def test_basic(self, daskify, values):
de = dpp.OrdinalEncoder()
df = dummy[["A", "D"]]
if daskify:
df = dd.from_pandas(df, 2)
de = de.fit(df)
trn = de.transform(df)
expected = pd.DataFrame(
{
"A": np.array([0, 1, 2, 0], dtype="int8"),
"D": np.array([1, 2, 3, 4])
},
columns=["A", "D"],
)
assert_eq_df(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_inverse_transform(self):
enc = dpp.OrdinalEncoder()
df = dd.from_pandas(pd.DataFrame({
"A":
np.arange(10),
"B":
pd.Categorical(['a'] * 4 + ['b'] * 6)
}),
npartitions=2)
enc.fit(df)
assert_eq_df(df, enc.inverse_transform(enc.transform(df)))
assert_eq_df(df, enc.inverse_transform(enc.transform(df).compute()))
assert_eq_df(df, enc.inverse_transform(enc.transform(df).values))
assert_eq_df(df,
enc.inverse_transform(enc.transform(df).values.compute()))
def test_inverse_transform(self):
enc = dpp.OrdinalEncoder()
df = dd.from_pandas(
pd.DataFrame(
{"A": np.arange(10), "B": pd.Categorical(["a"] * 4 + ["b"] * 6)}
),
npartitions=2,
)
enc.fit(df)
assert dask.is_dask_collection(enc.inverse_transform(enc.transform(df).values))
assert dask.is_dask_collection(enc.inverse_transform(enc.transform(df)))
assert_eq_df(df, enc.inverse_transform(enc.transform(df)))
assert_eq_df(df, enc.inverse_transform(enc.transform(df)))
assert_eq_df(df, enc.inverse_transform(enc.transform(df).values))
assert_eq_df(df, enc.inverse_transform(enc.transform(df).values))
def test_transform_raises(self):
de = dpp.OrdinalEncoder()
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.OrdinalEncoder()
result = de.fit_transform(a)
assert isinstance(result, dd.DataFrame)