def test_to_and_from_json(self):
# training data
d = {
"col1": [1, 2, 3, 4, 5, 6, 7, 8.0, 9, 10],
"col2": [21, 22.0, 23, 24, 25, 26, 27, 28, 29, 30],
}
df = pd.DataFrame(data=d)
scale = PreprocessingScale(["col1"])
scale.fit(df)
# do not transform
assert_almost_equal(np.mean(df["col1"]), 5.5)
assert_almost_equal(np.mean(df["col2"]), 25.5)
# to and from json
json_data = scale.to_json()
print(json_data)
scale2 = PreprocessingScale()
scale2.from_json(json_data)
# transform with loaded scaler
df = scale2.transform(df)
assert_almost_equal(np.mean(df["col1"]), 0)
assert_almost_equal(np.mean(df["col2"]), 25.5)
def from_json(self, data_json):
if "remove_columns" in data_json:
self._remove_columns = data_json.get("remove_columns", [])
if "missing_values" in data_json:
self._missing_values = []
for mv_data in data_json["missing_values"]:
mv = PreprocessingMissingValues()
mv.from_json(mv_data)
self._missing_values += [mv]
if "categorical" in data_json:
self._categorical = []
for cat_data in data_json["categorical"]:
cat = PreprocessingCategorical()
cat.from_json(cat_data)
self._categorical += [cat]
if "scale" in data_json:
self._scale = []
for scale_data in data_json["scale"]:
sc = PreprocessingScale()
sc.from_json(scale_data)
self._scale += [sc]
if "categorical_y" in data_json:
self._categorical_y = LabelEncoder()
self._categorical_y.from_json(data_json["categorical_y"])