def decode(fitted_encoder: BaseEstimator, features: List[str],
df: pd.DataFrame) -> pd.DataFrame:
"""
Pipeline function to decode data with fitted sklearn OneHotEncoder.
Parameters
----------
fitted_encoder : sklearn OneHotEncoder
Encodes input data.
features : list
List of categorical feature.
df : pd.DataFrame
Data we want to normalize
Returns
-------
output : pd.DataFrame
Whole DataFrame with encoded values
"""
output = df.copy()
encoded_features = fitted_encoder.get_feature_names(features)
# Prevent errors for datasets without categorical data
# inverse_transform cannot handle these cases
if len(encoded_features) == 0:
return output
output[features] = fitted_encoder.inverse_transform(
output[encoded_features])
output = output.drop(encoded_features, axis=1)
return output
def hook(self, model: BaseEstimator, history: History):
noimages = self.datapoints.shape[0]
latvar = model.transform(self.datapoints)
konstrukt = model.inverse_transform(latvar())
last = history.last()
filename = 'rekonstrukt-%02de-%03db.png' % (last[1], last[2])
img = visualize_reconstruction(self.datapoints, konstrukt, noimages)
img.save(join(self.outdir, filename))
def descale(fitted_scaler: BaseEstimator, features: List[str],
df: pd.DataFrame) -> pd.DataFrame:
"""
Pipeline function to de-normalize data with fitted sklearn scaler.
Parameters
----------
fitted_scaler : sklearn Scaler
Normalizes input data
features : list
List of continuous feature
df : pd.DataFrame
Data we want to de-normalize
Returns
-------
output : pd.DataFrame
Whole DataFrame with de-normalized values
"""
output = df.copy()
output[features] = fitted_scaler.inverse_transform(output[features])
return output
def scaled_linspace(x: np.ndarray, y: np.ndarray, num: int,
scaler: BaseEstimator) -> np.ndarray:
"""Generate a linspace, evenly spaced according to the normalization
Args:
x (np.ndarray): First point
y (np.ndarray): Sencond point
num (int): Number of points (in between the two points)
method (str): Normalization method
Returns:
np.ndarray: Sequence of points evenly spaced
"""
# Normalize the points
x = scaler.transform([x])[0]
y = scaler.transform([y])[0]
# Generate the linspace
ls = np.linspace(x, y, num=num + 1, endpoint=True)
# Unnormalize the points
ls = scaler.inverse_transform(ls)
return ls
