From 37258dd67300b87b49d77dabbb08958cf248ccb0 Mon Sep 17 00:00:00 2001
From: Jorge Escobar <jorge.e.escobar@omb.eop.gov>
Date: Fri, 8 Apr 2022 14:41:15 -0400
Subject: [PATCH] passing tests

---
 data/data-pipeline/data_pipeline/etl/base.py   | 18 +++++++++---------
 .../etl/sources/national_risk_index/etl.py     |  1 +
 .../data_pipeline/tests/conftest.py            |  5 +++++
 .../tests/sources/example/test_etl.py          |  1 +
 4 files changed, 16 insertions(+), 9 deletions(-)

diff --git a/data/data-pipeline/data_pipeline/etl/base.py b/data/data-pipeline/data_pipeline/etl/base.py
index 4e4d9792..56c080bc 100644
--- a/data/data-pipeline/data_pipeline/etl/base.py
+++ b/data/data-pipeline/data_pipeline/etl/base.py
@@ -43,6 +43,7 @@ class ExtractTransformLoad:
     DATA_PATH: pathlib.Path = APP_ROOT / "data"
     TMP_PATH: pathlib.Path = DATA_PATH / "tmp"
     CONTENT_CONFIG: pathlib.Path = APP_ROOT / "content" / "config"
+    DATASET_CONFIG: pathlib.Path = APP_ROOT / "etl" / "score" / "config"
 
     # Parameters
     GEOID_FIELD_NAME: str = "GEOID10"
@@ -82,10 +83,11 @@ class ExtractTransformLoad:
 
     output_df: pd.DataFrame = None
 
-    def yaml_config_load(self):
+    @classmethod
+    def yaml_config_load(cls):
         # check if the class instance has score YAML definitions
         datasets_config = load_yaml_dict_from_file(
-            self.APP_ROOT / "etl" / "score" / "config" / "datasets.yml",
+            cls.DATASET_CONFIG / "datasets.yml",
             DatasetsConfig,
         )
 
@@ -94,21 +96,19 @@ class ExtractTransformLoad:
             dataset_config = next(
                 item
                 for item in datasets_config.get("datasets")
-                if item["module_name"] == "self.NAME"
+                if item["module_name"] == cls.NAME
             )
         except StopIteration:
             # Note: it'd be nice to log the name of the dataframe, but that's not accessible in this scope.
             logger.error(
-                f"Exception encountered while extracting dataset config for dataset {self.NAME}"
+                f"Exception encountered while extracting dataset config for dataset {cls.NAME}"
             )
             sys.exit()
 
         # set the fields
-        self.LAST_UPDATED_YEAR = dataset_config["last_updated_year"]
-        self.SOURCE_URL = dataset_config["source_url"]
-        self.INPUT_CSV = (
-            self.get_tmp_path() / dataset_config["extracted_file_name"]
-        )
+        cls.LAST_UPDATED_YEAR = dataset_config["last_updated_year"]
+        cls.SOURCE_URL = dataset_config["source_url"]
+        cls.INPUT_EXTRACTED_FILE_NAME = dataset_config["extracted_file_name"]
 
     # This is a classmethod so it can be used by `get_data_frame` without
     # needing to create an instance of the class. This is a use case in `etl_score`.
diff --git a/data/data-pipeline/data_pipeline/etl/sources/national_risk_index/etl.py b/data/data-pipeline/data_pipeline/etl/sources/national_risk_index/etl.py
index 1f57ca62..936b0a50 100644
--- a/data/data-pipeline/data_pipeline/etl/sources/national_risk_index/etl.py
+++ b/data/data-pipeline/data_pipeline/etl/sources/national_risk_index/etl.py
@@ -67,6 +67,7 @@ class NationalRiskIndexETL(ExtractTransformLoad):
             self.CONTAINS_AGRIVALUE,
         ]
 
+        self.INPUT_CSV = self.get_tmp_path() / self.INPUT_EXTRACTED_FILE_NAME
         self.df: pd.DataFrame
 
     def extract(self) -> None:
diff --git a/data/data-pipeline/data_pipeline/tests/conftest.py b/data/data-pipeline/data_pipeline/tests/conftest.py
index f1dc63ac..5535a97e 100644
--- a/data/data-pipeline/data_pipeline/tests/conftest.py
+++ b/data/data-pipeline/data_pipeline/tests/conftest.py
@@ -52,3 +52,8 @@ def mock_etl(monkeypatch, mock_paths) -> None:
     data_path, tmp_path = mock_paths
     monkeypatch.setattr(ExtractTransformLoad, "DATA_PATH", data_path)
     monkeypatch.setattr(ExtractTransformLoad, "TMP_PATH", tmp_path)
+    monkeypatch.setattr(
+        ExtractTransformLoad,
+        "CONTENT_CONFIG",
+        Path.cwd() / "data_pipeline" / "score" / "config",
+    )
diff --git a/data/data-pipeline/data_pipeline/tests/sources/example/test_etl.py b/data/data-pipeline/data_pipeline/tests/sources/example/test_etl.py
index cac6dcfb..3dc7f8b2 100644
--- a/data/data-pipeline/data_pipeline/tests/sources/example/test_etl.py
+++ b/data/data-pipeline/data_pipeline/tests/sources/example/test_etl.py
@@ -148,6 +148,7 @@ class TestETL:
         etl = self._get_instance_of_etl_class()
         data_path, tmp_path = mock_paths
 
+        etl.__init__()
         actual_file_path = etl._get_output_file_path()
 
         expected_file_path = (