assessment predictions pipelines added

src/pipeline/data_preprocessor.py

@@ -1,5 +1,13 @@
 import pandas as pd
 import os
+import logging
+from logging.handlers import RotatingFileHandler
+
+
+handler = RotatingFileHandler('/root/ds_erp_ai/logs/prediction_pipeline.log', maxBytes=100000, backupCount=3)
+logger = logging.getLogger(__name__)
+logger.setLevel(logging.INFO)
+logger.addHandler(handler)
 
 class DataPreprocessor:
     def __init__(self, input_path, company_id):

src/pipeline/inference.py

@@ -0,0 +1,85 @@
+import pandas as pd
+import joblib
+import os
+
+class AssessmentInference:
+    def __init__(self, company_id, num_assessments, model_dir='models'):
+        self.company_id = company_id
+        self.num_assessments = num_assessments
+        self.model_dir = model_dir
+        self.model = None
+        self.latest_data = None
+
+    def load_model(self):
+        # Load the trained model
+        model_path = os.path.join(self.model_dir, 'assessment_prediction', self.company_id, f'{self.company_id}_model.pkl')
+        self.model = joblib.load(model_path)
+        print(f"Model loaded from {model_path}")
+
+    def load_latest_data(self):
+        # Load the latest assessment data
+        latest_data_path = os.path.join(self.model_dir, 'assessment_prediction', self.company_id, f'{self.company_id}_latest_data.csv')
+        self.latest_data = pd.read_csv(latest_data_path)
+        print(f"Latest data loaded from {latest_data_path}")
+
+    def predict_next_assessment(self, current_data, assessment_type):
+        # Update assessment type (weekly, biweekly, quarterly) in the data for prediction
+        current_data['assessment_type_weekly'] = 1 if assessment_type == 'weekly' else 0
+        current_data['assessment_type_biweekly'] = 1 if assessment_type == 'biweekly' else 0
+        current_data['assessment_type_quarterly'] = 1 if assessment_type == 'quarterly' else 0
+
+        # Exclude target variables (open_items, red_flags) from the feature set
+        features = current_data.drop(columns=['open_items', 'red_flags'])
+
+        # Predict the next open items and red flags
+        prediction = self.model.predict(features)
+        open_items_pred, red_flags_pred = prediction[0]
+
+        # Ensure the predictions are integers by rounding
+        open_items_pred = int(round(open_items_pred))
+        red_flags_pred = int(round(red_flags_pred))
+
+        return {
+            'assessment_type': assessment_type,
+            'open_items': open_items_pred,
+            'red_flags': red_flags_pred
+        }
+
+    def predict_next_assessments(self):
+        predictions = []
+        current_data = self.latest_data.copy()
+
+        # Iteratively forecast the next assessments
+        for i in range(self.num_assessments):
+            print(f"\nForecasting assessment {i + 1}/{self.num_assessments}")
+
+            # Predict for weekly, biweekly, and quarterly for the same forecast step
+            weekly_prediction = self.predict_next_assessment(current_data, 'weekly')
+            biweekly_prediction = self.predict_next_assessment(current_data, 'biweekly')
+            quarterly_prediction = self.predict_next_assessment(current_data, 'quarterly')
+
+            # Append predictions for all types in one forecast step
+            predictions.append({
+                'forecast_step': i + 1,
+                'weekly': weekly_prediction,
+                'biweekly': biweekly_prediction,
+                'quarterly': quarterly_prediction
+            })
+
+            # Update the current data with the weekly prediction (or any of the predictions) for the next step
+            current_data['open_items'] = weekly_prediction['open_items']
+            current_data['red_flags'] = weekly_prediction['red_flags']
+
+        return predictions
+
+    def run(self):
+        self.load_model()
+        self.load_latest_data()
+        predictions = self.predict_next_assessments()
+        return predictions
+
+
+# Example usage
+#inference = AssessmentInference(company_id='testid', num_assessments=5)
+#predictions = inference.run()
+#print(predictions)