在使用sklearn进行一元二次拟合的时候遇到fit_transform函数,对下面的列表进行变换
X = [[50], [100], [150], [200], [250], [300]]
quadratic_featurizer=PolynomialFeatures(degree=2)
X_train_quadratic = quadratic_featurizer.fit_transform(X)
[[1.00e+00 5.00e+01 2.50e+03]
[1.00e+00 1.00e+02 1.00e+04]
[1.00e+00 1.50e+02 2.25e+04]
[1.00e+00 2.00e+02 4.00e+04]
[1.00e+00 2.50e+02 6.25e+04]
[1.00e+00 3.00e+02 9.00e+04]]
class PolynomialFeatures(BaseEstimator, TransformerMixin):
"""Generate polynomial and interaction features.
Generate a new feature matrix consisting of all polynomial combinations
of the features with degree less than or equal to the specified degree.
For example, if an input sample is two dimensional and of the form
[a, b], the degree-2 polynomial features are [1, a, b, a^2, ab, b^2].
Parameters
----------
degree : integer
The degree of the polynomial features. Default = 2.
interaction_only : boolean, default = False
If true, only interaction features are produced: features that are
products of at most ``degree`` *distinct* input features (so not
``x[1] ** 2``, ``x[0] * x[2] ** 3``, etc.).
include_bias : boolean
If True (default), then include a bias column, the feature in which
all polynomial powers are zero (i.e. a column of ones - acts as an
intercept term in a linear model).
Examples
--------
>>> X = np.arange(6).reshape(3, 2)
>>> X
array([[0, 1],
[2, 3],
[4, 5]])
>>> poly = PolynomialFeatures(2)
>>> poly.fit_transform(X)
array([[ 1., 0., 1., 0., 0., 1.],
[ 1., 2., 3., 4., 6., 9.],
[ 1., 4., 5., 16., 20., 25.]])
>>> poly = PolynomialFeatures(interaction_only=True)
>>> poly.fit_transform(X)
array([[ 1., 0., 1., 0.],
[ 1., 2., 3., 6.],
[ 1., 4., 5., 20.]])
Attributes
----------
powers_ : array, shape (n_output_features, n_input_features)
powers_[i, j] is the exponent of the jth input in the ith output.
n_input_features_ : int
The total number of input features.
n_output_features_ : int
The total number of polynomial output features. The number of output
features is computed by iterating over all suitably sized combinations
of input features.
Notes
-----
Be aware that the number of features in the output array scales
polynomially in the number of features of the input array, and
exponentially in the degree. High degrees can cause overfitting.
See :ref:`examples/linear_model/plot_polynomial_interpolation.py
<sphx_glr_auto_examples_linear_model_plot_polynomial_interpolation.py>`
"""
def __init__(self, degree=2, interaction_only=False, include_bias=True):
self.degree = degree
self.interaction_only = interaction_only
self.include_bias = include_bias
@staticmethod
def _combinations(n_features, degree, interaction_only, include_bias):
comb = (combinations if interaction_only else combinations_w_r)
start = int(not include_bias)
return chain.from_iterable(comb(range(n_features), i)
for i in range(start, degree + 1))
@property
def powers_(self):
check_is_fitted(self, 'n_input_features_')
combinations = self._combinations(self.n_input_features_, self.degree,
self.interaction_only,
self.include_bias)
return np.vstack([np.bincount(c, minlength=self.n_input_features_)
for c in combinations])
def get_feature_names(self, input_features=None):
"""
Return feature names for output features
Parameters
----------
input_features : list of string, length n_features, optional
String names for input features if available. By default,
"x0", "x1", ... "xn_features" is used.
Returns
-------
output_feature_names : list of string, length n_output_features
"""
powers = self.powers_
if input_features is None:
input_features = ['x%d' % i for i in range(powers.shape[1])]
feature_names = []
for row in powers:
inds = np.where(row)[0]
if len(inds):
name = " ".join("%s^%d" % (input_features[ind], exp)
if exp != 1 else input_features[ind]
for ind, exp in zip(inds, row[inds]))
else:
name = "1"
feature_names.append(name)
return feature_names
def fit(self, X, y=None):
"""
Compute number of output features.
Parameters
----------
X : array-like, shape (n_samples, n_features)
The data.
Returns
-------
self : instance
"""
n_samples, n_features = check_array(X, accept_sparse=True).shape
combinations = self._combinations(n_features, self.degree,
self.interaction_only,
self.include_bias)
self.n_input_features_ = n_features
self.n_output_features_ = sum(1 for _ in combinations)
return self
def transform(self, X):
"""Transform data to polynomial features
Parameters
----------
X : array-like or sparse matrix, shape [n_samples, n_features]
The data to transform, row by row.
Sparse input should preferably be in CSC format.
Returns
-------
XP : np.ndarray or CSC sparse matrix, shape [n_samples, NP]
The matrix of features, where NP is the number of polynomial
features generated from the combination of inputs.
"""
check_is_fitted(self, ['n_input_features_', 'n_output_features_'])
X = check_array(X, dtype=FLOAT_DTYPES, accept_sparse='csc')
n_samples, n_features = X.shape
if n_features != self.n_input_features_:
raise ValueError("X shape does not match training shape")
combinations = self._combinations(n_features, self.degree,
self.interaction_only,
self.include_bias)
if sparse.isspmatrix(X):
columns = []
for comb in combinations:
if comb:
out_col = 1
for col_idx in comb:
out_col = X[:, col_idx].multiply(out_col)
columns.append(out_col)
else:
columns.append(sparse.csc_matrix(np.ones((X.shape[0], 1))))
XP = sparse.hstack(columns, dtype=X.dtype).tocsc()
else:
XP = np.empty((n_samples, self.n_output_features_), dtype=X.dtype)
for i, comb in enumerate(combinations):
XP[:, i] = X[:, comb].prod(1)
return XP
def normalize(X, norm='l2', axis=1, copy=True, return_norm=False):
"""Scale input vectors individually to unit norm (vector length).
Read more in the :ref:`User Guide <preprocessing_normalization>`.
Parameters
----------
X : {array-like, sparse matrix}, shape [n_samples, n_features]
The data to normalize, element by element.
scipy.sparse matrices should be in CSR format to avoid an
un-necessary copy.
norm : 'l1', 'l2', or 'max', optional ('l2' by default)
The norm to use to normalize each non zero sample (or each non-zero
feature if axis is 0).
axis : 0 or 1, optional (1 by default)
axis used to normalize the data along. If 1, independently normalize
each sample, otherwise (if 0) normalize each feature.
copy : boolean, optional, default True
set to False to perform inplace row normalization and avoid a
copy (if the input is already a numpy array or a scipy.sparse
CSR matrix and if axis is 1).
return_norm : boolean, default False
whether to return the computed norms
Returns
-------
X : {array-like, sparse matrix}, shape [n_samples, n_features]
Normalized input X.
norms : array, shape [n_samples] if axis=1 else [n_features]
An array of norms along given axis for X.
When X is sparse, a NotImplementedError will be raised
for norm 'l1' or 'l2'.
See also
--------
Normalizer: Performs normalization using the ``Transformer`` API
(e.g. as part of a preprocessing :class:`sklearn.pipeline.Pipeline`).
Notes
-----
For a comparison of the different scalers, transformers, and normalizers,
see :ref:`examples/preprocessing/plot_all_scaling.py
<sphx_glr_auto_examples_preprocessing_plot_all_scaling.py>`.
"""
if norm not in ('l1', 'l2', 'max'):
raise ValueError("'%s' is not a supported norm" % norm)
if axis == 0:
sparse_format = 'csc'
elif axis == 1:
sparse_format = 'csr'
else:
raise ValueError("'%d' is not a supported axis" % axis)
X = check_array(X, sparse_format, copy=copy,
estimator='the normalize function', dtype=FLOAT_DTYPES)
if axis == 0:
X = X.T
if sparse.issparse(X):
if return_norm and norm in ('l1', 'l2'):
raise NotImplementedError("return_norm=True is not implemented "
"for sparse matrices with norm 'l1' "
"or norm 'l2'")
if norm == 'l1':
inplace_csr_row_normalize_l1(X)
elif norm == 'l2':
inplace_csr_row_normalize_l2(X)
elif norm == 'max':
_, norms = min_max_axis(X, 1)
norms_elementwise = norms.repeat(np.diff(X.indptr))
mask = norms_elementwise != 0
X.data[mask] /= norms_elementwise[mask]
else:
if norm == 'l1':
norms = np.abs(X).sum(axis=1)
elif norm == 'l2':
norms = row_norms(X)
elif norm == 'max':
norms = np.max(X, axis=1)
norms = _handle_zeros_in_scale(norms, copy=False)
X /= norms[:, np.newaxis]
if axis == 0:
X = X.T
if return_norm:
return X, norms
else:
return X