def test_reductions():
assert str(compute(sum(t['amount']), s, post_compute=False)) == \
str(sa.sql.functions.sum(s.c.amount))
assert str(compute(mean(t['amount']), s, post_compute=False)) == \
str(sa.sql.func.avg(s.c.amount))
assert str(compute(count(t['amount']), s, post_compute=False)) == \
str(sa.sql.func.count(s.c.amount))
assert 'amount_sum' == compute(sum(t['amount']), s, post_compute=False).name
def test_reductions():
assert str(compute(sum(t['amount']), s, post_compute=False)) == \
str(sa.sql.functions.sum(s.c.amount))
assert str(compute(mean(t['amount']), s, post_compute=False)) == \
str(sa.sql.func.avg(s.c.amount))
assert str(compute(count(t['amount']), s, post_compute=False)) == \
str(sa.sql.func.count(s.c.amount))
assert 'amount_sum' == compute(sum(t['amount']), s,
post_compute=False).name
def test_lean_by_with_summary():
assert lean_projection(by(t.x, total=t.y.sum()))._child.isidentical(t[["x", "y"]])
tt = t[["x", "y"]]
result = lean_projection(by(t.x, a=t.y.sum(), b=t.z.sum())[["x", "a"]])
expected = Projection(By(Field(tt, "x"), summary(a=sum(Field(tt, "y")))), ("x", "a"))
assert result.isidentical(expected)
def test_by():
t = TableSymbol("t", "{name: string, amount: int32, id: int32}")
r = by(t["name"], total=sum(t["amount"]))
print(r.schema)
assert isinstance(r.schema[0], Record)
assert str(r.schema[0]["name"]) == "string"
def test_by():
t = TableSymbol('t', '{name: string, amount: int32, id: int32}')
r = by(t['name'], sum(t['amount']))
print(r.schema)
assert isinstance(r.schema[0], Record)
assert str(r.schema[0]['name']) == 'string'
def test_by():
t = symbol('t', 'var * {name: string, amount: int32, id: int32}')
r = by(t['name'], total=sum(t['amount']))
print(r.schema)
assert isinstance(r.schema[0], Record)
assert str(r.schema[0]['name']) == 'string'
def test_sum():
(chunk, chunk_expr), (agg, agg_expr) = split(t, t.amount.sum())
assert chunk.schema == t.schema
assert chunk_expr.isidentical(chunk.amount.sum(keepdims=True))
assert isscalar(agg.dshape.measure)
assert agg_expr.isidentical(sum(agg))
def test_sum():
(chunk, chunk_expr), (agg, agg_expr) = split(t, t.amount.sum())
assert chunk.schema == t.schema
assert chunk_expr.isidentical(chunk.amount.sum(keepdims=True))
assert isscalar(agg.dshape.measure)
assert agg_expr.isidentical(sum(agg))
def test_by_two():
result = compute(by(tbig[['name', 'sex']], total=sum(tbig['amount'])),
dfbig)
expected = DataFrame(
[['Alice', 'F', 200], ['Drew', 'F', 100], ['Drew', 'M', 300]],
columns=['name', 'sex', 'total'])
tm.assert_frame_equal(result, expected)
def test_by_two():
result = compute(by(tbig[['name', 'sex']], sum(tbig['amount'])), dfbig)
expected = DataFrame([['Alice', 'F', 200],
['Drew', 'F', 100],
['Drew', 'M', 300]],
columns=['name', 'sex', 'amount_sum'])
assert str(result) == str(expected)
def test_reductions():
assert compute(sum(t['amount']), data) == 100 + 200 + 50
assert compute(min(t['amount']), data) == 50
assert compute(max(t['amount']), data) == 200
assert compute(nunique(t['amount']), data) == 3
assert compute(nunique(t['name']), data) == 2
assert compute(count(t['amount']), data) == 3
assert compute(any(t['amount'] > 150), data) is True
assert compute(any(t['amount'] > 250), data) is False
def test_by_two():
result = compute(by(tbig[['name', 'sex']], total=sum(tbig['amount'])), dfbig)
expected = DataFrame([['Alice', 'F', 200],
['Drew', 'F', 100],
['Drew', 'M', 300]],
columns=['name', 'sex', 'total'])
assert str(result) == str(expected)
def test_reductions():
assert compute(sum(t['amount']), data) == 100 + 200 + 50
assert compute(min(t['amount']), data) == 50
assert compute(max(t['amount']), data) == 200
assert compute(nunique(t['amount']), data) == 3
assert compute(nunique(t['name']), data) == 2
assert compute(count(t['amount']), data) == 3
assert compute(any(t['amount'] > 150), data) is True
assert compute(any(t['amount'] > 250), data) is False
def test_reductions():
assert compute(mean(t['amount']), ddf) == 350 / 3
assert compute(count(t['amount']), ddf) == 3
assert compute(sum(t['amount']), ddf) == 100 + 200 + 50
assert compute(min(t['amount']), ddf) == 50
assert compute(max(t['amount']), ddf) == 200
assert compute(var(t['amount']), ddf) == df.amount.var(ddof=0)
assert compute(var(t['amount'], unbiased=True), ddf) == df.amount.var()
assert compute(std(t['amount']), ddf) == df.amount.std(ddof=0)
assert compute(std(t['amount'], unbiased=True), ddf) == df.amount.std()
def test_reductions():
assert compute(mean(t['amount']), ddf) == 350 / 3.0
assert compute(count(t['amount']), ddf) == 3
assert compute(sum(t['amount']), ddf) == 100 + 200 + 50
assert compute(min(t['amount']), ddf) == 50
assert compute(max(t['amount']), ddf) == 200
tm.assert_almost_equal(compute(var(t['amount']), ddf), df.amount.var(ddof=0))
tm.assert_almost_equal(compute(var(t['amount'], unbiased=True), ddf), df.amount.var())
assert compute(std(t['amount']), ddf) == df.amount.std(ddof=0)
assert compute(std(t['amount'], unbiased=True), ddf) == df.amount.std()
def test_lean_by_with_summary():
assert lean_projection(by(t.x, total=t.y.sum()))._child.isidentical(
t[['x', 'y']], )
tt = t[['x', 'y']]
result = lean_projection(by(t.x, a=t.y.sum(), b=t.z.sum())[['x', 'a']])
expected = Projection(
By(Field(tt, 'x'), summary(a=sum(Field(tt, 'y')))),
('x', 'a'),
)
assert result.isidentical(expected)
def test_reductions():
assert compute(mean(t['amount']), df) == 350./3
assert compute(count(t['amount']), df) == 3
assert compute(sum(t['amount']), df) == 100 + 200 + 50
assert compute(min(t['amount']), df) == 50
assert compute(max(t['amount']), df) == 200
assert compute(nunique(t['amount']), df) == 3
assert compute(nunique(t['name']), df) == 2
assert compute(any(t['amount'] > 150), df) == True
assert compute(any(t['amount'] > 250), df) == False
assert compute(var(t['amount']), df) == df.amount.var(ddof=0)
assert compute(var(t['amount'], unbiased=True), df) == df.amount.var()
assert compute(std(t['amount']), df) == df.amount.std(ddof=0)
assert compute(std(t['amount'], unbiased=True), df) == df.amount.std()
def test_reduction():
t = TableSymbol("t", "{name: string, amount: int32}")
r = sum(t["amount"])
assert r.dshape in (dshape("int64"), dshape("{amount: int64}"), dshape("{amount_sum: int64}"))
assert "amount" not in str(t.count().dshape)
assert t.count().dshape[0] in (int32, int64)
assert "int" in str(t.count().dshape)
assert "int" in str(t.nunique().dshape)
assert "string" in str(t["name"].max().dshape)
assert "string" in str(t["name"].min().dshape)
assert "string" not in str(t.count().dshape)
t = TableSymbol("t", "{name: string, amount: real, id: int}")
assert "int" in str(t["id"].sum().dshape)
assert "int" not in str(t["amount"].sum().dshape)
def test_reduction():
t = TableSymbol('t', '{name: string, amount: int32}')
r = sum(t['amount'])
assert r.dshape in (dshape('int64'), dshape('{amount: int64}'),
dshape('{amount_sum: int64}'))
assert 'amount' not in str(t.count().dshape)
assert t.count().dshape[0] in (int32, int64)
assert 'int' in str(t.count().dshape)
assert 'int' in str(t.nunique().dshape)
assert 'string' in str(t['name'].max().dshape)
assert 'string' in str(t['name'].min().dshape)
assert 'string' not in str(t.count().dshape)
t = TableSymbol('t', '{name: string, amount: real, id: int}')
assert 'int' in str(t['id'].sum().dshape)
assert 'int' not in str(t['amount'].sum().dshape)
def test_reduction():
t = symbol('t', 'var * {name: string, amount: int32}')
r = sum(t['amount'])
assert r.dshape in (dshape('int64'),
dshape('{amount: int64}'),
dshape('{amount_sum: int64}'))
assert 'amount' not in str(t.count().dshape)
assert t.count().dshape[0] in (int32, int64)
assert 'int' in str(t.count().dshape)
assert 'int' in str(t.nunique().dshape)
assert 'string' in str(t['name'].max().dshape)
assert 'string' in str(t['name'].min().dshape)
assert 'string' not in str(t.count().dshape)
t = symbol('t', 'var * {name: string, amount: real, id: int}')
assert 'int' in str(t['id'].sum().dshape)
assert 'int' not in str(t['amount'].sum().dshape)
def test_reduction():
t = TableSymbol('t', '{name: string, amount: int32}')
r = sum(t['amount'])
print(type(r.dshape))
print(type(dshape('int32')))
print(r.dshape)
assert r.dshape in (dshape('int32'),
dshape('{amount: int32}'),
dshape('{amount_sum: int32}'))
assert 'amount' not in str(t.count().dshape)
assert first(t.count().dshape[0].types)[0] in (int32, int64)
assert 'int' in str(t.count().dshape)
assert 'int' in str(t.nunique().dshape)
assert 'string' in str(t['name'].max().dshape)
assert 'string' in str(t['name'].min().dshape)
assert 'string' not in str(t.count().dshape)
t = TableSymbol('t', '{name: string, amount: real, id: int}')
assert 'int' in str(t['id'].sum().dshape)
assert 'int' not in str(t['amount'].sum().dshape)
def test_by_summary():
t = TableSymbol('t', '{name: string, amount: int32, id: int32}')
a = by(t['name'], sum=sum(t['amount']))
b = by(t['name'], summary(sum=sum(t['amount'])))
assert a.isidentical(b)
def test_by_summary():
t = TableSymbol("t", "{name: string, amount: int32, id: int32}")
a = by(t["name"], sum=sum(t["amount"]))
b = by(t["name"], summary(sum=sum(t["amount"])))
assert a.isidentical(b)
def test_by_summary_printing():
t = symbol("t", "var * {name: string, amount: int32, id: int32}")
assert str(by(t.name, total=sum(t.amount))) == "by(t.name, total=sum(t.amount))"
def test_by_summary_printing():
t = symbol('t', 'var * {name: string, amount: int32, id: int32}')
assert (str(by(t.name, total=sum(t.amount))) ==
'by(t.name, total=sum(t.amount))')
def test_by_summary():
t = symbol('t', 'var * {name: string, amount: int32, id: int32}')
a = by(t['name'], sum=sum(t['amount']))
b = by(t['name'], summary(sum=sum(t['amount'])))
assert a.isidentical(b)
