cleanup names and comments

- rename input arg to `update` to avoid reassignment later
- comment and reuse args_insert
- spelling
- comment magic constant used in output format
- rename location-network/catchmentid map

Author: nmdefries

src/acquisition/flusurv/flusurv.py

@@ -3,7 +3,7 @@
 === Purpose ===
 ===============
 
-Fetches FluSurv-NET data (flu hospitaliation rates) from CDC. Unlike the other
+Fetches FluSurv-NET data (flu hospitalization rates) from CDC. Unlike the other
 CDC-hosted datasets (e.g. FluView), FluSurv is not available as a direct
 download. This program emulates web browser requests for the web app and
 extracts data of interest from the JSON response.
@@ -49,7 +49,7 @@
 
 # all currently available FluSurv locations and their associated codes
 # the number pair represents NetworkID and CatchmentID
-location_codes = {
+location_to_code = {
     "CA": (2, 1),
     "CO": (2, 2),
     "CT": (2, 3),
@@ -155,7 +155,7 @@ def mmwrid_to_epiweek(mmwrid):
 
 def extract_from_object(data_in):
     """
-    Given a FluSurv data object, return hospitaliation rates.
+    Given a FluSurv data object, return hospitalization rates.
 
     The returned object is indexed first by epiweek, then by zero-indexed age
     group.
@@ -171,11 +171,16 @@ def extract_from_object(data_in):
             #   capture as-of-yet undefined age groups 10, 11, and 12
             continue
         age_index = obj["age"] - 1
-        # iterage over weeks
+        # iterate over weeks
         for mmwrid, _, _, rate in obj["data"]:
             epiweek = mmwrid_to_epiweek(mmwrid)
             if epiweek not in data_out:
                 # weekly rate of each age group
+                # TODO what is this magic constant? Maybe total # of age
+                #  groups?? Appears to be assuming that age groups are
+                #  numbered sequentially. Better to store data_out in a
+                #  dictionary of dictionaries, given new age group ids
+                #  (e.g. 99, 21, etc)
                 data_out[epiweek] = [None] * 9
             prev_rate = data_out[epiweek][age_index]
             if prev_rate is None:
@@ -201,7 +206,7 @@ def get_data(location_code):
 
     This method performs the following operations:
       - fetches FluSurv data from CDC
-      - extracts and returns hospitaliation rates
+      - extracts and returns hospitalization rates
     """
 
     # fetch

src/acquisition/flusurv/flusurv_update.py

@@ -90,17 +90,16 @@ def get_rows(cur):
         return num
 
 
-def update(issue, location_name, test_mode=False):
+def update(issue, location, test_mode=False):
     """Fetch and store the currently avialble weekly FluSurv dataset."""
 
     # fetch data
-    location_code = flusurv.location_codes[location_name]
-    print("fetching data for", location_name, location_code)
+    location_code = flusurv.location_to_code[location]
+    print("fetching data for", location, location_code)
     data = flusurv.get_data(location_code)
 
     # metadata
     epiweeks = sorted(data.keys())
-    location = location_name
     release_date = str(EpiDate.today())
 
     # connect to the database
@@ -142,8 +141,9 @@ def update(issue, location_name, test_mode=False):
             # values (including duplicates) were stored on each run.
             continue
         args_meta = [release_date, issue, epiweek, location, lag]
+        # List of values in order of columns specified in sql statement above
         args_insert = data[epiweek]
-        args_update = [release_date] + data[epiweek]
+        args_update = [release_date] + args_insert
         cur.execute(sql, tuple(args_meta + args_insert + args_update))
 
     # commit and disconnect
@@ -184,7 +184,7 @@ def main():
     # fetch flusurv data
     if args.location == "all":
         # all locations
-        for location in flusurv.location_codes.keys():
+        for location in flusurv.location_to_code.keys():
             update(issue, location, args.test)
     else:
         # single location