def test_basic(self, daskify, values):
de = dpp.DummyEncoder()
df = dummy[['A', 'D']]
if daskify:
df = dd.from_pandas(df, 2)
de = de.fit(df)
trn = de.transform(df)
expected = pd.DataFrame(
{
"D": np.array([1, 2, 3, 4]),
"A_a": np.array([1, 0, 0, 1], dtype='uint8'),
"A_b": np.array([0, 1, 0, 0], dtype='uint8'),
"A_c": np.array([0, 0, 1, 0], dtype='uint8'),
},
columns=['D', 'A_a', 'A_b', 'A_c'])
assert_eq(trn, expected)
if values:
trn = trn.values
result = de.inverse_transform(trn)
if daskify:
df = df.compute()
result = result.compute()
tm.assert_frame_equal(result, df)
def test_encode_subset_of_columns(self, daskify):
de = dpp.DummyEncoder(columns=["B"])
df = dummy[["A", "B"]]
if daskify:
df = dd.from_pandas(df, 2)
de = de.fit(df)
trn = de.transform(df)
expected = pd.DataFrame(
{
"A": pd.Categorical(["a", "b", "c", "a"], ordered=True),
"B_a": np.array([1, 0, 0, 1], dtype="uint8"),
"B_b": np.array([0, 1, 0, 0], dtype="uint8"),
"B_c": np.array([0, 0, 1, 0], dtype="uint8"),
},
columns=["A", "B_a", "B_b", "B_c"],
)
assert_eq_df(trn, expected)
result = de.inverse_transform(trn)
if daskify:
df = df.compute()
result = result.compute()
tm.assert_frame_equal(result, df)
def test_inverse_transform(self):
de = dpp.DummyEncoder()
df = dd.from_pandas(
pd.DataFrame(
{"A": np.arange(10), "B": pd.Categorical(["a"] * 4 + ["b"] * 6)}
),
npartitions=2,
)
de.fit(df)
assert_eq_df(df, de.inverse_transform(de.transform(df)))
assert_eq_df(df, de.inverse_transform(de.transform(df).values))
def test_drop_first(self, daskify):
if daskify:
df = dd.from_pandas(dummy, 2)
else:
df = dummy
de = dpp.DummyEncoder(drop_first=True)
trn = de.fit_transform(df)
assert len(trn.columns) == 8
result = de.inverse_transform(trn)
if daskify:
result, df = compute(result, df)
tm.assert_frame_equal(result, dummy)
def test_transform_raises(self):
de = dpp.DummyEncoder()
de.fit(dummy)
with pytest.raises(ValueError) as rec:
de.transform(dummy.drop("B", axis='columns'))
assert rec.match("Columns of 'X' do not match the training")
def test_da(self):
a = dd.from_pandas(dummy, npartitions=2)
de = dpp.DummyEncoder()
result = de.fit_transform(a)
assert isinstance(result, dd.DataFrame)
def test_transform_explicit_columns(self):
de = dpp.DummyEncoder(columns=["A", "B", "C"])
de.fit(dummy)
with pytest.raises(ValueError) as rec:
de.transform(dummy.drop("B", axis="columns"))
assert rec.match("Columns of 'X' do not match the training")
