def test_column(sql):
t = Table(sql)
r = compute(t['x'])
assert r == [1, 10, 100]
assert compute(t[['x']]) == [(1,), (10,), (100,)]
assert compute(t.count()) == 3
def test_column():
data = [(1, 2), (10, 20), (100, 200)]
sql = SQL('sqlite:///:memory:', 'foo', schema='{x: int, y: int}')
sql.extend(data)
t = Table(sql)
assert compute(t['x']) == [1, 10, 100]
assert compute(t[['x']]) == [(1,), (10,), (100,)]
assert compute(t.count()) == 3
def build_table(table_name, rows):
"""build the table to use in our example.
if already built just open it"""
if not os.path.exists(table_name):
ds = 'x, {i: int64; f: float64}'
p = params(clevel=5, storage=table_name)
t = Table([], dshape=ds, params=p)
for i in xrange(rows):
t.append((i, random()))
t.commit()
else:
t = open(table_name)
return t
def test_all_construct():
# Assert that the pretty pritner works for all of the
# toplevel structures
expected_ds = dshape('3, int')
a = NDArray([1,2,3])
str(a)
repr(a)
a.datashape._equal(expected_ds)
a = Array([1,2,3])
str(a)
repr(a)
a.datashape._equal(expected_ds)
a = NDTable([(1, 1)])
str(a)
repr(a)
#a.datashape._equal(expected_ds)
a = Table([(1, 1)])
str(a)
repr(a)
def test_expr_client_interactive():
ec = Client('localhost:6363', 'accounts')
t = Table(ec)
assert compute(t.name) == ['Alice', 'Bob']
assert (into(set, compute(by(t.name, min=t.amount.min(),
max=t.amount.max()))) ==
set([('Alice', 100, 100), ('Bob', 200, 200)]))
def test_string_dataset(tmpcsv):
raw = 'a,b,2.0\nc,1999,3.0\nd,3.0,4.0'
with open(tmpcsv, mode='w') as f:
f.write(raw)
csv = CSV(tmpcsv, columns=list('xyz'))
t = Table(csv)
x = into(list, t)
assert x == [('a', 'b', 2.0), ('c', '1999', 3.0), ('d', '3.0', 4.0)]
def test_simple():
if not os.path.exists('./noaa_data'):
p = params(clevel=5, storage='./noaa_data')
t = Table([], dshape='{f0: int, f1:int, f2:int, f3:float}', params=p)
# TODO: chunkwise copy
t.append(adapter[:])
t.commit()
else:
t = open('ctable://noaa_data')
print '--------------------------------------'
print 'mean', mean(t, 'f3')
print 'std', std(t, 'f2')
print '--------------------------------------'
qs1 = select(t, lambda x: x > 80000, 'f0')
qs2 = select2(t, lambda x,y: x > y, ['f0', 'f1'])
result = t[qs1]
def test_custom_dshape():
from blaze import RecordDecl, derived
from blaze import int32
class CustomStock(RecordDecl):
max = int32
min = int32
@derived
def mid(self):
return (self.min + self.max) / 2
a = Table([('GOOG', 120, 153)], CustomStock)
def build_table(table_name, rows):
"""build the table to use in our example.
if already built just open it"""
if not os.path.exists(table_name):
ds = 'x, {i: int64; f: float64}'
p = params(clevel=5, storage=table_name)
t = Table([], dshape=ds, params=p)
for i in xrange(rows):
t.append((i, random()))
t.commit()
else:
t = open(table_name)
return t
def test_simple():
if not os.path.exists('./noaa_data'):
p = params(clevel=5, storage='./noaa_data')
t = Table([], dshape='{f0: int, f1:int, f2:int, f3:float}', params=p)
# TODO: chunkwise copy
t.append(adapter[:])
t.commit()
else:
t = open('ctable://noaa_data')
print '--------------------------------------'
print 'mean', mean(t, 'f3')
print 'std', std(t, 'f2')
print '--------------------------------------'
qs1 = select(t, lambda x: x > 80000, 'f0')
qs2 = select2(t, lambda x, y: x > y, ['f0', 'f1'])
result = t[qs1]
def test_different_schema_raises():
with tmpfile('.csv') as filename:
df = pd.DataFrame(np.random.randn(10, 2))
df.to_csv(filename, index=False, header=False)
with pytest.raises(TypeError):
Table(CSV(filename), columns=list('ab'))
