style(flynt): convert .format and % strings to f-strings

src/acquisition/afhsb/afhsb_csv.py

@@ -51,15 +51,15 @@ def get_flu_cat(dx):
             if dx.startswith(prefix):
                 return 1
         for i in range(12, 19):
-            prefix = "J{}".format(i)
+            prefix = f"J{i}"
             if dx.startswith(prefix):
                 return 2
         for i in range(0, 7):
-            prefix = "J0{}".format(i)
+            prefix = f"J0{i}"
             if dx.startswith(prefix):
                 return 3
         for i in range(20, 23):
-            prefix = "J{}".format(i)
+            prefix = f"J{i}"
             if dx.startswith(prefix):
                 return 3
         for prefix in ["J40", "R05", "H669", "R509", "B9789"]:
@@ -79,7 +79,7 @@ def get_field(row, column):
 
     def row2flu(row):
         for i in range(1, 9):
-            dx = get_field(row, "dx{}".format(i))
+            dx = get_field(row, f"dx{i}")
             flu_cat = get_flu_cat(dx)
             if flu_cat is not None:
                 return flu_cat
@@ -136,7 +136,7 @@ def get_country_mapping():
 
 
 def format_dmisid_csv(filename, target_name):
-    src_path = os.path.join(TARGET_DIR, "{}.csv".format(filename))
+    src_path = os.path.join(TARGET_DIR, f"{filename}.csv")
     dst_path = os.path.join(TARGET_DIR, target_name)
 
     src_csv = open(src_path, encoding="utf-8-sig")
@@ -231,10 +231,10 @@ def state2region_csv():
 
 def write_afhsb_csv(period):
     flu_mapping = {0: "ili-flu3", 1: "flu1", 2: "flu2-flu1", 3: "flu3-flu2"}
-    results_dict = pickle.load(open(os.path.join(TARGET_DIR, "{}.pickle".format(period)), "rb"))
+    results_dict = pickle.load(open(os.path.join(TARGET_DIR, f"{period}.pickle"), "rb"))
 
     fieldnames = ["id", "epiweek", "dmisid", "flu_type", "visit_sum"]
-    with open(os.path.join(TARGET_DIR, "{}.csv".format(period)), "w") as csvfile:
+    with open(os.path.join(TARGET_DIR, f"{period}.csv"), "w") as csvfile:
         writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
         writer.writeheader()
 
@@ -248,7 +248,7 @@ def write_afhsb_csv(period):
                     for flu in sorted(dmisid_dict.keys()):
                         visit_sum = dmisid_dict[flu]
                         i += 1
-                        epiweek = int("{}{:02d}".format(year, week))
+                        epiweek = int(f"{year}{week:02d}")
                         flu_type = flu_mapping[flu]
 
                         row = {
@@ -290,8 +290,8 @@ def dmisid_start_time():
 
 
 def fillin_zero_to_csv(period, dmisid_start_record):
-    src_path = os.path.join(TARGET_DIR, "{}.csv".format(period))
-    dst_path = os.path.join(TARGET_DIR, "filled_{}.csv".format(period))
+    src_path = os.path.join(TARGET_DIR, f"{period}.csv")
+    dst_path = os.path.join(TARGET_DIR, f"filled_{period}.csv")
 
     # Load data into a dictionary
     src_csv = open(src_path)
@@ -352,7 +352,7 @@ def fillin_zero_to_csv(period, dmisid_start_record):
                 if i % 100000 == 0:
                     print(row)
                 i += 1
-    print("Wrote {} rows".format(i))
+    print(f"Wrote {i} rows")
 
 
 ######################### Functions for AFHSB data ##########################

src/acquisition/afhsb/afhsb_sql.py

@@ -73,7 +73,7 @@ def init_region_table(sourcefile):
 
 
 def init_raw_data(table_name, sourcefile):
-    print("Initialize {}".format(table_name))
+    print(f"Initialize {table_name}")
     (u, p) = secrets.db.epi
     cnx = connector.connect(user=u, passwd=p, database="epidata")
     create_table_cmd = f"""

src/acquisition/cdcp/cdc_dropbox_receiver.py

@@ -101,7 +101,7 @@ def fetch_data():
             if resp.status_code != 200:
                 raise Exception(["resp.status_code", resp.status_code])
             dropbox_len = meta.size
-            print("  need %d bytes..." % dropbox_len)
+            print(f"  need {int(dropbox_len)} bytes...")
             content_len = int(resp.headers.get("Content-Length", -1))
             if dropbox_len != content_len:
                 info = ["dropbox_len", dropbox_len, "content_len", content_len]

src/acquisition/cdcp/cdc_extract.py

@@ -110,7 +110,7 @@ def get_total_hits(cur, epiweek, state):
     for (total,) in cur:
         pass
     if total is None:
-        raise Exception("missing data for %d-%s" % (epiweek, state))
+        raise Exception(f"missing data for {int(epiweek)}-{state}")
     return total
 
 
@@ -166,7 +166,7 @@ def extract(first_week=None, last_week=None, test_mode=False):
         cur.execute("SELECT max(`epiweek`) FROM `cdc_meta`")
         for (last_week,) in cur:
             pass
-    print("extracting %d--%d" % (first_week, last_week))
+    print(f"extracting {int(first_week)}--{int(last_week)}")
 
     # update each epiweek
     for epiweek in flu.range_epiweeks(first_week, last_week, inclusive=True):
@@ -180,7 +180,7 @@ def extract(first_week=None, last_week=None, test_mode=False):
                 store_result(cur, epiweek, state, *nums, total)
                 print(f" {epiweek}-{state}: {' '.join(str(n) for n in nums)} ({total})")
             except Exception as ex:
-                print(" %d-%s: failed" % (epiweek, state), ex)
+                print(f" {int(epiweek)}-{state}: failed", ex)
                 # raise ex
             sys.stdout.flush()
 

src/acquisition/cdcp/cdc_upload.py

@@ -232,7 +232,7 @@ def parse_zip(zf, level=1):
                 if handler is not None:
                     with zf.open(name) as temp:
                         count = handler(csv.reader(io.StringIO(str(temp.read(), "utf-8"))))
-                    print(prefix, " %d rows" % count)
+                    print(prefix, f" {int(count)} rows")
             else:
                 print(prefix, " (ignored)")
 

src/acquisition/ecdc/ecdc_db_update.py

@@ -87,7 +87,7 @@ def safe_int(i):
 def get_rows(cnx, table="ecdc_ili"):
     # Count and return the number of rows in the `ecdc_ili` table.
     select = cnx.cursor()
-    select.execute("SELECT count(1) num FROM %s" % table)
+    select.execute(f"SELECT count(1) num FROM {table}")
     for (num,) in select:
         pass
     select.close()
@@ -100,7 +100,7 @@ def update_from_file(issue, date, dir, test_mode=False):
     u, p = secrets.db.epi
     cnx = mysql.connector.connect(user=u, password=p, database="epidata")
     rows1 = get_rows(cnx, "ecdc_ili")
-    print("rows before: %d" % (rows1))
+    print(f"rows before: {int(rows1)}")
     insert = cnx.cursor()
 
     # load the data, ignoring empty rows
@@ -115,9 +115,9 @@ def update_from_file(issue, date, dir, test_mode=False):
                 row["region"] = data[4]
                 row["incidence_rate"] = data[3]
                 rows.append(row)
-    print(" loaded %d rows" % len(rows))
+    print(f" loaded {len(rows)} rows")
     entries = [obj for obj in rows if obj]
-    print(" found %d entries" % len(entries))
+    print(f" found {len(entries)} entries")
 
     sql = """
     INSERT INTO
@@ -149,7 +149,7 @@ def update_from_file(issue, date, dir, test_mode=False):
     else:
         cnx.commit()
         rows2 = get_rows(cnx)
-    print("rows after: %d (added %d)" % (rows2, rows2 - rows1))
+    print(f"rows after: {int(rows2)} (added {int(rows2 - rows1)})")
     cnx.close()
 
 
@@ -171,7 +171,7 @@ def main():
         raise Exception("--file and --issue must both be present or absent")
 
     date = datetime.datetime.now().strftime("%Y-%m-%d")
-    print("assuming release date is today, %s" % date)
+    print(f"assuming release date is today, {date}")
 
     ensure_tables_exist()
     if args.file:

src/acquisition/flusurv/flusurv.py

@@ -80,7 +80,7 @@ def fetch_json(path, payload, call_count=1, requests_impl=requests):
 
     # it's polite to self-identify this "bot"
     delphi_url = "https://delphi.cmu.edu/index.html"
-    user_agent = "Mozilla/5.0 (compatible; delphibot/1.0; +%s)" % delphi_url
+    user_agent = f"Mozilla/5.0 (compatible; delphibot/1.0; +{delphi_url})"
 
     # the FluSurv AMF server
     flusurv_url = "https://gis.cdc.gov/GRASP/Flu3/" + path
@@ -106,7 +106,7 @@ def fetch_json(path, payload, call_count=1, requests_impl=requests):
     if resp.status_code == 500 and call_count <= 2:
         # the server often fails with this status, so wait and retry
         delay = 10 * call_count
-        print("got status %d, will retry in %d sec..." % (resp.status_code, delay))
+        print(f"got status {int(resp.status_code)}, will retry in {int(delay)} sec...")
         time.sleep(delay)
         return fetch_json(path, payload, call_count=call_count + 1)
     elif resp.status_code != 200:
@@ -180,7 +180,7 @@ def extract_from_object(data_in):
         raise Exception("no data found")
 
     # print the result and return flu data
-    print("found data for %d weeks" % len(data_out))
+    print(f"found data for {len(data_out)} weeks")
     return data_out
 
 

src/acquisition/flusurv/flusurv_update.py

@@ -108,7 +108,7 @@ def update(issue, location_name, test_mode=False):
     cnx = mysql.connector.connect(host=secrets.db.host, user=u, password=p, database="epidata")
     cur = cnx.cursor()
     rows1 = get_rows(cur)
-    print("rows before: %d" % rows1)
+    print(f"rows before: {int(rows1)}")
 
     # SQL for insert/update
     sql = """
@@ -148,7 +148,7 @@ def update(issue, location_name, test_mode=False):
 
     # commit and disconnect
     rows2 = get_rows(cur)
-    print("rows after: %d (+%d)" % (rows2, rows2 - rows1))
+    print(f"rows after: {int(rows2)} (+{int(rows2 - rows1)})")
     cur.close()
     if test_mode:
         print("test mode: not committing database changes")
@@ -170,7 +170,7 @@ def main():
 
     # scrape current issue from the main page
     issue = flusurv.get_current_issue()
-    print("current issue: %d" % issue)
+    print(f"current issue: {int(issue)}")
 
     # fetch flusurv data
     if args.location == "all":

src/acquisition/fluview/fluview.py

@@ -108,23 +108,23 @@ def get_tier_ids(name):
     location_ids[Key.TierType.hhs] = sorted(set(location_ids[Key.TierType.hhs]))
     num = len(location_ids[Key.TierType.hhs])
     if num != 10:
-        raise Exception("expected 10 hhs regions, found %d" % num)
+        raise Exception(f"expected 10 hhs regions, found {int(num)}")
 
     # add location ids for census divisions
     for row in data[Key.TierListEntry.cen]:
         location_ids[Key.TierType.cen].append(row[Key.TierIdEntry.cen])
     location_ids[Key.TierType.cen] = sorted(set(location_ids[Key.TierType.cen]))
     num = len(location_ids[Key.TierType.cen])
     if num != 9:
-        raise Exception("expected 9 census divisions, found %d" % num)
+        raise Exception(f"expected 9 census divisions, found {int(num)}")
 
     # add location ids for states
     for row in data[Key.TierListEntry.sta]:
         location_ids[Key.TierType.sta].append(row[Key.TierIdEntry.sta])
     location_ids[Key.TierType.sta] = sorted(set(location_ids[Key.TierType.sta]))
     num = len(location_ids[Key.TierType.sta])
     if num != 57:
-        raise Exception("expected 57 states/territories/cities, found %d" % num)
+        raise Exception(f"expected 57 states/territories/cities, found {int(num)}")
 
     # return a useful subset of the metadata
     # (latest epiweek, latest season, tier ids, location ids)
@@ -181,7 +181,7 @@ def save_latest(path=None):
     data = fetch_metadata(sess)
     info = get_issue_and_locations(data)
     issue = info["epiweek"]
-    print("current issue: %d" % issue)
+    print(f"current issue: {int(issue)}")
 
     # establish timing
     dt = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
@@ -200,7 +200,7 @@ def save_latest(path=None):
         ("cen", Key.TierType.cen),
         ("sta", Key.TierType.sta),
     ):
-        name = "ilinet_%s_%d_%s.zip" % (delphi_name, issue, dt)
+        name = f"ilinet_{delphi_name}_{int(issue)}_{dt}.zip"
         if path is None:
             filename = name
         else:
@@ -209,12 +209,12 @@ def save_latest(path=None):
         locations = info["location_ids"][cdc_name]
 
         # download and show timing information
-        print("downloading %s" % delphi_name)
+        print(f"downloading {delphi_name}")
         t0 = time.time()
         size = download_data(tier_id, locations, seasons, filename)
         t1 = time.time()
 
-        print(" saved %s (%d bytes in %.1f seconds)" % (filename, size, t1 - t0))
+        print(f" saved {filename} ({int(size)} bytes in {t1 - t0:.1f} seconds)")
         files.append(filename)
 
     # return the current issue and the list of downloaded files