def test_to_and_from_json_booleans(self):
# training data
d = {"col1": ["a", "a", "c"], "col2": [True, True, False]}
df = pd.DataFrame(data=d)
# fit binarizer
lb1 = LabelBinarizer()
lb1.fit(df, "col1")
lb2 = LabelBinarizer()
lb2.fit(df, "col2")
# test data
d_test = {
"col1": ["c", "c", "a"],
"col2": [False, False, True],
"col3": [2, 3, 4],
}
df_test = pd.DataFrame(data=d_test)
# to json and from json
new_lb1 = LabelBinarizer()
new_lb2 = LabelBinarizer()
new_lb1.from_json(lb1.to_json())
new_lb2.from_json(json.loads(json.dumps(lb2.to_json(), indent=4)))
# transform
df_test = new_lb1.transform(df_test, "col1")
df_test = new_lb2.transform(df_test, "col2")
# for binary column, only one value is left, old column should be deleted
self.assertTrue("col1_c" in df_test.columns)
self.assertTrue("col1" not in df_test.columns)
self.assertEqual(2, np.sum(df_test["col1_c"]))
# for multiple value colum, all columns should be added
self.assertTrue("col2_True" in df_test.columns)
self.assertTrue("col2" not in df_test.columns)
self.assertEqual(1, np.sum(df_test["col2_True"]))
# do not touch continuous attribute
self.assertTrue("col3" in df_test.columns)
def inverse_transform(self, X):
for column, lbl_params in self._convert_params.items():
if "unique_values" in lbl_params and "new_columns" in lbl_params:
# convert to one hot
lbl = LabelBinarizer()
lbl.from_json(lbl_params)
X = lbl.inverse_transform(X, column) # should raise exception
else:
# convert to integer
lbl = LabelEncoder()
lbl.from_json(lbl_params)
X.loc[:, column] = lbl.inverse_transform(X.loc[:, column])
return X
def transform(self, X):
if (self._convert_method == PreprocessingCategorical.CONVERT_LOO
and self._columns):
return self._enc.transform(X)
else:
for column, lbl_params in self._convert_params.items():
if "unique_values" in lbl_params and "new_columns" in lbl_params:
# convert to one hot
lbl = LabelBinarizer()
lbl.from_json(lbl_params)
X = lbl.transform(X, column)
else:
# convert to integer
lbl = LabelEncoder()
lbl.from_json(lbl_params)
X.loc[:, column] = lbl.transform(X.loc[:, column])
return X
