guillaumelenoir / wavepal Goto Github PK
View Code? Open in Web Editor NEWFrequency and time-frequency analysis for irregularly sampled time series
License: MIT License
Frequency and time-frequency analysis for irregularly sampled time series
License: MIT License
Hello
for following command I am getting this error (please see below)
"x.freq_analysis(freqstep=0.0001,D=600.,percentile=percentile,n_moments=12,mywindow=7,computes_amplitude=True)"
############ command line outputs#########
Re-estimated D factor (WOSA): 600.1687
Preliminary steps for the WOSA periodogram:
100%|██████████| 9/9 [00:02<00:00, 4.23it/s]
Re-estimated frequency range: from 0.00175540168582 to 0.127055640806
Main loop, over the frequencies:
0%| | 0/1254 [00:00<?, ?it/s]
Traceback (most recent call last):
File "spectrum_by_wavepal_method.py", line 59, in
x.freq_analysis(freqstep=0.0001,D=600.,percentile=percentile,n_moments=12,mywindow=7,computes_amplitude=True)
File "build/bdist.linux-x86_64/egg/wavepal/Wavepal.py", line 1158, in freq_analysis
TypeError: norm() got an unexpected keyword argument 'axis'
please suggest me what to do?
Thanks
Phanindra
Hello,
Thanks for your efforts for the project. I wondered if there is a Python 3 compatible version or some quick guidelines to make it Python 3 compatible?
Thank you.
Hi 👊
This is my first visit to this fine repo, but it seems you have been working hard to keep all dependencies updated so far.
Once you have closed this issue, I'll create seperate pull requests for every update as soon as I find one.
That's it for now!
Happy merging! 🤖
Hi there,
I am having uneven spaced time series with temporal resolution 0.1 year to 4.5year (1800 data points). I am very sure that my data has quasi-periodic and/or non-stationary periodicities.
Trying to apply CARMA(p,q) { eg: p>1, 1<=q<=p-1} and then wanna apply wavepal for wavelets.
This is my present error....!!!!!
Any help, please...
Thank you.
Note1: I Understand that the roots of Auto Regressive polynomial has Imaginary roots....!!
and also Importantly, I see Boost.Python.ArgumentError: Python argument types in
did not match C++ signature:
is this because of the BOOST version..?
Note2: I have used the commands that were presented in your example codes Lenoir 2018 paper-1.
############### Error..............................###############
Calculating PSD Lorentzian parameters...
Calculating coefficients of AR polynomial...
Calculating sigma...
Calculating log-likelihoods...
Decorrelation length (in number of samples) - Estimation: 7
SECOND ROUND: generates 70000 samples
Traceback (most recent call last):
File "spectrum_by_wavepal_method.py", line 60, in
x.carma_params(p=2,q=0,path_to_figure_folder=mypath,nmcmc=nmcmc,signif_level_type="n",make_carma_fig=False,nbins=15,dpi=400)
File "build/bdist.linux-x86_64/egg/wavepal/Wavepal.py", line 650, in carma_params
File "/usr/lib64/python2.7/site-packages/carmcmc/carma_pack.py", line 84, in run_mcmc
self.p, self.q, ntemperatures, False, nthin, init)
Boost.Python.ArgumentError: Python argument types in
carmcmc._carmcmc.run_mcmc_carma(numpy.int64, numpy.int64, vecD, vecD, vecD, int, int, int, bool, int, vecD)
did not match C++ signature:
run_mcmc_carma(int, int, std::vector<double, std::allocator >, std::vector<double, std::allocator >, std::vector<double, std::allocator >, int, int, int)
run_mcmc_carma(int, int, std::vector<double, std::allocator >, std::vector<double, std::allocator >, std::vector<double, std::allocator >, int, int, int, bool)
run_mcmc_carma(int, int, std::vector<double, std::allocator >, std::vector<double, std::allocator >, std::vector<double, std::allocator >, int, int, int, bool, int)
run_mcmc_carma(int, int, std::vector<double, std::allocator >, std::vector<double, std::allocator >, std::vector<double, std::allocator >, int, int, int, bool, int, std::vector<double, std::allocator >)
Hi,
I was trying to install this package in Ubuntu and MACOS M1, but I couldn't. In the end, I got an error message regarding the carmcmc package that was not found. Do I need to install it separately? What do I do? Please help me with the installation of this in any machine. Any help would be appreciated.
Wishes,
Ajay
On Ubuntu 18, installed boost 1.59 and appears to build ok, but fails during tests, the last part of the output is:
SECOND ROUND: generates 16000 samples
Running sampler...
Number of steps added: 1
Number of tracked steps added: 1
Setting starting values...
Drawn from priors
...Initializing 0.2699
0.9582
-0.0003
-5.7993
Burning in... (8000 iterations)
0% 10 20 30 40 50 60 70 80 90 100%
|----|----|----|----|----|----|----|----|----|----|
**************************************************Average RAM Acceptance Rate is 0.275125
*
Sampling...
0% 10 20 30 40 50 60 70 80 90 100%
|----|----|----|----|----|----|----|----|----|----|
Calculating sigma...
Calculating log-likelihoods...
Traceback (most recent call last):
File "test.py", line 25, in
x.carma_params(make_carma_fig=True,nbins=20,dpi=400,path_to_figure_folder=path_to_figure_folder)
File "build/bdist.linux-x86_64/egg/wavepal/Wavepal.py", line 653, in carma_params
TypeError: assess_fit() takes at most 4 arguments (12 given)
I am unable to supress the legend, ylabel, xlabel texts in frequency analysis
"
plot_periodogram=x.plot_periodogram(xaxis='period')
plot_periodogram.suptitle("")
"
no use
Hi,
I've tried to install Wavepal on my Ubuntu machine in a conda environment that runs Python 2.7, but I've encountered numerous errors in the terminal stating that, amongst other warning, "error: Failed building wheel for acor", "error: could not build wheels or acor, which is required to install pyproject.toml-based projects". it is also stating to avoid running setup.py directly and to use pypa/build, while also stating that carmama and wavepal are not available despite them being downloaded onto the machine. Please let me know what I need to change in order for me to properly install the software.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.