[Pspp-commits] [SCM] GNU PSPP branch, master, updated. v0.7.9-906-g4443108

[John Darrington]

This is an automated email from the git hooks/post-receive script. It was
generated because a ref change was pushed to the repository containing
the project "GNU PSPP".

The branch, master has been updated
       via  4443108e98b43b196f3f07217c6ec8bd96581367 (commit)
       via  3acf6da8d49333d9cc037dfe92a80c1615224a27 (commit)
       via  8603f5581522bca588e17a2155aff1bec3b0de1b (commit)
       via  7e413bbdf7b01f2ff0153c8cbf79c2e4fa71f4d5 (commit)
       via  f39bc32dac9f869c01af47dbfd18af98f81d8b70 (commit)
      from  1ad157fcdfc62c0751b03c2781e3c2c0bd193c60 (commit)

Those revisions listed above that are new to this repository have
not appeared on any other notification email; so we list those
revisions in full, below.

- Log -----------------------------------------------------------------
commit 4443108e98b43b196f3f07217c6ec8bd96581367
Author: John Darrington <address@hidden>
Date:   Tue Jul 2 19:41:16 2013 +0200

    Fixed incorrect behaviour of REGRESSION when multiple dependent variables 
are entered
    
    The REGRESSION command behaved badly when more than one dependent variable 
was entered.
    The cause was that the unnormalised covariance matrix returned from the 
covariance
    module was mutated for each variable.  Consequently, each variable after 
the first
    was wrong.  This change fixes that by changing the ownership semantics of 
the returned
    matrix (and thereby its constness).
    
    This change also adds some comments, attends to constness and fixes the 
remaining
    memory leaks associated with regression.

commit 3acf6da8d49333d9cc037dfe92a80c1615224a27
Author: John Darrington <address@hidden>
Date:   Mon Jul 1 19:02:54 2013 +0200

    Fix problems associated with LINEAR REGRESSION and splits

commit 8603f5581522bca588e17a2155aff1bec3b0de1b
Author: John Darrington <address@hidden>
Date:   Tue Jul 2 19:37:08 2013 +0200

    Added test to check that REGRESSION works with multiple dependent variables

commit 7e413bbdf7b01f2ff0153c8cbf79c2e4fa71f4d5
Author: John Darrington <address@hidden>
Date:   Tue Jul 2 19:44:57 2013 +0200

    Added a test to ensure that SPLITS vs REGRESSION/SAVE works ok

commit f39bc32dac9f869c01af47dbfd18af98f81d8b70
Author: John Darrington <address@hidden>
Date:   Tue Jul 2 19:06:15 2013 +0200

    Rename tests from REGRESSION to LINEAR REGRESSION
    
    This way I can run just the linear regression tests without the
    logistic regression tests.

-----------------------------------------------------------------------

Summary of changes:
 src/language/stats/glm.c           |   15 +-
 src/language/stats/oneway.c        |    8 +-
 src/language/stats/regression.c    |  480 ++++++++++++++++++------------------
 src/math/covariance.c              |   18 +-
 src/math/covariance.h              |    2 +-
 src/math/linreg.c                  |    4 +-
 src/math/linreg.h                  |    4 +-
 tests/language/stats/regression.at |  139 ++++++++++-
 8 files changed, 399 insertions(+), 271 deletions(-)


hooks/post-receive
-- 
GNU PSPP