Merge pull request #96 from Hestia-Homes/carbon-dev-model

Carbon dev model

.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

@@ -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: |

.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 +8,25 @@
         "active": true
     },
     "sap": {
-        "version": "v0.14.0",
+        "version": "v0.4.0",
         "stage": {
-            "dev": "v0.14.0"
+            "dev": "v0.4.0"
         },
         "registered": true,
         "active": true
     },
     "heat": {
-        "version": "v0.5.0",
+        "version": "v0.3.0",
         "stage": {
-            "dev": "v0.5.0"
+            "dev": "v0.3.0"
         },
         "registered": true,
         "active": true
     },
     "carbon": {
-        "version": "v0.5.0",
+        "version": "v0.3.0",
         "stage": {
-            "dev": "v0.5.0"
+            "dev": "v0.3.0"
         },
         "registered": true,
         "active": true

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

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/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/README.md

@@ -1,3 +1,3 @@
-# The generic reproducible ML-pipeline
+# The generic reproducible ML-pipeline!
 
 Pipeline required to build a model to produce an output, that gets hashed via DVC

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

@@ -33,6 +33,7 @@ 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(f"--- Initiate MLModel ---")
 
 model = model_factory(build_model_params["model_type"])

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

@@ -14,9 +14,8 @@ 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']
+      excluded_model_types: ['RF', 'FASTAI', 'CAT', 'NN_TORCH', 'KNN', 'XT']
       infer_limit: 0.05
       infer_limit_batch_size: 10000
-      ag_args_ensemble: {'num_folds_parallel': 2}

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

@@ -18,30 +18,44 @@ def remove_starting_columns(df):
     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")
+def keep_negative_heat_change(df):
+    df = df[df["heat_demand_change"] < 0]
     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)
+def keep_non_negative_carbon_ending(df):
+    df = df[df["carbon_ending"] > 0]
     return df
 
 
-def keep_flats(df):
-    df = df[df["property_type"] == "Flat"]
+def keep_negative_carbon_change(df):
+    df = df[df["carbon_change"] < 0]
     return df
 
 
-def keep_non_zero_rdsap(df):
-    df = df[df["rdsap_change"] != 0]
+# TODO: Move to ETL pipeline
+def remove_unreasonable_habitable_rooms(df):
+    """
+    Assumption is that proportion of floor area to habitable rooms should be at least 6.5m2
+    """
+    minimum_room_size_index = (
+        df["total_floor_area_ending"] / df["number_habitable_rooms"] >= 6.5
+    )
+    df = df[minimum_room_size_index]
+    return df
+
+
+def remove_top_1_percent_heat_demand(df):
+    # threshold_value = df.describe(percentiles=[0.99])['HEAT_DEMAND_STARTING']['99%']
+    threshold_value = 860
+    df = df[df["heat_demand_starting"] < threshold_value]
+    return df
+
+
+def remove_top_1_percent_carbon(df):
+    # threshold_value = df.describe(percentiles=[0.99])['CARBON_STARTING']['99%']
+    threshold_value = 18
+    df = df[df["carbon_starting"] < threshold_value]
     return df
 
 
@@ -54,10 +68,12 @@ 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_unreasonable_habitable_rooms": remove_unreasonable_habitable_rooms,
+    "keep_negative_heat_change": keep_negative_heat_change,
+    "keep_negative_carbon_change": keep_negative_carbon_change,
+    "remove_top_1_percent_heat_demand": remove_top_1_percent_heat_demand,
+    "remove_top_1_percent_carbon": remove_top_1_percent_carbon,
+    "keep_non_negative_carbon_ending": keep_non_negative_carbon_ending
     # "remove_starting_columns": remove_starting_columns
     # "keep_ENDING_COLUMNS": keep_ending_columns
 }

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

@@ -5,19 +5,18 @@ 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,
 ) -> 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"]
-    )
-    predictions_df.loc[replace_index, "predictions"] = (
-        predictions_df.loc[replace_index, "sap_starting"] + minimum_value
-    )
+    replace_index = predictions_df["predictions"] > predictions_df["carbon_starting"]
+    predictions_df.loc[replace_index, "predictions"] = predictions_df.loc[
+        replace_index, "carbon_starting"
+    ]
 
     predictions_new = predictions_df["predictions"]
     predictions_new.name = series_name

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

@@ -18,11 +18,12 @@ 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
-    train_proportion: 0.9
+    # 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
+    data_filepath: s3://retrofit-datalake-dev/dataset_with0perm_all.parquet
+    train_proportion: 1
     output_train_filepath: ./data/prepared_data/train.parquet
     output_test_filepath: ./data/prepared_data/test.parquet
 
@@ -31,37 +32,11 @@ default:
     feature_processor_config:
       subsample_amount: null
       subsample_seed: 0
-      target: sap_ending
+      target: carbon_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']
+      drop_columns: ["heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "sap_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

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

@@ -245,8 +245,7 @@ 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 +294,3 @@ 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/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
     }
 
@@ -151,7 +151,6 @@ class AutogluonAutoML:
         "excluded_model_types",
         "infer_limit",
         "infer_limit_batch_size",
-        "ag_args_ensemble",
     ]
 
     def load_model(self, path: Union[Path, str]) -> None:
@@ -208,7 +207,6 @@ class AutogluonAutoML:
             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

@@ -1,16 +1,5 @@
 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:
@@ -25,44 +14,35 @@ stages:
         - 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
+        - sap_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: carbon_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-datalake-dev/dataset_with0perm_all.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
         default.prepare_data.output_train_filepath: ./data/prepared_data/train.parquet
-        default.prepare_data.train_proportion: 0.9
+        default.prepare_data.train_proportion: 1
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 45056059
+      md5: 44737880f5437e23143479a7818a3136.dir
+      size: 36064622
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
     deps:
     - path: 2_build_model.py
       hash: md5
-      md5: 7231450b78920b0c5e7c6bada496b24a
-      size: 4820
+      md5: 090bfb7dbaff39f45784b7fe332a9b8e
+      size: 4819
     - path: data/prepared_data
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 45056059
+      md5: 44737880f5437e23143479a7818a3136.dir
+      size: 36064622
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -79,33 +59,32 @@ 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
+              - FASTAI
               - CAT
               - NN_TORCH
               - KNN
               - XT
               infer_limit: 0.05
               infer_limit_batch_size: 10000
-              ag_args_ensemble:
-                num_folds_parallel: 2
     outs:
     - path: data/fit_predictions/
       hash: md5
-      md5: d9c9afc05e8780db47c0548b19bf7d19.dir
-      size: 3349989
+      md5: 7b74ae1174ae2c7fab03ee0ce0a8ae71.dir
+      size: 3877514
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: 13c3100e1486c27a83a8a47491077842.dir
-      size: 773523079
-      nfiles: 36
+      md5: d2ebaa73a894387f85083c49e58637bc.dir
+      size: 798349514
+      nfiles: 32
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 2ff70a2a45813e1bcdf2ea3aa8e07d4a
-      size: 224
+      md5: 51c9c678bbd19bc9f7e16f0bf5df3fef
+      size: 229
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -115,13 +94,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: 13c3100e1486c27a83a8a47491077842.dir
-      size: 773523079
-      nfiles: 36
+      md5: d2ebaa73a894387f85083c49e58637bc.dir
+      size: 798349514
+      nfiles: 32
     - path: data/prepared_data
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 45056059
+      md5: 44737880f5437e23143479a7818a3136.dir
+      size: 36064622
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -133,25 +112,25 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
-      size: 463197
+      md5: ac0a698f14fb9002b337b1b163997333.dir
+      size: 638033
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
     deps:
     - path: 4_generate_metrics.py
       hash: md5
-      md5: 4fedb86d89d528f0a6597934ba3890a0
-      size: 3484
+      md5: d09a80dd55f1f69e2a832b1991b3c406
+      size: 3485
     - path: data/predictions
       hash: md5
-      md5: 5d07bcebf3160a72bb18dfd79106e85c.dir
-      size: 463197
+      md5: ac0a698f14fb9002b337b1b163997333.dir
+      size: 638033
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 80c9e138146a1d96b9d16091c207e2e8.dir
-      size: 45056059
+      md5: 44737880f5437e23143479a7818a3136.dir
+      size: 36064622
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -161,30 +140,16 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 3e08df02fd5c5d094bcf936e1338d596
-      size: 223
-  generate_scenerio_metrics:
-    cmd: python 5_generate_scenarios.py
+      md5: 47aa4601e71a93163d2cc1b85d0eda91
+      size: 228
+  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: b1b12f6b6393fbf8b83d23684df0a3d4
+      size: 1220
     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

@@ -71,17 +71,6 @@ 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/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
+dvc==3.36.0
+dvc-s3==3.0.1
+gto==1.6.1
 pyOpenSSL==23.3.0