Fix optimizer, add time data and add optim param

main.py

@@ -47,6 +47,11 @@ if __name__ == "__main__":
         help="Automatically split dataset into subsystems and treat them once at a time.",
         action="store_true"
     )
+    parser.add_argument(
+        "-optim",
+        help="Optimize the different hyper parameters according to what's wirtten in the algorithm_params.json file",
+        action="store_true"
+    )
     parser.add_argument(
         "-d", "--docker",
         help="Use Docker containers directly to run the algorithm. Allow to run algorithms without cloning repo",
@@ -151,13 +156,13 @@ if __name__ == "__main__":
                 algo_params = json.load(f)
 
             with open(f"{INPUT_DIR}/{config_name}/time.csv", "a", encoding="utf-8") as f:
-                f.write("Algorithm,dataset,duration\n")
+                f.write("Algorithm,Dataset,Step,Duration\n")
 
             for algo in args.algorithms:
                 params = algo_params[algo]
                 train = params.pop("training")
                 trainer = BaseTrainer(f"{INPUT_DIR}/{config_name}", algo, train, **params)
-                trainer.start()
+                trainer.start(optim=args.optim)
                 trainers.append(trainer)
 
     # =================================================================================================================

trainers/base.py

@@ -14,21 +14,6 @@ from sklearn.metrics import roc_auc_score#, f1_score
 from .correlations import CORRELATION_CLASSES
 
 
-def __vote_for_score(scores, length):
-    """
-    Compute the score for each point of the dataset instead of a per window basis.
-    """
-    scores = np.nan_to_num(scores)
-    results = np.zeros(length)
-    w_size = length - len(scores) + 1
-
-    for idx in range(length):
-        start = idx - w_size if idx - w_size >= 0 else 0
-        end = idx + w_size if idx + w_size < length else length
-
-        results[idx] = np.mean(scores[start:end])
-
-    return results
 
 
 class BaseTrainer():
@@ -46,7 +31,7 @@ class BaseTrainer():
         self.train = train
         self.pwd = ""
 
-    def start(self):
+    def start(self, optim=False):
         """
         This method orchestrates the optimization, training and computing of the results for the
         current algorithm
@@ -61,13 +46,19 @@ class BaseTrainer():
         path = f"{self.pwd}/{self.data_path}"
 
         os.makedirs(f"{path}/results_{self.algorithm}", exist_ok=True)
-        optimize_time = self.optimize("dataset", path)
+        if optim:
+            optimize_time = self.optimize("dataset", path)
+            with open(f"{path}/time.csv", "a", encoding="utf-8") as f:
+                f.write(f"{self.algorithm},dataset,optimize,{optimize_time}\n")
 
         files = __exec(f"find -L {self.data_path} -regex '^.*dataset[-_0-9]*\(_auto_split\)*.csv'")
 
         for file in files:
             file_name = file.split("/")[-1][:-4]
             train_time, run_time = self.run(file_name, path)
+            with open(f"{path}/time.csv", "a", encoding="utf-8") as f:
+                f.write(f"{self.algorithm},{file_name},train,{train_time}")
+                f.write(f"{self.algorithm},{file_name},run,{run_time}")
 
     def optimize(self, file, path):
         """
@@ -76,6 +67,22 @@ class BaseTrainer():
         It uses Bayesian Optimization to search within the space defined in the file
         `algorithm_params.json` present at the root of the project.
         """
+        def __vote_for_score(scores, length):
+            """
+            Compute the score for each point of the dataset instead of a per window basis.
+            """
+            scores = np.nan_to_num(scores)
+            results = np.zeros(length)
+            w_size = length - len(scores) + 1
+
+            for idx in range(length):
+                start = idx - w_size if idx - w_size >= 0 else 0
+                end = idx + w_size if idx + w_size < length else length
+
+                results[idx] = np.mean(scores[start:end])
+
+            return results
+
         def __exec(cmd) -> str:
             """
             Execute a shell command and process its output as expected.