def test_merge_project():
accounts = TableSymbol("accounts", "{name: string, balance: int32, id: int32}")
new_amount = (accounts["balance"] * 1.5).label("new")
c = merge(accounts[["name", "balance"]], new_amount)
assert c["new"].isidentical(new_amount)
assert c["name"].isidentical(accounts["name"])
assert c[["name", "new"]].isidentical(merge(accounts.name, new_amount))
def test_merge_project():
accounts = symbol('accounts',
'var * {name: string, balance: int32, id: int32}')
new_amount = (accounts['balance'] * 1.5).label('new')
c = merge(accounts[['name', 'balance']], new_amount)
assert c['new'].isidentical(new_amount)
assert c['name'].isidentical(accounts['name'])
assert c[['name', 'new']].isidentical(merge(accounts.name, new_amount))
def test_merge_project():
accounts = TableSymbol('accounts',
'{name: string, balance: int32, id: int32}')
new_amount = (accounts['balance'] * 1.5).label('new')
c = merge(accounts[['name', 'balance']], new_amount)
assert c['new'].isidentical(new_amount)
assert c['name'].isidentical(accounts['name'])
assert c[['name', 'new']].isidentical(merge(accounts.name, new_amount))
def test_merge():
t = TableSymbol("t", "int64")
p = TableSymbol("p", "{amount:int}")
accounts = TableSymbol("accounts", "{name: string, balance: int32, id: int32}")
new_amount = (accounts.balance * 1.5).label("new")
c = merge(accounts[["name", "balance"]], new_amount)
assert c.fields == ["name", "balance", "new"]
assert c.schema == dshape("{name: string, balance: int32, new: float64}")
with pytest.raises(ValueError):
merge(t, t)
with pytest.raises(ValueError):
merge(t, p)
def test_merge():
t = TableSymbol('t', 'int64')
p = TableSymbol('p', '{amount:int}')
accounts = TableSymbol('accounts',
'{name: string, balance: int32, id: int32}')
new_amount = (accounts['balance'] * 1.5).label('new')
c = merge(accounts[['name', 'balance']], new_amount)
assert c.columns == ['name', 'balance', 'new']
with pytest.raises(TypeError):
merge(t, t)
with pytest.raises(ValueError):
merge(t, p)
def test_merge():
t = symbol('t', 'int64')
p = symbol('p', 'var * {amount:int}')
accounts = symbol('accounts',
'var * {name: string, balance: int32, id: int32}')
new_amount = (accounts.balance * 1.5).label('new')
c = merge(accounts[['name', 'balance']], new_amount)
assert c.fields == ['name', 'balance', 'new']
assert c.schema == dshape('{name: string, balance: int32, new: float64}')
with pytest.raises(ValueError):
merge(t, t)
with pytest.raises(ValueError):
merge(t, p)
def test_merge():
t = TableSymbol('t', 'int64')
p = TableSymbol('p', '{amount:int}')
accounts = TableSymbol('accounts',
'{name: string, balance: int32, id: int32}')
new_amount = (accounts['balance'] * 1.5).label('new')
c = merge(accounts[['name', 'balance']], new_amount)
assert c.fields == ['name', 'balance', 'new']
assert c.schema == dshape('{name: string, balance: int32, new: float64}')
with pytest.raises(ValueError):
merge(t, t)
with pytest.raises(ValueError):
merge(t, p)
def test_complex_group_by():
expr = by(merge(tbig.amount // 10, tbig.id % 2), count=tbig.name.count())
result = compute(expr, dfbig) # can we do this? yes we can!
expected = dfbig.groupby([dfbig.amount // 10,
dfbig.id % 2])['name'].count().reset_index()
expected = expected.rename(columns={'name': 'count'})
tm.assert_frame_equal(result, expected)
def test_merge():
accounts = TableSymbol('accounts',
'{name: string, balance: int32, id: int32}')
new_amount = (accounts['balance'] * 1.5).label('new')
c = merge(accounts[['name', 'balance']], new_amount)
assert c.columns == ['name', 'balance', 'new']
def test_complex_group_by():
expr = by(merge(tbig.amount // 10, tbig.id % 2),
count=tbig.name.count())
result = compute(expr, dfbig) # can we do this? yes we can!
expected = dfbig.groupby([dfbig.amount // 10,
dfbig.id % 2])['name'].count().reset_index()
expected = expected.rename(columns={'name': 'count'})
tm.assert_frame_equal(result, expected)
def test_merge():
col = (t['amount'] * 2).label('new')
expr = merge(t['name'], col)
expected = DataFrame([['Alice', 200], ['Bob', 400], ['Alice', 100]],
columns=['name', 'new'])
result = compute(expr, df)
tm.assert_frame_equal(result, expected)
def test_merge():
t = symbol('t', 'int64')
p = symbol('p', 'var * {amount: int}')
accounts = symbol('accounts',
'var * {name: string, balance: int32, id: int32}')
new_amount = (accounts.balance * 1.5).label('new')
c = merge(accounts[['name', 'balance']], new_amount)
assert c.fields == ['name', 'balance', 'new']
assert c.schema == dshape('{name: string, balance: int32, new: float64}')
d = merge(t, p)
assert d.fields == ['t', 'amount']
assert_dshape_equal(d.dshape, dshape('var * {t: int64, amount: int}'))
with pytest.raises(TypeError) as e:
merge(t, t)
assert str(e.value) == 'cannot merge all scalar expressions'
def test_merge_with_common_subexpression():
df = DataFrame(np.random.rand(5, 2), columns=list('ab'))
t = symbol('t', discover(df))
expr = merge((t.a - t.a % 3).label('a'), (t.a % 3).label('b'))
result = compute(expr, {t: df})
expected = pd.concat(
[pd.Series(df.a - df.a % 3, name='a'),
pd.Series(df.a % 3, name='b')],
axis=1)
tm.assert_frame_equal(result, expected)
def test_merge():
t = symbol('t', 'int64')
p = symbol('p', 'var * {amount: int}')
accounts = symbol('accounts',
'var * {name: string, balance: int32, id: int32}')
new_amount = (accounts.balance * 1.5).label('new')
c = merge(accounts[['name', 'balance']], new_amount)
assert c.fields == ['name', 'balance', 'new']
assert c.schema == dshape('{name: string, balance: int32, new: float64}')
d = merge(t, p)
assert d.fields == ['t', 'amount']
assert_dshape_equal(d.dshape, dshape('var * {t: int64, amount: int}'))
with pytest.raises(TypeError) as e:
merge(t, t)
assert str(e.value) == 'cannot merge all scalar expressions'
def test_by_groupby_deep():
data = [(1, 2, 'Alice'), (1, 3, 'Bob'), (2, 4, 'Alice'), (2, 4, '')]
schema = '{x: int, y: int, name: string}'
t = Symbol('t', datashape.var * schema)
t2 = t[t['name'] != '']
t3 = merge(t2.x, t2.name)
expr = by(t3.name, t3.x.mean())
result = set(compute(expr, data))
assert result == set([('Alice', 1.5), ('Bob', 1.0)])
def test_merge():
col = (t['amount'] * 2).label('new')
expr = merge(t['name'], col)
result = str(compute(expr, s))
assert 'amount * ' in result
assert 'FROM accounts' in result
assert 'SELECT accounts.name' in result
assert 'new' in result
def test_merge():
col = (t['amount'] * 2).label('new')
expr = merge(t['name'], col)
expected = DataFrame([['Alice', 200],
['Bob', 400],
['Alice', 100]],
columns=['name', 'new'])
result = compute(expr, df)
tm.assert_frame_equal(result, expected)
def test_merge():
col = (t['amount'] * 2).label('new')
expr = merge(t['name'], col)
result = str(compute(expr, s))
assert 'amount * ' in result
assert 'FROM accounts' in result
assert 'SELECT accounts.name' in result
assert 'new' in result
def test_merge_where():
t2 = t[t.id == 1]
expr = merge(t2[['amount', 'name']], t2.id)
result = compute(expr, s)
expected = normalize("""SELECT
accounts.amount,
accounts.name,
accounts.id
FROM accounts
WHERE accounts.id = :id_1
""")
assert normalize(str(result)) == expected
def test_merge_where():
t2 = t[t.id == 1]
expr = merge(t2[['amount', 'name']], t2.id)
result = compute(expr, s)
expected = normalize("""SELECT
accounts.amount,
accounts.name,
accounts.id
FROM accounts
WHERE accounts.id = :id_1
""")
assert normalize(str(result)) == expected
def test_merge_with_common_subexpression():
df = DataFrame(np.random.rand(5, 2), columns=list('ab'))
t = symbol('t', discover(df))
expr = merge((t.a - t.a % 3).label('a'), (t.a % 3).label('b'))
result = compute(expr, {t: df})
expected = pd.concat(
[
pd.Series(df.a - df.a % 3, name='a'),
pd.Series(df.a % 3, name='b')
],
axis=1
)
tm.assert_frame_equal(result, expected)
def test_by_groupby_deep():
data = [(1, 2, 'Alice'),
(1, 3, 'Bob'),
(2, 4, 'Alice'),
(2, 4, '')]
schema = '{x: int, y: int, name: string}'
t = TableSymbol('t', schema)
t2 = t[t['name'] != '']
t3 = merge(t2.x, t2.name)
expr = by(t3.name, t3.x.mean())
result = set(compute(expr, data))
assert result == set([('Alice', 1.5), ('Bob', 1.0)])
def test_merge():
expr = lean_projection(merge(a=t.x + 1, y=t.y))
assert expr._child.isidentical(t[["x", "y"]])
def test_merge_repeats():
accounts = symbol('accounts',
'var * {name: string, balance: int32, id: int32}')
with pytest.raises(ValueError):
merge(accounts, (accounts.balance + 1).label('balance'))
def test_merge_with_table():
expr = lean_projection(merge(t, a=t.x + 1))
assert expr.isidentical(expr) # wut?
def test_merge():
col = (t['amount'] * 2).label('new')
expr = merge(t['name'], col)
assert list(compute(expr, data)) == [(row[0], row[1] * 2) for row in data]
def test_complex_group_by():
expr = by(merge(tbig.amount // 10, tbig.id % 2),
count=tbig.name.count())
compute(expr, dfbig) # can we do this?
def test_merge_with_table():
expr = lean_projection(merge(t, a=t.x + 1))
assert expr.isidentical(expr) # wut?
def test_merge_repeats():
accounts = TableSymbol('accounts',
'{name: string, balance: int32, id: int32}')
with pytest.raises(ValueError):
merge(accounts, (accounts.balance + 1).label('balance'))
def test_merge_repeats():
accounts = TableSymbol("accounts", "{name: string, balance: int32, id: int32}")
with pytest.raises(ValueError):
merge(accounts, (accounts.balance + 1).label("balance"))
def test_merge():
col = (t['amount'] * 2).label('new')
expr = merge(t['name'], col)
assert list(compute(expr, data)) == [(row[0], row[1] * 2) for row in data]
def test_merge():
expr = lean_projection(merge(a=t.x + 1, y=t.y))
assert expr._child.isidentical(t[['x', 'y']])
