add restriction to datast

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

@@ -23,6 +23,37 @@ def keep_negative_heat_change(df):
     return df
 
 
+def keep_negative_carbon_change(df):
+    df = df[df["CARBON_CHANGE"] < 0]
+    return df
+
+
+# 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
+
+
 # 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()
@@ -32,7 +63,11 @@ def keep_negative_heat_change(df):
 #     return df
 
 business_logic = {
-    "keep_negative_heat_change": keep_negative_heat_change
+    "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,
     # "remove_starting_columns": remove_starting_columns
     # "keep_ENDING_COLUMNS": keep_ending_columns
 }

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

@@ -29,8 +29,8 @@ stages:
     outs:
     - path: data/prepared_data/
       hash: md5
-      md5: 6f9c63363ad52a836524dbb6fae7a2ac.dir
-      size: 34480114
+      md5: f235f38714fefcf6e4927ae95ba912c3.dir
+      size: 30774760
       nfiles: 2
   build_model:
     cmd: python 2_build_model.py
@@ -41,8 +41,8 @@ stages:
       size: 4149
     - path: data/prepared_data
       hash: md5
-      md5: 6f9c63363ad52a836524dbb6fae7a2ac.dir
-      size: 34480114
+      md5: f235f38714fefcf6e4927ae95ba912c3.dir
+      size: 30774760
       nfiles: 2
     params:
       configs/build_model.yaml:
@@ -68,13 +68,13 @@ stages:
     outs:
     - path: data/model/
       hash: md5
-      md5: 452eba2d92233e81d321814aacefe5c2.dir
-      size: 323127043
+      md5: a868845999b46e0272dc27f5cb5bc618.dir
+      size: 310555147
       nfiles: 24
     - path: metrics/fit_metrics.json
       hash: md5
-      md5: 888124b56e0c5008a6423e290fc5cc71
-      size: 222
+      md5: 809f27735c77cbcb62866b96018eedea
+      size: 216
   generate_predictions:
     cmd: python 3_generate_predictions.py
     deps:
@@ -84,13 +84,13 @@ stages:
       size: 2464
     - path: data/model
       hash: md5
-      md5: 452eba2d92233e81d321814aacefe5c2.dir
-      size: 323127043
+      md5: a868845999b46e0272dc27f5cb5bc618.dir
+      size: 310555147
       nfiles: 24
     - path: data/prepared_data
       hash: md5
-      md5: 6f9c63363ad52a836524dbb6fae7a2ac.dir
-      size: 34480114
+      md5: f235f38714fefcf6e4927ae95ba912c3.dir
+      size: 30774760
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -102,8 +102,8 @@ stages:
     outs:
     - path: data/predictions/
       hash: md5
-      md5: f852550a0a51f0c2b120b0680c1a9b54.dir
-      size: 325890
+      md5: 2098fe82304751025e427f2cc241a2ff.dir
+      size: 295849
       nfiles: 1
   generate_metrics:
     cmd: python 4_generate_metrics.py
@@ -114,13 +114,13 @@ stages:
       size: 3448
     - path: data/predictions
       hash: md5
-      md5: f852550a0a51f0c2b120b0680c1a9b54.dir
-      size: 325890
+      md5: 2098fe82304751025e427f2cc241a2ff.dir
+      size: 295849
       nfiles: 1
     - path: data/prepared_data
       hash: md5
-      md5: 6f9c63363ad52a836524dbb6fae7a2ac.dir
-      size: 34480114
+      md5: f235f38714fefcf6e4927ae95ba912c3.dir
+      size: 30774760
       nfiles: 2
     params:
       configs/settings.yaml:
@@ -130,7 +130,7 @@ stages:
     outs:
     - path: metrics/metrics.json
       hash: md5
-      md5: ed3012943593fac4ac7ad9a5499ac18f
+      md5: aa671878e1bd8c6a8d4b5f9788c817c4
       size: 219
   startup_cleanup:
     cmd: python 0_startup_cleanup.py