SIENTIAPDE-1273

Update version and enhance metrics calculation in Laborious system

- Updated image tag in values.yaml from 1.1.0 to 1.1.1.
- Modified GITHUB_BRANCH environment variable for consistency.
- Added a new method `calculate_simple_metrics` in model_metrics.py to compute various model performance metrics including RMSE, MSE, MAE, and R2.
- Integrated the new metrics calculation into the worker setup, allowing for concurrent processing of simple metrics.
- Updated tests to cover the new metrics calculation functionality, ensuring comprehensive validation of the implementation.

laborious/activities/model_metrics.py

@@ -13,6 +13,7 @@ with workflow.unsafe.imports_passed_through():
     from sientia.ModelAnalysis import ModelAnalysis
     from laborious import metrics
     import time
+    import numpy as np
     from sientia_do.temporal.constants import DATETIME_FORMAT, DATETIME_FORMAT_WITH_TZ
     import warnings
     import traceback
@@ -20,7 +21,6 @@ with workflow.unsafe.imports_passed_through():
 warnings.filterwarnings('ignore', category=RuntimeWarning, message='Degrees of freedom <= 0')
 warnings.filterwarnings('ignore', category=RuntimeWarning, message='invalid value encountered in scalar divide')
 
-
 class ModelMetrics(SientiaMonitoring):
     """
     Metrics activities for the Laborious system.
@@ -264,3 +264,84 @@ class ModelMetrics(SientiaMonitoring):
         
         return drift_df.to_dict()
 
+    async def calculate_simple_metrics(self, input_data: dict[str, Any]) -> dict[Hashable, Any]:
+        """
+        Calculate simple metrics for a model. Metrics available are:
+            - rmse
+            - mse
+            - mae
+            - r2
+            - accuracy
+            - precision
+            - recall
+            - f1
+        Args:
+            input_data (dict[str, Any]): Input data containing:
+                - metadata (dict): Workflow execution metadata
+                - model_id (str): ID of the MLFlow model
+                - target_data (pd.DataFrame): Target data for calculating metrics, containing target and prediction columns
+                - metrics (list[str]): List of metrics to calculate
+        Returns:
+            dict[Hashable, Any]: Dictionary containing the calculated metrics
+        """
+
+        metadata = input_data['metadata']
+        model_id = input_data['model_id']
+        target_data = DataFrame(input_data['target_data'])
+        metrics = input_data['metrics']
+        interval_minutes = input_data['interval_minutes']
+
+        data_size = len(target_data)
+
+        output_data = []
+
+        diff = target_data['target'] - target_data['prediction']
+        diff_squared = diff ** 2
+
+        self.info(f'Calculating simple metrics for model {model_id}: {metrics}', metadata)
+
+        for metric in metrics:
+            if metric == 'rmse':
+                output_data.append({
+                    'metric': 'rmse',
+                    'value': np.sqrt(np.mean(diff_squared))
+                })
+            elif metric == 'mse':
+                output_data.append({
+                    'metric': 'mse',
+                    'value': np.mean(diff_squared)
+                })
+            elif metric == 'mae':
+                output_data.append({
+                    'metric': 'mae',
+                    'value': np.mean(np.abs(diff))
+                })
+            elif metric == 'r2':
+                y_true = target_data['target']
+                y_mean = np.mean(y_true)
+                
+                ss_res = np.sum(diff_squared)
+                ss_tot = np.sum((y_true - y_mean) ** 2)
+                
+                # Evita divisão por zero
+                if ss_tot == 0:
+                    r2_score = 0.0
+                else:
+                    r2_score = 1 - (ss_res / ss_tot)
+                
+                output_data.append({
+                    'metric': 'r2',
+                    'value': r2_score
+                })
+        
+        data = DataFrame(output_data)
+        data['model_id'] = model_id
+        data['timestamp'] = target_data['timestamp'].max()
+        data['data_size'] = data_size
+        data['interval_minutes'] = interval_minutes
+
+        self.debug(f'Simple metrics dataframe: Size {data.shape} \n{data.head(5).to_string()}', metadata)
+
+        return data.to_dict()
+
+