.dockerignore

@@ -1,9 +0,0 @@
-modules/ml-pipeline/src/pipeline/data/predictions
-modules/ml-pipeline/src/pipeline/data/fit_predictions
-modules/ml-pipeline/src/pipeline/data/prepared_data
-modules/ml-pipeline/src/pipeline/data/model/allmodels
-modules/ml-pipeline/src/pipeline/metrics
-modules/ml-pipeline/src/pipeline/__pycache__
-modules/ml-pipeline/src/pipeline/.dvc
-modules/ml-pipeline/src/pipeline/analysis
-modules/ml-pipeline/src/pipeline/metrics

.github/workflows/Deploy.yml

@@ -2,7 +2,7 @@ name: Sap Change Model Deploy
 
 on:
   push:
-    branches: [ sap-dev, sap-prod, heat-dev, heat-prod, carbon-dev, carbon-prod]
+    branches: [ sap-dev, sap-prod ]
 
 jobs:
   deploy:
@@ -19,8 +19,8 @@ jobs:
 
       - name: Install Serverless and plugins
         run: |
-          npm install -g serverless@^3.38.0
-          npm install -g serverless-domain-manager@^7.3.8
+          npm install -g serverless
+          npm install -g serverless-domain-manager
 
       - name: Install DVC
         run: |
@@ -32,7 +32,8 @@ jobs:
         id: secret_prefix
         run: |
             # Convert branch name to uppercase and replace hyphens with underscores
-            echo "::set-output name=secret_prefix::$(echo "${{ github.ref_name }}" | tr 'a-z-' 'A-Z_')"
+            # TODO: Remove the CHANGE line by changing the secrets name
+            echo "::set-output name=secret_prefix::$(echo "${{ github.ref_name }}" | sed  's/-/_change-/g' | tr 'a-z-' 'A-Z_')"
 
       - name: Set domain name
         id: set_domain
@@ -57,9 +58,9 @@ jobs:
           # Take branch prefix and add "model" for stack name
           stack_name=$( echo ${{ github.ref_name }} | awk -F"-" '{print $1}' | sed 's/$/model/g')
           if [ -z "${stack_name}" ]; then
-            echo "::set-output name=stack_name::"
-          else
             echo "::set-output name=stack_name::${stack_name}"
+          else
+            echo "::set-output name=stack_name::"
           fi
 
       - name: Set runtime_environment

.github/workflows/MLPipelinePostMerge.yml

@@ -42,14 +42,7 @@ jobs:
         if [ -z "${latest_version}" ]; then
           increment_version="1.0.0"
         else
-          increment_version=$(echo ${latest_version} | awk 'BEGIN {
-              FS="\\."   # Set the field separator to a period
-              OFS="."    # Set the output field separator to a period
-          }
-          {
-              major = $1 + 1   # Increment the major version
-              print major, "0", "0"   # Print the new version
-          }')
+          increment_version=$(echo ${latest_version} | awk -F'.' '{OFS="."; $1+=1; print}')
         fi
 
         new_tag=${REGISTER_MODEL_NAME}@v${increment_version}
@@ -87,14 +80,7 @@ jobs:
         if [ -z "${latest_version}" ]; then
           increment_version="0.1.0"
         else
-          increment_version=$(echo ${latest_version} | awk 'BEGIN {
-              FS="\\."   # Set the field separator to a period
-              OFS="."    # Set the output field separator to a period
-          }
-          {
-              minor = $2 + 1   # Increment the minor version
-              print $1, minor, "0"   # Print the new version
-          }')
+          increment_version=$(echo ${latest_version} | awk 'BEGIN{FS=OFS="."} {$2++; print}')
         fi
 
         new_tag=${REGISTER_MODEL_NAME}@v${increment_version}
@@ -132,14 +118,7 @@ jobs:
         if [ -z "${latest_version}" ]; then
           increment_version="0.0.1"
         else
-          increment_version=$(echo ${latest_version} | awk 'BEGIN {
-              FS="\\."   # Set the field separator to a period
-              OFS="."    # Set the output field separator to a period
-          }
-          {
-              patch = $3 + 1   # Increment the patch version
-              print $1, $2, patch   # Print the new version
-          }')
+          increment_version=$(echo ${latest_version} | awk 'BEGIN{FS=OFS="."} {$3++; print}')
         fi
 
         new_tag=${REGISTER_MODEL_NAME}@v${increment_version}
@@ -209,7 +188,7 @@ jobs:
         git config user.name "Github-Bot"
         git config user.email "Github-Bot@no-reply.com"
 
-        latest_dev_version=$(gto history ${REGISTER_MODEL_NAME} --asc --plain | awk '{print $NF}' | awk '/dev/' | awk 'END {print}')
+        latest_dev_version=$(gto history ${REGISTER_MODEL_NAME} --asc --plain | awk '{print $NF}' | awk '/dev/')
         if [ -z "${latest_dev_version}" ]; then
           increment_version="1"
         else
@@ -217,7 +196,7 @@ jobs:
         fi
 
         new_tag=${REGISTER_MODEL_NAME}#dev#${increment_version}
-        latest_version=$(gto show ${REGISTER_MODEL_NAME}@latest --ref | awk -F"@" '{print $2}')
+        latest_version=$(gto show model@latest --ref | awk -F"@" '{print $2}')
 
         echo ${new_tag}
 

.github/workflows/MLPipelinePullRequest.yml

@@ -98,16 +98,6 @@ jobs:
         git fetch --depth=1 origin ${TARGET_BRANCH}:${TARGET_BRANCH}
         dvc metrics diff --md --all ${TARGET_BRANCH} >> report.md
 
-        echo "## Scenario comparison" >> report.md
-
-        cat metrics/scenario_table.md >> report.md
-
-        echo "" >> report.md
-
-        echo "## Scenario metrics" >> report.md
-
-        cat metrics/scenario_metrics.md >> report.md
-
         cml comment create report.md
 
         # echo "## Residuals plot from model" >> report.md

MODEL_REGISTRY.md

@@ -8,25 +8,9 @@
         "active": true
     },
     "sap": {
-        "version": "v0.14.0",
+        "version": "v0.0.1",
         "stage": {
-            "dev": "v0.14.0"
-        },
-        "registered": true,
-        "active": true
-    },
-    "heat": {
-        "version": "v0.5.0",
-        "stage": {
-            "dev": "v0.5.0"
-        },
-        "registered": true,
-        "active": true
-    },
-    "carbon": {
-        "version": "v0.5.0",
-        "stage": {
-            "dev": "v0.5.0"
+            "dev": "v0.0.1"
         },
         "registered": true,
         "active": true

README.md

@@ -10,9 +10,9 @@ tracking and a model registry
 	- A bolt-on service that can implement model monitoring
 
 There are multiple protected branches which adapt the generic pipeline to produce different models:
-- sap-{dev/staging/prod}-**
-- heat-{dev/staging/prod}-**
-- carbon-{dev/staging/prod}-**
+- sap_change-**
+- heat_change-**
+- carbon_change-**
 
 These branches will differ by the configuration files that define the data used and the outputs of the ML-pipeline
 - There can be different additional logic for each branch but the pipeline will be the same.
@@ -31,7 +31,7 @@ In order for this to be set up, some key environment variables needs to be inser
 secrets. Each different model and protected branch has its own set of secrets which allows for flexibility
 between different pipelines.
 
-For example, for the branch sap-dev, the prefix=SAP_DEV, and the following secrets are:
+For example, for the branch sap_change-dev, the prefix=SAP_CHANGE_DEV, and the following secrets are:
 
 - {prefix}_ECR_URI, which is the URI of the ECR repository to push to. For example, for the
    sap change model this is the lambda-sap-prediction-dev repository.
@@ -58,7 +58,7 @@ First, navigate to the root directory of the repository. Open a terminal and exe
 2. command to build the Docker image:
 
 ```bash
-docker build -t sap -f deployment/Dockerfile.prediction.lambda .
+docker build -t sap_change -f deployment/Dockerfile.prediction.lambda .
 ```
 
 This will build a Docker image tagged as sap_change using the Dockerfile.prediction.lambda located
@@ -68,7 +68,7 @@ in the deployment directory.
 Once the image is built, you can run it using the following command:
 
 ```bash
-docker run -p 9000:8080 -v ~/.aws/credentials:/root/.aws/credentials:ro -e RUNTIME_ENVIRONMENT=dev -e PREDICTIONS_BUCKET=retrofit-sap-predictions-dev sap
+docker run -p 9000:8080 -v ~/.aws/credentials:/root/.aws/credentials:ro -e RUNTIME_ENVIRONMENT=dev sap_change
 ```
 This command does the following:
 
@@ -79,7 +79,6 @@ Sets the RUNTIME_ENVIRONMENT variable to dev.
 To test the Lambda function, use the following curl command:
 
 ```json
-curl -XPOST "http://localhost:9000/2015-03-31/functions/function/invocations" -d '{"body": "{\"file_location\": \"s3://retrofit-data-dev/sap_change_model/one_sample_test_dataset.parquet\", \"property_id\": 1, \"portfolio_id\": 4, \"created_at\": \"now\"}"}'
+curl -XPOST "http://localhost:9000/2015-03-31/functions/function/invocations" -d '{"body": "{\"file_location\": \"s3://retrofit-data-dev/model_build_data/change_data/rdsap_full/test_data_with_id.parquet\", \"property_id\": 1, \"portfolio_id\": 4, \"created_at\": \"now\"}"'
 ```
-
 This will send a POST request to the running Lambda function and pass in the required data as JSON.

deployment/.dockerignore

@@ -1,9 +0,0 @@
-modules/ml-pipeline/src/pipeline/data/predictions
-modules/ml-pipeline/src/pipeline/data/fit_predictions
-modules/ml-pipeline/src/pipeline/data/prepared_data
-modules/ml-pipeline/src/pipeline/data/model/allmodels
-modules/ml-pipeline/src/pipeline/metrics
-modules/ml-pipeline/src/__pycache__
-modules/ml-pipeline/src/.dvc
-modules/ml-pipeline/src/analysis
-modules/ml-pipeline/src/metrics

deployment/Dockerfile.prediction.lambda

@@ -9,7 +9,7 @@ ARG RUNTIME_ENVIRONMENT
 ENV RUNTIME_ENVIRONMENT=${RUNTIME_ENVIRONMENT}
 
 # Install necessary build tools - required to test locally
-RUN yum install -y gcc python3-devel gcc-c++
+RUN yum install -y gcc python3-devel
 
 # Install python packages
 COPY modules/ml-pipeline/src/pipeline/requirements/predictions/requirements.txt ./requirements.txt

deployment/handlers/prediction_app.py

@@ -69,7 +69,9 @@ def handler(event, context):
 
         storage_filepath = f"s3://{PREDICTIONS_BUCKET}/{portfolio_id}/{property_id}/{created_at}.parquet"
 
+        logger.info("-------------------------")
         logger.info(f"--- Initiate MLModel ---")
+        logger.info("-------------------------")
 
         build_model_params = settings.build_model
         client_params = settings.client
@@ -78,13 +80,17 @@ def handler(event, context):
 
         model = model_factory(build_model_params["model_type"])
 
+        logger.info("----------------------------")
         logger.info(f"--- Initiate Input DataClient ---")
+        logger.info("----------------------------")
         input_dataclient = dataclient_factory(
             dataclient_type="aws-s3",
             dataclient_config=client_params["aws-s3"],
         )
 
+        logger.info("----------------------------")
         logger.info(f"--- Initiate Output DataClient ---")
+        logger.info("----------------------------")
         output_dataclient = dataclient_factory(
             dataclient_type="aws-s3",
             dataclient_config=client_params["aws-s3"],
@@ -101,7 +107,6 @@ def handler(event, context):
             predictions_column_name=generate_predictions_params[
                 "predictions_column_name"
             ],
-            identifier_column=generate_predictions_params["identifier_column"],
         )
 
         return {

modules/ml-pipeline/.dvc/.gitignore

@@ -0,0 +1,3 @@
+/config.local
+/tmp
+/cache

modules/ml-pipeline/.dvc/config

@@ -0,0 +1,2 @@
+['remote "myremote"']
+    url = /tmp/dvcstore

modules/ml-pipeline/.dvcignore

@@ -0,0 +1,3 @@
+# Add patterns of files dvc should ignore, which could improve
+# the performance. Learn more at
+# https://dvc.org/doc/user-guide/dvcignore

modules/ml-pipeline/.gto

@@ -0,0 +1,2 @@
+# .gto config file
+stages: [dev, stage, prod] # list of allowed Stages

modules/ml-pipeline/Makefile

@@ -9,16 +9,16 @@ init: dev-conda
 .PHONY: dev-conda
 dev-conda:
 	# conda deactivate || echo "Not in conda environment"
-	# conda remove --name ${CONDA_ENV} --all -y || echo "No environment created previously"
-	conda create --name ${CONDA_ENV} python=$(PYTHON_VERSION) -y
+	# conda remove --name $CONDA_ENV --all -y || echo "No environment created previously"
+	conda create --name $CONDA_ENV python=$(PYTHON_VERSION) -y
 	conda init bash
-	conda run -v -n ${CONDA_ENV} pip install --upgrade pip
-	conda run -v -n ${CONDA_ENV} pip install -r src/pipeline/requirements/training/requirements-dev.txt
-	conda run -v -n ${CONDA_ENV} pip install -r src/pipeline/requirements/version_control/requirements.txt
-	conda run -v -n ${CONDA_ENV} pre-commit install
-	conda run -v -n ${CONDA_ENV} pip install ipykernel
+	conda run -vvvv -n $CONDA_ENV pip install --upgrade pip
+	conda run -vvvv -n $CONDA_ENV pip install -r src/pipeline/requirements/training/requirements-dev.txt
+	conda run -vvvv -n $CONDA_ENV pip install -r src/pipeline/requirements/version_control/requirements.txt
+	conda run -vvvv -n $CONDA_ENV pre-commit install
+	conda run -vvvv -n $CONDA_ENV pip install ipykernel
 	echo "TO ACTIVATE ENVIRONMENT, USE THE FOLLOWING COMMAND"
-	echo "conda activate ${CONDA_ENV}"
+	echo "conda activate $CONDA_ENV"
 
 
 .PHONY: dev-pyenv

modules/ml-pipeline/src/.dockerignore

@@ -1,8 +0,0 @@
-pipeline/data/predictions
-pipeline/data/fit_predictions
-pipeline/data/prepared_data/train.parquet
-pipeline/data/fit_predictions
-pipeline/data/model/allmodels
-pipeline/metrics
-pipeline/.dvc
-pipeline/analysis

modules/ml-pipeline/src/Prediction.Dockerfile

@@ -1,7 +1,7 @@
 # Dockerfile that can be used to test loading a model to generate a prediction (part of CI/CD flow)
 FROM python:3.10.12-slim
 
-RUN apt-get update && apt-get install -y libgomp1 gcc python3-dev
+RUN apt-get update && apt-get install -y libgomp1
 
 COPY pipeline/requirements/predictions/requirements.txt requirements.txt
 

modules/ml-pipeline/src/pipeline/0_startup_cleanup.py

@@ -16,9 +16,13 @@ def run_cleanup(artefacts_directory: str, metrics_directory: str) -> None:
     Remove the directory where artefacts are stored
     """
 
+    logger.info("---------------------")
     logger.info(f"--- Run Clean up ---")
+    logger.info("---------------------")
 
+    logger.info("-------------------------")
     logger.info(f"--- Delete artefacts ---")
+    logger.info("-------------------------")
 
     artefact_directory_path = Path(artefacts_directory)
 
@@ -27,7 +31,9 @@ def run_cleanup(artefacts_directory: str, metrics_directory: str) -> None:
         logger.info(f"Removing the directory: {artefacts_directory}")
         shutil.rmtree(artefact_directory_path)
 
+    logger.info("-----------------------")
     logger.info(f"--- Delete metrics ---")
+    logger.info("-----------------------")
 
     metrics_directory_path = Path(metrics_directory)
 
@@ -39,11 +45,15 @@ def run_cleanup(artefacts_directory: str, metrics_directory: str) -> None:
 
 if __name__ == "__main__":
 
+    logger.info("----------------------------")
     logger.info(f"--- {__file__} - Start! ---")
+    logger.info("----------------------------")
 
     run_cleanup(
         artefacts_directory=startup_cleanup_params["artefacts"],
         metrics_directory=startup_cleanup_params["metrics"],
     )
 
+    logger.info("-------------------------------")
     logger.info(f"--- {__file__} - Complete! ---")
+    logger.info("-------------------------------")

modules/ml-pipeline/src/pipeline/1_prepare_data.py

@@ -17,7 +17,9 @@ from core.DataClient import dataclient_factory
 from core.FeatureProcessor import feature_processor_factory
 from config import settings
 
+logger.info("----------------------------")
 logger.info(f"--- Initiate Parameters ---")
+logger.info("----------------------------")
 
 RUNTIME_ENVIRONMENT = os.environ.get("RUNTIME_ENVIRONMENT", "local")
 
@@ -31,7 +33,9 @@ output_train_filepath = prepare_data_params["output_train_filepath"]
 output_test_filepath = prepare_data_params["output_test_filepath"]
 feature_processor_config = feature_process_params["feature_processor_config"]
 
+logger.info("----------------------------")
 logger.info(f"--- Initiate DataClient ---")
+logger.info("----------------------------")
 
 input_dataclient_type = prepare_data_params["input_dataclient_type"]
 output_dataclient_type = prepare_data_params["output_dataclient_type"]
@@ -45,7 +49,9 @@ output_dataclient = dataclient_factory(
     dataclient_config=client_params[output_dataclient_type],
 )
 
+logger.info("----------------------------------")
 logger.info(f"--- Initiate FeatureProcessor ---")
+logger.info("----------------------------------")
 
 feature_processor = feature_processor_factory(
     feature_process_params["feature_processor_type"]
@@ -70,11 +76,15 @@ def prepare_data(
     :param pipeline_mode: bool, Default False, this caches out the file for experimentation, objects returned in pipeline mode
     """
 
+    logger.info("--------------------")
     logger.info("--- Loading data ---")
+    logger.info("--------------------")
 
     data = input_dataclient.load_data(location=data_filepath, load_config={})
 
+    logger.info("--------------------------")
     logger.info("--- Feature Processing ---")
+    logger.info("--------------------------")
 
     data = feature_processor.feature_process(
         data,
@@ -83,12 +93,13 @@ def prepare_data(
         new_feature_funcs=new_feature_funcs,
     )
 
+    logger.info("----------------------")
     logger.info("--- Splitting data ---")
+    logger.info("----------------------")
 
     if train_proportion == 1:
         train = data
-        # Sample 10% of the data for testing
-        test = data.sample(round(len(data) * 0.1))
+        test = None
     else:
         train, test = train_test_split(
             data, train_size=train_proportion, test_size=(1 - train_proportion)
@@ -97,7 +108,9 @@ def prepare_data(
 
     train = train.reset_index(drop=True)
 
+    logger.info("-----------------------")
     logger.info("--- Outputting data ---")
+    logger.info("-----------------------")
 
     output_dataclient.save_data(
         obj=train, location=output_train_filepath, save_config=None
@@ -113,9 +126,13 @@ def prepare_data(
 
 if __name__ == "__main__":
 
+    logger.info("----------------------------")
     logger.info(f"--- {__file__} - Start! ---")
+    logger.info("----------------------------")
 
+    logger.info("---------------------------")
     logger.info(f"--- Prepare Data Stage ---")
+    logger.info("---------------------------")
 
     prepare_data(
         input_dataclient=input_dataclient,
@@ -130,4 +147,6 @@ if __name__ == "__main__":
         new_feature_funcs=new_feature_funcs,
     )
 
+    logger.info("-------------------------------")
     logger.info(f"--- {__file__} - Complete! ---")
+    logger.info("-------------------------------")

modules/ml-pipeline/src/pipeline/2_build_model.py

@@ -18,7 +18,9 @@ from core.MLMetrics import metrics_factory
 from configs.post_prediction_logic import post_prediction_logic
 from config import settings
 
+logger.info("----------------------------")
 logger.info(f"--- Initiate Parameters ---")
+logger.info("----------------------------")
 
 RUNTIME_ENVIRONMENT = os.environ.get("RUNTIME_ENVIRONMENT", "local")
 
@@ -26,12 +28,9 @@ prepare_data_params = settings.prepare_data
 build_model_params = settings.build_model
 feature_process_params = settings.feature_processor
 generate_metrics_params = settings.generate_metrics
-generate_predictions_params = settings.generate_predictions
 
 model_type = build_model_params["model_type"]
 target = feature_process_params["feature_processor_config"]["target"]
-fit_predictions_filepath = build_model_params["fit_predictions_filepath"]
-predictions_column_name = generate_predictions_params["predictions_column_name"]
 identifier_columns = feature_process_params["feature_processor_config"][
     "identifier_columns"
 ]
@@ -41,16 +40,22 @@ train_filepath = prepare_data_params["output_train_filepath"]
 test_filepath = prepare_data_params["output_test_filepath"]
 fit_metrics_filepath = build_model_params["fit_metrics_filepath"]
 
+logger.info("----------------------------")
 logger.info(f"--- Initiate DataClient ---")
+logger.info("----------------------------")
 
 # Output of previous prepare data step, will be where the data is
 dataclient = dataclient_factory(prepare_data_params["output_dataclient_type"])
 
+logger.info("-------------------------")
 logger.info(f"--- Initiate MLModel ---")
+logger.info("-------------------------")
 
 model = model_factory(model_type)
 
+logger.info("-------------------------")
 logger.info(f"--- Initiate Metrics ---")
+logger.info("-------------------------")
 
 metrics = metrics_factory(generate_metrics_params["metrics_type"])
 
@@ -63,8 +68,6 @@ def build_model(
     identifier_columns: List[str],
     model_save_location: str,
     model_hyperparameters: dict,
-    fit_predictions_filepath: str,
-    predictions_column_name: str,
     fit_metrics_filepath: str,
     train_filepath: Union[str, None] = None,
     test_filepath: Union[str, None] = None,
@@ -72,7 +75,9 @@ def build_model(
     test_data: Union[pd.DataFrame, None] = None,
     pipeline_mode: bool = False,
 ):
+    logger.info("--------------------------------------")
     logger.info("--- Loading Data for build process ---")
+    logger.info("--------------------------------------")
 
     if train_data is None:
         if train_filepath is None:
@@ -84,7 +89,9 @@ def build_model(
             raise ValueError(f"Need {test_filepath} if no data supplied")
         test_data = dataclient.load_data(location=test_filepath, load_config=None)
 
+    logger.info("----------------------")
     logger.info("--- Training model ---")
+    logger.info("----------------------")
 
     model.train_model(
         data=train_data.drop(columns=identifier_columns),
@@ -92,33 +99,32 @@ def build_model(
         model_hyperparameters=model_hyperparameters,
     )
 
+    logger.info("----------------------------------")
     logger.info("--- Generating fit predictions ---")
+    logger.info("----------------------------------")
 
     fit_predictions = model.predict(
         data=train_data, post_prediction_logic=post_prediction_logic
     )
 
-    logger.info("--- Saving fit predictions ---")
-
-    predictions_df = pd.DataFrame(fit_predictions)
-    predictions_df.columns = [predictions_column_name]
-
-    dataclient.save_data(
-        obj=predictions_df, location=fit_predictions_filepath, save_config=None
-    )
-
+    logger.info("------------------------------")
     logger.info("--- Generating fit metrics ---")
+    logger.info("------------------------------")
 
     metrics_output = metrics.generate_metrics(
         target=train_data[target],
         predictions=pd.Series(fit_predictions),
     )
 
+    logger.info("--------------------")
     logger.info("--- Saving model ---")
+    logger.info("--------------------")
 
     model.save_model(path=Path(model_save_location))
 
+    logger.info("--------------------------")
     logger.info("--- Saving fit metrics ---")
+    logger.info("--------------------------")
 
     dataclient.save_data(
         obj=metrics_output, location=fit_metrics_filepath, save_config=None
@@ -127,9 +133,13 @@ def build_model(
 
 if __name__ == "__main__":
 
+    logger.info("----------------------------")
     logger.info(f"--- {__file__} - Start! ---")
+    logger.info("----------------------------")
 
+    logger.info("--------------------------")
     logger.info(f"--- Build Model Stage ---")
+    logger.info("--------------------------")
 
     build_model(
         dataclient=dataclient,
@@ -142,8 +152,8 @@ if __name__ == "__main__":
         train_filepath=train_filepath,
         test_filepath=test_filepath,
         fit_metrics_filepath=fit_metrics_filepath,
-        fit_predictions_filepath=fit_predictions_filepath,
-        predictions_column_name=predictions_column_name,
     )
 
+    logger.info("-------------------------------")
     logger.info(f"--- {__file__} - Complete! ---")
+    logger.info("-------------------------------")

modules/ml-pipeline/src/pipeline/3_generate_predictions.py

@@ -10,7 +10,9 @@ from core.Logger import logger
 from config import settings
 from generate_predictions import generate_predictions
 
+logger.info("----------------------------")
 logger.info(f"--- Initiate Parameters ---")
+logger.info("----------------------------")
 
 RUNTIME_ENVIRONMENT = os.environ.get("RUNTIME_ENVIRONMENT", "local")
 
@@ -31,11 +33,15 @@ model_filepath = build_model_params["model_save_filepath"]
 predictions_output_filepath = generate_predictions_params["predictions_output_filepath"]
 predictions_column_name = generate_predictions_params["predictions_column_name"]
 
+logger.info("-------------------------")
 logger.info(f"--- Initiate MLModel ---")
+logger.info("-------------------------")
 
 model = model_factory(build_model_params["model_type"])
 
+logger.info("----------------------------")
 logger.info(f"--- Initiate DataClient ---")
+logger.info("----------------------------")
 
 # We may have different locations of loading hence why we use one specified in generate_predictions.yaml
 # I.e. for metric runs, this will be a local data client
@@ -53,9 +59,13 @@ output_dataclient = dataclient_factory(
 
 if __name__ == "__main__":
 
+    logger.info("----------------------------")
     logger.info(f"--- {__file__} - Start! ---")
+    logger.info("----------------------------")
 
+    logger.info("----------------------------------")
     logger.info(f"--- Generate Predictions Stage---")
+    logger.info("----------------------------------")
 
     generate_predictions(
         input_dataclient=input_dataclient,
@@ -68,4 +78,6 @@ if __name__ == "__main__":
         predictions_column_name=predictions_column_name,
     )
 
+    logger.info("-------------------------------")
     logger.info(f"--- {__file__} - Complete! ---")
+    logger.info("-------------------------------")

modules/ml-pipeline/src/pipeline/4_generate_metrics.py

@@ -16,7 +16,9 @@ from core.MLMetrics import metrics_factory
 from core.Logger import logger
 from config import settings
 
+logger.info("----------------------------")
 logger.info(f"--- Initiate Parameters ---")
+logger.info("----------------------------")
 
 RUNTIME_ENVIRONMENT = os.environ.get("RUNTIME_ENVIRONMENT", "local")
 
@@ -33,11 +35,16 @@ predictions_output_filepath = generate_predictions_params["predictions_output_fi
 predictions_column_name = generate_predictions_params["predictions_column_name"]
 metrics_output_filepath = generate_metrics_params["metrics_output_filepath"]
 
+
+logger.info("-------------------------")
 logger.info(f"--- Initiate MLModel ---")
+logger.info("-------------------------")
 
 model = model_factory(build_model_params["model_type"])
 
+logger.info("----------------------------")
 logger.info(f"--- Initiate DataClient ---")
+logger.info("----------------------------")
 
 # Use data client for input and output, as we use dvc to cache later to the cloud
 dataclient_type = generate_metrics_params["dataclient_type"]
@@ -46,7 +53,9 @@ dataclient = dataclient_factory(
     dataclient_config=client_params[dataclient_type],
 )
 
+logger.info("---------------------------")
 logger.info(f"--- Initiate MLMetrics ---")
+logger.info("---------------------------")
 
 metrics = metrics_factory(generate_metrics_params["metrics_type"])
 
@@ -66,26 +75,34 @@ def generate_metrics(
     For a given model, we generate prediction and evaluate this against the true target
     """
 
+    logger.info("-------------------------")
     logger.info("--- Loading test data ---")
+    logger.info("-------------------------")
 
     test_data = input_dataclient.load_data(
         location=test_data_filepath, load_config=None
     )
 
+    logger.info("---------------------------")
     logger.info("--- Loading predictions ---")
+    logger.info("---------------------------")
 
     predictions = input_dataclient.load_data(
         location=predictions_output_filepath, load_config=None
     )
 
+    logger.info("--------------------------")
     logger.info("--- Generating metrics ---")
+    logger.info("--------------------------")
 
     metrics_output = metrics.generate_metrics(
         target=test_data[target],
         predictions=pd.Series(predictions[predictions_column_name]),
     )
 
+    logger.info("----------------------")
     logger.info("--- Saving metrics ---")
+    logger.info("----------------------")
 
     output_dataclient.save_data(
         obj=metrics_output, location=metrics_output_filepath, save_config=None
@@ -94,9 +111,13 @@ def generate_metrics(
 
 if __name__ == "__main__":
 
+    logger.info("----------------------------")
     logger.info(f"--- {__file__} - Start! ---")
+    logger.info("----------------------------")
 
+    logger.info("------------------------------")
     logger.info(f"--- Generate Metrics Stage---")
+    logger.info("------------------------------")
 
     generate_metrics(
         input_dataclient=dataclient,
@@ -110,4 +131,6 @@ if __name__ == "__main__":
         metrics_output_filepath=metrics_output_filepath,
     )
 
+    logger.info("-------------------------------")
     logger.info(f"--- {__file__} - Complete! ---")
+    logger.info("-------------------------------")

modules/ml-pipeline/src/pipeline/5_generate_scenarios.py

@@ -1,162 +0,0 @@
-"""
-Fourth part of the pipeline:
-After the model is built and metrics are generated,
-we want to test this model against known scenarios
-"""
-
-import os
-import pandas as pd
-from core.interface.InterfaceModels import MLModel
-from core.interface.InterfaceDataClient import DataClient
-from core.interface.InterfaceMetrics import MLMetrics
-from configs.post_prediction_logic import post_prediction_logic
-from core.DataClient import dataclient_factory
-from core.MLModels import model_factory
-from core.MLMetrics import metrics_factory
-from core.Logger import logger
-from config import settings
-
-logger.info(f"--- Initiate Parameters ---")
-
-RUNTIME_ENVIRONMENT = os.environ.get("RUNTIME_ENVIRONMENT", "local")
-
-client_params = settings.client
-prepare_data_params = settings.prepare_data
-build_model_params = settings.build_model
-generate_predictions_params = settings.generate_predictions
-generate_metrics_params = settings.generate_metrics
-feature_process_params = settings.feature_processor
-scenarios_params = settings.scenarios
-
-model_filepath = build_model_params["model_save_filepath"]
-target = feature_process_params["feature_processor_config"]["target"]
-scenario_data_filepaths = scenarios_params["scenario_data_filepaths"]
-predictions_column_name = generate_predictions_params["predictions_column_name"]
-comparison_output_filepath = scenarios_params["comparison_output_filepath"]
-metrics_output_filepath = scenarios_params["metrics_output_filepath"]
-
-logger.info(f"--- Initiate MLModel ---")
-
-model = model_factory(build_model_params["model_type"])
-
-logger.info(f"--- Initiate DataClient ---")
-
-# Use data client for input and output, as we use dvc to cache later to the cloud
-input_dataclient_type = scenarios_params["input_dataclient_type"]
-input_dataclient = dataclient_factory(
-    dataclient_type=input_dataclient_type,
-    dataclient_config=client_params[input_dataclient_type],
-)
-
-output_dataclient_type = scenarios_params["output_dataclient_type"]
-output_dataclient = dataclient_factory(
-    dataclient_type=output_dataclient_type,
-    dataclient_config=client_params[output_dataclient_type],
-)
-
-logger.info(f"--- Initiate MLMetrics ---")
-
-metrics = metrics_factory(generate_metrics_params["metrics_type"])
-
-
-def generate_scenario_predictions(
-    input_dataclient: DataClient,
-    output_dataclient: DataClient,
-    model: MLModel,
-    metrics: MLMetrics,
-    model_filepath: str,
-    scenario_data_filepaths: list,
-    predictions_column_name: str,
-    comparison_output_filepath: str,
-    metrics_output_filepath: str,
-):
-    """
-    Given the new model, we generate prediction for expected scenarios
-    """
-
-    logger.info("--- Loading Scenario Data ---")
-
-    scenario_data = pd.DataFrame()
-
-    # If we have no scenario data, we can save empty dataframes
-    if scenario_data_filepaths is None:
-        logger.info("No scenario data filepaths provided")
-        output_dataclient.save_data(
-            obj=scenario_data, location=comparison_output_filepath, save_config=None
-        )
-
-        output_dataclient.save_data(
-            obj=scenario_data, location=metrics_output_filepath, save_config=None
-        )
-        return
-
-    # Can have multiple scenario data files
-    for scenario_data_filepath in scenario_data_filepaths:
-        scenario_data = pd.concat(
-            [
-                scenario_data,
-                input_dataclient.load_data(scenario_data_filepath, load_config=None),
-            ]
-        )
-
-    logger.info("--- Loading Model ---")
-
-    model.load_model(model_filepath)
-
-    logger.info("--- Generating Predictions ---")
-
-    predictions = model.predict(
-        data=scenario_data, post_prediction_logic=post_prediction_logic
-    )
-
-    logger.info("--- Generate Scenario Predicted Impact ---")
-
-    predictions_df = pd.DataFrame(predictions)
-    predictions_df.columns = [predictions_column_name]
-
-    scenario_data = pd.concat([scenario_data, predictions_df], axis=1)
-    scenario_data["predicted_impact"] = abs(
-        scenario_data[predictions_column_name] - scenario_data["sap_starting"]
-    )
-
-    logger.info("--- Generate Metrics ---")
-
-    metrics_dict = metrics.generate_metrics(
-        scenario_data["impact"], scenario_data["predicted_impact"]
-    )
-
-    metrics_df = pd.DataFrame(metrics_dict, index=[0]).T.reset_index()
-    metrics_df.columns = ["metric", "value"]
-
-    logger.info("--- Save prediction into metrics ---")
-
-    output_df = scenario_data[["uprn", "id", "impact", "predicted_impact"]]
-
-    output_dataclient.save_data(
-        obj=output_df, location=comparison_output_filepath, save_config=None
-    )
-
-    output_dataclient.save_data(
-        obj=metrics_df, location=metrics_output_filepath, save_config=None
-    )
-
-
-if __name__ == "__main__":
-
-    logger.info(f"--- {__file__} - Start! ---")
-
-    logger.info(f"--- Generate Scenario Predictions ---")
-
-    generate_scenario_predictions(
-        input_dataclient=input_dataclient,
-        output_dataclient=output_dataclient,
-        model=model,
-        metrics=metrics,
-        model_filepath=model_filepath,
-        scenario_data_filepaths=scenario_data_filepaths,
-        predictions_column_name=predictions_column_name,
-        comparison_output_filepath=comparison_output_filepath,
-        metrics_output_filepath=metrics_output_filepath,
-    )
-
-    logger.info(f"--- {__file__} - Complete! ---")

modules/ml-pipeline/src/pipeline/README.md

@@ -37,4 +37,3 @@ Workflow:
     - This experiment will have the corresponding .dvc files for the hashed model and data
 - Use version control as normal
     - git add, git commit etc
-- To revert change, use `git checkout {COMMIT_HASH}`, followed by `git switch -c {NEW_BRANCH_NAME}`

modules/ml-pipeline/src/pipeline/config.py

@@ -7,7 +7,6 @@ settings = Dynaconf(
         "./configs/settings.yaml",
         "./configs/build_model.yaml",
         "./configs/analysis.yaml",
-        "./configs/scenarios.yaml",
     ],
 )
 

modules/ml-pipeline/src/pipeline/configs/analysis.yaml

@@ -13,4 +13,4 @@ default:
     dataclient_type: local
     nshap_samples: 100 # how many samples to use to approximate each Shapely value, larger values will be slower
     n_val: 30  # how many datapoints from validation data should we interpret predictions for, larger values will be slower
-    row_index: [20695, 50243, 7653] # index of an example datapoint
+    row_index: [0, 10, 20] # index of an example datapoint

modules/ml-pipeline/src/pipeline/configs/build_model.yaml

@@ -3,7 +3,6 @@ default:
     model_type: AutogluonAutoML
     model_save_filepath: ./data/model/optimised/
     fit_metrics_filepath: ./metrics/fit_metrics.json
-    fit_predictions_filepath: ./data/fit_predictions/predictions.parquet
 
     SKLearnLinearRegression: null
 
@@ -14,9 +13,6 @@ default:
       output_filepath: ./data/model/allmodels/
       problem_type: regression
       eval_metric: mean_squared_error #mean_absolute_error
-      time_limit: 1800
+      time_limit: 4000
       presets: medium_quality
-      excluded_model_types: ['RF', 'CAT', 'NN_TORCH', 'KNN', 'XT']
-      infer_limit: 0.05
-      infer_limit_batch_size: 10000
-      ag_args_ensemble: {'num_folds_parallel': 2}
+      excluded_model_types: ['KNN', 'RF']

modules/ml-pipeline/src/pipeline/configs/feature_processor_logic.py

@@ -9,42 +9,15 @@ Business Logic dict + functions
 
 def remove_starting_columns(df):
     keep_column_index = [
-        False if col_name.endswith("_starting") else True
+        False if col_name.endswith("_STARTING") else True
         for col_name in list(df.columns)
     ]
     keep_columns = df.columns[keep_column_index].to_list()
-    keep_columns.append("sap_starting")
+    keep_columns.append("SAP_STARTING")
     df = df[keep_columns]
     return df
 
 
-def remove_floor_height_ending(df):
-    # df.describe(percentiles=[0.005,0.99])['FLOOR_HEIGHT_ENDING']
-    # shows bottom 0.5 percentile is 1.665
-    # So keep anything above this
-    df = df[df["floor_height_ending"] > 1.665].reset_index(drop=True)
-    print("we in here")
-    return df
-
-
-def remove_minimum_habitable_room_size(df):
-    # Need minimum of 6.5m per habitable room
-    df = df[
-        df["total_floor_area_ending"] / df["number_habitable_rooms"] > 6.5
-    ].reset_index(drop=True)
-    return df
-
-
-def keep_flats(df):
-    df = df[df["property_type"] == "Flat"]
-    return df
-
-
-def keep_non_zero_rdsap(df):
-    df = df[df["rdsap_change"] != 0]
-    return df
-
-
 # def keep_ending_columns(df):
 #     ending_column_index = [ col_name.endswith("_ENDING") for col_name in list(df.columns)]
 #     keep_columns = df.columns[ending_column_index].to_list()
@@ -54,10 +27,6 @@ def keep_non_zero_rdsap(df):
 #     return df
 
 business_logic = {
-    # "keep_non_zero_rdsap": keep_non_zero_rdsap,
-    # "keep_flats": keep_flats,
-    # "remove_minimum_habitable_room_size": remove_minimum_habitable_room_size,
-    # "remove_floor_height_ending": remove_floor_height_ending
     # "remove_starting_columns": remove_starting_columns
     # "keep_ENDING_COLUMNS": keep_ending_columns
 }

modules/ml-pipeline/src/pipeline/configs/post_prediction_logic.py

@@ -5,18 +5,16 @@ import pandas as pd
 
 
 def clip_predictions_to_minimum_value(
-    data: pd.DataFrame, predictions: pd.Series, minimum_value: int = 0
+    data: pd.DataFrame, predictions: pd.Series, minimum_value: int = 1
 ) -> pd.Series:
 
     series_name = predictions.name
     predictions.name = "predictions"
     predictions_df = pd.concat([data, predictions], axis=1)
     # We expect all prediction to be atleast one point improvement
-    replace_index = (
-        predictions_df["sap_starting"] + minimum_value > predictions_df["predictions"]
-    )
+    replace_index = predictions_df["SAP_STARTING"] + 1 > predictions_df["predictions"]
     predictions_df.loc[replace_index, "predictions"] = (
-        predictions_df.loc[replace_index, "sap_starting"] + minimum_value
+        predictions_df.loc[replace_index, "SAP_STARTING"] + minimum_value
     )
 
     predictions_new = predictions_df["predictions"]

modules/ml-pipeline/src/pipeline/configs/scenarios.yaml

@@ -1,13 +0,0 @@
-default:
-  scenarios:
-    input_dataclient_type: aws-s3
-    output_dataclient_type: local
-    scenario_data_filepaths:
-      # - s3://retrofit-data-dev/scenario_data/22-03-2024-19-20-09/recommendations_scoring_data.parquet
-      # - s3://retrofit-data-dev/scenario_data/24-03-2024-20-23-25/recommendations_scoring_data.parquet
-      # - s3://retrofit-data-dev/scenario_data/27-03-2024-11-38-15/recommendations_scoring_data.parquet
-      # - s3://retrofit-data-dev/scenario_data/26-05-2024-08-47-45/recommendations_scoring_data.parquet
-      # - s3://retrofit-data-dev/scenario_data/26-05-2024-10-44-53/recommendations_scoring_data.parquet
-      - s3://retrofit-data-dev/scenario_data/28-05-2024-19-22-41/recommendations_scoring_data.parquet
-    comparison_output_filepath: ./metrics/scenario_table.md
-    metrics_output_filepath: ./metrics/scenario_metrics.md

modules/ml-pipeline/src/pipeline/configs/settings.yaml

@@ -18,10 +18,10 @@ default:
   prepare_data:
     input_dataclient_type: aws-s3
     output_dataclient_type: local
-    # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-03-22-18-56-53/dataset_rooms.parquet
-    # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-25-08-36-36/dataset_rooms.parquet
-    # data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-26-10-31-39/dataset_rooms.parquet
-    data_filepath: s3://retrofit-data-dev/sap_change_model/2024-05-28-19-08-25/dataset_rooms.parquet
+    # data_filepath: s3://retrofit-data-dev/sap_change_model/dataset_with_differencing.parquet
+    # data_filepath: s3://retrofit-data-dev/sap_change_model/floor_area_clean_test.parquet
+    # data_filepath: s3://retrofit-data-dev/sap_change_model/dataset_without_differencing.parquet
+    data_filepath: s3://retrofit-data-dev/sap_change_model/dataset.parquet
     train_proportion: 0.9
     output_train_filepath: ./data/prepared_data/train.parquet
     output_test_filepath: ./data/prepared_data/test.parquet
@@ -31,37 +31,11 @@ default:
     feature_processor_config:
       subsample_amount: null
       subsample_seed: 0
-      target: sap_ending
-      identifier_columns: ["uprn"]
-      # drop_columns: ["heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "carbon_ending", "days_to_starting", "days_to_ending"]
-      drop_columns: [
-        "heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "carbon_ending", "days_to_starting", "days_to_ending",
-        'number_habitable_rooms_starting', 'number_habitable_rooms_ending', 'number_heated_rooms_starting', 'number_heated_rooms_ending',
-        'number_habitable_rooms', 'number_heated_rooms']
+      target: SAP_ENDING
+      identifier_columns: ["UPRN"]
+      drop_columns: ["HEAT_DEMAND_CHANGE", "CARBON_CHANGE", "RDSAP_CHANGE", "HEAT_DEMAND_ENDING", "CARBON_ENDING"]
+      # retain_features: ["SAP_STARTING", "TOTAL_FLOOR_AREA_DIFF"]
       retain_features: null
-      # retain_features: ['uprn', 'sap_starting', 'hot_water_energy_eff_ending',
-      #  'mainheat_energy_eff_ending', 'constituency', 'roof_energy_eff_ending',
-      #  'walls_energy_eff_ending', 'secondheat_description_ending',
-      #  'property_type', 'mainheatc_energy_eff_ending', 'built_form',
-      #  'walls_insulation_thickness_ending', 'potential_energy_efficiency',
-      #  'transaction_type_ending',
-      #  'floor_thermal_transmittance_ending',
-      #  'low_energy_lighting_ending', 'heat_demand_starting',
-      #  'photo_supply_ending', 'carbon_starting',
-      #  'walls_thermal_transmittance_ending',
-      #  'roof_insulation_thickness_ending',
-      #  'total_floor_area_ending', 'number_open_fireplaces_ending',
-      #  'windows_energy_eff_ending',
-      #  'floor_height_ending',
-      #  'extension_count_ending',
-      #  'has_air_source_heat_pump_ending',
-      #  'charging_system_ending', 'construction_age_band', 'glazed_type_ending',
-      #  'roof_thermal_transmittance_ending',
-      #  'floor_insulation_thickness_ending', 'has_mains_gas_ending',
-      #  'estimated_perimeter_starting', 'energy_consumption_potential',
-      #  'environment_impact_potential', 'heater_type_ending',
-      #  'multi_glaze_proportion_ending',
-      #  'lighting_energy_eff_ending', 'fixed_lighting_outlets_count']
 
   generate_predictions:
     input_dataclient_type: local
@@ -69,7 +43,6 @@ default:
     test_data_filepath: ./data/prepared_data/test.parquet
     predictions_output_filepath: ./data/predictions/predictions.parquet
     predictions_column_name: predictions
-    identifier_column: id
 
   generate_metrics:
     dataclient_type: local

modules/ml-pipeline/src/pipeline/core/DataClient.py

@@ -142,15 +142,9 @@ class AWSS3Client:
         buffer = BytesIO()
         obj.to_parquet(buffer, index=False)
 
-        # Reset the buffer position to the beginning
-        buffer.seek(0)
-
         bucket, key = location.strip("s3://").split("/", 1)
         self.client.upload_fileobj(buffer, bucket, key)
 
-        # Close the buffer
-        buffer.close()
-
     def _load_parquet(self, location: str, load_config: dict) -> pd.DataFrame:
         """
         Load a parquet file
@@ -245,8 +239,7 @@ class LocalClient:
 
         save_methods = {
             ".parquet": self._save_parquet,
-            ".json": self._save_json,
-            ".md": self._save_md,
+            ".json": self._save_json
             # "": _save_directory(**save_config),
             # ADD MORE save_methods HERE
         }
@@ -295,10 +288,3 @@ class LocalClient:
         # Write the contents of the buffer to the local file
         with open(location, "wb") as f:
             f.write(buffer.getvalue())
-
-    def _save_md(self, obj: pd.DataFrame, location: str, save_config: dict):
-        """
-        Save object as markdown
-        """
-
-        obj.to_markdown(location, **save_config)

modules/ml-pipeline/src/pipeline/core/Logger.py

@@ -21,7 +21,6 @@ def setup_logger():
 
     # Add the stream handler to the logger
     logger.addHandler(stream_handler)
-    logger.propagate = False
 
     return logger
 

modules/ml-pipeline/src/pipeline/core/MLMetrics.py

@@ -4,7 +4,6 @@ Implementation of MLMetrics, all of which will have two methods:
 - Generate Plot Suite
 """
 
-import numpy as np
 import pandas as pd
 from typing import Union
 from sklearn.metrics import (
@@ -15,18 +14,6 @@ from sklearn.metrics import (
 )
 from core.interface.InterfaceMetrics import MLMetrics
 
-# Define the function to return the SMAPE value
-def symmetric_mape(actual, predicted) -> float:
-
-    # Convert actual and predicted to numpy
-    # array data type if not already
-    if not all([isinstance(actual, np.ndarray), isinstance(predicted, np.ndarray)]):
-        actual, predicted = np.array(actual), np.array(predicted)
-
-    return np.mean(
-        np.abs(predicted - actual) / ((np.abs(predicted) + np.abs(actual)) / 2)
-    )
-
 
 def metrics_factory(metrics_type: str) -> MLMetrics:
     metrics = {
@@ -47,7 +34,7 @@ class RegressionMetrics:
         median_absolute_error,
         mean_squared_error,
         mean_absolute_percentage_error,
-        symmetric_mape,
+        # max_error
     ]
 
     def generate_metrics(

modules/ml-pipeline/src/pipeline/core/MLModels.py

@@ -25,7 +25,7 @@ def model_factory(model_type: str) -> MLModel:
     models = {
         "SKLearnLinearRegression": SKLearnLinearRegression(),
         "SKLearnSVMRegression": SKLearnSVMRegression(),
-        "AutogluonAutoML": AutogluonAutoML(),
+        "AutogluonAutoML": AutogluonAutoML()
         # ADD OTHER MODELS HERE
     }
 
@@ -149,9 +149,6 @@ class AutogluonAutoML:
         "time_limit",
         "presets",
         "excluded_model_types",
-        "infer_limit",
-        "infer_limit_batch_size",
-        "ag_args_ensemble",
     ]
 
     def load_model(self, path: Union[Path, str]) -> None:
@@ -206,9 +203,6 @@ class AutogluonAutoML:
             time_limit=model_hyperparameters["time_limit"],
             presets=model_hyperparameters["presets"],
             excluded_model_types=model_hyperparameters["excluded_model_types"],
-            infer_limit=model_hyperparameters["infer_limit"],
-            infer_limit_batch_size=model_hyperparameters["infer_limit_batch_size"],
-            ag_args_ensemble=model_hyperparameters["ag_args_ensemble"],
         )
 
     def predict(

modules/ml-pipeline/src/pipeline/dvc.lock

@@ -1,46 +1,26 @@
 schema: '2.0'
 stages:
-  startup_cleanup:
-    cmd: python 0_startup_cleanup.py
-    deps:
-    - path: 0_startup_cleanup.py
-      hash: md5
-      md5: b1b12f6b6393fbf8b83d23684df0a3d4
-      size: 1220
-    params:
-      configs/settings.yaml:
-        default.startup_cleanup.artefacts: ./data
-        default.startup_cleanup.metrics: ./metrics
   prepare_data:
     cmd: python 1_prepare_data.py
     deps:
     - path: 1_prepare_data.py
       hash: md5
-      md5: 11a3b8bfdfe199ab7ecc39ccc5652649
-      size: 4298
+      md5: c9f030df733e318b80d1fa91b7732f79
+      size: 5132
     params:
       configs/settings.yaml:
         default.feature_processor.feature_processor_config.drop_columns:
-        - heat_demand_change
-        - carbon_change
-        - rdsap_change
-        - heat_demand_ending
-        - carbon_ending
-        - days_to_starting
-        - days_to_ending
-        - number_habitable_rooms_starting
-        - number_habitable_rooms_ending
-        - number_heated_rooms_starting
-        - number_heated_rooms_ending
-        - number_habitable_rooms
-        - number_heated_rooms
+        - HEAT_DEMAND_CHANGE
+        - CARBON_CHANGE
+        - RDSAP_CHANGE
+        - HEAT_DEMAND_ENDING
+        - CARBON_ENDING
         default.feature_processor.feature_processor_config.retain_features:
         default.feature_processor.feature_processor_config.subsample_amount:
         default.feature_processor.feature_processor_config.subsample_seed: 0
-        default.feature_processor.feature_processor_config.target: sap_ending
+        default.feature_processor.feature_processor_config.target: SAP_ENDING
         default.feature_processor.feature_processor_type: dataframe
-        default.prepare_data.data_filepath:
-          s3://retrofit-data-dev/sap_change_model/2024-05-28-19-08-25/dataset_rooms.parquet
+        default.prepare_data.data_filepath: s3://retrofit-data-dev/sap_change_model/dataset.parquet
         default.prepare_data.input_dataclient_type: aws-s3
         default.prepare_data.output_dataclient_type: local
         default.prepare_data.output_test_filepath: ./data/prepared_data/test.parquet
@@ -49,20 +29,20 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 45056059
+      md5: 9ce5c45722da7fc40491b5a4d00daf9e.dir
+      size: 33881619
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
     deps:
     - path: 2_build_model.py
       hash: md5
-      md5: 7231450b78920b0c5e7c6bada496b24a
-      size: 4820
+      md5: 84699d208874c52accaff61c6af9bb0a
+      size: 5359
     - path: data/prepared_data
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 45056059
+      md5: 9ce5c45722da7fc40491b5a4d00daf9e.dir
+      size: 33881619
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -71,7 +51,6 @@ stages:
             model_type: AutogluonAutoML
             model_save_filepath: ./data/model/optimised/
             fit_metrics_filepath: ./metrics/fit_metrics.json
-            fit_predictions_filepath: ./data/fit_predictions/predictions.parquet
             SKLearnLinearRegression:
             SKLearnSVMRegression:
               kernel: linear
@@ -79,49 +58,37 @@ stages:
               output_filepath: ./data/model/allmodels/
               problem_type: regression
               eval_metric: mean_squared_error
-              time_limit: 1800
+              time_limit: 4000
               presets: medium_quality
               excluded_model_types:
-              - RF
-              - CAT
-              - NN_TORCH
               - KNN
-              - XT
-              infer_limit: 0.05
-              infer_limit_batch_size: 10000
-              ag_args_ensemble:
-                num_folds_parallel: 2
+              - RF
     outs:
-    - path: data/fit_predictions/
-      hash: md5
-      md5: d9c9afc05e8780db47c0548b19bf7d19.dir
-      size: 3349989
-      nfiles: 1
     - path: data/model/
       hash: md5
-      md5: 13c3100e1486c27a83a8a47491077842.dir
-      size: 773523079
-      nfiles: 36
+      md5: 7bb5156243b4db39349e80a01ffecde4.dir
+      size: 473398662
+      nfiles: 27
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 2ff70a2a45813e1bcdf2ea3aa8e07d4a
-      size: 224
+      md5: 2bb16ac67de8778fbc08171d562b34d5
+      size: 184
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
     - path: 3_generate_predictions.py
       hash: md5
-      md5: 0a70ad4dfe99414a75d1261c75a177b9
-      size: 2464
+      md5: 5ef2856a5a977304f1ec01f9b4205262
+      size: 3028
     - path: data/model
       hash: md5
-      md5: 13c3100e1486c27a83a8a47491077842.dir
-      size: 773523079
-      nfiles: 36
+      md5: 7bb5156243b4db39349e80a01ffecde4.dir
+      size: 473398662
+      nfiles: 27
     - path: data/prepared_data
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 45056059
+      md5: 9ce5c45722da7fc40491b5a4d00daf9e.dir
+      size: 33881619
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -133,25 +100,25 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
-      size: 463197
+      md5: 0bb3cf991906953def81c8204cdcfaf0.dir
+      size: 374532
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
     deps:
     - path: 4_generate_metrics.py
       hash: md5
-      md5: 4fedb86d89d528f0a6597934ba3890a0
-      size: 3484
+      md5: 2c9fb78955a8c19cff0a098976f81d1b
+      size: 4487
     - path: data/predictions
       hash: md5
-      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
-      size: 463197
+      md5: 0bb3cf991906953def81c8204cdcfaf0.dir
+      size: 374532
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 45056059
+      md5: 9ce5c45722da7fc40491b5a4d00daf9e.dir
+      size: 33881619
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -161,30 +128,16 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 3e08df02fd5c5d094bcf936e1338d596
-      size: 223
-  generate_scenerio_metrics:
-    cmd: python 5_generate_scenarios.py
+      md5: 2e13ae67759a64261d03224f1c0d4bf4
+      size: 185
+  startup_cleanup:
+    cmd: python 0_startup_cleanup.py
     deps:
-    - path: 5_generate_scenarios.py
+    - path: 0_startup_cleanup.py
       hash: md5
-      md5: 40506749fefd926d47c60ff5b16db307
-      size: 5337
+      md5: fbb7e3b1b98b517c870f3e1df3e7f695
+      size: 1676
     params:
-      configs/scenarios.yaml:
-        default.scenarios:
-          input_dataclient_type: aws-s3
-          output_dataclient_type: local
-          scenario_data_filepaths:
-          - s3://retrofit-data-dev/scenario_data/28-05-2024-19-22-41/recommendations_scoring_data.parquet
-          comparison_output_filepath: ./metrics/scenario_table.md
-          metrics_output_filepath: ./metrics/scenario_metrics.md
-    outs:
-    - path: metrics/scenario_metrics.md
-      hash: md5
-      md5: fa4d6d7bbd7818613800da5f8f37ea96
-      size: 363
-    - path: metrics/scenario_table.md
-      hash: md5
-      md5: d6baf100a1623cc2467c2f8221d314c9
-      size: 2133
+      configs/settings.yaml:
+        default.startup_cleanup.artefacts: ./data
+        default.startup_cleanup.metrics: ./metrics

modules/ml-pipeline/src/pipeline/dvc.yaml

@@ -38,7 +38,6 @@ stages:
     - configs/build_model.yaml:
     outs:
     - data/model/
-    - data/fit_predictions/
     - metrics/fit_metrics.json
     always_changed: true
   generate_predictions:
@@ -71,17 +70,6 @@ stages:
     outs:
     - metrics/metrics.json
     always_changed: true
-  generate_scenerio_metrics:
-    cmd: python 5_generate_scenarios.py
-    deps:
-    - 5_generate_scenarios.py
-    params:
-    - configs/scenarios.yaml:
-      - default.scenarios
-    outs:
-    - metrics/scenario_table.md
-    - metrics/scenario_metrics.md
-    always_changed: true
 metrics:
   - metrics/metrics.json
   - metrics/fit_metrics.json

modules/ml-pipeline/src/pipeline/eda.py

@@ -190,35 +190,28 @@ prediction_analysis_params = settings.prediction_analysis
 model = model_factory(build_model_params["model_type"])
 model.load_model(build_model_params["model_save_filepath"])
 dataclient_type = prediction_analysis_params["dataclient_type"]
-# dataclient_type = 'aws-s3'
-# dataclient = dataclient_factory(
-#     dataclient_type=dataclient_type,
-#     dataclient_config=client_params[dataclient_type],
-# )
-# data = dataclient.load_data("s3://retrofit-data-dev/sap_change_model/dataset.parquet")
+dataclient = dataclient_factory(
+    dataclient_type=dataclient_type,
+    dataclient_config=client_params[dataclient_type],
+)
 
 target = feature_process_params["feature_processor_config"]["target"]
 predictions_column_name = generate_predictions_params["predictions_column_name"]
 output_test_filepath = prepare_data_params["output_test_filepath"]
 predictions_output_filepath = generate_predictions_params["predictions_output_filepath"]
 
-# score_data = dataclient.load_data("s3://retrofit-data-dev/carbon_change_predictions/51/2023-11-28T21:01:21.869339.parquet")
-
-
-local_dataclient = dataclient_factory(
-    dataclient_type="local",
-    dataclient_config=client_params["local"],
-)
-test_df = local_dataclient.load_data(output_test_filepath)
-predictions = local_dataclient.load_data(predictions_output_filepath)
+test_df = dataclient.load_data(output_test_filepath)
+predictions = dataclient.load_data(predictions_output_filepath)
 mix_df = pd.concat([test_df.copy(), predictions], axis=1)
 mix_df["residual"] = abs(mix_df[predictions_column_name] - mix_df[target])
 mix_df = mix_df.sort_values("residual", ascending=False)
 
-cosine_similarity_df = mix_df[mix_df.columns.difference(["predictions", "residual"])]
+cosine_similarity_df = mix_df[
+    mix_df.columns.difference(["predictions", "residual", "SAP_ENDING"])
+]
 from sklearn.metrics.pairwise import cosine_similarity
 
-row_index = 0
+row_index = 58199
 
 from sklearn.preprocessing import LabelEncoder
 
@@ -232,17 +225,7 @@ feature_vector = cosine_similarity_df.loc[[row_index]]
 
 cosine_similarity_df["cosine"] = cosine_similarity(cosine_similarity_df, feature_vector)
 similar_index = (
-    cosine_similarity_df.sort_values("cosine", ascending=False).head(15).index
+    cosine_similarity_df.sort_values("cosine", ascending=False).head(5).index
 )
 
 check_df = mix_df.loc[similar_index]
-
-columns_to_check = [
-    "LOW_ENERGY_LIGHTING_ENDING",
-    "walls_thermal_transmittance_ENDING",
-    "floor_thermal_transmittance_ENDING",
-    "roof_thermal_transmittance_ENDING",
-    "roof_insulation_thickness_ENDING",
-]
-
-cosine_similarity_df = mix_df[columns_to_check]

modules/ml-pipeline/src/pipeline/generate_predictions.py

@@ -14,23 +14,28 @@ def generate_predictions(
     test_data_filepath: str,
     predictions_output_filepath: str,
     predictions_column_name: str,
-    identifier_column: str = "id",
 ):
     """
     For a given model, we generate prediction and evaluate this against the true target
     """
 
+    logger.info("-------------------------")
     logger.info("--- Loading test data ---")
+    logger.info("-------------------------")
 
     test_data = input_dataclient.load_data(
         location=test_data_filepath, load_config=None
     )
 
+    logger.info("---------------------")
     logger.info("--- Loading model ---")
+    logger.info("---------------------")
 
     model.load_model(model_filepath)
 
+    logger.info("------------------------------")
     logger.info("--- Generating predictions ---")
+    logger.info("------------------------------")
 
     prediction_data = (
         test_data.drop(columns=target) if target in test_data.columns else test_data
@@ -40,17 +45,13 @@ def generate_predictions(
         data=prediction_data, post_prediction_logic=post_prediction_logic
     )
 
+    logger.info("--------------------------")
     logger.info("--- Saving predictions ---")
+    logger.info("--------------------------")
 
     predictions_df = pd.DataFrame(predictions)
     predictions_df.columns = [predictions_column_name]
 
-    output_df = (
-        pd.concat([test_data[identifier_column], predictions_df], axis=1)
-        if identifier_column in test_data.columns
-        else predictions_df
-    )
-
     output_dataclient.save_data(
-        obj=output_df, location=predictions_output_filepath, save_config=None
+        obj=predictions_df, location=predictions_output_filepath, save_config=None
     )

modules/ml-pipeline/src/pipeline/metrics/.gitignore

@@ -1,4 +1,2 @@
 /fit_metrics.json
 /metrics.json
-/scenario_table.md
-/scenario_metrics.md

modules/ml-pipeline/src/pipeline/requirements/predictions/requirements-dev.txt

@@ -1,7 +1,7 @@
 joblib==1.3.2
 boto3==1.28.17
-pandas==2.1.4
-autogluon.tabular[all]==1.0.0
-dynaconf==3.2.1
+pandas==1.5.3
+autogluon==0.8.2
+dynaconf==3.2.0
 pyarrow==13.0.0
 pre-commit==3.3.3

modules/ml-pipeline/src/pipeline/requirements/predictions/requirements.txt

@@ -1,7 +1,7 @@
 joblib==1.3.2
 boto3==1.28.17
-pandas==2.1.4
-autogluon.tabular[all]==1.0.0
-dynaconf==3.2.1
+pandas==1.5.3
+autogluon==0.8.2
+dynaconf==3.2.0
 pyarrow==13.0.0
 PyYAML==6.0.1

modules/ml-pipeline/src/pipeline/requirements/training/requirements-dev.txt

@@ -1,10 +1,9 @@
 joblib==1.3.2
 boto3==1.28.17
-pandas==2.1.4
-autogluon.tabular[all]==1.0.0
-ray==2.6.3
-dynaconf==3.2.1
-alibi==0.9.5
+pandas==1.5.3
+autogluon==0.8.2
+dynaconf==3.2.0
+alibi==0.9.4
 shap==0.42.1
 pyarrow==13.0.0
 pre-commit==3.3.3

modules/ml-pipeline/src/pipeline/requirements/training/requirements.txt

@@ -1,4 +1,4 @@
 boto3==1.28.41
-pandas==2.1.4
-autogluon.tabular[all]==1.0.0
-dynaconf==3.2.1
+pandas==1.5.3
+autogluon==0.8.2
+dynaconf==3.2.0

modules/ml-pipeline/src/pipeline/requirements/version_control/requirements.txt

@@ -1,4 +1,4 @@
-dvc==3.51.0
-dvc-s3==3.2.0
-gto==1.7.1
-pyOpenSSL==23.3.0
+dvc==3.18.0
+dvc-s3==2.23.0
+gto==1.0.4
+pyOpenSSL==23.2.0