Merge pull request #142 from Hestia-Homes/hotwaterkwh-dev-model

Hotwaterkwh dev model

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

@@ -160,7 +160,9 @@ def add_features_from_code(df):
 
     return df
 
-
+def add_estimate_annual_kwh(df):
+    df['estimate_annual_kwh'] = df['energy-consumption-current'] * df['total-floor-area']
+    return df
 
 # def keep_ending_columns(df):
 #     ending_column_index = [ col_name.endswith("_ENDING") for col_name in list(df.columns)]
@@ -172,7 +174,8 @@ def add_features_from_code(df):
 
 business_logic = {
     "add_features_from_code": add_features_from_code,
-    "remove_hotwaterkwh_bottom_percentile": remove_hotwaterkwh_bottom_percentile
+    "remove_hotwaterkwh_bottom_percentile": remove_hotwaterkwh_bottom_percentile,
+    "add_estimate_annual_kwh": add_estimate_annual_kwh
     # "keep_non_zero_rdsap": keep_non_zero_rdsap,
     # "keep_flats": keep_flats,
     # "remove_minimum_habitable_room_size": remove_minimum_habitable_room_size,

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

@@ -38,16 +38,13 @@ default:
         'hot-water-cost-current',
         'total-floor-area',
         'secondheat-description',
-        'environment-impact-current',
         'floor-description',
         'mainheat-energy-eff',
         'current-energy-efficiency',
-        'mainheat-env-eff',
         'walls-energy-eff',
         'roof-energy-eff',
         'property-type',
         'mainheat-description',
-        'hot-water-env-eff',
         'mechanical-ventilation',
         'floor-level',
         'built-form',
@@ -57,7 +54,6 @@ default:
         'energy-consumption-current',
         'construction-age-band',
         'hotwater-description',
-        # 'lodgement-datetime',
         'main-fuel',
         'hot-water-energy-eff',
         'co2-emiss-curr-per-floor-area',
@@ -67,37 +63,25 @@ default:
         'extension-count',
         'number-open-fireplaces',
         'number-heated-rooms',
-        # 'lodgement-date',
-        #  'number-habitable-rooms',
         'windows-description',
-        # 'local-authority',
         'photo-supply',
         'heat-loss-corridor',
-        # 'posttown',
-        #  'address',
         'flat-top-storey',
         'unheated-corridor-length',
         'fixed-lighting-outlets-count',
-        # 'inspection-date',
         'tenure',
-        # 'county',
-        # 'constituency-label',
         'multi-glaze-proportion',
         'solar-water-heating-flag',
-        #  'address2',
         'energy-tariff',
         'floor-height',
         'constituency',
-        # 'uprn-source',
         'transaction-type',
         'floor-energy-eff',
-        # 'postcode',
         'lodgement-month',
         'lighting-cost-current',
         'glazed-area',
-        #  'address1',
+        'main-heating-controls',
-        'floor-env-eff',
+        'estimate_annual_kwh',
-        'main-heating-controls'
       ]
 
   generate_predictions:

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

@@ -29,16 +29,13 @@ stages:
         - hot-water-cost-current
         - total-floor-area
         - secondheat-description
-        - environment-impact-current
         - floor-description
         - mainheat-energy-eff
         - current-energy-efficiency
-        - mainheat-env-eff
         - walls-energy-eff
         - roof-energy-eff
         - property-type
         - mainheat-description
-        - hot-water-env-eff
         - mechanical-ventilation
         - floor-level
         - built-form
@@ -74,8 +71,8 @@ stages:
         - lodgement-month
         - lighting-cost-current
         - glazed-area
-        - floor-env-eff
         - main-heating-controls
+        - estimate_annual_kwh
         default.feature_processor.feature_processor_config.subsample_amount:
         default.feature_processor.feature_processor_config.subsample_seed: 0
         default.feature_processor.feature_processor_config.target: hot_water_kwh
@@ -90,8 +87,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 295ac4fd05a1a3373401a7318b0b5186.dir
+      md5: 19abfc15e24cd8a869a0f3f087e09584.dir
-      size: 13131853
+      size: 13396685
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -102,8 +99,8 @@ stages:
       size: 4820
     - path: data/prepared_data
       hash: md5
-      md5: 295ac4fd05a1a3373401a7318b0b5186.dir
+      md5: 19abfc15e24cd8a869a0f3f087e09584.dir
-      size: 13131853
+      size: 13396685
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -135,18 +132,18 @@ stages:
     outs:
     - path: data/fit_predictions/
       hash: md5
-      md5: 3e48cec68f702bc822eed8fcb2c5c603.dir
+      md5: 0e2f1131b24eafa09ccbab91a36cac6c.dir
-      size: 1787931
+      size: 1787805
       nfiles: 1
     - path: data/model/
       hash: md5
-      md5: 37f7480141e920c68faacd39478a1a68.dir
+      md5: 77c0900cda64c1beaef6782d04fd712e.dir
-      size: 451364406
+      size: 518798187
-      nfiles: 35
+      nfiles: 36
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: e7a2a5efea57b1ddd1431b713d78bb11
+      md5: 0e03bb46cd03e9521095bf141ee92ed7
-      size: 219
+      size: 220
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -156,13 +153,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: 37f7480141e920c68faacd39478a1a68.dir
+      md5: 77c0900cda64c1beaef6782d04fd712e.dir
-      size: 451364406
+      size: 518798187
-      nfiles: 35
+      nfiles: 36
     - path: data/prepared_data
       hash: md5
-      md5: 295ac4fd05a1a3373401a7318b0b5186.dir
+      md5: 19abfc15e24cd8a869a0f3f087e09584.dir
-      size: 13131853
+      size: 13396685
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -174,8 +171,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: 9267a66c6fae4da5a589faab76fac14c.dir
+      md5: efc7b9dd9d40e42ad93e3e5acbeac92d.dir
-      size: 192482
+      size: 192502
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -186,13 +183,13 @@ stages:
       size: 3484
     - path: data/predictions
       hash: md5
-      md5: 9267a66c6fae4da5a589faab76fac14c.dir
+      md5: efc7b9dd9d40e42ad93e3e5acbeac92d.dir
-      size: 192482
+      size: 192502
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 295ac4fd05a1a3373401a7318b0b5186.dir
+      md5: 19abfc15e24cd8a869a0f3f087e09584.dir
-      size: 13131853
+      size: 13396685
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -202,8 +199,8 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: 3a08c29f028f5e3cb50fb8cd3608e2f4
+      md5: a8b7699dd2b171da5fead1fb04d954aa
-      size: 221
+      size: 220
   generate_scenerio_metrics:
     cmd: python 5_generate_scenarios.py
     deps: