def test_distinct_name():
t = Symbol('t', 'var * {id: int32, name: string}')
assert t.name.isidentical(t['name'])
assert t.distinct().name.isidentical(t.distinct()['name'])
assert t.id.distinct()._name == 'id'
assert t.name._name == 'name'
def test_Distinct():
x = np.array([('Alice', 100), ('Alice', -200), ('Bob', 100), ('Bob', 100)],
dtype=[('name', 'S5'), ('amount', 'i8')])
t = Symbol('t', 'var * {name: string, amount: int64}')
assert eq(compute(t['name'].distinct(), x), np.unique(x['name']))
assert eq(compute(t.distinct(), x), np.unique(x))
def test_Distinct():
t = Symbol('t', 'var * {name: string, amount: int32}')
r = distinct(t['name'])
print(r.dshape)
assert r.dshape == dshape('var * string')
assert r._name == 'name'
r = t.distinct()
assert r.dshape == t.dshape
def test_Distinct():
x = np.array([('Alice', 100),
('Alice', -200),
('Bob', 100),
('Bob', 100)],
dtype=[('name', 'S5'), ('amount', 'i8')])
t = Symbol('t', 'var * {name: string, amount: int64}')
assert eq(compute(t['name'].distinct(), x),
np.unique(x['name']))
assert eq(compute(t.distinct(), x),
np.unique(x))
t[t.amount > 50]['name']: [],
by(t.name, t.amount.sum()): [],
by(t.id, t.id.count()): [],
by(t[['id', 'amount']], t.id.count()): [],
by(t[['id', 'amount']], (t.amount + 1).sum()): [mongo],
by(t[['id', 'amount']], t.name.nunique()): [mongo],
by(t.id, t.amount.count()): [],
by(t.id, t.id.nunique()): [mongo],
# by(t, t.count()): [],
# by(t.id, t.count()): [df],
t[['amount', 'id']]: [x], # https://github.com/numpy/numpy/issues/3256
t[['id', 'amount']]: [x, bc], # bcolz sorting
t[0]: [sql, mongo],
t[::2]: [sql, mongo],
t.id.utcfromtimestamp: [sql],
t.distinct().nrows: [],
t.nelements(axis=0): [],
t.nelements(axis=None): []
}
base = df
def df_eq(a, b):
return (list(a.columns) == list(b.columns)
and list(a.dtypes) == list(b.dtypes)
and into(set, into(list, a)) == into(set, into(list, b)))
def typename(obj):
return type(obj).__name__
