def test_repeat_empty_frame2():
f0 = dt.Frame(A=[], B=[], C=[], stypes=[dt.int32, dt.str32, dt.float32])
f1 = dt.repeat(f0, 1000)
frame_integrity_check(f1)
assert f1.names == f0.names
assert f1.stypes == f0.stypes
assert f1.to_list() == f0.to_list()
def test_issue1921():
n = 1921
DTA = dt.Frame(A=range(n))
DTB = dt.repeat(dt.Frame(B=["hey"], stype=dt.str64), n)
DT = dt.cbind(DTA, DTB)
out = DT.to_csv()
assert out == "\n".join(["A,B"] + ["%d,hey" % i for i in range(n)] + [""])
def test_sort_consts():
DT = dt.Frame(A=[5], B=[7.9], C=["Hello"], D=[None])
DT = dt.repeat(DT, 1000)
assert_equals(DT[:, :, sort(f.A)], DT)
assert_equals(DT[:, :, sort(f.B)], DT)
assert_equals(DT[:, :, sort(f.C)], DT)
assert_equals(DT[:, :, sort(f.D)], DT)
def test_materialize():
DT1 = dt.Frame(A=range(12))[::2, :]
DT2 = dt.repeat(dt.Frame(B=["red", "green", "blue"]), 2)
DT3 = dt.Frame(C=[4, 2, 9.1, 12, 0])
DT = dt.cbind(DT1, DT2, DT3, force=True)
assert frame_columns_virtual(DT) == (True, True, True)
DT.materialize()
assert frame_columns_virtual(DT) == (False, False, False)
def test_tonumpy_issue2050():
n = 1234
DT = dt.Frame(A=[1, 2, None, 4, 5],
B=range(5),
C=[4, None, None, None, 4],
stype=int)
DT = dt.repeat(DT[:, ["A", "B", "C"]], n)
assert DT.sum().to_list() == [[12 * n], [10 * n], [8 * n]]
assert DT.to_numpy().sum() == 30 * n
def test_cast_huge_to_str():
# Test that converting a huge column into str would properly overflow it
# into str64 type. See issue #1695
# This test takes up to 2s to run (or up to 5s if doing an integrity check)
DT = dt.repeat(dt.Frame(BIG=["ABCDEFGHIJ" * 100000]), 3000)
assert DT.stypes == (dt.str32, )
RES = DT[:, dt.str32(f.BIG)]
assert RES.stypes == (dt.str64, )
assert RES[-1, 0] == DT[0, 0]
def test_dt_repeat_multicol():
f0 = dt.Frame(A=[None, 1.4, -2.6, 3.9998],
B=["row", "row", "row", "your boat"],
C=[25, -9, 18, 2],
D=[True, None, True, False])
f1 = dt.repeat(f0, 4)
frame_integrity_check(f1)
assert isview(f1)
assert f1.names == f0.names
assert f1.stypes == f0.stypes
assert f1.to_list() == [col * 4 for col in f0.to_list()]
def test_materialize():
DT1 = dt.Frame(A=range(12))[::2, :]
DT2 = dt.repeat(dt.Frame(B=["red", "green", "blue"]), 2)
DT3 = dt.Frame(C=[4, 2, 9.1, 12, 0])
DT = dt.cbind(DT1, DT2, DT3, force=True)
assert frame_column_rowindex(DT, 0).type == "slice"
assert frame_column_rowindex(DT, 1).type == "arr32"
assert frame_column_rowindex(DT, 2) is None
DT.materialize()
assert frame_column_rowindex(DT, 0) is None
assert frame_column_rowindex(DT, 1) is None
assert frame_column_rowindex(DT, 2) is None
def test_dt_repeat_empty_frame():
f0 = dt.Frame()
f1 = dt.repeat(f0, 5)
frame_integrity_check(f1)
assert f1.to_list() == []
def test_dt_repeat_view():
f0 = dt.Frame(A=[1, 3, 4, 5], B=[2, 6, 3, 1])
f1 = f0[::2, :]
f2 = dt.repeat(f1, 5)
frame_integrity_check(f2)
assert f2.to_dict() == {"A": [1, 4] * 5, "B": [2, 3] * 5}
def test_dt_repeat2():
f0 = dt.Frame(["A", "B", "CDE"])
f1 = dt.repeat(f0, 7)
frame_integrity_check(f1)
assert f1.to_list() == [f0.to_list()[0] * 7]
def test_dt_repeat():
f0 = dt.Frame(range(10))
f1 = dt.repeat(f0, 3)
frame_integrity_check(f1)
assert f1.to_list() == [list(range(10)) * 3]
def make_datatable(dt,
rows,
select,
groupby=None,
join=None,
sort=None,
engine=None,
mode=None,
replacement=None):
"""
Implementation of the `Frame.__call__()` method.
This is the "main" function in the module; it is responsible for
evaluating various transformations when they are applied to a target
Frame.
"""
if isinstance(groupby, datatable.join):
join = groupby
groupby = None
update_mode = mode == "update"
delete_mode = mode == "delete"
jframe = join.joinframe if join else None
with f.bind_datatable(dt), g.bind_datatable(jframe):
ee = make_engine(engine, dt, jframe)
ee.rowindex = dt.internal.rowindex
rowsnode = make_rowfilter(rows, ee)
grbynode = make_groupby(groupby, ee)
colsnode = make_columnset(select, ee, update_mode)
sortnode = make_sort(sort, ee)
if join:
join.execute(ee)
if sortnode:
if isinstance(rowsnode, AllRFNode) and not grbynode:
rowsnode = SortedRFNode(sortnode)
else: # pragma: no cover
raise NotImplementedError(
"Cannot yet apply sort argument to a view datatable or "
"combine with rows / groupby argument.")
assert not delete_mode
if update_mode:
assert grbynode is None
allrows = isinstance(rowsnode, AllRFNode)
# Without `materialize`, when an update is applied to a view,
# `rowsnode.execute()` will merge the rowindex implied by
# `rowsnode` with its parent's rowindex. This will cause the
# parent's data to be updated, which is wrong.
dt.materialize()
if isinstance(replacement, (int, float, str, type(None))):
replacement = datatable.Frame([replacement])
if allrows:
replacement = datatable.repeat(replacement, dt.nrows)
elif isinstance(replacement, datatable.Frame):
pass
elif isinstance(replacement, BaseExpr):
_col = replacement.evaluate_eager(ee)
_colset = core.columns_from_columns([_col])
replacement = _colset.to_frame(None)
else:
replacement = datatable.Frame(replacement)
rowsnode.execute()
colsnode.execute_update(dt, replacement)
return
rowsnode.execute()
if grbynode:
grbynode.execute(ee)
colsnode.execute()
res_dt = ee.columns.to_frame(colsnode.column_names)
if grbynode and res_dt.nrows == dt.nrows:
res_dt.internal.groupby = ee.groupby
return res_dt
raise RuntimeError("Unable to calculate the result") # pragma: no cover
def test_dt_repeat_empty_frame():
f0 = dt.Frame()
f1 = dt.repeat(f0, 5)
f1.internal.check()
assert f1.to_list() == []
def test_dt_repeat2():
f0 = dt.Frame(["A", "B", "CDE"])
f1 = dt.repeat(f0, 7)
f1.internal.check()
assert f1.to_list() == [f0.to_list()[0] * 7]
def test_dt_repeat():
f0 = dt.Frame(range(10))
f1 = dt.repeat(f0, 3)
f1.internal.check()
assert f1.to_list() == [list(range(10)) * 3]
