Create list_distances.py

list_distances.py

+import argparse
+import pandas as pd
+import numpy as np
+from mlpy import canberra_stability
+from itertools import combinations
+
+parser = argparse.ArgumentParser()
+parser.add_argument('--resultsdir', type=str, help='Results folder')
+parser.add_argument('--dataset', type=str, help='Dataset name')
+parser.add_argument('--model', type=str, default='randomForest', help='Model (default: %default)')
+parser.add_argument('--target', type=str, help='Clinical endpoint')
+parser.add_argument('--layers', type=str, nargs='+', help='')
+args = parser.parse_args()
+
+RESULTSDIR = args.resultsdir # top-level results directory
+DATASET = args.dataset # 'tcga_breast'
+TARGET = args.target # 'ER'
+MODEL = args.model
+LAYERS = args.layers
+N_LAYERS = len(LAYERS)
+MODE = 'rSNF'
+
+for k in range(2, N_LAYERS+1):
+    for comb in combinations(LAYERS, k):
+        layers_concat = '_'.join(comb)
+        bordas = []
+        for datatype in [DATASET, f'{DATASET}_SNFdap']:
+            bordaf = f'{RESULTSDIR}/{datatype}/{TARGET}/{MODEL}/Borda_splits_50-60_{MODE}_{layers_concat}.txt'
+            bordas.append(pd.read_csv(bordaf, sep='\t', index_col=None))
+        # prepare ranks for canberra_stability
+        ranks = pd.concat([np.argsort(bordas[0]['FEATURE_ID']),
+                           np.argsort(bordas[1]['FEATURE_ID'])], axis=1).transpose().values
+        for nf in np.arange(10, 60, 10):
+            cs = canberra_stability(ranks, nf)
+            print(f'{MODE} - {layers_concat} - stability({nf}) = {cs:.3f}')
+        print()