def test_rowcount():
assert str(dt.rowcount(f.A)) == str(f.A.rowcount())
assert str(dt.rowcount(f[:])) == str(f[:].rowcount())
DT = dt.Frame({"C": [2, 5, 30, 20, 10],
"D": [10, 8, 20, 20, 1]})
assert_equals(DT[:, f[:].rowcount()], DT[:, dt.rowcount(f[:])])
def test_rowcount_different_types():
DT = dt.Frame([[1, 4, None, 7, 0, None],
[True, None, None, False, False, False],
[7.4, math.nan, None, math.inf, -math.inf, 1.6e300],
["A", "", None, None, "NaN", "None"]])
RES = DT[:, rowcount(f[:])]
assert_equals(RES, dt.Frame([4, 2, 0, 3, 4, 3], stype=dt.int32))
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())
# 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 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
