add pre-commit hook, no customisation on black

model_data/simulation_system/.pre-commit-config.yaml

@@ -0,0 +1,11 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v2.3.0
+    hooks:
+    -   id: check-yaml
+    -   id: end-of-file-fixer
+    -   id: trailing-whitespace
+-   repo: https://github.com/psf/black
+    rev: 22.10.0
+    hooks:
+    -   id: black

model_data/simulation_system/MLModel/BaseMLModel.py

@@ -54,6 +54,7 @@ class MLModel(Protocol):
         Perfomance post processing on Model to ensure ready for deployment
         """
      
-    def generate_meta_data(self):
+    def model_metadata(self) -> dict:
         """
+        Extract out model metadata as dictionary
         """

model_data/simulation_system/MLModel/Models.py

@@ -135,6 +135,12 @@ class AutogluonModel:
 
         # This will return a string path of the location
         return self.model.clone_for_deployment(deployment_path)
+    
+    def model_metadata(self) -> dict:
+        """
+        For Autogluon model, use the inbuilt model info method 
+        """
+        return self.model.info()
 
         
 

model_data/simulation_system/predictions.py

@@ -112,13 +112,12 @@ def prediction(target_column: str = "RDSAP_CHANGE", model_path: str = None, data
     output_base = PREDICTION_LOCATION / target_column / uprn / TIMESTAMP
     output_base.mkdir(parents=True, exist_ok=True)
 
-    # TODO: change model.model.info to a class method for MLModel
     json_prediction = prediction.to_json(output_base / PREDICTION_FILE)
     prediction_metadata = {
         "model_type": model_type,
         "model_name": model_name,
         "model_location": model_location,
-        "model_settings": model.model.info()
+        "model_settings": model.model_metadata()
     }
 
     pd.DataFrame([prediction_metadata]).to_json(output_base / METADATA_FILE)

model_data/simulation_system/training.py

@@ -1,10 +1,8 @@
 
 import argparse
 # import boto3
-import os 
 from pathlib import Path
 from datetime import datetime
-from typing import List
 from core.Logger import logger
 from core.DataLoader import DataLoader
 from core.FeatureProcessor import FeatureProcessor