Merge pull request #107 from Hestia-Homes/carbon-dev-model

Carbon dev model

deployment/.dockerignore

@@ -0,0 +1,4 @@
+modules/ml-pipeline/src/pipeline/data/predictions*
+modules/ml-pipeline/src/pipeline/data/prepared_data*
+modules/ml-pipeline/src/pipeline/data/model/allmodels*
+modules/ml-pipeline/src/pipeline/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
+RUN yum install -y gcc python3-devel gcc-c++
 
 # Install python packages
 COPY modules/ml-pipeline/src/pipeline/requirements/predictions/requirements.txt ./requirements.txt

modules/ml-pipeline/.dvc/.gitignore

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

modules/ml-pipeline/.dvc/config

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

modules/ml-pipeline/.dvcignore

@@ -1,3 +0,0 @@
-# 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

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

modules/ml-pipeline/src/.dockerignore

@@ -0,0 +1,4 @@
+pipeline/data/predictions*
+pipeline/data/prepared_data/train.parquet*
+pipeline/data/model/allmodels*
+pipeline/metrics*

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

@@ -1,3 +1,4 @@
 
 # Ignore dynaconf secret files
 .secrets.*
+example.py

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

@@ -33,7 +33,6 @@ 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/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: [0, 10, 20] # index of an example datapoint
+    row_index: [20695, 50243, 7653] # index of an example datapoint

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

@@ -19,3 +19,4 @@ default:
       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

@@ -73,7 +73,7 @@ business_logic = {
     "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
+    "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

@@ -1,6 +1,7 @@
 """
 After predictions, we may want to apply some post processing to the predictions
 """
+
 import pandas as pd
 
 
@@ -11,6 +12,7 @@ def clip_predictions_to_minimum_value(
 
     series_name = predictions.name
     predictions.name = "predictions"
+    predictions = predictions.astype(data["carbon_starting"].dtype)
     predictions_df = pd.concat([data, predictions], axis=1)
     # We expect all prediction to be atleast one point improvement
     replace_index = predictions_df["predictions"] > predictions_df["carbon_starting"]

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

@@ -18,12 +18,8 @@ default:
   prepare_data:
     input_dataclient_type: aws-s3
     output_dataclient_type: local
-    # data_filepath: s3://retrofit-data-dev/sap_change_model/dataset_with_differencing.parquet
+    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/floor_area_clean_test.parquet
+    train_proportion: 0.9
-    # 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
 
@@ -34,7 +30,11 @@ default:
       subsample_seed: 0
       target: carbon_ending
       identifier_columns: ["uprn"]
-      drop_columns: ["heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "sap_ending"]
+      # drop_columns: ["heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "sap_ending"]
+      drop_columns: [
+        "heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_ending", "sap_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']
       # retain_features: ["SAP_STARTING", "TOTAL_FLOOR_AREA_DIFF"]
       retain_features: null
 

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

@@ -1,5 +1,16 @@
 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:
@@ -15,34 +26,43 @@ stages:
         - rdsap_change
         - heat_demand_ending
         - sap_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
         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: carbon_ending
         default.feature_processor.feature_processor_type: dataframe
-        default.prepare_data.data_filepath: s3://retrofit-datalake-dev/dataset_with0perm_all.parquet
+        default.prepare_data.data_filepath:
+          s3://retrofit-data-dev/sap_change_model/2024-03-22-18-56-53/dataset_rooms.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: 1
+        default.prepare_data.train_proportion: 0.9
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 44737880f5437e23143479a7818a3136.dir
+      md5: 824541f44e6538d2ef10e9d754c79743.dir
-      size: 36064622
+      size: 36691842
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
     deps:
     - path: 2_build_model.py
       hash: md5
-      md5: 090bfb7dbaff39f45784b7fe332a9b8e
+      md5: 7231450b78920b0c5e7c6bada496b24a
-      size: 4819
+      size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: 44737880f5437e23143479a7818a3136.dir
+      md5: 824541f44e6538d2ef10e9d754c79743.dir
-      size: 36064622
+      size: 36691842
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -70,21 +90,23 @@ stages:
               - 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: 7b74ae1174ae2c7fab03ee0ce0a8ae71.dir
+      md5: 5a3091120d3497fa00b994d91bc7e5eb.dir
-      size: 3877514
+      size: 3664806
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: d2ebaa73a894387f85083c49e58637bc.dir
+      md5: 074da8dcfa515b9f3d082b21c7d76616.dir
-      size: 798349514
+      size: 721558897
-      nfiles: 32
+      nfiles: 31
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 51c9c678bbd19bc9f7e16f0bf5df3fef
+      md5: 728a49dcef5a98182325df455f929a33
-      size: 229
+      size: 225
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -94,13 +116,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: d2ebaa73a894387f85083c49e58637bc.dir
+      md5: 074da8dcfa515b9f3d082b21c7d76616.dir
-      size: 798349514
+      size: 721558897
-      nfiles: 32
+      nfiles: 31
     - path: data/prepared_data
       hash: md5
-      md5: 44737880f5437e23143479a7818a3136.dir
+      md5: 824541f44e6538d2ef10e9d754c79743.dir
-      size: 36064622
+      size: 36691842
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -112,25 +134,25 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: ac0a698f14fb9002b337b1b163997333.dir
+      md5: 680f51234d214d4cab9e6a064c75fc5d.dir
-      size: 638033
+      size: 499546
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
     deps:
     - path: 4_generate_metrics.py
       hash: md5
-      md5: d09a80dd55f1f69e2a832b1991b3c406
+      md5: 4fedb86d89d528f0a6597934ba3890a0
-      size: 3485
+      size: 3484
     - path: data/predictions
       hash: md5
-      md5: ac0a698f14fb9002b337b1b163997333.dir
+      md5: 680f51234d214d4cab9e6a064c75fc5d.dir
-      size: 638033
+      size: 499546
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 44737880f5437e23143479a7818a3136.dir
+      md5: 824541f44e6538d2ef10e9d754c79743.dir
-      size: 36064622
+      size: 36691842
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -140,16 +162,5 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 47aa4601e71a93163d2cc1b85d0eda91
+      md5: 67b7ab30a4b0839d20bc6eb0c84e4dd1
-      size: 228
+      size: 226
-  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

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

@@ -190,28 +190,35 @@ 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 = dataclient_factory(
+# dataclient_type = 'aws-s3'
-    dataclient_type=dataclient_type,
+# dataclient = dataclient_factory(
-    dataclient_config=client_params[dataclient_type],
+#     dataclient_type=dataclient_type,
-)
+#     dataclient_config=client_params[dataclient_type],
+# )
+# data = dataclient.load_data("s3://retrofit-data-dev/sap_change_model/dataset.parquet")
 
 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"]
 
-test_df = dataclient.load_data(output_test_filepath)
+# score_data = dataclient.load_data("s3://retrofit-data-dev/carbon_change_predictions/51/2023-11-28T21:01:21.869339.parquet")
-predictions = dataclient.load_data(predictions_output_filepath)
+
+
+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)
 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[
+cosine_similarity_df = mix_df[mix_df.columns.difference(["predictions", "residual"])]
-    mix_df.columns.difference(["predictions", "residual", "SAP_ENDING"])
-]
 from sklearn.metrics.pairwise import cosine_similarity
 
-row_index = 58199
+row_index = 0
 
 from sklearn.preprocessing import LabelEncoder
 
@@ -225,7 +232,17 @@ 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(5).index
+    cosine_similarity_df.sort_values("cosine", ascending=False).head(15).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/requirements/predictions/requirements-dev.txt

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

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

@@ -1,9 +1,10 @@
 joblib==1.3.2
 boto3==1.28.17
-pandas==1.5.3
+pandas==2.1.4
-autogluon==0.8.2
+autogluon==1.0.0
-dynaconf==3.2.0
+ray==2.6.3
-alibi==0.9.4
+dynaconf==3.2.1
+alibi==0.9.5
 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==1.5.3
+pandas==2.1.4
-autogluon==0.8.2
+autogluon==1.0.0
-dynaconf==3.2.0
+dynaconf==3.2.1