corrected model

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

@@ -34,7 +34,7 @@ default:
       subsample_seed: 0
       target: sap_ending
       identifier_columns: ["uprn"]
-      drop_columns: ["heat_demand_change", "carbon_change", "rdsap_change", "heat_demand_change", "carbon_ending"]
+      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
 

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

@@ -13,7 +13,7 @@ stages:
         - heat_demand_change
         - carbon_change
         - rdsap_change
-        - heat_demand_change
+        - heat_demand_ending
         - carbon_ending
         default.feature_processor.feature_processor_config.retain_features:
         default.feature_processor.feature_processor_config.subsample_amount:
@@ -29,8 +29,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 3d1f4d54c7b520531e4f5ff5f33e34d8.dir
-      size: 40122363
+      md5: 5d29397fcafe6b3dc4d51ffaf1e55239.dir
+      size: 39303409
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -41,8 +41,8 @@ stages:
       size: 4149
     - path: data/prepared_data
       hash: md5
-      md5: 3d1f4d54c7b520531e4f5ff5f33e34d8.dir
-      size: 40122363
+      md5: 5d29397fcafe6b3dc4d51ffaf1e55239.dir
+      size: 39303409
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -68,13 +68,13 @@ stages:
     outs:
     - path: data/model/
       hash: md5
-      md5: 6a737d44dae68be2e75d6edb7f04f3ca.dir
-      size: 334981921
+      md5: 6265dafedf579905c31c676e81c2a9c7.dir
+      size: 344212462
       nfiles: 24
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 89ba30b943c911e24b13b4370db12d18
-      size: 225
+      md5: 5cd6b92af1b1df753e20e9ea33629c4d
+      size: 224
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -84,13 +84,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: 6a737d44dae68be2e75d6edb7f04f3ca.dir
-      size: 334981921
+      md5: 6265dafedf579905c31c676e81c2a9c7.dir
+      size: 344212462
       nfiles: 24
     - path: data/prepared_data
       hash: md5
-      md5: 3d1f4d54c7b520531e4f5ff5f33e34d8.dir
-      size: 40122363
+      md5: 5d29397fcafe6b3dc4d51ffaf1e55239.dir
+      size: 39303409
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -102,8 +102,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: c9a0ad3ef06f23d5d507bbec0ba86e98.dir
-      size: 362994
+      md5: b130faf5117b06897b2deed97f5868ee.dir
+      size: 367038
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -114,13 +114,13 @@ stages:
       size: 3484
     - path: data/predictions
       hash: md5
-      md5: c9a0ad3ef06f23d5d507bbec0ba86e98.dir
-      size: 362994
+      md5: b130faf5117b06897b2deed97f5868ee.dir
+      size: 367038
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 3d1f4d54c7b520531e4f5ff5f33e34d8.dir
-      size: 40122363
+      md5: 5d29397fcafe6b3dc4d51ffaf1e55239.dir
+      size: 39303409
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -130,8 +130,8 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: fa40071006901c4335b5dbd567c9d9b3
-      size: 226
+      md5: 3900cc1697d6d7308728b3d5b3025f85
+      size: 224
   startup_cleanup:
     cmd: python 0_startup_cleanup.py
     deps:

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=dataclient_type,
-    dataclient_config=client_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")
 
 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)
-predictions = dataclient.load_data(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)
 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(["UPRN", "predictions", "residual", "SAP_ENDING"])
-]
+cosine_similarity_df = mix_df[mix_df.columns.difference(["predictions", "residual"])]
 from sklearn.metrics.pairwise import cosine_similarity
 
-row_index = 20695
+row_index = 0
 
 from sklearn.preprocessing import LabelEncoder
 
@@ -224,8 +231,18 @@ cosine_similarity_df[object_columns.columns] = cosine_similarity_df[
 feature_vector = cosine_similarity_df.loc[[row_index]]
 
 cosine_similarity_df["cosine"] = cosine_similarity(cosine_similarity_df, feature_vector)
-
-similar_df = cosine_similarity_df.sort_values("cosine", ascending=False).head(5)
-similar_index = similar_df.index
+similar_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]