def test_rowfirst():
assert str(dt.rowfirst(f.A)) == str(f.A.rowfirst())
assert str(dt.rowfirst(f[:])) == str(f[:].rowfirst())
DT = dt.Frame({'A':[1, None, None, None],
'B':[None, 3, 4, None],
'C':[2, None, 5, None]})
assert_equals(DT[:, f[:].rowfirst()], DT[:, dt.rowfirst(f[:])])
def test_rowfirstlast_strs(st):
DT = dt.Frame([("a", None, "b", None), (None, None, "x", None),
("", "", "AHA!", "last")],
stype=st)
RES = DT[:, [rowfirst(f[:]), rowlast(f[:])]]
assert_equals(RES, dt.Frame([["a", "x", ""], ["b", "x", "last"]],
stype=st))
def test_rowfirstlast_floats(st):
DT = dt.Frame([(3.0, 7.0, math.nan),
(math.inf, None, None),
(math.nan, 2.5, -111)], stype=st)
RES = DT[:, [rowfirst(f[:]), rowlast(f[:])]]
assert_equals(RES, dt.Frame([[3.0, math.inf, 2.5],
[7.0, math.inf, -111.0]], stype=st))
def test_reprs():
# Check that row-expressions can be repr'd without errors
assert repr(rowall())
assert repr(rowany())
assert repr(rowsum())
assert repr(rowcount())
assert repr(rowmin())
assert repr(rowmax())
assert repr(rowfirst())
assert repr(rowlast())
assert repr(rowmean())
assert repr(rowsd())
def test_rowfirstlast_incompatible_types():
DT = dt.Frame([["a", None, "c", None], [1, 3, 4, None]])
assert_equals(DT[:, rowfirst(f[:])], dt.Frame(["a", "3", "c", None]))
def test_rowfirstlast_ints(st):
DT = dt.Frame([(7, 5, 19, 22), (None, 1, 2, None),
(None, None, None, None)],
stype=st)
RES = DT[:, [rowfirst(f[:]), rowlast(f[:])]]
assert_equals(RES, dt.Frame([[7, 1, None], [22, 2, None]], stype=st))
def test_rowfirstlast_bools():
DT = dt.Frame([(None, True, False), (False, None, None),
(None, None, None)])
RES = DT[:, [rowfirst(f[:]), rowlast(f[:])]]
assert_equals(RES, dt.Frame([[True, False, None], [False, False, None]]))
# remove black listed columns or column groups that smaller than minimal size
col_groups = {
key: val
for key, val in all_col_groups.items()
if not key in black_listed_columns or len(val) >= min_col_group_size
}
# list of column prefixes
columns = list(col_groups.keys())
# list of column ranges
ranges = [(min(idx), max(idx)) for idx in col_groups.values()]
# produce tuple for column slices
col_slices = [((col + "%d") % (desde), (col + "%d") % (hasta))
for (col, (desde, hasta)) in zip(columns, ranges)]
for c, r, s in zip(columns, ranges, col_slices):
update_map = {
c + "_sum": rowsum(f[s[0]:s[1]]),
c + "_mean": rowmean(f[s[0]:s[1]]),
c + "_sd": rowsd(f[s[0]:s[1]]),
c + "_max": rowmax(f[s[0]:s[1]]),
c + "_min": rowmin(f[s[0]:s[1]]),
c + "_range": rowmax(f[s[0]:s[1]]) - rowmin(f[s[0]:s[1]]),
c + "_first": rowfirst(f[s[0]:s[1]]),
c + "_last": rowlast(f[s[0]:s[1]]),
c + "_missing": (r[1] - r[0] + 1) - rowcount(f[s[0]:s[1]])
}
X[:, update(**update_map)]
return {"CreditCard-train-aug.csv": X}
def test_rowfirstlast_incompatible():
DT = dt.Frame(A=["a", "b", "c"], B=[1, 3, 4])
with pytest.raises(TypeError, match="Incompatible column types"):
assert DT[:, rowfirst(f[:])]
def create_data(
X: dt.Frame = None
) -> Union[str, List[str], dt.Frame, List[dt.Frame], np.ndarray,
List[np.ndarray], pd.DataFrame, List[pd.DataFrame], Dict[
str, str], # {data set names : paths}
Dict[str, dt.Frame], # {data set names : dt frames}
Dict[str, np.ndarray], # {data set names : np arrays}
Dict[str, pd.DataFrame], # {data set names : pd frames}
]:
if X is None:
return []
columns = None # columns = ["PAY_AMT", "BILL_AMT", "PAY_"]
ranges = None # [(1, 6), (1, 6), (2, 6)]
black_listed_columns = []
min_col_group_size = 2
# parse column names for time series column groups
if columns is None or columns == [] or \
ranges is None or ranges == []:
# match any column names that consist of alpha name (prefix) followed by integer index (suffix)
p = re.compile(r"^([a-zA-Z_]+)(\d+)$")
matches = [p.match(c) for c in X.names]
all_col_groups = defaultdict(list)
for m in matches:
if m is not None:
key = m.group(1)
val = int(m.group(2))
all_col_groups[key].append(val)
# remove black listed columns or column groups that smaller than minimal size
col_groups = {
key: val
for key, val in all_col_groups.items()
if not key in black_listed_columns
or len(val) >= min_col_group_size
}
# list of column prefixes
columns = list(col_groups.keys())
# list of column ranges
ranges = [(min(idx), max(idx)) for idx in col_groups.values()]
col_slices = [((col + "%d") % (desde), (col + "%d") % (hasta))
for (col, (desde, hasta)) in zip(columns, ranges)]
for c, r, s in zip(columns, ranges, col_slices):
update_map = {
c + "_sum": rowsum(f[s[0]:s[1]]),
c + "_mean": rowmean(f[s[0]:s[1]]),
c + "_sd": rowsd(f[s[0]:s[1]]),
c + "_max": rowmax(f[s[0]:s[1]]),
c + "_min": rowmin(f[s[0]:s[1]]),
c + "_range": rowmax(f[s[0]:s[1]]) - rowmin(f[s[0]:s[1]]),
c + "_first": rowfirst(f[s[0]:s[1]]),
c + "_last": rowlast(f[s[0]:s[1]]),
c + "_missing": (r[1] - r[0] + 1) - rowcount(f[s[0]:s[1]])
}
X[:, update(**update_map)]
return X
