def test_assign_with_groupby2():
DT = dt.Frame(A=range(5), B=[1, 1, 2, 2, 2])
DT[:, "C", by(f.B)] = f.A - dt.mean(f.A)
assert_equals(
DT, dt.Frame(A=range(5),
B=[1, 1, 2, 2, 2],
C=[-0.5, 0.5, -1.0, 0, 1.0]))
def test_groupby():
DT = dt.Frame(A=[1, 1, 1, 2, 2, 2],
B=[
d(2001, 7, 12, 0, 0, 0),
d(2005, 3, 14, 15, 9, 26), None,
d(2007, 11, 2, 19, 7, 38),
d(1965, 6, 19, 2, 17, 7),
d(2004, 4, 18, 12, 3, 31)
])
RES = DT[:, {
"count": dt.count(f.B),
"min": dt.min(f.B),
"max": dt.max(f.B),
"mean": dt.mean(f.B),
"first": dt.first(f.B),
"last": dt.last(f.B)
},
dt.by(f.A)]
assert_equals(
RES,
dt.Frame(A=[1, 2],
count=[2, 3] / dt.int64,
min=[d(2001, 7, 12, 0, 0, 0),
d(1965, 6, 19, 2, 17, 7)],
max=[d(2005, 3, 14, 15, 9, 26),
d(2007, 11, 2, 19, 7, 38)],
mean=[
d(2003, 5, 13, 19, 34, 43),
d(1992, 7, 13, 19, 9, 25, 333333)
],
first=[d(2001, 7, 12, 0, 0, 0),
d(2007, 11, 2, 19, 7, 38)],
last=[None, d(2004, 4, 18, 12, 3, 31)]))
def test_dt_nunique_with_by_for_ungroupped():
DT = dt.Frame(G=[1, 1, 1, 2, 2, 2], V=[None, None, None, None, 3, 5])
EXP = dt.Frame(G=[1, 2], V1=[0, 2] / dt.int64, V2=[0, 1] / dt.int64)
RES = DT[:, {
"V1": dt.nunique(f.V),
"V2": dt.nunique(dt.mean(f.V))
}, dt.by(f.G)]
assert_equals(EXP, RES)
def test_update_with_groupby():
DT = dt.Frame(A=range(5), B=[1, 1, 2, 2, 2])
DT[:, update(C=7, D=dt.mean(f.A), E=f.A + 1), by(f.B)]
assert_equals(
DT,
dt.Frame(A=range(5),
B=[1, 1, 2, 2, 2],
C=[7] * 5,
D=[0.5, 0.5, 3.0, 3.0, 3.0],
E=range(1, 6)))
def test_reducers():
DT = dt.Frame(TIME=[
d(2001, 7, 12, 0, 0, 0),
d(2005, 3, 14, 15, 9, 26), None,
d(2007, 11, 2, 19, 7, 38),
d(1965, 6, 19, 2, 17, 7),
d(2004, 4, 18, 12, 3, 31)
])
RES = DT[:, {
"count": dt.count(f.TIME),
"min": dt.min(f.TIME),
"max": dt.max(f.TIME),
"mean": dt.mean(f.TIME),
"first": dt.first(f.TIME),
"last": dt.last(f.TIME)
}]
assert_equals(
RES,
dt.Frame(count=[5] / dt.int64,
min=[d(1965, 6, 19, 2, 17, 7)],
max=[d(2007, 11, 2, 19, 7, 38)],
mean=[d(1996, 11, 12, 4, 55, 32, 400000)],
first=[d(2001, 7, 12, 0, 0, 0)],
last=[d(2004, 4, 18, 12, 3, 31)]))
# #### Number of unique observations per column
# In[3]:
# DT[, lapply(.SD, uniqueN)] --> Rdatatable
DT.nunique()
# #### Mean of all columns by `species`
# In[4]:
# DT[, lapply(.SD, mean), by = species] --> Rdatatable
DT[:, dt.mean(f[:]), by('species')]
# ### __Filtering__
# #### First two observations by species
# In[5]:
# DT[, .SD[1:2], by = species]
DT[:2, :, by('species')]
# In [datatable](https://datatable.readthedocs.io/en/latest/index.html), rows are selected in the `i` section after the grouping, unlike in R's [data.table](https://github.com/Rdatatable/data.table), where rows are selected in `i` before grouping, and rows selected in the `.SD` after grouping.
# #### Last two observations by `species`
def test_dt_count_na2():
DT = dt.Frame(G=[1, 1, 1, 2, 2, 2], V=[None, None, None, None, 3, 5])
EXP = dt.Frame(G=[1, 2], V1=[3, 1], V2=[3, 0])
RES = DT[:, [dt.countna(f.V), dt.countna(dt.mean(f.V))], dt.by(f.G)]
assert EXP.to_list() == RES.to_list()