def test_bad_dcids(self, urlopen):
""" Calling get_observations with dcids that do not exist returns empty
results.
"""
# Set the API key
dc.set_api_key('TEST-API-KEY')
# Get the input
dcids_1 = ['dc/p/x6t44d8jd95rd', 'dc/MadDcid']
dcids_2 = ['dc/MadDcid', 'dc/MadderDcid']
# Call get_observations
actual_1 = dc.get_observations(
dcids_1,
'count',
'measuredValue',
'2018-12',
observation_period='P1M',
measurement_method='BLSSeasonallyAdjusted')
actual_2 = dc.get_observations(
dcids_2,
'count',
'measuredValue',
'2018-12',
observation_period='P1M',
measurement_method='BLSSeasonallyAdjusted')
# Verify the results
self.assertDictEqual(actual_1, {'dc/p/x6t44d8jd95rd': 18704962.0})
self.assertDictEqual(actual_2, {})
def main():
# Create a list of dcids for California, Kentucky, and Maryland
ca, ky, md = 'geoId/06', 'geoId/21', 'geoId/24'
dcids = [ca, ky, md]
# Get the population of all employed individuals in the above states.
print('Get Populations for All Employed Individuals')
employed = dc.get_populations(dcids, 'Person', constraining_properties={
'employment': 'BLS_Employed'})
print(json.dumps(employed, indent=2))
# Get the count for all male / females for the above states in 2016
print('Get Population Counts for Employed Individuals in Maryland')
pop_dcids = [employed[md]]
obs = dc.get_observations(pop_dcids,
'count',
'measuredValue',
'2018-12',
observation_period='P1M',
measurement_method='BLSSeasonallyAdjusted')
print(json.dumps(obs, indent=2))
# Get all population and observation data of Mountain View.
print('Get Mountain View population and observation')
popobs = dc.get_pop_obs("geoId/0649670")
pprint.pprint(popobs)
def test_no_dcids(self, post_mock):
""" Calling get_observations with no dcids returns empty results. """
# Set the API key
dc.set_api_key('TEST-API-KEY')
actual = dc.get_observations([], 'count', 'measuredValue', '2018-12',
observation_period='P1M',
measurement_method='BLSSeasonallyAdjusted')
self.assertDictEqual(actual, {})
def test_multiple_dcids(self, urlopen):
""" Calling get_observations with proper dcids returns valid results. """
dcids = ['dc/p/x6t44d8jd95rd', 'dc/p/lr52m1yr46r44', 'dc/p/fs929fynprzs']
expected = {
'dc/p/lr52m1yr46r44': 3075662.0,
'dc/p/fs929fynprzs': 1973955.0,
'dc/p/x6t44d8jd95rd': 18704962.0
}
actual = dc.get_observations(dcids, 'count', 'measuredValue', '2018-12',
observation_period='P1M',
measurement_method='BLSSeasonallyAdjusted')
self.assertDictEqual(actual, expected)
def test_series_multiple_dcids(self, post_mock):
""" Calling get_observations with a Pandas Series and proper dcids returns
a Pandas Series with valid results.
"""
# Set the API key
dc.set_api_key('TEST-API-KEY')
dcids = pd.Series(
['dc/p/x6t44d8jd95rd', 'dc/p/lr52m1yr46r44', 'dc/p/fs929fynprzs'])
expected = pd.Series([18704962.0, 3075662.0, 1973955.0])
actual = dc.get_observations(dcids, 'count', 'measuredValue', '2018-12',
observation_period='P1M',
measurement_method='BLSSeasonallyAdjusted')
assert_series_equal(actual, expected)
def test_series_bad_dcids(self, post_mock):
""" Calling get_observations with a Pandas Series and dcids that do not
exist returns empty results.
"""
# Set the API key
dc.set_api_key('TEST-API-KEY')
# Get the input and expected output
dcids_1 = pd.Series(['dc/p/x6t44d8jd95rd', 'dc/MadDcid'])
dcids_2 = pd.Series(['dc/MadDcid', 'dc/MadderDcid'])
expected_1 = pd.Series([18704962.0, float('NaN')])
expected_2 = pd.Series([float('NaN'), float('NaN')])
# Call get_observations
actual_1 = dc.get_observations(dcids_1, 'count', 'measuredValue', '2018-12',
observation_period='P1M',
measurement_method='BLSSeasonallyAdjusted')
actual_2 = dc.get_observations(dcids_2, 'count', 'measuredValue', '2018-12',
observation_period='P1M',
measurement_method='BLSSeasonallyAdjusted')
# Verify the results
assert_series_equal(actual_1, expected_1)
assert_series_equal(actual_2, expected_2)
def main():
# Create a list of dcids for California, Kentucky, and Maryland
ca, ky, md = 'geoId/06', 'geoId/21', 'geoId/24'
dcids = [ca, ky, md]
# Get the population of all employed individuals in the above states.
utils._print_header('Get Populations for All Employed Individuals')
employed = dc.get_populations(
dcids,
'Person',
constraining_properties={'employment': 'BLS_Employed'})
print('> Printing all populations of employed individuals\n')
print(json.dumps(employed, indent=2))
# Get the count for all male / females for the above states in 2016
utils._print_header(
'Get Population Counts for Employed Individuals in Maryland')
pop_dcids = [employed[md]]
print('> Requesting observations for {} in December 2018\n'.format(
pop_dcids))
obs = dc.get_observations(pop_dcids,
'count',
'measuredValue',
'2018-12',
observation_period='P1M',
measurement_method='BLSSeasonallyAdjusted')
print(json.dumps(obs, indent=2))
# We perform the same workflow using a Pandas DataFrame. First, initialize a
# DataFrame with Santa Clara and Montgomery County.
utils._print_header('Initialize the DataFrame')
pd_frame = pd.DataFrame({'state': ['geoId/06', 'geoId/21', 'geoId/24']})
pd_frame['state_name'] = dc.get_property_values(pd_frame['state'], 'name')
pd_frame = dc.flatten_frame(pd_frame)
print(pd_frame)
# Get populations for employed individuals
utils._print_header('Add Population and Observation to DataFrame')
pd_frame['employed_pop'] = dc.get_populations(
pd_frame['state'],
'Person',
constraining_properties={'employment': 'BLS_Employed'})
# Add the observation for employed individuals
pd_frame['employed_count'] = dc.get_observations(
pd_frame['employed_pop'],
'count',
'measuredValue',
'2018-12',
observation_period='P1M',
measurement_method='BLSSeasonallyAdjusted')
print(pd_frame)
# Final dataframe. Use the convenience function "clean_frame" to convert
# columns to numerical types.
utils._print_header('Final Data Frame')
pd_frame = dc.clean_frame(pd_frame)
print(pd_frame)
# Get all population and observation data of Mountain View.
utils._print_header('Get Mountain View population and observation')
popobs = dc.get_pop_obs("geoId/0649670")
pprint.pprint(popobs)
def test_no_dcids(self, urlopen):
""" Calling get_observations with no dcids returns empty results. """
actual = dc.get_observations([], 'count', 'measuredValue', '2018-12',
observation_period='P1M',
measurement_method='BLSSeasonallyAdjusted')
self.assertDictEqual(actual, {})
