def get_metadata(self):
datasets = [
{
'table_id': 'GDP_SP',
'human_name': 'Nominal GDP',
'description': '2013 Gross Domestic Product (GDP) (state annual product)',
'source_name': self.name,
'source_url': 'http://bea.gov/regional/index.htm',
'geo_types': [State()],
'columns': ['2013 GDP'],
'count': 1
},
{
'table_id': 'RGDP_SP',
'human_name': 'Real GDP',
'description': '2013 Real GDP (state annual product)',
'source_name': self.name,
'source_url': 'http://bea.gov/regional/index.htm',
'geo_types': [State()],
'columns': ['2013 Real GDP'],
'count': 1
},
{
'table_id': 'PCRGDP_SP',
'human_name': 'Real GDP - Per Capita',
'description': '2013 Per capita Real GDP (state annual product)',
'source_name': self.name,
'source_url': 'http://bea.gov/regional/index.htm',
'geo_types': [State()],
'columns': ['2013 Per Capita Real GDP'],
'count': 1
},
{
'table_id': 'TPI_SI',
'human_name': 'Personal Income - Total',
'description': '2013 Total Personal Income (state annual income)',
'source_name': self.name,
'source_url': 'http://bea.gov/regional/index.htm',
'geo_types': [State()],
'columns': ['2013 Total Personal Income'],
'count': 1
},
{
'table_id': 'PCPI_SI',
'human_name': 'Personal Income - Per Capita',
'description': '2013 Per Capita personal income (state annual income)',
'source_name': self.name,
'source_url': 'http://bea.gov/regional/index.htm',
'geo_types': [State()],
'columns': ['2013 Per Capita Personal Income'],
'count': 1
}
]
return datasets
def column_info(self):
cols = [
{
'table_id': 'fpds',
'human_name': 'Federal Contracts',
'description': '',
'source_name': self.name,
'source_url': 'http://www.usaspending.gov/data',
'geo_types': [State(),
Zip5(), CongressionalDistrict()],
'count': 1, # probably a lot more,
'columns': '',
},
{
'table_id': 'faads',
'human_name': 'Federal Assistance',
'description': '',
'source_name': self.name,
'source_url': 'http://www.usaspending.gov/data',
'geo_types': [State(), City(), County()],
'count': 1, # probably a lot more
'columns': '',
},
{
'table_id': 'fsrs',
'human_name': 'Federal sub-awards',
'description': '',
'source_name': self.name,
'source_url': 'http://www.usaspending.gov/data',
'geo_types': [State(),
Zip5(), CongressionalDistrict()],
'count': 1, # probably a lot more
'columns': '',
},
]
for col in cols:
table_id = col['table_id']
url = '%s/%s/%s.php' % (self.base_url, table_id, table_id)
param = TABLE_PARAMS[table_id]['state']
query = {param: 'IL', 'detail': 's'}
params = urlencode(query)
table = self.fetch_xml(url, params)
col['count'] = len(table)
col['columns'] = [
' '.join(c.split('_')).title() for c in table.keys()
]
return cols
def get_metadata(self):
datasets = [{
'table_id':
'oes',
'human_name':
'Occupational Employment Statistics',
'description':
'Occupational Employment Statistics',
'source_name':
self.name,
'source_url':
'http://www.bls.gov/oes/',
'geo_types': [State(), StateFIPS()],
'columns':
[self.oes_column_lookup[col] for col in self.oes_column_lookup],
'count':
3
}, {
'table_id':
'qcew',
'human_name':
'Quarterly Census of Employment & Wages',
'description':
'Quarterly Census of Employment & Wages',
'source_name':
self.name,
'source_url':
'http://www.bls.gov/cew/home.htm',
'geo_types': [State(), StateFIPS()],
'columns':
[self.qcew_column_lookup[col] for col in self.qcew_column_lookup],
'count':
7
}]
return datasets
def column_info(self):
table_ids = [
"B01003", "B19013", "B19301", "B02001", "B01002", "B15002",
"B25077", "B26001", "B11009", "B05006"
]
columns = []
for table in table_ids:
info = self.urlopen('%s/table/%s' % (self.base_url, table))
table_info = json.loads(info)
d = {
'table_id':
table,
'human_name':
table_info['table_title'],
'description':
'',
'source_name':
self.name,
'source_url':
'http://censusreporter.org/tables/%s/' % table,
'geo_types': [
City(),
State(),
StateFIPS(),
StateCountyFIPS(),
Zip5(),
Zip9(),
County(),
SchoolDistrict(),
CongressionalDistrict(),
CensusTract()
],
'columns': [
v['column_title'] for v in table_info['columns'].values()
if v['indent'] is not None
]
}
d['columns'].extend(
['%s (error margin)' % v for v in d['columns']])
d['columns'] = sorted(d['columns'])
d['count'] = len(d['columns'])
columns.append(d)
return columns
def get_metadata(self):
table_ids = [
"B01003", # Total Population
"B19013", # Median Household Income
"B19301", # Per Capita Income
"B02001", # Race
"B01002", # Median Age by Sex"
"B25077", # Median Value (Dollars)
"B26001", # Group Quarters Population
"B11009", # Unmarried-partner Households by Sex of Partner
"B05006", # Place of Birth for the Foreign-born Population in the United States
"B19083", # Gini Index of Income Inequality
"B15003", # Educational Attainment
"B03002", # Hispanic or Latino Origin by Race
]
columns = []
for table in table_ids:
info = self.urlopen('%s/table/%s' % (self.base_url, table))
table_info = json.loads(info)
d = {
'table_id': table,
'human_name': table_info['table_title'],
'description': '',
'source_name': self.name,
'source_url': 'http://censusreporter.org/tables/%s/' % table,
'geo_types': [City(), State(), StateFIPS(), StateCountyFIPS(), Zip5(),
Zip9(), County(), SchoolDistrict(),
CongressionalDistrict(), CensusTract()],
'columns': [v['column_title'] for v in table_info['columns'].values() if v['indent'] is not None]
}
d['columns'].extend(['%s (error margin)' % v for v in d['columns']])
d['columns'] = sorted(d['columns'])
if table == 'B25077': # Overriding the name for "Median Value" table
d['human_name'] = 'Median Value, Owner-Occupied Housing Units'
d['columns'] = ['Median Value, Owner-Occupied Housing Units',
'Median Value, Owner-Occupied Housing Units (error margin)']
d['count'] = len(d['columns'])
columns.append(d)
return columns