daviddoji/Kalman-and-Bayesian-Filters-in-Python
1
0 Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
731 Commits 1 Branch 0 Tags
5d13589b8d08eabcb14fd5ea9270e703e83273f0
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Roger Labbe 5d13589b8d Cleaned up a lot of duplicate text. 2015-08-15 15:56:45 -07:00
Roger Labbe 44552eea48 Deleted empty cell. 2015-08-15 12:02:10 -07:00
Roger Labbe 3ae8eb88d5 Improved wording for Bayes Theorm section. 2015-08-15 12:01:04 -07:00
Roger Labbe b98f157169 Minor language clean up. 2015-08-15 07:08:20 -07:00
Roger Labbe 0cc841f68c Fixed latex errors. 2015-08-09 13:15:10 -07:00
Roger Labbe daed96898f Removed 1D example. 
We already do this in MKF chapter.
 2015-08-09 11:46:39 -07:00
Roger Labbe 9ea7fe6ed0 Fixed explanation of time invarient systems. 2015-08-08 18:17:15 -07:00
Roger Labbe f7fc01bf68 Fixed typos and bugs. 2015-08-08 18:09:13 -07:00
Roger Labbe 2ad95fa0e1 Cleaned up example for 1D vs 2D filter 
The code was very unclear, including unused variables.

I also expanded the example.
 2015-08-08 17:22:28 -07:00
Roger Labbe b0a4b5d159 Updated to require FilterPy 0.0.26 2015-08-08 17:22:04 -07:00
Roger Labbe 0bc0b9c348 Extensive code changes for readability. 
Content is largely the same, but I reduced the number of functions
that the code uses to minimize the amount of scrolling back and
forth. I move the dog simulation back into the notebook so that
it is easily inspected - people have been confused about what it
is doing.
 2015-08-08 14:48:20 -07:00
Roger Labbe be713acc68 Fixed display of marginals on 3d plots of Gaussian 
The contours were displaying multiple curves, which doesn't have
a lot of meaning. Replaced with the marginal distribution.
 2015-08-08 10:06:29 -07:00
Roger Labbe d481f3aaf4 Altered example to be consistent with text. 
The first example for computing the prediction used two different
values for the covariance matrix, making it a bit confusing.
 2015-08-08 10:05:39 -07:00
Roger Labbe 022cde4a1f Reran so all cells are sequentially executed. 2015-08-08 10:03:48 -07:00
Roger Labbe d72c8201a4 Fixed equations for derivation from Bayes. 2015-08-08 10:01:06 -07:00
Roger Labbe b27bc431e3 Added def. of marginal and joint distributions 2015-08-08 09:59:08 -07:00
Roger Labbe 383a3c18d7 Fixed allowed range for g-h filter in interactive 2015-08-01 13:13:46 -07:00
Roger Labbe f6ccb0ea95 Added interaction, better explanation 
Added interactive plot of 2D gaussian, and explained the
position-velociy Gaussian better.
 2015-08-01 13:09:52 -07:00
Roger Labbe 90cfc4c8bb fixed derivation of posterior of univariate Gaussian 2015-08-01 10:28:06 -07:00
Roger Labbe 912498a843 Lots of little fixes. 
I was referring to colors of plots, I wasn't printing out something
the text said was printed out, etc.
 2015-08-01 10:10:08 -07:00
Roger Labbe 391e8f4d49 Added MIT license to all files. 2015-08-01 08:52:48 -07:00
Roger Labbe 6bf7552212 Added license text and import from future. 
This code did not work for Python 2.x becaus I was not
importing from future. While I was altering all the files
I updated the header to include license information.
 2015-08-01 08:46:14 -07:00
Roger Labbe df2b92db79 Fix of latex. 2015-07-30 21:46:24 -07:00
Roger Labbe 625c89bee4 Added MMAE filtering section. 2015-07-30 21:45:13 -07:00
Roger Labbe e8b17d668b Added text for NEES 2015-07-30 21:44:31 -07:00
Roger Labbe 55c4d03f67 Minor reword, simplified function API. 2015-07-30 21:42:39 -07:00
Roger Labbe edd5f80c90 Trying a different font for body text. 2015-07-27 21:51:31 -07:00
Roger Labbe cf224dfa63 More explicit wording to identify curves. 
I was saying 'blue curve' 'green curve', but those have no meaning,
especially if printed in black and white. Switched to explicit
$\sigma=0.2$.

Also added second std in the chart showing the 68-95-99.7 rule.
 2015-07-27 21:50:03 -07:00
Roger Labbe 53b8e6f45b Added link to 6x9 version of book's PDF. 2015-07-27 16:00:32 -07:00
Roger Labbe a86e879f99 Removed 'blah's from text. 
I use 'blah' to indicate something needs to be written here, but
haven't written it yet.
 2015-07-27 15:59:57 -07:00
Roger Labbe c1b3703ce6 Changed notation for prior to a car. 
The ^- notation was pretty unreadable, and inconsistant with the
hat notation for estimates.
 2015-07-26 19:20:58 -07:00
Roger Labbe 7e6875b0a9 Modified 6x9 script to generate entire book. 2015-07-26 08:40:40 -07:00
Roger Labbe 925498a19e Edit to fit on 6x9 book. 
Somewhat arbitrary, but I want the code to be readable on
narrow paper than 8.5x11.
 2015-07-25 23:46:59 -07:00
Roger Labbe 82f4e1569b Removed input and output prompts from PDF. 
I think it looks much nicer without them.

Also adjusted margins a bit.
 2015-07-25 16:13:42 -07:00
Roger Labbe 39e833615b Indenting input code slightly. 
Want it to stand out from the book's text.
 2015-07-25 15:47:56 -07:00
Roger Labbe 335db298ff Implemeenting PDF in 6x9 format. 
I did the work on chapter 1 just to start somewhere. Trying to make
the book fit nicely on a 6x9 book format.
 2015-07-25 15:23:11 -07:00
Roger Labbe 0d836c7e03 Altered look of residual charts. 
User ulenka on gitter suggest changing the color for the
residual line. I found my changes garish, so I switched
to a thicker black line and changed the grids to dotted.
 2015-07-24 20:34:36 -07:00
Roger Labbe 056ada57af Minor typo fixes. 2015-07-23 16:07:05 -07:00
Roger Labbe 77ce3e9951 Expansion on non-integratable equations. 2015-07-23 15:44:21 -07:00
Roger Labbe 7f17a26e08 Fixed use of ```python blocks. 
Turns out my problem was the closing ``` needs to be on a line
of its own for nbconvert to parse it correctly.
 2015-07-22 12:55:58 -07:00
Roger Labbe 091f372b85 Fixed use of # in ```python block 
If not indented, gets treated as a header by nbconvert.
 2015-07-22 12:02:21 -07:00
Roger Labbe e7954be704 Made Gaussian equation more readable. 2015-07-22 11:56:32 -07:00
Roger Labbe 566f43e32f Vocabulary changes. 2015-07-22 11:56:11 -07:00
Roger Labbe a5b822c1c9 Rewording. 2015-07-22 11:14:01 -07:00
Roger Labbe 49a464bcfa Fixed assignment to F. dt=.1, but used dt=1. 2015-07-22 11:13:07 -07:00
Roger Labbe 364a2357d7 Better description of white noise. 2015-07-19 12:44:35 -07:00
Roger Labbe c258d429b4 Fixed MathJax rendering for nbviewer. 
Not sure why the font was not working, but neo-Euler was
rendering poorly on nbviewer. I've switched to "TeX" and
it looks fine.
 2015-07-19 11:53:43 -07:00
Roger Labbe 14478ce60a Experiement to see if MathJax is rending correctly. 
I was specifying the Neo-Euler font, which renders poorly
on nbviewer. This is a test to make sure it works before
checking in all notebooks. (I have to re-execute the notebook)
so that the script from the css file gets embedded into the
notebook).
 2015-07-19 10:58:19 -07:00
Roger Labbe ca88bd82b3 Fixed font issue for nbviewer. 
The Neo-Euler was rendering with no subscripts or superscripts.
Not sure why, but I swithed to the "TeX" font and all is well.
 2015-07-19 10:51:32 -07:00
Roger Labbe 96b3409da0 fixed calling of methods 'functions' 2015-07-18 18:33:38 -07:00
Roger Labbe 2c36c43da2 Minor rewording. function->method, mostly. 2015-07-18 18:26:57 -07:00
Roger Labbe f6d191353d nbconvert treated comment as chapter title! 
A comment in a markdown cell inside a ```python ...``` block
was treated as a chapter header by nbconvert. I filled a bug
report with IPython and removed the comment.
 2015-07-18 18:10:03 -07:00
Roger Labbe 43070a4439 Copy edit of UKF chapter. 
Also found a mistake in the text about computing the residual
of angles that was duplicated in the EKF chapter, so I fixed the
error in that chapter as well.

I pulled out the 'track in a circle' example as it is the usual
sort of textbook nonsense problem that no one cares about. I created
an 'old-content' Notebook in case anyone still wants to see it; I
may put more content there as I continue to edit.
 2015-07-18 17:21:27 -07:00
Roger Labbe 6092e06459 Better code formatting with ``python 
There is more than that here. I had a bad commit of a bunch of temporary
files, I had to reset back in time, and now I am doing a massive commit.
Sorry.
 2015-07-18 08:43:24 -07:00
Roger Labbe cc24dd6291 Copy edit of preface. 
Trying to reduce my verbosity. Still a way to go...
 2015-07-16 08:50:20 -07:00
Roger Labbe 60c17168b0 Moved naming conventions to FilterPy project. 
That had no business in the book. I put it in the documentation
for filterPy.
 2015-07-16 08:16:05 -07:00
Roger Labbe 335df7f42d Fixed bug in EKF residual function. 
Comment was wrong, it normalizes to [-pi, pi].

Also, code didn't handle cases where a-b > 2Pi
 2015-07-15 19:03:59 -07:00
Roger Labbe 7827a4df2d Lots of changes to preface. 
Too big a check in; got away from me. I rewrote a lot of the preface.
Added instructions for cloud.sagemath install. Removed import of
set_figsize and figsize in first cell because the first cell gets
deleted for the pdf.
 2015-07-15 18:17:48 -07:00
Roger Labbe 0906db75e3 Moved text from g-h chapter to LS chapter. 
There was text in gh chapter that made no sense unless you already
know least squares.
 2015-07-14 12:43:16 -07:00
Roger Labbe 539db41df3 Moved some text from Preface to Appendix 
Text is 'orphaned' - needs to be integrated into rest
of chapter.
 2015-07-14 12:41:58 -07:00
Roger Labbe 213c0427b6 Fixed bug in code. 
Plotting 2 data sets, but only scaled one of them by 1000.
 2015-07-14 12:40:40 -07:00
Roger Labbe cd6a2e9d42 Added lying to filter, and filterpy sections 2015-07-14 10:36:48 -07:00
Roger Labbe aba6a9dcf7 Moved all code to \code subdirectory. 
All these changes are to make the book easier to run from
cloud.sagemath.org. You can share individual notebooks there,
but not entire projects.By putting everything under code at the
user only needs to grab that one directory.

More on sagemath later, if I decide to pursue that as a delivery
mechanism...
 2015-07-13 23:16:04 -07:00
Roger Labbe 069982f128 Reran so output cells are in order. 2015-07-13 18:14:46 -07:00
Roger Labbe 967091f1c9 More copyediting changes. 2015-07-13 16:07:58 -07:00
Roger Labbe 2346a42e95 Typo fix. 2015-07-13 15:42:47 -07:00
Roger Labbe 8b233b4ff5 Copy edit of chapter 8. 
Note fully done, still have to figure out what to do with the ball
tracking code, and add a control example to the chapter.
 2015-07-13 14:42:34 -07:00
Roger Labbe acdc04af34 Fixed some latex issues. 2015-07-13 14:42:07 -07:00
Roger Labbe 511a3d1012 Ch rename for multivariate split; no underscores 
I split multivariate chapter into two as it was running 60+
pages. This required renumbering. While I was doing this
I changed names from using underscores to dashes; this seems
to help with line breaks when displaying links.
 2015-07-13 08:28:49 -07:00
Roger Labbe eada99482b Beginning of multivariate ch split. 2015-07-13 07:40:35 -07:00
Roger Labbe 878e4a5578 checkpoint; in midst of big re-org. 
This is not a 'useful'checkin. I'm heavily reorganizing teh
multivariate chapter (spliltting in two) and I am getting
worried about losing edits.
 2015-07-12 18:57:43 -07:00
Roger Labbe d739e6418b typo fixes 2015-07-12 16:16:08 -07:00
Roger Labbe 17e2b07416 Added text explaining FPF' example. 2015-07-12 16:14:24 -07:00
Roger Labbe 7b3821cc8d Made h1 h2 h3 left align for aesthetics 
Wordy titles got streched very badly across the page with
inch long spaces between words. left-align fixes this.
 2015-07-12 15:59:55 -07:00
Roger Labbe 389660de0c fixed use of term 'innovation'. 2015-07-12 15:59:27 -07:00
Roger Labbe 9064053e85 Added notebook to allow running via try.jupyter.org 
I need a way for people to run the book's animations. From this
notebook they can cut and paste code into try.jupyter.org.
 2015-07-12 15:57:05 -07:00
Roger Labbe 8e0d2f3185 Copy edit. Checkpoint before big change. 
I plan to reorder the design so that the prediction is
fully implemented and I show an example. The chapter just goes
on and on with no examples. Plus, talking about Q just after
discussion Fx makes the most sense.
 2015-07-11 19:50:29 -07:00
Roger Labbe f4aa2bdd28 Changed "unobserved" variable to "hidden" 
Not sure how I ended up calling hidden variables unobserved,
but it is fixed now.
 2015-07-11 19:49:13 -07:00
Roger Labbe 3dadc7f538 Removed overuse of word 'just'. 
I just use it just all the time, and it is just unnecessary.
 2015-07-11 11:40:17 -07:00
Roger Labbe 9449955e14 Start of re-edit. 2015-07-11 11:39:38 -07:00
Roger Labbe 5b5aabaead Added derivation of Gaussian product from Bayes. 2015-07-10 22:55:06 -07:00
Roger Labbe c1f3e8bfc0 Fixed links, added references. 2015-07-10 18:27:13 -07:00
Roger Labbe ce62a2ad43 Added explicit links so readable in PDF version. 2015-07-10 17:51:59 -07:00
Roger Labbe 81d55a99cf Many improvements to 1d KF chapter. 
I made the source code more concise.
I added a lot of text to help clarify the relationship to Bayes
and the g-h filter.
Added an interaction for computing Gaussian products.
 2015-07-10 15:15:38 -07:00
Roger Labbe 8f192d537c Added appendixes back to the PDF version. 2015-07-09 14:40:00 -07:00
Roger Labbe 9a22c6793d Removed notebook used to report old github bug 2015-07-09 14:38:25 -07:00
Roger Labbe 259de39b7d Reran to ensure compliance with recent changes 2015-07-09 14:34:35 -07:00
Roger Labbe 9b60578728 refactor to minimize code plot size. 
Added code to set x,y labels and title, and to set xlim, ylim
in one line.

Also moved some plotting code to the *internal.py files.
 2015-07-09 14:28:50 -07:00
Roger Labbe 6cc83b462e Improved wording, and removal of plt.show() calls. 
I used plt.show() to elimiante the <Matplotlib....>  messages
on the output line, but using a ; on the last statement also
suppresses this data. Shorter code  is better.
 2015-07-09 10:41:57 -07:00
Roger Labbe 25a1c29e9e Updated to require FilterPy 0.0.22 2015-07-08 18:59:38 -07:00
Roger Labbe dff91d9a6f Fixed notebooks for FilterPy code reorg. 
I made a separate filterpy.stats module becuase it made
little sense to import filterpy.common for stats
functions. This required a lot of changes in the notebooks
and supporting code.
 2015-07-08 18:42:12 -07:00
Roger Labbe 4306a09182 Made markers more reable in plots. 2015-07-08 16:13:03 -07:00
Roger Labbe 540e61313b Minor wording changes. 2015-07-08 16:12:23 -07:00
Roger Labbe 600e7ca167 Fixed a few erroneous claims and improved text. 2015-07-08 16:11:23 -07:00
Roger Labbe 01f2527f29 Renamed variables, expanded Bayesian coverage. 
Trying to get the language of the book consistatn and more
formal, otherwise it is too hard to go from this to the
literature. Also, I need a bit more proof, so the formalism
is useful.
 2015-07-08 14:34:58 -07:00
Roger Labbe baab280e8d Fixed missing import statement. 2015-07-07 14:21:59 -07:00
Roger Labbe d44cca32ab Cleaned up equations for Gaussians. 
Made them more readable by avoiding raised exponent for e, which made
it easier to compare univariate and multivariate cases.
 2015-07-05 17:32:29 -07:00
Roger Labbe 0269f2ec22 Merge branch 'master' of https://github.com/rlabbe/Kalman-and-Bayesian-Filters-in-Python 2015-07-04 21:16:34 -07:00
Roger Labbe 0a4c54a56a Updated to include particle filter chapter. 2015-07-04 21:16:04 -07:00
Roger Labbe f8896bbb80 Lots of material on resampling. 
Happy 4th of July!
 2015-07-04 20:12:33 -07:00