SIENTIAPDE-1182

Update tests.ipynb and values.yaml for improved functionality and versioning

- Updated execution count in tests.ipynb for reproducibility.
- Modified DataFrame creation in tests.ipynb to include a timestamp column and save to CSV.
- Changed image tag in values.yaml from "0.4.4" to "0.4.5" for versioning.
- Updated GITHUB_BRANCH in values.yaml to reflect the latest branch adjustments.

laborious/activities/gates.py

@@ -403,6 +403,10 @@ class Gates(BaseActivity):
 
         data = DataFrame(input_data['data'])
 
+        # Create timestamp column from index and reset index
+        data['timestamp'] = data.index
+        data = data.reset_index(drop=True)
+
         self.debug(
             f"Prediction store policy: {prediction_store_policy}", metadata)
 
@@ -410,29 +414,24 @@ class Gates(BaseActivity):
             prediction_store_policy, metadata)
 
         # If data has no timestamp, we use the default timestamp and not sort the data
-        if 'timestamp' not in data.columns:
-            self.warning(
-                "Data has no timestamp, using default timestamp", metadata)
-            data['timestamp'] = input_data['timestamp']
-        else:
-            self.debug(
-                "Data has timestamp, sorting data by timestamp", metadata)
+        self.info(
+            f"Sorting data by timestamp and applying policy: {policy_type}:{policy_value}", metadata)
 
-            # If policy_type is lts, we need to sort the data by timestamp descending and take the first policy_value rows
-            if policy_type == 'lts':
-                self.debug(
-                    "Sorting data by timestamp descending", metadata)
-                data = data.sort_values(by='timestamp', ascending=False)
-            # If policy_type is erl, we need to sort the data by timestamp ascending and take the first policy_value rows
-            elif policy_type == 'erl':
-                self.debug(
-                    "Sorting data by timestamp ascending", metadata)
-                data = data.sort_values(by='timestamp', ascending=True)
-            else:
-                self.error(
-                    f"Invalid policy type: {policy_type}, using default policy", metadata)
-                raise ValueError(
-                    f"Invalid policy type: {policy_type}")
+        # If policy_type is lts, we need to sort the data by timestamp descending and take the first policy_value rows
+        if policy_type == 'lts':
+            self.debug(
+                "Sorting data by timestamp descending", metadata)
+            data = data.sort_values(by='timestamp', ascending=False)
+        # If policy_type is erl, we need to sort the data by timestamp ascending and take the first policy_value rows
+        elif policy_type == 'erl':
+            self.debug(
+                "Sorting data by timestamp ascending", metadata)
+            data = data.sort_values(by='timestamp', ascending=True)
+        else:
+            self.error(
+                f"Invalid policy type: {policy_type}, using default policy", metadata)
+            raise ValueError(
+                f"Invalid policy type: {policy_type}")
 
         data = data.head(int(policy_value))
 

laborious/utils/repository/model_repository.py

@@ -39,6 +39,7 @@ class MLFlowRepository():
         """
 
         try:
+
             return {
                 'success': True,
                 'content': self.model_serving.get_cached_transform(
@@ -67,12 +68,15 @@ class MLFlowRepository():
             - dict: A dictionary containing the predicted data.
         """
         try:
+
+            input_index = data.index
             start_time = datetime.now()
             data = self.model_serving.get_cached_predict(
                 model_name, data, model_retention)
 
             end_time = datetime.now()
             data = pd.DataFrame(data, columns=['prediction'])
+            data.index = input_index
             data['response_time'] = (end_time - start_time).total_seconds()
 
             return {