def fit(self, x: np.ndarray, groups: np.ndarray = None):
if groups is not None:
group_index = group_mapping(groups)
self.mean = aggregate(group_index, x, 'mean')
self.std = aggregate(group_index, x, 'std', self.ddof)
self.labels = np.unique(groups)
else:
self.mean = simple_mean(x, axis=0)
self.std = simple_std(x, axis=0, ddof=self.ddof)
def standardize(x: np.ndarray, groups: np.ndarray = None, ddof=1) -> np.ndarray:
if groups is not None:
groups = group_mapping(groups)
mean_values = transform(groups, x, 'mean')
std_values = transform(groups, x, 'std', ddof)
return (x - mean_values) / np.maximum(std_values, 1e-8)
else:
return (x - simple_mean(x, axis=0)) / np.maximum(simple_std(x, axis=0, ddof=ddof), 1e-8)
def winsorize_normal(x: np.ndarray,
num_stds: int = 3,
groups: np.ndarray = None) -> np.ndarray:
if groups is not None:
groups = group_mapping(groups)
mean_values = transform(groups, x, 'mean')
std_values = transform(groups, x, 'std')
res = mask_values_2d(x, mean_values, std_values, num_stds)
else:
std_values = simple_std(x, axis=0)
mean_values = simple_mean(x, axis=0)
res = mask_values_1d(x, mean_values, std_values, num_stds)
return res
def winsorize_normal(x: np.ndarray,
num_stds: int = 3,
ddof=1,
groups: np.ndarray = None,
method: str = 'flat',
interval: float = 0.5) -> np.ndarray:
if groups is not None:
groups = group_mapping(groups)
mean_values = transform(groups, x, 'mean')
std_values = transform(groups, x, 'std', ddof)
if method == 'flat':
res = mask_values_2d(x, mean_values, std_values, num_stds)
else:
res = interp_values_2d(x, groups, mean_values, std_values,
num_stds, interval)
else:
std_values = simple_std(x, axis=0, ddof=ddof)
mean_values = simple_mean(x, axis=0)
if method == 'flat':
res = mask_values_1d(x, mean_values, std_values, num_stds)
else:
res = interp_values_1d(x, mean_values, std_values, num_stds,
interval)
return res
def fit(self, x: np.ndarray):
self.mean_ = simple_mean(x, axis=0)
self.std_ = simple_std(x, axis=0, ddof=self.ddof_)