def test_update_schema():
from dataflows import Flow, printer, update_schema, validate
f = Flow([['a', '-'], ['a', 0]], update_schema(-1, missingValues=['-']),
validate(), printer())
results, dp, stats = f.results()
print(dp.descriptor)
assert results[0] == [
dict(col0='a', col1=None),
dict(col0='a', col1=0),
]
def process_stack_demand(stack):
def collect_cats():
F = 'כלל המדגם'
def f(rows):
cat = None
for row in rows:
if F in row:
v = row[F]
if v.startswith('סך הכל '):
cat = v[7:]
elif v.startswith('--- '):
if not v.endswith('ללא פירוט'):
subcat = v[4:]
row['category'] = cat
row['subcategory'] = subcat
yield row
else:
yield row
return DF.Flow(
DF.add_field('category', 'string', resources=-1),
DF.add_field('subcategory', 'string', resources=-1),
f,
DF.delete_fields([F], resources=-1),
)
def fix_nones(row):
row['demand_pct'] = row['demand_pct'] or 0
key = 'stack:demand'
try:
demand_stacks = _cache.get(key)
except KeyError:
demand_stacks = DF.Flow(
DF.load('demand.xlsx', infer_strategy=DF.load.INFER_STRINGS, headers=2),
collect_cats(),
DF.update_schema(-1, missingValues=['--']),
DF.unpivot(
unpivot_fields=[dict(
name='(.+) \\([A-Z]\\)',
keys=dict(
neighborhood='\\1'
),
)],
extra_keys=[dict(
name='neighborhood', type='string'
)],
extra_value=dict(
name='demand_pct', type='number'
),
resources=-1
),
DF.validate(),
DF.duplicate('demand', 'demand_stacks'),
DF.join_with_self('demand', ['category', 'subcategory'], dict(
category=None, subcategory=None, max_demand=dict(name='demand_pct', aggregate='max')
)),
DF.join(
'demand', ['category', 'subcategory'],
'demand_stacks', ['category', 'subcategory'],
dict(
max_demand=None
)
),
fix_nones,
DF.add_field('display', 'string', lambda r: '{:.0f}%'.format(r['demand_pct'] * 100)),
DF.add_field('value', 'number', lambda r: r['demand_pct']),
DF.add_field('score', 'number', lambda r: r['demand_pct'] / r['max_demand'] * 6),
DF.delete_fields(['demand_pct', 'max_demand']),
DF.sort_rows('{score}', reverse=True),
DF.add_field('scores', 'object', lambda r: dict(
title=r['neighborhood'],
score_display=r['display'],
score_value=float(r['value']),
geometry_score=float(r['score']),
)),
DF.join_with_self('demand_stacks', ['category', 'subcategory'], dict(
category=None, subcategory=None,
scores=dict(aggregate='array'),
)),
DF.add_field('card', 'object', lambda r: dict(
title='ביקוש ל{}'.format(r['subcategory']),
content='',
scores=r['scores'],
test='demand__{category}__{subcategory}'.format(**r).replace(' ', '_')
)),
DF.join_with_self('demand_stacks', ['category'], dict(
category=None,
cards=dict(name='card', aggregate='array'),
)),
DF.add_field('name', 'string', lambda r: 'demand.{}'.format(r['category']).replace(' ', '_')),
).results()[0][0]
_cache.set(key, demand_stacks)
cards = [s for s in demand_stacks if s['name'] == stack['name']][0]['cards']
stack.update(dict(
layout='scores',
currentField='neighborhood',
map=True
))
stack.setdefault('cards', []).extend(cards)
update_schema('time-series-19-covid-combined',
missingValues=['None', ''],
fields=[{
"format": "%Y-%m-%d",
"name": "Date",
"type": "date"
}, {
"format": "default",
"name": "Country/Region",
"type": "string"
}, {
"format": "default",
"name": "Province/State",
"type": "string"
}, {
"decimalChar": ".",
"format": "default",
"groupChar": "",
"name": "Lat",
"type": "number"
}, {
"decimalChar": ".",
"format": "default",
"groupChar": "",
"name": "Long",
"type": "number"
}, {
"format": "default",
"groupChar": "",
"name": "Confirmed",
"title": "Cumulative total confirmed cases to date",
"type": "integer"
}, {
"format": "default",
"groupChar": "",
"name": "Recovered",
"title": "Cumulative total recovered cases to date",
"type": "integer"
}, {
"format": "default",
"groupChar": "",
"name": "Deaths",
"title": "Cumulative total deaths to date",
"type": "integer"
}]),
update_schema('worldwide-aggregated',
fields=[{
"format": "%Y-%m-%d",
"name": "Date",
"type": "date"
}, {
"format": "default",
"name": "Country/Region",
"type": "string"
}, {
"format": "default",
"name": "Province/State",
"type": "string"
}, {
"decimalChar": ".",
"format": "default",
"groupChar": "",
"name": "Lat",
"type": "number"
}, {
"decimalChar": ".",
"format": "default",
"groupChar": "",
"name": "Long",
"type": "number"
}, {
"format": "default",
"groupChar": "",
"name": "Confirmed",
"title": "Cumulative total confirmed cases to date",
"type": "integer"
}, {
"format": "default",
"groupChar": "",
"name": "Recovered",
"title": "Cumulative total recovered cases to date",
"type": "integer"
}, {
"format": "default",
"groupChar": "",
"name": "Deaths",
"title": "Cumulative total deaths to date",
"type": "integer"
}]),
