class MaxAbsScaler(FeatureTransformAlgorithm):
r"""Implementation of feature scaling by its maximum absolute value.
Date:
2020
Author:
Luka Pečnik
License:
MIT
Documentation:
https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.MaxAbsScaler.html#sklearn.preprocessing.MaxAbsScaler
See Also:
* :class:`niaaml.preprocessing.feature_transform.FeatureTransformAlgorithm`
"""
Name = 'Maximum Absolute Scaler'
def __init__(self, **kwargs):
r"""Initialize MaxAbsScaler.
"""
super(MaxAbsScaler, self).__init__()
self.__max_abs_scaler = MAS()
def fit(self, x, **kwargs):
r"""Fit implemented transformation algorithm.
Arguments:
x (pandas.core.frame.DataFrame): n samples to fit transformation algorithm.
"""
self.__max_abs_scaler.fit(x)
def transform(self, x, **kwargs):
r"""Transforms the given x data.
Arguments:
x (pandas.core.frame.DataFrame): Data to transform.
Returns:
pandas.core.frame.DataFrame: Transformed data.
"""
return self.__max_abs_scaler.transform(x)
def to_string(self):
r"""User friendly representation of the object.
Returns:
str: User friendly representation of the object.
"""
return FeatureTransformAlgorithm.to_string(self).format(
name=self.Name,
args=self._parameters_to_string(
self.__max_abs_scaler.get_params()))
# Importing data
cwd = Path(os.getcwd())
p = cwd / 'DATA'
data = pd.read_csv(p / "yacht_hydro.csv")
# boxplots
#for col in data.columns:
# plt.figure()
# plt.boxplot(data[col])
# plt.title(col)
# scaling the data
data_scaled = data.copy()
scaler = MaxAbsScaler()
data_scaled.loc[:, :] = scaler.fit_transform(data)
scaler_params = scaler.get_params()
# We will eventually need the physical (unscaled) data to display the results
extract_scaling_function = np.ones((1, data_scaled.shape[1]))
extract_scaling_function = scaler.inverse_transform(extract_scaling_function)
pd.set_option('display.max_columns', 7)
#print(data_scaled.iloc[:3,:])
## Shuffling data
#data = data.sample(frac=1,random_state=0).reset_index(drop=True)
#
#
## Separating inputs from outputs
#X_data = np.array(data.iloc[:,:6])
#y_data = np.array(data.iloc[:,-1])
