def _compute_coefs(self, xx, yy, p=None, var=1):
x, y = np.atleast_1d(xx, yy)
x = x.ravel()
dx = np.diff(x)
must_sort = (dx < 0).any()
if must_sort:
ind = x.argsort()
x = x[ind]
y = y[..., ind]
dx = np.diff(x)
n = len(x)
# ndy = y.ndim
szy = y.shape
nd = prod(szy[:-1])
ny = szy[-1]
if n < 2:
raise ValueError('There must be >=2 data points.')
elif (dx <= 0).any():
raise ValueError('Two consecutive values in x can not be equal.')
elif n != ny:
raise ValueError('x and y must have the same length.')
dydx = np.diff(y) / dx
if (n == 2): # % straight line
coefs = np.vstack([dydx.ravel(), y[0, :]])
else:
dx1 = 1. / dx
D = sparse.spdiags(var * ones(n), 0, n, n) # The variance
u, p = self._compute_u(p, D, dydx, dx, dx1, n)
dx1.shape = (n - 1, -1)
dx.shape = (n - 1, -1)
zrs = zeros(nd)
if p < 1:
# faster than yi-6*(1-p)*Q*u
Qu = D * diff(vstack(
[zrs, diff(vstack([zrs, u, zrs]), axis=0) * dx1, zrs]),
axis=0)
ai = (y - (6 * (1 - p) * Qu).T).T
else:
ai = y.reshape(n, -1)
# The piecewise polynominals are written as
# fi=ai+bi*(x-xi)+ci*(x-xi)^2+di*(x-xi)^3
# where the derivatives in the knots according to Carl de Boor are:
# ddfi = 6*p*[0;u] = 2*ci;
# dddfi = 2*diff([ci;0])./dx = 6*di;
# dfi = diff(ai)./dx-(ci+di.*dx).*dx = bi;
ci = np.vstack([zrs, 3 * p * u])
di = (diff(vstack([ci, zrs]), axis=0) * dx1 / 3)
bi = (diff(ai, axis=0) * dx1 - (ci + di * dx) * dx)
ai = ai[:n - 1, ...]
if nd > 1:
di = di.T
ci = ci.T
ai = ai.T
if not any(di):
if not any(ci):
coefs = vstack([bi.ravel(), ai.ravel()])
else:
coefs = vstack([ci.ravel(), bi.ravel(), ai.ravel()])
else:
coefs = vstack(
[di.ravel(),
ci.ravel(),
bi.ravel(),
ai.ravel()])
return coefs, x
def _compute_coefs(self, xx, yy, p=None, var=1):
x, y = np.atleast_1d(xx, yy)
x = x.ravel()
dx = np.diff(x)
must_sort = (dx < 0).any()
if must_sort:
ind = x.argsort()
x = x[ind]
y = y[..., ind]
dx = np.diff(x)
n = len(x)
#ndy = y.ndim
szy = y.shape
nd = prod(szy[:-1])
ny = szy[-1]
if n < 2:
raise ValueError('There must be >=2 data points.')
elif (dx <= 0).any():
raise ValueError('Two consecutive values in x can not be equal.')
elif n != ny:
raise ValueError('x and y must have the same length.')
dydx = np.diff(y) / dx
if (n == 2): # % straight line
coefs = np.vstack([dydx.ravel(), y[0, :]])
else:
dx1 = 1. / dx
D = sp.spdiags(var * ones(n), 0, n, n) # The variance
u, p = self._compute_u(p, D, dydx, dx, dx1, n)
dx1.shape = (n - 1, -1)
dx.shape = (n - 1, -1)
zrs = zeros(nd)
if p < 1:
# faster than yi-6*(1-p)*Q*u
ai = (y - (6 * (1 - p) * D *
diff(vstack([zrs,
diff(vstack([zrs, u, zrs]), axis=0) * dx1,
zrs]), axis=0)).T).T
else:
ai = y.reshape(n, -1)
# The piecewise polynominals are written as
# fi=ai+bi*(x-xi)+ci*(x-xi)^2+di*(x-xi)^3
# where the derivatives in the knots according to Carl de Boor are:
# ddfi = 6*p*[0;u] = 2*ci;
# dddfi = 2*diff([ci;0])./dx = 6*di;
# dfi = diff(ai)./dx-(ci+di.*dx).*dx = bi;
ci = np.vstack([zrs, 3 * p * u])
di = (diff(vstack([ci, zrs]), axis=0) * dx1 / 3)
bi = (diff(ai, axis=0) * dx1 - (ci + di * dx) * dx)
ai = ai[:n - 1, ...]
if nd > 1:
di = di.T
ci = ci.T
ai = ai.T
if not any(di):
if not any(ci):
coefs = vstack([bi.ravel(), ai.ravel()])
else:
coefs = vstack([ci.ravel(), bi.ravel(), ai.ravel()])
else:
coefs = vstack(
[di.ravel(), ci.ravel(), bi.ravel(), ai.ravel()])
return coefs, x
feature_list = []
if options.features:
print options.features
feature_list = map(lambda s : int(s), options.features.split(','))
print feature_list
if options.prefix:
prefix = options.prefix
#prefix = 'data/tallinn_201s_title_rdist_10000'
X, y = load_data(prefix + '.train', feature_list=feature_list)
#print y.shape
#X, y = load_svmlight_file(prefix + '.train')
testX, testY = load_data(prefix + '.test', feature_list=feature_list)
X = vstack((X, testX))
X = preprocessing.scale(X)
print X
#y = vstack((y, testY))
#y = y + testY
#y = y.transpose()
#print y.shape, testY.shape
y = hstack((y, testY))
print y
if options.data:
log('loading ' + str(options.data))
X, y = load_data(options.data, feature_list=feature_list)
if False:
pos_start = 0
