Run YAML load on all subclasses (#1518)

data/data-pipeline/data_pipeline/etl/base.py

@@ -98,10 +98,13 @@ class ExtractTransformLoad:
     # It is used on the "load" base class method
     output_df: pd.DataFrame = None
 
+    def __init_subclass__(cls) -> None:
+        cls.DATASET_CONFIG = cls.yaml_config_load()
+
     @classmethod
     def yaml_config_load(cls) -> dict:
         """Generate config dictionary and set instance variables from YAML dataset."""
-
+        if cls.NAME is not None:
             # check if the class instance has score YAML definitions
             datasets_config = load_yaml_dict_from_file(
                 cls.DATASET_CONFIG / "datasets.yml",

data/data-pipeline/data_pipeline/etl/score/config/datasets.yml

@@ -99,4 +99,18 @@ datasets:
         include_in_csv: true
         include_in_excel: true
         column_position: 1
+  - long_name: "Exaple ETL"
+    short_name: "Example"
+    module_name: "example_dataset"
+    description: "An example dataset for documentation"
+    input_geoid_tract_field_name: "GEOID10_TRACT"
+    load_fields:
+      - short_name: "EXAMPLE_FIELD"
+        df_field_name: "Input Field 1"
+        long_name: "Example Field 1" 
+        field_type: float
+        include_in_tiles: true
+        include_in_csv: true
+        include_in_excel: true
+        column_position: 1
 

data/data-pipeline/data_pipeline/etl/sources/child_opportunity_index/etl.py

@@ -38,7 +38,6 @@ class ChildOpportunityIndex(ExtractTransformLoad):
     READING_FIELD: str
 
     def __init__(self):
-        self.DATASET_CONFIG = super().yaml_config_load()
         self.SOURCE_URL = (
             "https://data.diversitydatakids.org/datastore/zip/f16fff12-b1e5-4f60-85d3-"
             "3a0ededa30a0?format=csv"

data/data-pipeline/data_pipeline/etl/sources/doe_energy_burden/etl.py

@@ -19,8 +19,6 @@ class DOEEnergyBurden(ExtractTransformLoad):
     REVISED_ENERGY_BURDEN_FIELD_NAME: str
 
     def __init__(self):
-        self.DATASET_CONFIG = super().yaml_config_load()
-
         self.OUTPUT_PATH: Path = (
             self.DATA_PATH / "dataset" / "doe_energy_burden"
         )

data/data-pipeline/data_pipeline/etl/sources/national_risk_index/etl.py

@@ -26,9 +26,6 @@ class NationalRiskIndexETL(ExtractTransformLoad):
     AGRIVALUE_LOWER_BOUND = 408000
 
     def __init__(self):
-        # load YAML config
-        self.DATASET_CONFIG = super().yaml_config_load()
-
         # define the full path for the input CSV file
         self.INPUT_CSV = self.get_tmp_path() / "NRI_Table_CensusTracts.csv"