class MinMaxScaler Found at: sklearn.preprocessing.data
class MinMaxScaler(BaseEstimator, TransformerMixin):
def __init__(self, feature_range=(0, 1), copy=True):
self.feature_range = feature_range
self.copy = copy
def _reset(self):
"""Reset internal data-dependent state of the scaler, if
necessary.
__init__ parameters are not touched.
"""
# Checking one attribute is enough, becase they are all set
together
# in partial_fit
if hasattr(self, 'scale_'):
del self.scale_
del self.min_
del self.n_samples_seen_
del self.data_min_
del self.data_max_
del self.data_range_
def fit(self, X, y=None):
"""Compute the minimum and maximum to be used for later
scaling.
Parameters
----------
X : array-like, shape [n_samples, n_features]
The data used to compute the per-feature minimum and
maximum
used for later scaling along the features axis.
"""
# Reset internal state before fitting
self._reset()
return self.partial_fit(X, y)
def partial_fit(self, X, y=None):
"""Online computation of min and max on X for later scaling.
All of X is processed as a single batch. This is intended for
cases
when `fit` is not feasible due to very large number of
`n_samples`
or because X is read from a continuous stream.
Parameters
----------
X : array-like, shape [n_samples, n_features]
The data used to compute the mean and standard deviation
used for later scaling along the features axis.
y : Passthrough for ``Pipeline`` compatibility.
"""
feature_range = self.feature_range
if feature_range[0] >= feature_range[1]:
raise ValueError(
"Minimum of desired feature range must be smaller"
" than maximum. Got %s." %
str(feature_range))
if sparse.issparse(X):
raise TypeError("MinMaxScaler does no support sparse
input. "
"You may consider to use MaxAbsScaler instead.")
X = check_array(X, copy=self.copy, warn_on_dtype=True,
estimator=self, dtype=FLOAT_DTYPES)
data_min = np.min(X, axis=0)
data_max = np.max(X, axis=0)
# First pass
if not hasattr(self, 'n_samples_seen_'):
self.n_samples_seen_ = X.shape[0]
else:
data_min = np.minimum(self.data_min_, data_min)
data_max = np.maximum(self.data_max_, data_max)
self.n_samples_seen_ += X.shape[0] # Next steps
data_range = data_max - data_min
self.scale_ = (feature_range[1] - feature_range[0]) /
_handle_zeros_in_scale(data_range)
self.min_ = feature_range[0] - data_min * self.scale_
self.data_min_ = data_min
self.data_max_ = data_max
self.data_range_ = data_range
return self
def transform(self, X):
"""Scaling features of X according to feature_range.
Parameters
----------
X : array-like, shape [n_samples, n_features]
Input data that will be transformed.
"""
check_is_fitted(self, 'scale_')
X = check_array(X, copy=self.copy, dtype=FLOAT_DTYPES)
X *= self.scale_
X += self.min_
return X
def inverse_transform(self, X):
"""Undo the scaling of X according to feature_range.
Parameters
----------
X : array-like, shape [n_samples, n_features]
Input data that will be transformed. It cannot be sparse.
"""
check_is_fitted(self, 'scale_')
X = check_array(X, copy=self.copy, dtype=FLOAT_DTYPES)
X -= self.min_
X /= self.scale_
return X
