def test_process_individual_county_greene(data_clean):
county_data = process_individual_county(data_clean,
DATA_INDEX,
county_name="Greene")
df_deaths = county_data["deaths"]
print("\n", df_deaths)
def test_process_individual_county_washington(data_clean):
county_data = process_individual_county(data_clean,
DATA_INDEX,
county_name="Washington")
df_deaths = county_data["deaths"]
print("\n", df_deaths)
def greene_county_data(greene_county_dict, data_clean) -> Dict[str, pd.DataFrame]:
"""
Creates county_data, ie. a dict of pandas Dataframes with processed cases, deaths, test
data for Greene county
"""
county_name_clean = greene_county_dict["42059"]["name"].replace(" County", "")
return process_individual_county(
data_clean, DATA_INDEX, county_name=county_name_clean
)
def dauphin_county_data(dauphin_info, data_clean) -> Dict[str, pd.DataFrame]:
"""
Creates county_data, ie. a dict of pandas Dataframes with processed cases, deaths, test
data for Dauphin county
"""
county_name = dauphin_info["name"]
county_name_clean = county_name.replace(" County", "")
return process_individual_county(
data_clean, DATA_INDEX, county_name=county_name_clean
)
def test_process_individual_county_total(data_clean):
state_data = process_individual_county(data_clean,
DATA_INDEX,
county_name="Total")
df_cases = state_data["cases"]
df_cases = df_cases.set_index("date")
# assertions
cases_total_july_27 = df_cases.at["2020-07-27", "total"]
cases_moving_avg_july_27 = df_cases.at["2020-07-27", "moving_avg"]
assert cases_total_july_27 == 108264
assert int(cases_moving_avg_july_27) == 932
def test_process_individual_county_dauphin(data_clean):
county_data = process_individual_county(data_clean,
DATA_INDEX,
county_name="Dauphin")
df_cases = county_data["cases"]
df_cases = df_cases.set_index("date")
# assertions
cases_total_july_27 = df_cases.at["2020-07-27", "total"]
cases_total_per_capita_july_27 = df_cases.at["2020-07-27",
"total_per_capita"]
assert cases_total_july_27 == 2559
assert int(round(cases_total_per_capita_july_27)) == 920
def main(
counties: Dict[str, Dict],
email_send: bool = True,
custom_subject_line: str = None,
condense_email: bool = True,
aws_bucket: str = AWS_BUCKET,
aws_dir: str = AWS_DIR,
) -> None:
"""
Generates a unique newsletter based on COVID-19 data and emails it to selected counties.
Args:
counties (Dict[str, Dict]): Dict of dicts representing county names and sendgrid email ID,
email_send (bool, optional): Whether to send emails. Defaults to True. Useful for testing program without
sending emails.
custom_subject_line (str, optional): A custom subject line that overwrites the programmatically generated
subject line. Useful for testing purposes. Disabled by default.
condense_email (bool, optional): Condenses multiple white spaces in email HTML into single spaces before
sending. Defaults to True.
aws_bucket (optional, str): AWS bucket where charts will be uploaded to. Defaults to value stored in
definitions.py
aws_dir (optional, str): Directory within AWS bucket where charts will be uploaded. Defaults to value stored in
definitions.py
Returns:
None.
"""
# set up basic settings
init_program()
# fetch COVID-19 data + Spotlight stories for promo purposes
data_raw = fetch_data(FETCH_DIR_URL, DATA_INDEX)
stories_raw = fetch_stories(3)
# clean, filter, process data
stories_clean = process_stories(stories_raw)
data_clean = process_clean(data_raw)
gdf_raw = process_geo(PATH_PA_GEOJSON)
gdf_processed = merge_geo(gdf_raw, data_clean)
# loop over dict of counties and generate charts and chatter
for fips, county_dict in counties.items():
# skip county if there are no subscribers to email list
county_name = county_dict["name"]
email_list_id = county_dict["id"]
subscriber_count = count_subscribers(email_list_id)
if subscriber_count == 0:
logging.info(
f"No subscribers in {county_name} email list, moving on to next county..."
)
continue
logging.info(
f"Creating newsletter payload for {county_name}, which has {subscriber_count} subscribers."
)
county_name_clean = county_name.replace(" County", "")
county_data = process_individual_county(
data_clean, DATA_INDEX, county_name=county_name_clean
)
# create email payload
county_payload = gen_county_payload(
county_name_clean=county_name_clean,
data_clean=data_clean,
county_data=county_data,
gdf=gdf_processed,
aws_bucket=aws_bucket,
aws_dir=aws_dir,
)
# Generate HTML
newsletter_filename = f"newsletter_{county_name_clean}_{est_now_iso()}.html"
newsletter_local_path = DIR_OUTPUT / newsletter_filename
newsletter_browser_link = (
f"https://{aws_bucket}/{aws_dir}/{newsletter_filename}"
)
newsletter_vars = gen_jinja_vars(
county_name=county_name,
county_payload=county_payload,
newsletter_browser_link=newsletter_browser_link,
story_promo=stories_clean,
)
html = gen_html(templates_path=DIR_TEMPLATES, template_vars=newsletter_vars)
# Upload copy of HTML to s3
with open(newsletter_local_path, "w") as fout:
fout.writelines(html)
copy_to_s3(newsletter_local_path, aws_bucket, aws_dir, content_type="text/html")
# Send email
if email_send:
html = html if not condense_email else condense_whitespace(html)
subject = (
f"COVID-19 Update: {county_name} ({est_now_ap_brief()})"
if not custom_subject_line
else custom_subject_line
)
logging.info(f"Sending email for {county_name}...")
logging.info(f"Subject line: {subject}")
send_email_list(html, email_list_id, subject=subject)
else:
logging.info("No email has been sent because 'email_send' option is False")