234 error handling on finding best metric

.github/workflows/automerge.yml

@@ -5,7 +5,7 @@ name: Python application
 
 on:
   push:
-    branches: [ "main", "229-pico-scale-tests-on-hpo-setup" ]
+    branches: [ "main", "234-error-handling-on-finding-best-metric" ]
 
 permissions:
   contents: read
@@ -40,14 +40,12 @@ jobs:
     # - name: Test text classifier - random search - ham-spam
     #   run: python3 text-class-ham-or-spam.py
     #   timeout-minutes: 90
-    # Add back !!!!
     # - name: Test image classifier - small subset of CIFAR10 # add back
     #   timeout-minutes: 90
     #   run: python3 cifar10-example.py
-    # 
     - name: Generative Proof Of Concept
       timeout-minutes: 180
       run: python3 generative-proof-of-concept-CPU-preprocessing-in-memory.py
-    - name: Phishing email detection with GPT2 embedding
-      timeout-minutes: 420
-      run: python3 phishing_email_detection_gpt2.py
+    # - name: Phishing email detection with GPT2 embedding
+    #   timeout-minutes: 420
+    #   run: python3 phishing_email_detection_gpt2.py

cerebros/simplecerebrosrandomsearch/simple_cerebros_random_search.py

@@ -566,18 +566,29 @@ def run_random_search(self):
         print(f"metric_to_rank_by is: '{self.metric_to_rank_by}'")
         print(
             f"Type of metric_to_rank_by is: {str(type(self.metric_to_rank_by))}")
+        def has_valid_metric(num):
+            try:
+                float(num)
+                return True
+            except Exception as exc:
+                print(exc)
+                return False
+        rows_having_a_valid_metric = oracles[self.metric_to_rank_by].apply(lambda x: has_valid_metric(x))
+        oracles_having_valid_metrics = oracles[rows_having_a_valid_metric]
+
         if self.direction == "maximize" or self.direction == "max":
-
-            best = float(oracles[oracles[self.metric_to_rank_by]
-                         != self.metric_to_rank_by]
-                         [self.metric_to_rank_by].astype(float).max())
+            best = float(oracles_having_valid_metrics[self.metric_to_rank_by].astype(float).max())
+            # best = float(oracles[oracles[self.metric_to_rank_by]
+            #              != self.metric_to_rank_by]
+            #              [self.metric_to_rank_by].astype(float).max())
         else:
             print(f"metric_to_rank_by is: '{self.metric_to_rank_by}'")
             print(
                 f"Type of metric_to_rank_by is: {str(type(self.metric_to_rank_by))}")
-            best = float(oracles[oracles[self.metric_to_rank_by]
-                                 != self.metric_to_rank_by]
-                         [self.metric_to_rank_by].astype(float).min())
+            best = float(oracles_having_valid_metrics[self.metric_to_rank_by].astype(float).min())
+            # best = float(oracles[oracles[self.metric_to_rank_by]
+            #                      != self.metric_to_rank_by]
+            #              [self.metric_to_rank_by].astype(float).min())
         print(f"Best result this trial was: {best}")
         print(f"Type of best result: {type(best)}")
         self.best_model_path =\

generative-proof-of-concept-CPU-preprocessing-in-memory.py

@@ -17,7 +17,7 @@
 N_TRIALS = 30
 
 
-mlflow.set_tracking_uri(uri="http://127.0.0.1:{MLFLOW_PORT}")
+mlflow.set_tracking_uri(uri=f"http://127.0.0.1:{MLFLOW_PORT}")
 
 mlflow.set_experiment(f"single-worker-1st-pass-tuning-{EXPERIMENT_ITERATION}-a")