'interpret')
# load models and data
models = load(join(fitting_dir, 'selected_models'))
view_data, dataset_names, sample_names, view_feat_names = \
load_data(*fpaths)
n_views = len(fpaths)
view_data = [pd.DataFrame(view_data[v],
index=sample_names,
columns=view_feat_names[v])
for v in range(n_views)]
# possibly load metadata for comparison
if vars2compare_fpath is not None:
vars2compare = pd.read_csv(vars2compare_fpath, index_col=0)
vars2compare = vars2compare.loc[sample_names, :]
else:
vars2compare = None
# possibly load super data
parser.add_argument('--fpaths', nargs='+', help='Paths to data sets.')
args = parser.parse_args()
inches = 8
n_top_clust = 10
results_dir = args.results_dir
fpaths = args.fpaths
fitting_dir = join(results_dir, 'model_fitting')
ephys_viz_dir = join(results_dir, 'interpret', 'bd_mvmm', 'ephys_pca_feats')
# load models and data
models = load(join(fitting_dir, 'selected_models'))
view_data, dataset_names, sample_names, view_feat_names = load_data(*fpaths)
# load raw ephys data
orig_data_dir = join(MouseETPaths().raw_data_dir, 'inh_patchseq_spca_files',
'orig_data_csv')
ephys_raw = load_raw_ephys(orig_data_dir, concat=False)
for k in ephys_raw.keys():
ephys_raw[k] = ephys_raw[k].loc[sample_names]
print(k, ephys_raw[k].shape)
n_datasets = len(ephys_raw)
# get data for plotting
v = 1
cluster_super_means, super_data_means, super_data_stds, y_cnts = \
get_ephys_super_data(model=models['bd_mvmm'].final_.view_models_[v],
fit_data=view_data[v],
res_writer = ResultsWriter(join(log_dir, 'single_view_fitting.txt'),
delete_if_exists=True)
res_writer.write(args)
run_start_time = time()
n_views = len(args.fpaths)
#############
# load data #
#############
view_data, dataset_names, sample_names, feat_names = \
load_data(*args.fpaths)
for v in range(n_views):
res_writer.write('{} (view {}) shape : {}'.format(dataset_names[v], v,
view_data[v].shape))
################
# setup models #
################
cat_gmm_n_comp_seq = np.arange(args.min_ncomp_cat, args.max_ncomp_cat + 1)
# view_gmm_n_comp_seq = [np.arange(args.min_ncomp_cat, args.max_ncomp_v0 + 1),
# np.arange(args.min_ncomp_cat, args.max_ncomp_v1 + 1)]
view_gmm_n_comp_seq = [