def _pre_fit(self, X, y):
X, event, time = check_arrays_survival(X, y, copy=self.copy_X)
# center feature matrix
X_offset = numpy.average(X, axis=0)
X -= X_offset
if self.normalize:
X = f_normalize(X, copy=False, axis=0)
# sort descending
o = numpy.argsort(-time, kind="mergesort")
X = numpy.asfortranarray(X[o, :])
event_num = event[o].astype(numpy.uint8)
time = time[o].astype(numpy.float64)
return X, event_num, time
def _pre_fit(self, X, y):
X, event, time = check_arrays_survival(X, y, copy=self.copy_X)
X = self._validate_data(X)
# center feature matrix
X_offset = numpy.average(X, axis=0)
X -= X_offset
if self.normalize:
X, X_scale = f_normalize(X, copy=False, axis=0, return_norm=True)
else:
X_scale = numpy.ones(X.shape[1], dtype=X.dtype)
# sort descending
o = numpy.argsort(-time, kind="mergesort")
X = numpy.asfortranarray(X[o, :])
event_num = event[o].astype(numpy.uint8)
time = time[o].astype(numpy.float64)
return X, event_num, time, X_offset, X_scale
def _preprocess_data(X, y, fit_intercept, normalize=False, copy=True,
sample_weight=None, return_mean=False, check_input=True):
"""Center and scale data.
Centers data to have mean zero along axis 0. If fit_intercept=False or if
the X is a sparse matrix, no centering is done, but normalization can still
be applied. The function returns the statistics necessary to reconstruct
the input data, which are X_offset, y_offset, X_scale, such that the output
X = (X - X_offset) / X_scale
X_scale is the L2 norm of X - X_offset. If sample_weight is not None,
then the weighted mean of X and y is zero, and not the mean itself. If
return_mean=True, the mean, eventually weighted, is returned, independently
of whether X was centered (option used for optimization with sparse data in
coordinate_descend).
This is here because nearly all linear models will want their data to be
centered. This function also systematically makes y consistent with X.dtype
"""
if isinstance(sample_weight, numbers.Number):
sample_weight = None
if sample_weight is not None:
sample_weight = np.asarray(sample_weight)
if check_input:
X = check_array(X, copy=copy, accept_sparse=['csr', 'csc'],
dtype=FLOAT_DTYPES)
elif copy:
if issparse(X):
X = X.copy()
else:
X = X.copy(order='K')
y = np.asarray(y, dtype=X.dtype)
if fit_intercept:
if issparse(X):
X_offset, X_var = mean_variance_axis(X, axis=0)
if not return_mean:
X_offset[:] = X.dtype.type(0)
if normalize:
# TODO: f_normalize could be used here as well but the function
# inplace_csr_row_normalize_l2 must be changed such that it
# can return also the norms computed internally
# transform variance to norm in-place
X_var *= X.shape[0]
X_scale = np.sqrt(X_var, X_var)
del X_var
X_scale[X_scale == 0] = 1
inplace_column_scale(X, 1. / X_scale)
else:
X_scale = np.ones(X.shape[1], dtype=X.dtype)
else:
X_offset = np.average(X, axis=0, weights=sample_weight)
X -= X_offset
if normalize:
X, X_scale = f_normalize(X, axis=0, copy=False,
return_norm=True)
else:
X_scale = np.ones(X.shape[1], dtype=X.dtype)
y_offset = np.average(y, axis=0, weights=sample_weight)
y = y - y_offset
else:
if normalize:
if issparse(X):
_, X_var = mean_variance_axis(X, axis=0)
# transform variance to norm in-place
X_var *= X.shape[0]
X_scale = np.sqrt(X_var, X_var)
del X_var
X_scale[X_scale == 0] = 1
inplace_column_scale(X, 1. / X_scale)
else:
X, X_scale = f_normalize(X, axis=0, copy=False,
return_norm=True)
else:
X_scale = np.ones(X.shape[1], dtype=X.dtype)
X_offset = np.zeros(X.shape[1], dtype=X.dtype)
if y.ndim == 1:
y_offset = X.dtype.type(0)
else:
y_offset = np.zeros(y.shape[1], dtype=X.dtype)
return X, y, X_offset, y_offset, X_scale
