Multiple output for measure action. These multiple output are written in json.

quillotm
1 parent e828890879
Showing 1 changed file with 29 additions and 14 deletions Side-by-side Diff
volia/clustering.py
@@ -11,6 +11,7 @@
 from sklearn.metrics import v_measure_score
  
 import core.measures
+import json
  
  
 CLUSTERING_METHODS = {
  
  
  
  
  
  
@@ -28,26 +29,40 @@
  
  
 def measure_run(measure: str, features: str, lst: str, truelabels: str, model: str, modeltype: str):
+    """
+
+    @param measure:
+    @param features:
+    @param lst:
+    @param truelabels:
+    @param model:
+    @param modeltype:
+    @return:
+    """
     module = CLUSTERING_METHODS[modeltype]
     module.load(model)
-    evaluation = EVALUATION_METHODS[measure]
-    feats_dict = read_features(features)
-    labels_dict = read_labels(truelabels)
-    lst_dict = read_lst(lst)
-    lst_keys = [key for key in lst_dict]
-    feats = np.asarray([feats_dict[key] for key in lst_keys])
-    Y_pred = module.predict(feats)
-    Y_truth = [labels_dict[key][0] for key in lst_keys]
  
-    le = LabelEncoder()
-    le.fit(Y_truth)
-    Y_truth = le.transform(Y_truth)
+    eval = {}
+    for ms in measure:
+        evaluation = EVALUATION_METHODS[ms]
+        feats_dict = read_features(features)
+        labels_dict = read_labels(truelabels)
+        lst_dict = read_lst(lst)
+        lst_keys = [key for key in lst_dict]
+        feats = np.asarray([feats_dict[key] for key in lst_keys])
+        Y_pred = module.predict(feats)
+        Y_truth = [labels_dict[key][0] for key in lst_keys]
  
-    eval = evaluation(Y_truth, Y_pred)
-    print(eval)
+        le = LabelEncoder()
+        le.fit(Y_truth)
+        Y_truth = le.transform(Y_truth)
  
+        eval[ms] = evaluation(Y_truth, Y_pred)
  
+    print(json.dumps(eval))
  
+
+
 def kmeans_run(features: str, lst: str, k:int, kmax: int, klist, output: str):
     """
  
@@ -125,7 +140,7 @@
  
     parser_measure.add_argument("--measure",
                                 required=True,
-                                type=str,
+                                nargs="+",
                                 choices=[key for key in EVALUATION_METHODS],
                                 help="...")
     parser_measure.add_argument("--features", required=True, type=str, help="...")
...	...	@@ -11,6 +11,7 @@
11	11	from sklearn.metrics import v_measure_score
12	12
13	13	import core.measures
	14	+import json
14	15
15	16
16	17	CLUSTERING_METHODS = {
17	18
18	19
19	20
20	21
21	22
22	23
...	...	@@ -28,26 +29,40 @@
28	29
29	30
30	31	def measure_run(measure: str, features: str, lst: str, truelabels: str, model: str, modeltype: str):
	32	+ """
	33	+
	34	+ @param measure:
	35	+ @param features:
	36	+ @param lst:
	37	+ @param truelabels:
	38	+ @param model:
	39	+ @param modeltype:
	40	+ @return:
	41	+ """
31	42	module = CLUSTERING_METHODS[modeltype]
32	43	module.load(model)
33		- evaluation = EVALUATION_METHODS[measure]
34		- feats_dict = read_features(features)
35		- labels_dict = read_labels(truelabels)
36		- lst_dict = read_lst(lst)
37		- lst_keys = [key for key in lst_dict]
38		- feats = np.asarray([feats_dict[key] for key in lst_keys])
39		- Y_pred = module.predict(feats)
40		- Y_truth = [labels_dict[key][0] for key in lst_keys]
41	44
42		- le = LabelEncoder()
43		- le.fit(Y_truth)
44		- Y_truth = le.transform(Y_truth)
	45	+ eval = {}
	46	+ for ms in measure:
	47	+ evaluation = EVALUATION_METHODS[ms]
	48	+ feats_dict = read_features(features)
	49	+ labels_dict = read_labels(truelabels)
	50	+ lst_dict = read_lst(lst)
	51	+ lst_keys = [key for key in lst_dict]
	52	+ feats = np.asarray([feats_dict[key] for key in lst_keys])
	53	+ Y_pred = module.predict(feats)
	54	+ Y_truth = [labels_dict[key][0] for key in lst_keys]
45	55
46		- eval = evaluation(Y_truth, Y_pred)
47		- print(eval)
	56	+ le = LabelEncoder()
	57	+ le.fit(Y_truth)
	58	+ Y_truth = le.transform(Y_truth)
48	59
	60	+ eval[ms] = evaluation(Y_truth, Y_pred)
49	61
	62	+ print(json.dumps(eval))
50	63
	64	+
	65	+
51	66	def kmeans_run(features: str, lst: str, k:int, kmax: int, klist, output: str):
52	67	"""
53	68
...	...	@@ -125,7 +140,7 @@
125	140
126	141	parser_measure.add_argument("--measure",
127	142	required=True,
128		- type=str,
	143	+ nargs="+",
129	144	choices=[key for key in EVALUATION_METHODS],
130	145	help="...")
131	146	parser_measure.add_argument("--features", required=True, type=str, help="...")