def test_ohe_preserves_custom_index(index):
df = pd.DataFrame({"categories": [f"cat_{i}" for i in range(5)], "numbers": np.arange(5)},
index=index)
ohe = OneHotEncoder()
new_df = ohe.fit_transform(df)
pd.testing.assert_index_equal(new_df.index, df.index)
assert not new_df.isna().any(axis=None)
def test_ohe_output_bools():
X = ww.DataTable(
pd.DataFrame({
"bool": [bool(i % 2) for i in range(100)],
"categorical": ["dog"] * 20 + ["cat"] * 40 + ["fish"] * 40,
"integers": [i for i in range(100)]
}))
y = ww.DataColumn(pd.Series([i % 2 for i in range(100)]))
ohe = OneHotEncoder()
output = ohe.fit_transform(X, y)
for name, types in output.types["Logical Type"].items():
if name == 'integers':
assert str(types) == "Integer"
else:
assert str(types) == "Boolean"
assert len(output.columns) == 5
def check_df_equality(random_seed):
ohe = OneHotEncoder(top_n=4, random_seed=random_seed)
df1 = ohe.fit_transform(df).to_dataframe()
df2 = ohe.fit_transform(df).to_dataframe()
assert_frame_equal(df1, df2)
def check_df_equality(random_state):
ohe = OneHotEncoder(top_n=4, random_state=random_state)
df1 = ohe.fit_transform(df)
df2 = ohe.fit_transform(df)
pd.testing.assert_frame_equal(df1, df2)
