Merge pull request #454 from cmu-delphi/nchs-list

Fix linting for nchs

Author: krivard

nchs_mortality/delphi_nchs_mortality/pull.py

@@ -33,12 +33,12 @@ def pull_nchs_mortality_data(token: str, map_df: pd.DataFrame, test_mode: str):
         Dataframe as described above.
     """
     # Constants
-    KEEP_COLUMNS = ['covid_deaths', 'total_deaths',
+    keep_columns = ['covid_deaths', 'total_deaths',
                     'percent_of_expected_deaths', 'pneumonia_deaths',
                     'pneumonia_and_covid_deaths', 'influenza_deaths',
                     'pneumonia_influenza_or_covid_19_deaths']
-    TYPE_DICT = {key: float for key in KEEP_COLUMNS}
-    TYPE_DICT["timestamp"] = 'datetime64[ns]'
+    type_dict = {key: float for key in keep_columns}
+    type_dict["timestamp"] = 'datetime64[ns]'
 
     if test_mode == "":
         # Pull data from Socrata API
@@ -52,18 +52,18 @@ def pull_nchs_mortality_data(token: str, map_df: pd.DataFrame, test_mode: str):
     # Check missing start_week == end_week
     try:
         assert sum(df["timestamp"] != df["end_week"]) == 0
-    except AssertionError:
+    except AssertionError as exc:
         raise ValueError(
             "end_week is not always the same as start_week, check the raw file"
-        )
+        ) from exc
 
     try:
-        df = df.astype(TYPE_DICT)
-    except KeyError:
+        df = df.astype(type_dict)
+    except KeyError as exc:
         raise ValueError("Expected column(s) missed, The dataset "
-            "schema may have changed. Please investigate and "
-            "amend the code.")
-    
+                         "schema may have changed. Please investigate and "
+                         "amend the code.") from exc
+
     df = df[df["state"] != "United States"]
     df.loc[df["state"] == "New York City", "state"] = "New York"
 
@@ -91,7 +91,7 @@ def pull_nchs_mortality_data(token: str, map_df: pd.DataFrame, test_mode: str):
         )
 
     # Add population info
-    KEEP_COLUMNS.extend(["timestamp", "geo_id", "population"])
-    df = df.merge(map_df, on="state")[KEEP_COLUMNS]
-    
+    keep_columns.extend(["timestamp", "geo_id", "population"])
+    df = df.merge(map_df, on="state")[keep_columns]
+
     return df

nchs_mortality/delphi_nchs_mortality/run.py

@@ -27,9 +27,9 @@
         "prop"
 ]
 INCIDENCE_BASE = 100000
-geo_res = "state"
+GEO_RES = "state"
 
-def run_module():
+def run_module():  # pylint: disable=too-many-branches,too-many-statements
     """Run module for processing NCHS mortality data."""
     params = read_params()
     export_start_date = params["export_start_date"]
@@ -65,7 +65,7 @@ def run_module():
             sensor_name = "_".join(["wip", metric])
             export_csv(
                 df,
-                geo_name=geo_res,
+                geo_name=GEO_RES,
                 export_dir=daily_export_dir,
                 start_date=datetime.strptime(export_start_date, "%Y-%m-%d"),
                 sensor=sensor_name,
@@ -82,7 +82,7 @@ def run_module():
                 sensor_name = "_".join(["wip", metric, sensor])
                 export_csv(
                     df,
-                    geo_name=geo_res,
+                    geo_name=GEO_RES,
                     export_dir=daily_export_dir,
                     start_date=datetime.strptime(export_start_date, "%Y-%m-%d"),
                     sensor=sensor_name,
@@ -104,7 +104,7 @@ def run_module():
             params["aws_credentials"])
 
         # Dont update cache from S3 (has daily files), only simulate a update_cache() call
-        weekly_arch_diff._cache_updated = True
+        weekly_arch_diff._cache_updated = True  # pylint: disable=protected-access
 
         # Diff exports, and make incremental versions
         _, common_diffs, new_files = weekly_arch_diff.diff_exports()