1859.1.81
by Skipper Seabold
Minor change to README |
1 |
========================= |
1855
by Skipper Seabold
Added setup files. Need to change setup.py to build test directory |
2 |
Installation from sources |
3 |
========================= |
|
4 |
||
5 |
In the directory example (the same as the file you are reading now), just do: |
|
6 |
||
7 |
python setup.py install |
|
8 |
||
1912
by Skipper Seabold
Added examples to docstring of tools.categorical |
9 |
See INSTALL.txt for requirements or |
10 |
||
11 |
http://statsmodels.sourceforge.net/ |
|
12 |
||
13 |
For more information. |
|
14 |
||
15 |
||
16 |
============= |
|
17 |
Release Notes |
|
18 |
============= |
|
19 |
||
20 |
Background |
|
21 |
========== |
|
22 |
||
23 |
The statsmodels code was started by Jonathan Taylor and was formerly included |
|
24 |
as part of scipy. It was taken up to be tested, corrected, and extended as part |
|
25 |
of the Google Summer of Code 2009. |
|
26 |
||
27 |
What it is |
|
28 |
========== |
|
29 |
||
1859.1.81
by Skipper Seabold
Minor change to README |
30 |
Statsmodels under the scikits namespace as scikits.statsmodels. Statsmodels is a |
31 |
pure python package that requires numpy and scipy. It offers a convenient |
|
32 |
interface for fitting parameterized statistical models with growing support |
|
33 |
for displaying univariate and multivariate summary statistics, regression summaries, |
|
34 |
and (postestimation) statistical tests. |
|
1912
by Skipper Seabold
Added examples to docstring of tools.categorical |
35 |
|
36 |
Main Feautures |
|
37 |
============== |
|
38 |
||
39 |
* regression: Generalized least squares (including weighted least squares and |
|
40 |
least squares with autoregressive errors), ordinary least squares. |
|
41 |
* glm: Generalized linear models with support for all of the one-parameter |
|
42 |
exponential family distributions. |
|
1859.1.80
by Skipper Seabold
Updated README |
43 |
* discrete choice models: Poisson, probit, logit, multinomial logit |
1912
by Skipper Seabold
Added examples to docstring of tools.categorical |
44 |
* rlm: Robust linear models with support for several M-estimators. |
45 |
* datasets: Datasets to be distributed and used for examples and in testing. |
|
1859.1.81
by Skipper Seabold
Minor change to README |
46 |
* PyDTA: Tools for reading Stata *.dta files into numpy arrays. |
1912
by Skipper Seabold
Added examples to docstring of tools.categorical |
47 |
|
48 |
There is also a sandbox which contains code for generalized additive models |
|
49 |
(untested), mixed effects models, cox proportional hazards model (both are |
|
50 |
untested and still dependent on the nipy formula framework), generating |
|
1859.1.80
by Skipper Seabold
Updated README |
51 |
descriptive statistics, and printing table output to ascii, latex, and html. |
52 |
There is also experimental code for systems of equations regression, |
|
53 |
time series models, and information theoretic measures. None of this code |
|
54 |
is considered "production ready". |
|
1912
by Skipper Seabold
Added examples to docstring of tools.categorical |
55 |
|
56 |
Where to get it |
|
57 |
=============== |
|
58 |
||
59 |
Development branches will be on LaunchPad. This is where to go to get the most |
|
60 |
up to date code in the trunk branch. Experimental code will also be hosted here |
|
1859.1.80
by Skipper Seabold
Updated README |
61 |
in different branches and merged to trunk often. We try to make sure that the |
62 |
trunk code is always stable. |
|
1912
by Skipper Seabold
Added examples to docstring of tools.categorical |
63 |
|
64 |
https://code.launchpad.net/statsmodels |
|
65 |
||
66 |
Source download of stable tags will be on SourceForge. |
|
67 |
||
68 |
https://sourceforge.net/projects/statsmodels/ |
|
69 |
||
70 |
or |
|
71 |
||
72 |
PyPi: http://pypi.python.org/pypi/scikits.statsmodels/ |
|
73 |
||
74 |
License |
|
75 |
======= |
|
76 |
||
77 |
Simplified BSD |
|
78 |
||
79 |
Documentation |
|
80 |
============= |
|
81 |
||
82 |
The official documentation is hosted on SourceForge. |
|
83 |
||
84 |
http://statsmodels.sourceforge.net/ |
|
85 |
||
86 |
The sphinx docs are currently undergoing a lot of work. They are not yet |
|
87 |
comprehensive, but should get you started. |
|
88 |
||
89 |
Our blog will continue to be updated as we make progress on the code. |
|
90 |
||
91 |
http://scipystats.blogspot.com |
|
92 |
||
93 |
||
94 |
Discussion and Development |
|
95 |
========================== |
|
96 |
||
97 |
All chatter will take place on the or scipy-user mailing list. We are very |
|
98 |
interested in receiving feedback about usability, suggestions for improvements, |
|
99 |
and bug reports via the mailing list or the bug tracker at |
|
100 |
https://bugs.launchpad.net/statsmodels. |
|
101 |
||
102 |
There is also a google group at |
|
103 |
||
104 |
http://groups.google.com/group/pystatsmodels |
|
105 |
||
106 |
to discuss development and design issues that are deemed to be too specialized |
|
107 |
for the scipy-dev/user list. |