[Scipy-svn] r6409 - in trunk/scipy: linalg maxentropy sparse
scipy-svn at scipy.org
scipy-svn at scipy.org
Mon May 24 09:11:59 EDT 2010
Author: rgommers
Date: 2010-05-24 08:11:58 -0500 (Mon, 24 May 2010)
New Revision: 6409
Modified:
trunk/scipy/linalg/basic.py
trunk/scipy/maxentropy/maxentropy.py
trunk/scipy/sparse/dok.py
Log:
DOC: merge wiki edits - linalg, maxentropy and sparse.
Modified: trunk/scipy/linalg/basic.py
===================================================================
--- trunk/scipy/linalg/basic.py 2010-05-24 13:11:41 UTC (rev 6408)
+++ trunk/scipy/linalg/basic.py 2010-05-24 13:11:58 UTC (rev 6409)
@@ -292,38 +292,50 @@
### Linear Least Squares
def lstsq(a, b, cond=None, overwrite_a=False, overwrite_b=False):
- """Compute least-squares solution to equation :m:`a x = b`
+ """
+ Compute least-squares solution to equation Ax = b.
- Compute a vector x such that the 2-norm :m:`|b - a x|` is minimised.
+ Compute a vector x such that the 2-norm ``|b - A x|`` is minimized.
Parameters
----------
a : array, shape (M, N)
+ Left hand side matrix (2-D array).
b : array, shape (M,) or (M, K)
- cond : float
+ Right hand side matrix or vector (1-D or 2-D array).
+ cond : float, optional
Cutoff for 'small' singular values; used to determine effective
- rank of a. Singular values smaller than rcond*largest_singular_value
- are considered zero.
- overwrite_a : boolean
- Discard data in a (may enhance performance)
- overwrite_b : boolean
- Discard data in b (may enhance performance)
+ rank of a. Singular values smaller than
+ ``rcond * largest_singular_value`` are considered zero.
+ overwrite_a : bool, optional
+ Discard data in `a` (may enhance performance). Default is False.
+ overwrite_b : bool, optional
+ Discard data in `b` (may enhance performance). Default is False.
Returns
-------
x : array, shape (N,) or (N, K) depending on shape of b
- Least-squares solution
- residues : array, shape () or (1,) or (K,)
- Sums of residues, squared 2-norm for each column in :m:`b - a x`
+ Least-squares solution.
+ residues : ndarray, shape () or (1,) or (K,)
+ Sums of residues, squared 2-norm for each column in ``b - a x``.
If rank of matrix a is < N or > M this is an empty array.
- If b was 1-d, this is an (1,) shape array, otherwise the shape is (K,)
- rank : integer
- Effective rank of matrix a
+ If b was 1-D, this is an (1,) shape array, otherwise the shape is (K,).
+ rank : int
+ Effective rank of matrix `a`.
s : array, shape (min(M,N),)
- Singular values of a. The condition number of a is abs(s[0]/s[-1]).
+ Singular values of `a`. The condition number of a is
+ ``abs(s[0]/s[-1])``.
- Raises LinAlgError if computation does not converge
+ Raises
+ ------
+ LinAlgError :
+ If computation does not converge.
+
+ See Also
+ --------
+ optimize.nnls : linear least squares with non-negativity constraint
+
"""
a1, b1 = map(asarray_chkfinite, (a, b))
if len(a1.shape) != 2:
Modified: trunk/scipy/maxentropy/maxentropy.py
===================================================================
--- trunk/scipy/maxentropy/maxentropy.py 2010-05-24 13:11:41 UTC (rev 6408)
+++ trunk/scipy/maxentropy/maxentropy.py 2010-05-24 13:11:58 UTC (rev 6409)
@@ -788,15 +788,16 @@
class conditionalmodel(model):
- """A conditional maximum-entropy (exponential-form) model p(x|w) on a
+ """
+ A conditional maximum-entropy (exponential-form) model p(x|w) on a
discrete sample space. This is useful for classification problems:
given the context w, what is the probability of each class x?
- The form of such a model is
+ The form of such a model is::
p(x | w) = exp(theta . f(w, x)) / Z(w; theta)
- where Z(w; theta) is a normalization term equal to
+ where Z(w; theta) is a normalization term equal to::
Z(w; theta) = sum_x exp(theta . f(w, x)).
@@ -804,11 +805,11 @@
the constructor as the parameter 'samplespace'.
Such a model form arises from maximizing the entropy of a conditional
- model p(x | w) subject to the constraints:
+ model p(x | w) subject to the constraints::
K_i = E f_i(W, X)
- where the expectation is with respect to the distribution
+ where the expectation is with respect to the distribution::
q(w) p(x | w)
@@ -818,7 +819,7 @@
x) with respect to the empirical distribution.
This method minimizes the Lagrangian dual L of the entropy, which is
- defined for conditional models as
+ defined for conditional models as::
L(theta) = sum_w q(w) log Z(w; theta)
- sum_{w,x} q(w,x) [theta . f(w,x)]
@@ -827,8 +828,10 @@
entire sample space, since q(w,x) = 0 for all w,x not in the training
set.
- The partial derivatives of L are:
+ The partial derivatives of L are::
+
dL / dtheta_i = K_i - E f_i(X, Y)
+
where the expectation is as defined above.
"""
Modified: trunk/scipy/sparse/dok.py
===================================================================
--- trunk/scipy/sparse/dok.py 2010-05-24 13:11:41 UTC (rev 6408)
+++ trunk/scipy/sparse/dok.py 2010-05-24 13:11:58 UTC (rev 6409)
@@ -13,12 +13,13 @@
from sputils import isdense, getdtype, isshape, isintlike, isscalarlike, upcast
class dok_matrix(spmatrix, dict):
- """Dictionary Of Keys based sparse matrix.
+ """
+ Dictionary Of Keys based sparse matrix.
This is an efficient structure for constructing sparse
matrices incrementally.
- This can be instatiated in several ways:
+ This can be instantiated in several ways:
dok_matrix(D)
with a dense matrix, D
More information about the Scipy-svn
mailing list