def test_pivot(self):
domain = self.table.domain
pivot = Pivot(self.table, Pivot.Functions, domain[0], domain[1], domain[2])
pivot_tab = pivot.pivot_table
atts = (Dv("Aggregate", ["Count", "Count defined", "Sum", "Mean",
"Min", "Max", "Mode", "Median", "Var"]),
Cv("c"), Cv("d"), Cv("e"))
X = np.array([[0, 0, 2, 1, 0],
[0, 1, 2, 1, 0],
[0, 2, 5, 2, 0],
[0, 3, 2.5, 2, np.nan],
[0, 4, 1, 2, np.nan],
[0, 5, 4, 2, np.nan],
[0, 6, 1, 2, np.nan],
[0, 7, 2.5, 2, np.nan],
[0, 8, 2.25, 0, np.nan],
[1, 0, 2, 1, 1],
[1, 1, 2, 0, 1],
[1, 2, 11, 0, 7],
[1, 3, 5.5, np.nan, 7],
[1, 4, 5, np.nan, 7],
[1, 5, 6, np.nan, 7],
[1, 6, 5, np.nan, 7],
[1, 7, 5.5, np.nan, 7],
[1, 8, 0.25, np.nan, 0]])
self.assert_table_equal(pivot_tab, Table(Domain(domain[:1] + atts), X))
def test_pivot_no_col_var(self):
domain = self.table.domain
pivot = Pivot(self.table, Pivot.Functions, domain[0], None, domain[2])
pivot_tab = pivot.pivot_table
atts = (Dv("Aggregate",
["Count", "Count defined", "Sum", "Mean",
"Min", "Max", "Mode", "Median", "Var"]),
Cv("a"), Cv("b"))
X = np.array([[0, 0, 4, 0],
[0, 1, 4, 0],
[0, 2, 10, 0],
[0, 3, 2.5, np.nan],
[0, 4, 1, np.nan],
[0, 5, 4, np.nan],
[0, 6, 1, np.nan],
[0, 7, 2.5, np.nan],
[0, 8, 1.25, np.nan],
[1, 0, 0, 4],
[1, 1, 0, 3],
[1, 2, 0, 18],
[1, 3, np.nan, 6],
[1, 4, np.nan, 5],
[1, 5, np.nan, 7],
[1, 6, np.nan, 5],
[1, 7, np.nan, 6],
[1, 8, np.nan, 2 / 3]])
self.assert_table_equal(pivot_tab, Table(Domain(domain[:1] + atts), X))
def test_pivot_no_val_var(self):
domain = self.table.domain
pivot = Pivot(self.table, Pivot.Functions, domain[0], domain[1])
pivot_tab = pivot.pivot_table
atts = (Dv("Aggregate", ["Count"]), Cv("c"), Cv("d"), Cv("e"))
X = np.array([[0, 0, 2, 1, 0], [1, 0, 2, 1, 1]])
self.assert_table_equal(pivot_tab, Table(Domain(domain[:1] + atts), X))
def setUpClass(cls):
domain = Domain([Dv("d1", ("a", "b")),
Dv("d2", ("c", "d", "e")), Cv("c1")])
X = np.array([[0, 0, 1], [0, 1, 2], [0, np.nan, 3], [0, 0, 4],
[1, 0, 5], [1, 0, 6], [1, 1, np.nan], [1, 2, 7],
[np.nan, 0, 8]])
cls.table = Table(domain, X)
domain = Domain([Cv("c0"), Dv("d1", ("a", "b")), Cv("c1"),
Dv("d2", ("a", "b")), Cv("c2")],
Dv("cls", ("a", "b")), [sv("m1"), sv("m2")])
X = np.array([[np.nan, 0, 1, 0, 2], [np.nan, 1, 2, np.nan, 3],
[np.nan, 0, 3, 1, np.nan]])
M = np.array([["aa", "dd"], ["bb", "ee"], ["cc", ""]], dtype=object)
cls.table1 = Table(domain, X, np.array([0, 0, 1]), M)
def test_pivot_time_val_var(self):
domain = Domain([Dv("d1", ("a", "b")), Dv("d2", ("c", "d")),
Tv("t1", have_date=1)])
X = np.array([[0, 1, 1e9], [0, 0, 1e8], [1, 0, 2e8], [1, 1, np.nan]])
table = Table(domain, X)
# Min
pivot = Pivot(table, [Pivot.Min],
domain[0], domain[1], domain[2])
atts = (domain[0], Dv("Aggregate", ["Min"]),
Tv("c", have_date=1), Tv("d", have_date=1))
X = np.array([[0, 0, 1e8, 1e9],
[1, 0, 2e8, np.nan]])
self.assert_table_equal(pivot.pivot_table, Table(Domain(atts), X))
# Min, Max
pivot = Pivot(table, [Pivot.Min, Pivot.Max],
domain[0], domain[1], domain[2])
atts = (domain[0], Dv("Aggregate", ["Min", "Max"]),
Tv("c", have_date=1), Tv("d", have_date=1))
X = np.array([[0, 0, 1e8, 1e9],
[0, 1, 1e8, 1e9],
[1, 0, 2e8, np.nan],
[1, 1, 2e8, np.nan]])
self.assert_table_equal(pivot.pivot_table, Table(Domain(atts), X))
# Count defined, Sum
pivot = Pivot(table, [Pivot.Count_defined, Pivot.Sum],
domain[0], domain[1], domain[2])
atts = (domain[0], Dv("Aggregate", ["Count defined", "Sum"]),
Cv("c"), Cv("d"))
X = np.array([[0, 0, 1, 1],
[0, 1, 1e8, 1e9],
[1, 0, 1, 0],
[1, 1, 2e8, 0]])
self.assert_table_equal(pivot.pivot_table, Table(Domain(atts), X))
# Count defined, Max
pivot = Pivot(table, [Pivot.Count_defined, Pivot.Max],
domain[0], domain[1], domain[2])
atts = (domain[0], Dv("Aggregate", ["Count defined", "Max"]),
Dv("c", ["1.0", "1973-03-03", "1976-05-03"]),
Dv("d", ["0.0", "1.0", "2001-09-09"]))
X = np.array([[0, 0, 0, 1],
[0, 1, 1, 2],
[1, 0, 0, 0],
[1, 1, 2, np.nan]])
self.assert_table_equal(pivot.pivot_table, Table(Domain(atts), X))
def test_pivot_total(self):
domain = self.table.domain
pivot = Pivot(self.table, [Pivot.Functions.Count, Pivot.Functions.Sum],
domain[0], domain[1], domain[2])
atts = (Dv(domain[0].name, ["Total"]),
Dv("Aggregate", ["Count", "Sum"]), Cv("c"), Cv("d"), Cv("e"))
X = np.array([[0, 0, 4, 2, 1], [0, 1, 16, 2, 7]])
table = Table(Domain(atts), X)
self.assert_table_equal(pivot.pivot_total_h, table)
table = Table(Domain((Cv("Total"),)), np.array([[3], [7], [4], [18]]))
self.assert_table_equal(pivot.pivot_total_v, table)
table = Table(Domain((Cv("Total"),)), np.array([[7], [25]]))
self.assert_table_equal(pivot.pivot_total, table)
def test_pivot_no_col_var(self):
domain = self.table.domain
pivot = Pivot(self.table, Pivot.Functions, domain[0], None, domain[2])
pivot_tab = pivot.pivot_table
atts = (Dv(
"Aggregate",
["数目", "非缺失数目", "总和", "平均值", "最小值", "最大值", "众数", "中位数", "方差"]),
Cv("a"), Cv("b"))
X = np.array([[0, 0, 4, 0], [0, 1, 4, 0], [0, 2, 10, 0],
[0, 3, 2.5, np.nan], [0, 4, 1,
np.nan], [0, 5, 4, np.nan],
[0, 6, 1, np.nan], [0, 7, 2.5, np.nan],
[0, 8, 1.25, np.nan], [1, 0, 0, 4], [1, 1, 0, 3],
[1, 2, 0, 18], [1, 3, np.nan, 6], [1, 4, np.nan, 5],
[1, 5, np.nan, 7], [1, 6, np.nan, 5], [1, 7, np.nan, 6],
[1, 8, np.nan, 2 / 3]])
self.assert_table_equal(pivot_tab, Table(Domain(domain[:1] + atts), X))
def test_pivot(self):
domain = self.table.domain
pivot = Pivot(self.table, Pivot.Functions, domain[0], domain[1],
domain[2])
pivot_tab = pivot.pivot_table
atts = (Dv(
"Aggregate",
["数目", "非缺失数目", "总和", "平均值", "最小值", "最大值", "众数", "中位数", "方差"]),
Cv("c"), Cv("d"), Cv("e"))
X = np.array([[0, 0, 2, 1, 0], [0, 1, 2, 1, 0], [0, 2, 5, 2, 0],
[0, 3, 2.5, 2, np.nan], [0, 4, 1, 2, np.nan],
[0, 5, 4, 2, np.nan], [0, 6, 1, 2, np.nan],
[0, 7, 2.5, 2, np.nan], [0, 8, 2.25, 0, np.nan],
[1, 0, 2, 1, 1], [1, 1, 2, 0, 1], [1, 2, 11, 0, 7],
[1, 3, 5.5, np.nan, 7], [1, 4, 5, np.nan, 7],
[1, 5, 6, np.nan, 7], [1, 6, 5, np.nan, 7],
[1, 7, 5.5, np.nan, 7], [1, 8, 0.25, np.nan, 0]])
self.assert_table_equal(pivot_tab, Table(Domain(domain[:1] + atts), X))
def test_group_table(self):
domain = self.table.domain
pivot = Pivot(self.table, Pivot.Functions, domain[0], domain[1])
group_tab = pivot.group_table
atts = (Cv("(数目)"), Cv("d1 (非缺失数目)"), Dv("d1 (最常见)", ["a", "b"]),
Cv("d2 (非缺失数目)"), Dv("d2 (最常见)",
["c", "d", "e"]), Cv("c1 (非缺失数目)"),
Cv("c1 (总和)"), Cv("c1 (平均值)"), Cv("c1 (最小值)"), Cv("c1 (最大值)"),
Cv("c1 (众数)"), Cv("c1 (中位数)"), Cv("c1 (方差)"))
X = np.array([[0, 0, 2, 2, 0, 2, 0, 2, 5, 2.5, 1, 4, 1, 2.5, 2.25],
[0, 1, 1, 1, 0, 1, 1, 1, 2, 2, 2, 2, 2, 2, 0],
[
0, 2, 0, 0, np.nan, 0, np.nan, 0, 0, np.nan, np.nan,
np.nan, np.nan, np.nan, np.nan
], [1, 0, 2, 2, 1, 2, 0, 2, 11, 5.5, 5, 6, 5, 5.5, 0.25],
[
1, 1, 1, 1, 1, 1, 1, 0, 0, np.nan, np.nan, np.nan,
np.nan, np.nan, np.nan
], [1, 2, 1, 1, 1, 1, 2, 1, 7, 7, 7, 7, 7, 7, 0]])
self.assert_table_equal(group_tab, Table(Domain(domain[:2] + atts), X))
def test_group_table_1(self):
var = self.table1.domain.variables[1]
domain = Domain([
var,
Cv("(count)"),
Cv("c0 (count defined)"),
Cv("c0 (sum)"),
Cv("c0 (mean)"),
Cv("c0 (min)"),
Cv("c0 (max)"),
Cv("c0 (mode)"),
Cv("c0 (median)"),
Cv("c0 (var)"),
Cv("d1 (count defined)"),
Dv("d1 (majority)", ["a", "b"]),
Cv("c1 (count defined)"),
Cv("c1 (sum)"),
Cv("c1 (mean)"),
Cv("c1 (min)"),
Cv("c1 (max)"),
Cv("c1 (mode)"),
Cv("c1 (median)"),
Cv("c1 (var)"),
Cv("d2 (count defined)"),
Dv("d2 (majority)", ["a", "b"]),
Cv("c2 (count defined)"),
Cv("c2 (sum)"),
Cv("c2 (mean)"),
Cv("c2 (min)"),
Cv("c2 (max)"),
Cv("c2 (mode)"),
Cv("c2 (median)"),
Cv("c2 (var)"),
Cv("cls (count defined)"),
Dv("cls (majority)", ["a", "b"]),
Cv("m1 (count defined)"),
Cv("m2 (count defined)")
])
X = np.array([[
0, 2, 0, 0, np.nan, np.nan, np.nan, np.nan, np.nan, np.nan, 2, 0,
2, 4, 2, 1, 3, 1, 2, 1, 2, 0, 1, 2, 2, 2, 2, 2, 2, 0, 2, 0, 2, 1
],
[
1, 1, 0, 0, np.nan, np.nan, np.nan, np.nan, np.nan,
np.nan, 1, 1, 1, 2, 2, 2, 2, 2, 2, 0, 0, np.nan, 1,
3, 3, 3, 3, 3, 3, 0, 1, 0, 1, 1
]])
pivot = Pivot(self.table1, Pivot.Functions, var)
group_tab = pivot.group_table
self.assert_table_equal(group_tab, Table(domain, X))
def test_group_table_update(self):
domain = self.table.domain
atts = (Cv("(count)"), Cv("d1 (count defined)"),
Dv("d1 (majority)", ["a", "b"]), Cv("d2 (count defined)"),
Dv("d2 (majority)",
["c", "d", "e"]), Cv("c1 (count defined)"), Cv("c1 (sum)"),
Cv("c1 (mean)"), Cv("c1 (min)"), Cv("c1 (max)"),
Cv("c1 (mode)"), Cv("c1 (median)"), Cv("c1 (var)"))
X = np.array([[0, 0, 2, 2, 0, 2, 0, 2, 5, 2.5, 1, 4, 1, 2.5, 2.25],
[0, 1, 1, 1, 0, 1, 1, 1, 2, 2, 2, 2, 2, 2, 0],
[
0, 2, 0, 0, np.nan, 0, np.nan, 0, 0, np.nan, np.nan,
np.nan, np.nan, np.nan, np.nan
], [1, 0, 2, 2, 1, 2, 0, 2, 11, 5.5, 5, 6, 5, 5.5, 0.25],
[
1, 1, 1, 1, 1, 1, 1, 0, 0, np.nan, np.nan, np.nan,
np.nan, np.nan, np.nan
], [1, 2, 1, 1, 1, 1, 2, 1, 7, 7, 7, 7, 7, 7, 0]])
table = Table(Domain(domain[:2] + atts), X)
agg = [Pivot.Functions.Count, Pivot.Functions.Sum]
pivot = Pivot(self.table, agg, domain[0], domain[1])
group_tab = pivot.group_table
pivot.update_group_table(Pivot.Functions)
self.assert_table_equal(pivot.group_table, table)
pivot.update_group_table(agg)
self.assert_table_equal(group_tab, pivot.group_table)
def test_group_table_no_col_var_metas(self):
for var in self.table1.domain.metas:
self.assertRaises(TypeError, Pivot, self.table1, var)
domain = Domain(
[Dv("d1", ("a", "b")),
Cv("c1"),
Dv("d2", ("a", "b")),
Cv("c2")])
X = np.array([[0, 1, 0, 2], [1, 2, np.nan, 3], [0, 3, 1, np.nan]])
table = Table(domain, X).transform(
Domain(domain.attributes[:2], metas=domain.attributes[2:]))
pivot = Pivot(table, Pivot.Functions, table.domain[-1])
group_tab = pivot.group_table
atts = (table.domain[-1], Cv("(count)"), Cv("d1 (count defined)"),
Dv("d1 (majority)",
["a", "b"]), Cv("c1 (count defined)"), Cv("c1 (sum)"),
Cv("c1 (mean)"), Cv("c1 (min)"), Cv("c1 (max)"),
Cv("c1 (mode)"), Cv("c1 (median)"), Cv("c1 (var)"),
Cv("d2 (count defined)"), Dv("d2 (majority)", ["a", "b"]),
Cv("c2 (count defined)"), Cv("c2 (sum)"), Cv("c2 (mean)"),
Cv("c2 (min)"), Cv("c2 (max)"), Cv("c2 (mode)"),
Cv("c2 (median)"), Cv("c2 (var)"))
X = np.array([[
0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 2, 2, 2, 2, 2, 2, 0
],
[
1, 1, 1, 0, 1, 3, 3, 3, 3, 3, 3, 0, 1, 1, 0, 0,
np.nan, np.nan, np.nan, np.nan, np.nan, np.nan
]],
dtype=float)
self.assert_table_equal(group_tab, Table(Domain(atts), X))
def test_group_table_no_col_var(self):
domain = self.table.domain
pivot = Pivot(self.table, Pivot.Functions, domain[0])
group_tab = pivot.group_table
atts = (Cv("(count)"), Cv("d1 (count defined)"),
Dv("d1 (majority)", ["a", "b"]), Cv("d2 (count defined)"),
Dv("d2 (majority)",
["c", "d", "e"]), Cv("c1 (count defined)"), Cv("c1 (sum)"),
Cv("c1 (mean)"), Cv("c1 (min)"), Cv("c1 (max)"),
Cv("c1 (mode)"), Cv("c1 (median)"), Cv("c1 (var)"))
domain = Domain(domain[:1] + atts)
X = np.array([[0, 4, 4, 0, 3, 0, 4, 10, 2.5, 1, 4, 1, 2.5, 1.25],
[1, 4, 4, 1, 4, 0, 3, 18, 6, 5, 7, 5, 6, 2 / 3]],
dtype=float)
self.assert_table_equal(group_tab, Table(Domain(domain[:1] + atts), X))
pivot = Pivot(self.table, Pivot.Functions, domain[0], domain[0])
group_tab_same_vars = pivot.group_table
self.assert_table_equal(group_tab, group_tab_same_vars)
def test_group_table_use_cached(self, count_func, sum_func):
domain = self.table.domain
pivot = Pivot(self.table, [Pivot.Count, Pivot.Sum], domain[0],
domain[1])
group_tab = pivot.group_table
count_func.reset_mock()
sum_func.reset_mock()
pivot.update_group_table(Pivot.Functions)
count_func.assert_not_called()
sum_func.assert_not_called()
atts = (Cv("(count)"), Cv("d1 (count defined)"),
Dv("d1 (majority)", ["a", "b"]), Cv("d2 (count defined)"),
Dv("d2 (majority)",
["c", "d", "e"]), Cv("c1 (count defined)"), Cv("c1 (sum)"),
Cv("c1 (mean)"), Cv("c1 (min)"), Cv("c1 (max)"),
Cv("c1 (mode)"), Cv("c1 (median)"), Cv("c1 (var)"))
X = np.array([[0, 0, 2, 2, 0, 2, 0, 2, 5, 2.5, 1, 4, 1, 2.5, 2.25],
[0, 1, 1, 1, 0, 1, 1, 1, 2, 2, 2, 2, 2, 2, 0],
[
0, 2, 0, 0, np.nan, 0, np.nan, 0, 0, np.nan, np.nan,
np.nan, np.nan, np.nan, np.nan
], [1, 0, 2, 2, 1, 2, 0, 2, 11, 5.5, 5, 6, 5, 5.5, 0.25],
[
1, 1, 1, 1, 1, 1, 1, 0, 0, np.nan, np.nan, np.nan,
np.nan, np.nan, np.nan
], [1, 2, 1, 1, 1, 1, 2, 1, 7, 7, 7, 7, 7, 7, 0]])
self.assert_table_equal(pivot.group_table,
Table(Domain(domain[:2] + atts), X))
pivot.update_group_table([Pivot.Count, Pivot.Sum])
count_func.assert_not_called()
sum_func.assert_not_called()
self.assert_table_equal(pivot.group_table, group_tab)
def test_group_table_use_cached(self, count_func, sum_func):
domain = self.table.domain
pivot = Pivot(self.table, [Pivot.Count, Pivot.Sum], domain[0],
domain[1])
group_tab = pivot.group_table
count_func.reset_mock()
sum_func.reset_mock()
pivot.update_group_table(Pivot.Functions)
count_func.assert_not_called()
sum_func.assert_not_called()
atts = (Cv("(数目)"), Cv("d1 (非缺失数目)"), Dv("d1 (最常见)", ["a", "b"]),
Cv("d2 (非缺失数目)"), Dv("d2 (最常见)",
["c", "d", "e"]), Cv("c1 (非缺失数目)"),
Cv("c1 (总和)"), Cv("c1 (平均值)"), Cv("c1 (最小值)"), Cv("c1 (最大值)"),
Cv("c1 (众数)"), Cv("c1 (中位数)"), Cv("c1 (方差)"))
X = np.array([[0, 0, 2, 2, 0, 2, 0, 2, 5, 2.5, 1, 4, 1, 2.5, 2.25],
[0, 1, 1, 1, 0, 1, 1, 1, 2, 2, 2, 2, 2, 2, 0],
[
0, 2, 0, 0, np.nan, 0, np.nan, 0, 0, np.nan, np.nan,
np.nan, np.nan, np.nan, np.nan
], [1, 0, 2, 2, 1, 2, 0, 2, 11, 5.5, 5, 6, 5, 5.5, 0.25],
[
1, 1, 1, 1, 1, 1, 1, 0, 0, np.nan, np.nan, np.nan,
np.nan, np.nan, np.nan
], [1, 2, 1, 1, 1, 1, 2, 1, 7, 7, 7, 7, 7, 7, 0]])
self.assert_table_equal(pivot.group_table,
Table(Domain(domain[:2] + atts), X))
pivot.update_group_table([Pivot.Count, Pivot.Sum])
count_func.assert_not_called()
sum_func.assert_not_called()
self.assert_table_equal(pivot.group_table, group_tab)
def test_group_table_no_col_var(self):
domain = self.table.domain
pivot = Pivot(self.table, Pivot.Functions, domain[0])
group_tab = pivot.group_table
atts = (Cv("(数目)"), Cv("d1 (非缺失数目)"), Dv("d1 (最常见)", ["a", "b"]),
Cv("d2 (非缺失数目)"), Dv("d2 (最常见)",
["c", "d", "e"]), Cv("c1 (非缺失数目)"),
Cv("c1 (总和)"), Cv("c1 (平均值)"), Cv("c1 (最小值)"), Cv("c1 (最大值)"),
Cv("c1 (众数)"), Cv("c1 (中位数)"), Cv("c1 (方差)"))
domain = Domain(domain[:1] + atts)
X = np.array([[0, 4, 4, 0, 3, 0, 4, 10, 2.5, 1, 4, 1, 2.5, 1.25],
[1, 4, 4, 1, 4, 0, 3, 18, 6, 5, 7, 5, 6, 2 / 3]],
dtype=float)
self.assert_table_equal(group_tab, Table(Domain(domain[:1] + atts), X))
pivot = Pivot(self.table, Pivot.Functions, domain[0], domain[0])
group_tab_same_vars = pivot.group_table
self.assert_table_equal(group_tab, group_tab_same_vars)
def test_group_table_no_col_var_metas(self):
for var in self.table1.domain.metas:
self.assertRaises(TypeError, Pivot, self.table1, var)
domain = Domain(
[Dv("d1", ("a", "b")),
Cv("c1"),
Dv("d2", ("a", "b")),
Cv("c2")])
X = np.array([[0, 1, 0, 2], [1, 2, np.nan, 3], [0, 3, 1, np.nan]])
table = Table(domain, X).transform(
Domain(domain.attributes[:2], metas=domain.attributes[2:]))
pivot = Pivot(table, Pivot.Functions, table.domain[-1])
group_tab = pivot.group_table
atts = (table.domain[-1], Cv("(数目)"), Cv("d1 (非缺失数目)"),
Dv("d1 (最常见)", ["a", "b"]), Cv("c1 (非缺失数目)"), Cv("c1 (总和)"),
Cv("c1 (平均值)"), Cv("c1 (最小值)"), Cv("c1 (最大值)"), Cv("c1 (众数)"),
Cv("c1 (中位数)"), Cv("c1 (方差)"), Cv("d2 (非缺失数目)"),
Dv("d2 (最常见)", ["a", "b"]), Cv("c2 (非缺失数目)"), Cv("c2 (总和)"),
Cv("c2 (平均值)"), Cv("c2 (最小值)"), Cv("c2 (最大值)"), Cv("c2 (众数)"),
Cv("c2 (中位数)"), Cv("c2 (方差)"))
X = np.array([[
0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 2, 2, 2, 2, 2, 2, 0
],
[
1, 1, 1, 0, 1, 3, 3, 3, 3, 3, 3, 0, 1, 1, 0, 0,
np.nan, np.nan, np.nan, np.nan, np.nan, np.nan
]],
dtype=float)
self.assert_table_equal(group_tab, Table(Domain(atts), X))
def test_group_table_metas(self):
domain = Domain(
[Dv("d1", ("a", "b")),
Cv("c1"),
Dv("d2", ("a", "b")),
Cv("c2")])
X = np.array([[0, 1, 0, 2], [1, 2, np.nan, 3], [0, 3, 1, np.nan]])
table = Table(domain, X).transform(
Domain(domain.attributes[:2], metas=domain.attributes[2:])).copy()
with table.unlocked():
table.metas = table.metas.astype(object)
pivot = Pivot(table, Pivot.Functions, table.domain[-1])
group_tab = pivot.group_table
atts = (table.domain[-1], Cv("(数目)"), Cv("d1 (非缺失数目)"),
Dv("d1 (最常见)", ["a", "b"]), Cv("c1 (非缺失数目)"), Cv("c1 (总和)"),
Cv("c1 (平均值)"), Cv("c1 (最小值)"), Cv("c1 (最大值)"), Cv("c1 (众数)"),
Cv("c1 (中位数)"), Cv("c1 (方差)"), Cv("d2 (非缺失数目)"),
Dv("d2 (最常见)", ["a", "b"]), Cv("c2 (非缺失数目)"), Cv("c2 (总和)"),
Cv("c2 (平均值)"), Cv("c2 (最小值)"), Cv("c2 (最大值)"), Cv("c2 (众数)"),
Cv("c2 (中位数)"), Cv("c2 (方差)"))
X = np.array([[
0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 2, 2, 2, 2, 2, 2, 0
],
[
1, 1, 1, 0, 1, 3, 3, 3, 3, 3, 3, 0, 1, 1, 0, 0,
np.nan, np.nan, np.nan, np.nan, np.nan, np.nan
]],
dtype=float)
self.assert_table_equal(group_tab, Table(Domain(atts), X))
def test_group_table_metas(self):
domain = Domain([Dv("d1", ("a", "b")), Cv("c1"),
Dv("d2", ("a", "b")), Cv("c2")])
X = np.array([[0, 1, 0, 2], [1, 2, np.nan, 3], [0, 3, 1, np.nan]])
table = Table(domain, X).transform(
Domain(domain.attributes[:2], metas=domain.attributes[2:]),
copy=True)
with table.unlocked():
table.metas = table.metas.astype(object)
pivot = Pivot(table, Pivot.Functions, table.domain[-1])
group_tab = pivot.group_table
atts = (table.domain[-1], Cv("(count)"), Cv("d1 (count defined)"),
Dv("d1 (majority)", ["a", "b"]),
Cv("c1 (count defined)"), Cv("c1 (sum)"), Cv("c1 (mean)"),
Cv("c1 (min)"), Cv("c1 (max)"), Cv("c1 (mode)"),
Cv("c1 (median)"), Cv("c1 (var)"), Cv("d2 (count defined)"),
Dv("d2 (majority)", ["a", "b"]), Cv("c2 (count defined)"),
Cv("c2 (sum)"), Cv("c2 (mean)"), Cv("c2 (min)"), Cv("c2 (max)"),
Cv("c2 (mode)"), Cv("c2 (median)"), Cv("c2 (var)"))
X = np.array([[0, 1, 1, 0, 1, 1, 1, 1, 1, 1,
1, 0, 1, 0, 1, 2, 2, 2, 2, 2, 2, 0],
[1, 1, 1, 0, 1, 3, 3, 3, 3, 3, 3, 0, 1, 1, 0, 0, np.nan,
np.nan, np.nan, np.nan, np.nan, np.nan]], dtype=float)
self.assert_table_equal(group_tab, Table(Domain(atts), X))
def test_group_table_1(self):
var = self.table1.domain.variables[1]
domain = Domain([
var,
Cv("(数目)"),
Cv("c0 (非缺失数目)"),
Cv("c0 (总和)"),
Cv("c0 (平均值)"),
Cv("c0 (最小值)"),
Cv("c0 (最大值)"),
Cv("c0 (众数)"),
Cv("c0 (中位数)"),
Cv("c0 (方差)"),
Cv("d1 (非缺失数目)"),
Dv("d1 (最常见)", ["a", "b"]),
Cv("c1 (非缺失数目)"),
Cv("c1 (总和)"),
Cv("c1 (平均值)"),
Cv("c1 (最小值)"),
Cv("c1 (最大值)"),
Cv("c1 (众数)"),
Cv("c1 (中位数)"),
Cv("c1 (方差)"),
Cv("d2 (非缺失数目)"),
Dv("d2 (最常见)", ["a", "b"]),
Cv("c2 (非缺失数目)"),
Cv("c2 (总和)"),
Cv("c2 (平均值)"),
Cv("c2 (最小值)"),
Cv("c2 (最大值)"),
Cv("c2 (众数)"),
Cv("c2 (中位数)"),
Cv("c2 (方差)"),
Cv("cls (非缺失数目)"),
Dv("cls (最常见)", ["a", "b"]),
Cv("m1 (非缺失数目)"),
Cv("m2 (非缺失数目)")
])
X = np.array([[
0, 2, 0, 0, np.nan, np.nan, np.nan, np.nan, np.nan, np.nan, 2, 0,
2, 4, 2, 1, 3, 1, 2, 1, 2, 0, 1, 2, 2, 2, 2, 2, 2, 0, 2, 0, 2, 1
],
[
1, 1, 0, 0, np.nan, np.nan, np.nan, np.nan, np.nan,
np.nan, 1, 1, 1, 2, 2, 2, 2, 2, 2, 0, 0, np.nan, 1,
3, 3, 3, 3, 3, 3, 0, 1, 0, 1, 1
]])
pivot = Pivot(self.table1, Pivot.Functions, var)
group_tab = pivot.group_table
self.assert_table_equal(group_tab, Table(domain, X))
def test_group_table_update(self):
domain = self.table.domain
atts = (Cv("(数目)"), Cv("d1 (非缺失数目)"), Dv("d1 (最常见)", ["a", "b"]),
Cv("d2 (非缺失数目)"), Dv("d2 (最常见)",
["c", "d", "e"]), Cv("c1 (非缺失数目)"),
Cv("c1 (总和)"), Cv("c1 (平均值)"), Cv("c1 (最小值)"), Cv("c1 (最大值)"),
Cv("c1 (众数)"), Cv("c1 (中位数)"), Cv("c1 (方差)"))
X = np.array([[0, 0, 2, 2, 0, 2, 0, 2, 5, 2.5, 1, 4, 1, 2.5, 2.25],
[0, 1, 1, 1, 0, 1, 1, 1, 2, 2, 2, 2, 2, 2, 0],
[
0, 2, 0, 0, np.nan, 0, np.nan, 0, 0, np.nan, np.nan,
np.nan, np.nan, np.nan, np.nan
], [1, 0, 2, 2, 1, 2, 0, 2, 11, 5.5, 5, 6, 5, 5.5, 0.25],
[
1, 1, 1, 1, 1, 1, 1, 0, 0, np.nan, np.nan, np.nan,
np.nan, np.nan, np.nan
], [1, 2, 1, 1, 1, 1, 2, 1, 7, 7, 7, 7, 7, 7, 0]])
table = Table(Domain(domain[:2] + atts), X)
agg = [Pivot.Functions.Count, Pivot.Functions.Sum]
pivot = Pivot(self.table, agg, domain[0], domain[1])
group_tab = pivot.group_table
pivot.update_group_table(Pivot.Functions)
self.assert_table_equal(pivot.group_table, table)
pivot.update_group_table(agg)
self.assert_table_equal(group_tab, pivot.group_table)