def transform(self, y):
"""Perform encoding if already fit.
Parameters
----------
y : array_like, shape=(n_samples,)
The array to encode
Returns
-------
e : array_like, shape=(n_samples,)
The encoded array
"""
check_is_fitted(self, 'classes_')
y = column_or_1d(y, warn=True)
classes = np.unique(y)
_check_numpy_unicode_bug(classes)
# Check not too many:
unseen = _get_unseen()
if len(classes) >= unseen:
raise ValueError('Too many factor levels in feature. Max is %i' % unseen)
e = np.array([
np.searchsorted(self.classes_, x) if x in self.classes_ else unseen
for x in y
])
return e
def transform(self, y):
check_is_fitted(self, 'classes_')
y = column_or_1d(y, warn=True)
classes = np.unique(y)
_check_numpy_unicode_bug(classes)
## Check not too many:
unseen = get_unseen()
if len(classes) >= unseen:
raise ValueError('Too many factor levels in feature. Max is %i' % unseen)
return np.array([np.searchsorted(self.classes_, x)\
if x in self.classes_\
else unseen\
for x in y])
def fit(self, X, y=None):
"""Fit label encoder
Parameters
----------
y : array-like of shape (n_samples,)
Target values.
Returns
-------
self : returns an instance of self.
"""
X = column_or_1d(X.ravel(), warn=True)
_check_numpy_unicode_bug(X)
self.classes_ = np.unique(X)
if isinstance(self.classes_[0], np.float64):
self.classes_ = self.classes_[np.isfinite(self.classes_)]
return self
def transform(self, y):
"""Transform labels to normalized encoding.
Parameters
----------
y : array-like of shape [n_samples]
Target values.
Returns
-------
y : array-like of shape [n_samples]
"""
check_is_fitted(self, 'classes_')
y = column_or_1d(y.ravel(), warn=True)
classes = np.unique(y)
if isinstance(classes[0], np.float64):
classes = classes[np.isfinite(classes)]
_check_numpy_unicode_bug(classes)
if len(np.intersect1d(classes, self.classes_)) < len(classes):
diff = np.setdiff1d(classes, self.classes_)
print(self.classes_)
raise ValueError("y contains new labels: %s" % str(diff))
return np.searchsorted(self.classes_, y).reshape(-1, 1)
def mapper(y):
y = column_or_1d(y, warn=True)
_check_numpy_unicode_bug(y)
return np.unique(y)
def mapper(y):
y = column_or_1d(y, warn=True)
_check_numpy_unicode_bug(y)
return np.unique(y)
