def race_and_age(data):
# Filters rows without age data
only_with_age = data['with_years_in_prison'].where(
lambda r: r['age'] is not None
)
# Group by race
race_groups = only_with_age.group_by('race')
# Sub-group by age cohorts (20s, 30s, etc.)
race_and_age_groups = race_groups.group_by(
lambda r: '%i0s' % (r['age'] // 10),
key_name='age_group'
)
# Aggregate medians for each group
medians = race_and_age_groups.aggregate([
('years_in_prison', agate.Length(), 'count'),
('years_in_prison', agate.Median(), 'median_years_in_prison')
])
# Sort the results
sorted_groups = medians.order_by('median_years_in_prison', reverse=True)
# Print out the results
print(sorted_groups.format(max_rows=10))
def main():
table = agate.Table.from_csv('data.csv')
print(list(zip(table.column_names, table.column_types)))
with_decimals = table.compute([
('year', agate.Formula(agate.Text(), lambda r: r['Date'].year)),
('lat', DecimalDegrees('Latitude')),
('lng', DecimalDegrees('Longitude')),
])
with_decimals.to_csv('with_decimals.csv')
by_year = with_decimals.group_by('year')
by_usable = by_year.group_by(
lambda r: r['lat'] is not None and r['lng'] is not None)
by_year.aggregate([('count', agate.Length())]).print_csv()
by_usable.aggregate([('count', agate.Length())]).print_table()
data = {}
for year, table in by_year.items():
data[year] = []
for row in table.rows:
if not row['lat'] or not row['lng']:
continue
data[year].append(
geojson.Point([float(row['lng']),
float(row['lat'])]))
with open('src/data/attacks.json', 'w') as f:
geojson.dump(data, f, sort_keys=True)
def by_country(data):
by_country = data['table'].group_by('Home country*')
data['failed_by_country'] = by_country.aggregate([('failed_banks',
agate.Length())])