got the predictions working

.idea/Model.iml

@@ -7,7 +7,7 @@
       <sourceFolder url="file://$MODULE_DIR$/open_uprn" isTestSource="false" />
       <sourceFolder url="file://$MODULE_DIR$/recommendations" isTestSource="false" />
     </content>
-    <orderEntry type="jdk" jdkName="Python 3.10 (simulation_system)" jdkType="Python SDK" />
+    <orderEntry type="jdk" jdkName="Python 3.10 (simulation_system_prediction)" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
 </module>

.idea/misc.xml

@@ -1,6 +1,6 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <project version="4">
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10 (simulation_system)" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10 (simulation_system_prediction)" project-jdk-type="Python SDK" />
   <component name="PythonCompatibilityInspectionAdvertiser">
     <option name="version" value="3" />
   </component>

model_data/simulation_system/core/Helpers.py

@@ -1,17 +0,0 @@
-from pathlib import Path
-
-
-def ensure_relative_path(file_path: str, relative_to: str | Path = None) -> Path:
-    """
-    Convert the given path to a relative path.
-
-    :param file_path: The path to check and possibly convert.
-    :param relative_to: Optional path to which the given path should be made relative.
-                        If not provided, the current working directory is used.
-    :return: The relative path.
-    """
-    path = Path(file_path)
-    if path.is_absolute():
-        base_path = Path(relative_to) if relative_to else Path.cwd()
-        return path.relative_to(base_path)
-    return path

model_data/simulation_system/requirements/prediction.txt

@@ -0,0 +1,2 @@
+autogluon==0.8.2
+pandas==1.5.3

model_data/simulation_system/training.py

@@ -8,6 +8,7 @@ from model_data.simulation_system.core.FeatureProcessor import FeatureProcessor
 from model_data.simulation_system.MLModel.Models import AutogluonModel
 import pandas as pd
 from model_data.simulation_system.core.Settings import (
+    MODEL_DIRECTORY,
     BASE_REGISTRY_PATH,
     REGISTRY_FILE,
     MODEL_FOLDER,
@@ -16,7 +17,6 @@ from model_data.simulation_system.core.Settings import (
     SUBSAMPLE_FACTOR,
     MODEL_HYPERPARAMETERS
 )
-from model_data.simulation_system.core.Helpers import ensure_relative_path
 import seaborn as sns
 import matplotlib.pyplot as plt
 
@@ -100,7 +100,7 @@ def training(
 
     if model_type == "autogluon":
         model_root = f"{target_column}-{hyperparameters['presets']}-{hyperparameters['time_limit']}-{TIMESTAMP}".lower()
-        output_base = BASE_REGISTRY_PATH / target_column / model_type / model_root
+        output_base = Path(MODEL_DIRECTORY) / target_column / model_type / model_root
 
         model = AutogluonModel(
             output_filepath=output_base / MODEL_FOLDER
@@ -157,9 +157,6 @@ def training(
     logger.info("--- Optimising model for deployment ---")
 
     deployment_model_path = model.optimise_model_for_deployment(deployment_path=output_base / DEPLOYMENT_FOLDER)
-    # Autogluon requires models to be stored at relative paths. This will likely eventually be s3 however we
-    # make sure the path is relative to the location of this script
-    deployment_model_path = ensure_relative_path(deployment_model_path, Path(__file__).parent)
     logger.info(f"Optimised version of best model can be found at: {deployment_model_path}")
 
     # TODO: Need a model registry - for now have this as a CSV