def test_california_los_angeles():
util.run_scraper_and_assert(scraper_cls=CaliforniaLosAngeles,
assertions={
'Date Published':
datetime(2020, 7, 16).date(),
'Total Cases':
150000,
'Total Deaths':
4000,
'Count Cases Black/AA':
4000,
'Count Deaths Black/AA':
400,
'Pct Includes Unknown Race':
False,
'Pct Includes Hispanic Black':
False,
'Pct Cases Black/AA':
to_percentage(4000, 78500),
'Pct Deaths Black/AA':
to_percentage(400, 3650),
'Count Cases Known Race':
78500,
'Count Deaths Known Race':
3650
})
def test_delaware():
util.run_scraper_and_assert(scraper_cls=Delaware,
assertions={
'Date Published':
datetime(2020, 7, 16).date(),
'Total Cases':
13000,
'Total Deaths':
500,
'Count Cases Black/AA':
3000,
'Count Deaths Black/AA':
100,
'Pct Includes Unknown Race':
False,
'Pct Includes Hispanic Black':
False,
'Pct Cases Black/AA':
to_percentage(3000, 12000),
'Pct Deaths Black/AA':
to_percentage(100, 480),
'Count Cases Known Race':
12000,
'Count Deaths Known Race':
480
})
def test_california_sf():
mocked_requests = {
'date': util.MockSeleniumWireRequest(response_body=loader.get_blob('california_san_francisco_date.txt')),
'cases_by_race': util.MockSeleniumWireRequest(
response_body=loader.get_blob('california_san_francisco_cases.txt')),
'deaths_by_race': util.MockSeleniumWireRequest(
response_body=loader.get_blob('california_san_francisco_deaths.txt'))
}
mocked_webdriver = util.mocked_webdriver_runner(requests=mocked_requests)
with mock.patch('covid19_scrapers.states.california_san_francisco.WebdriverRunner', mocked_webdriver):
util.run_scraper_and_assert(
scraper_cls=CaliforniaSanFrancisco,
assertions={
'Date Published': datetime(2020, 7, 17).date(),
'Total Cases': 5100,
'Total Deaths': 130,
'Count Cases Black/AA': 300,
'Count Deaths Black/AA': 5,
'Pct Includes Unknown Race': False,
'Pct Includes Hispanic Black': False,
'Pct Cases Black/AA': to_percentage(300, 4400),
'Pct Deaths Black/AA': to_percentage(5, 30),
'Count Cases Known Race': 4400,
'Count Deaths Known Race': 30
})
def test_alabama(patched_geoservice):
# setup constants and mock data
AA_IDX = 1
UNKNOWN_IDX = 3
cases = {
'Racecat': ['Asian', 'Black', 'Other', 'Unknown', 'White'],
'value': [200, 19000, 3000, 18000, 20000]
}
deaths = {
'Racecat': ['Asian', 'Black', 'Other', 'Unknown', 'White'],
'value': [10, 500, 25, 50, 600]
}
known_cases_by_race = sum(cases['value']) - cases['value'][UNKNOWN_IDX]
known_deaths_by_race = sum(deaths['value']) - deaths['value'][UNKNOWN_IDX]
# patch geoservice
patched_geoservice.side_effect = [
util.make_query_geoservice_data(data=cases),
util.make_query_geoservice_data(data=deaths)
]
# run and test
util.run_scraper_and_assert(scraper_cls=Alabama,
assertions={
'Date Published':
date.today(),
'Total Cases':
sum(cases['value']),
'Total Deaths':
sum(deaths['value']),
'Count Cases Black/AA':
cases['value'][AA_IDX],
'Count Deaths Black/AA':
deaths['value'][AA_IDX],
'Pct Includes Unknown Race':
False,
'Pct Includes Hispanic Black':
False,
'Pct Cases Black/AA':
to_percentage(cases['value'][AA_IDX],
known_cases_by_race),
'Pct Deaths Black/AA':
to_percentage(deaths['value'][AA_IDX],
known_deaths_by_race),
'Count Cases Known Race':
known_cases_by_race,
'Count Deaths Known Race':
known_deaths_by_race
})
def test_arkansas():
util.run_scraper_and_assert(
scraper_cls=Arkansas,
assertions={
'Date Published': date.today(),
'Total Cases': 31000,
'Total Deaths': 300,
'Count Cases Black/AA': 6000,
'Count Deaths Black/AA': 90,
'Pct Includes Unknown Race': False,
'Pct Includes Hispanic Black': True,
'Pct Cases Black/AA': to_percentage(6000, 27000),
'Pct Deaths Black/AA': to_percentage(90, 297),
'Count Cases Known Race': 27000,
'Count Deaths Known Race': 297
})
def test_alaska():
util.run_scraper_and_assert(
scraper_cls=Alaska,
assertions={
'Date Published': date.today(),
'Total Cases': 1733,
'Total Deaths': 17,
'Count Cases Black/AA': 41,
'Count Deaths Black/AA': 0,
'Pct Includes Unknown Race': False,
'Pct Includes Hispanic Black': True,
'Pct Cases Black/AA': to_percentage(41, 1171),
'Pct Deaths Black/AA': to_percentage(0, 17),
'Count Cases Known Race': 1171,
'Count Deaths Known Race': 17
})
def test_wisconsin():
util.run_scraper_and_assert(
scraper_cls=Wisconsin,
assertions={
'Date Published': date.today(),
'Total Cases': 40000,
'Total Deaths': 800,
'Count Cases Black/AA': 6600,
'Count Deaths Black/AA': 200,
'Pct Includes Unknown Race': False,
'Pct Includes Hispanic Black': True,
'Pct Cases Black/AA': to_percentage(6600, 40000 - 3800),
'Pct Deaths Black/AA': to_percentage(200, 800 - 10),
'Count Cases Known Race': 40000 - 3800,
'Count Deaths Known Race': 800 - 10
})
def test_wisconsin():
_, df = util.make_query_geoservice_data(json_file='wisconsin.json')
df['DATE'] = pd.Timestamp.today()
with mock.patch('covid19_scrapers.states.wisconsin.query_geoservice', mock.MagicMock(return_value=(date, df))):
util.run_scraper_and_assert(
scraper_cls=Wisconsin,
assertions={
'Date Published': date.today(),
'Total Cases': 40000,
'Total Deaths': 800,
'Count Cases Black/AA': 6600,
'Count Deaths Black/AA': 200,
'Pct Includes Unknown Race': False,
'Pct Includes Hispanic Black': True,
'Pct Cases Black/AA': to_percentage(6600, 40000 - 3800),
'Pct Deaths Black/AA': to_percentage(200, 800 - 10),
'Count Cases Known Race': 40000 - 3800,
'Count Deaths Known Race': 800 - 10
})
def test_illinois():
util.run_scraper_and_assert(scraper_cls=Illinois,
assertions={
'Date Published':
datetime(2020, 7, 18).date(),
'Total Cases':
160000,
'Total Deaths':
7000,
'Count Cases Black/AA':
27000,
'Count Deaths Black/AA':
2000,
'Pct Includes Unknown Race':
True,
'Pct Includes Hispanic Black':
False,
'Pct Cases Black/AA':
to_percentage(27000, 160000),
'Pct Deaths Black/AA':
to_percentage(2000, 7000)
})
def test_maryland():
util.run_scraper_and_assert(scraper_cls=Maryland,
assertions={
'Total Cases':
75000,
'Total Deaths':
3000,
'Count Cases Black/AA':
20000,
'Count Deaths Black/AA':
1000,
'Pct Includes Unknown Race':
False,
'Pct Includes Hispanic Black':
False,
'Pct Cases Black/AA':
to_percentage(20000, 63000),
'Pct Deaths Black/AA':
to_percentage(1000, 2990),
'Count Cases Known Race':
63000,
'Count Deaths Known Race':
2990
})
def test_california():
mock_dfs = [
util.mock_read_csv_dataframe('california_cases.csv',
parse_dates=['date']),
util.mock_read_csv_dataframe('california_demographics.csv',
index_col=['date', 'race_ethnicity'],
parse_dates=['date'])
]
with mock.patch('covid19_scrapers.states.california.pd.read_csv',
side_effect=mock_dfs):
util.run_scraper_and_assert(scraper_cls=California,
assertions={
'Date Published':
datetime(2020, 7, 16).date(),
'Total Cases':
10000,
'Total Deaths':
1500,
'Count Cases Black/AA':
10000,
'Count Deaths Black/AA':
600,
'Pct Includes Unknown Race':
False,
'Pct Includes Hispanic Black':
False,
'Pct Cases Black/AA':
to_percentage(10000, 45000),
'Pct Deaths Black/AA':
to_percentage(600, 4100),
'Count Cases Known Race':
45000,
'Count Deaths Known Race':
4100
})