def test_arbitrary_encoding_automatically_find_variables(df_enc):
# test case 2: automatically select variables, unordered encoding
encoder = OrdinalEncoder(encoding_method="arbitrary", variables=None)
X = encoder.fit_transform(df_enc)
# expected output
transf_df = df_enc.copy()
transf_df["var_A"] = [
0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2
]
transf_df["var_B"] = [
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2
]
# test init params
assert encoder.encoding_method == "arbitrary"
assert encoder.variables is None
# test fit attr
assert encoder.variables_ == ["var_A", "var_B"]
assert encoder.encoder_dict_ == {
"var_A": {
"A": 0,
"B": 1,
"C": 2
},
"var_B": {
"A": 0,
"B": 1,
"C": 2
},
}
assert encoder.n_features_in_ == 3
# test transform output
pd.testing.assert_frame_equal(X, transf_df)
def test_arbitrary_encoding_automatically_find_variables_ignore_format(
df_enc_numeric):
encoder = OrdinalEncoder(encoding_method="arbitrary",
variables=None,
ignore_format=True)
X = encoder.fit_transform(df_enc_numeric[["var_A", "var_B"]])
# expected output
transf_df = df_enc_numeric[["var_A", "var_B"]].copy()
transf_df["var_A"] = [
0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2
]
transf_df["var_B"] = [
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2
]
# test init params
assert encoder.encoding_method == "arbitrary"
assert encoder.variables is None
# test fit attr
assert encoder.variables_ == ["var_A", "var_B"]
assert encoder.encoder_dict_ == {
"var_A": {
1: 0,
2: 1,
3: 2
},
"var_B": {
1: 0,
2: 1,
3: 2
},
}
assert encoder.n_features_in_ == 2
# test transform output
pd.testing.assert_frame_equal(X, transf_df)