by

Where communities thrive


  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
People
Repo info
Activity
    Tomáš Mikula
    @wilima
    hi, is this project/library still active? I am looking for some fuzzy library for Python
    xxauroraxx
    @xxauroraxx
    Does SciKit work on Python 3?
    I can run it in 2.7 fine, but 3 is giving me issues
    Josh Warner
    @JDWarner
    What exactly is your problem with 3.x? We test against everything up through 3.6, and I have no known issues (tests pass) on 3.7.
    @xxauroraxx
    xxauroraxx
    @xxauroraxx
    Figured it out. One of the PEPs changed the way iteration should be interrupted. Rather than throwing an exception, you should return instead
    Don't have the file open to point out exactly where, but I think it was near line 730 in ControlSystem.py or something really similar
    (also not throwing, raising XD)
    just checked, the repo was updated 12 days ago. Must have been using a previous version
    sooraj-sudhakar
    @sooraj-sudhakar
    Hi .. Have anybody used it with neural networks.. Any links for fuzzification of inputs to neural networks ?
    Goulaf
    @Goulaf
    Hi all, I wonder how to add a singleton in a membership function ?
    NihalKarne
    @NihalKarne
    how to use float for membership function?
    Josh Warner
    @JDWarner
    @Goulaf
    There is no such thing as a delta function in scikit-fuzzy. All comparisons are done as floats, with inherent imprecision in the math, so any hard == comparison would fail.
    You can have a membership function which is zero except for a very small range, which makes a plateau, but at the edges of said tiny plateau the result would be a fraction between 0 and 1.
    @NihalKarne Floating point math is what is inherently used everywhere, I don't understand the question.
    leonard147
    @leonard147
    Hi everyone, does anyone know what fuzzy method did used for this library? thanks
    leonard147
    @leonard147
    im wondering if it use mamdani, but when when i comparing my manual calculate with this library result, it got different (ex mine : 12,4, library : 15,5)
    Fazrin Adinugraha
    @eifzed_twitter
    hello, id like to ask, is scikit-fuzzy available for raspberry pi?
    Ahmed Ablak
    @ablak
    @JDWarner Thank you for your feedback. I have resolved the issue faced earlier by removing all redundant rules and moved some of the complex computations to pyOpenCL with multiple GPUs.
    Ahmed Ablak
    @ablak
    @eifzed_twitter Wherever you can run python, scikit-fuzzy will be available.
    rosarius
    @rosarius
    Hi - I've performed fuzzy c means clustering using cluster.cmeans. I'm specifically trying to figure out how I can get the membership probabilities for each class, for each sample point (say for two classes, for every point in my data I'm looking for two values - the probability of belonging to class 1, and the probability of belonging to class 2). Alternatively, if the algorithm doesn't use probabilities, whatever the membership value is. I can't seem to figure out how to get this - any pointers?
    rosarius
    @rosarius
    Disregard, I figured it out - my input data wasn't meeting the specifications so I was getting back a u matrix that didn't fit the shape of my sample.
    Doug Ransom
    @dougransom
    anyone know how to update the conda-forge package for skfuzzy? I see the source has recently been updated to current networkx and matplotlib.
    elcesi
    @elcesi
    Hi, how can I modify the defuzzification method in this example: https://pythonhosted.org/scikit-fuzzy/auto_examples/plot_tipping_problem_newapi.html
    KhaiCyber
    @KhaiCyber
    Hello everyone, I have installed Scikit-fuzzy on my raspberry, i met the need of condition due to install Scikit, but now i don't know reason when i try to run my file.py which notified No module "Skfuzzy" and i want to know that the environment to run SciKit_Fuzzy. If some one know please comment below, because i am in need of it to make project. Thanks guys so much
    Josh Warner
    @JDWarner
    @elcesi the docs on PythonHosted are old because they decided to freeze them and stop the ability for us to update or fix them. That should still work though, if you follow it in Jupyter or a script.
    @KhaiCyber Scikit-Fuzzy is not correctly installed for you. It fails to import in your project manager. Your system probably has more than one Python installation or is working from multiple virtual environments. Please direct your project manager to the Python install you put Scikit-Fuzzy in, or reinstall it there.
    Bob0123456
    @Bob0123456
    Are there examples of fuzzy inference calculations?I am a beginner and want to learn by example,thanks
    roura12
    @roura12
    Hello, I need some help. I am both a beginner in python and in fuzzy logic. I have found this example : https://pythonhosted.org/scikit-fuzzy/auto_examples/plot_tipping_problem_newapi.html and read it and understood it as much as i could. However, I am not able to find any other problem/example online. As if this is the only full code available. Can anyone help me with another full coded skfuzzy example. like the irrigation problem that everyone keep on mentioning but without code. Thank you very much
    roura12
    @roura12
    ok I tried to make my own irrigation similar to tipping (using same code) and i get error at the last step .compute() : ValueError: All antecedents must have input values!. I thought it could be due to this "temp['cold'] = trimf(temp.universe, [5, 13.75, 22.5]) " but even when I changed it to this "# temp['cold'] = trimf(temp.universe, [5, 13, 22])" , still got same error. Can anyone help.
    Ali
    @Strongsaxophone_twitter

    Hi I got error on this line from this example : https://scikit-fuzzy.readthedocs.io/en/stable/auto_examples/plot_tipping_problem_newapi.html
    114: rule1.view()
    the error is :
    Out[2]:
    (<Figure size 640x480 with 1 Axes>,
    <matplotlib.axes._subplots.AxesSubplot at 0x7fc404563700>)

    Now How I solve this error?

    Ali
    @Strongsaxophone_twitter
    when I write """ ax.view_init(30, 200) """ nothing happends but I expect it draw the 3d diagram
    Max Feinberg
    @mxfeinberg
    Hi @JDWarner, I have a quick question regarding rounding differences between a FIS model built in MATLAB and a its counterpart built with skfuzzy.
    image.png
    image.png
    I've built several different models in both, but I just started finding some significant discrepancies today. I am just using made up data but because of the number of rules, it can be difficult to debug. Do the differences in the second image seem too large to just be from rounding?
    Josh Warner
    @JDWarner
    I do not have and have never used Matlab's fuzzy logic toolkit. Scikit-fuzzy with a properly built system is very robustly tested against other open options, and against publicly available systems with known output.
    The differences should be in the realm of floating point error.
    There may be minor inherent differences in Matlab versus Scikit-Fuzzy, if rounding is involved, because MATLAB rounds incorrectly. Specifically, MATLAB always rounds 0.5 up. IEEE correct rounding behavior - which is what Python and more importantly NumPy follow - round to the nearest even number to minimize systematic error when rounding. So Scikit-Fuzzy will round 0.5 down to 0 (nearest even int).
    Max Feinberg
    @mxfeinberg
    @JDWarner Thank you for the reply! I realized that the discrepancies were actually due to differences in membership functions. Scikit-Fuzzy is a great library and I appreciate all the work you've done.
    Josh Warner
    @JDWarner
    Glad to hear it!
    Marceliwut
    @Marceliwut

    Hello,
    I must say that i love your work! This library is simple to use, but also can fulfill most of the needs!
    The only question i have is how to accomodate more than 2 statements in a rules? np.fmin and np.fmax can take only two arrays as arguments i would need three.
    I am creating fuzzy apartment search engine for my university. So basically i need rules like - "IF Apartment price is in given range AND apartment size is bit low AND apartment room number is too low THEN apartment score is MEDIUM" -this one is only an example.

    Any ideas for such thing? :)

    Thanks!

    Josh Warner
    @JDWarner
    Hi @Marceliwut - I think you're going to be pleasantly surprised. The tipping project example only creates Rules which relate two Antecedents... but the actual underlying infrastructure supports an arbitrary combination using binary logic.
    So you would make a rule like (making up variable names) ctrl.Rule(price['medium'] & size['low'] & number['low'], score['medium']) and it should work just great!
    When everything is AND connected, you don't need to concern yourself with order of operations. However, order of operations is supported via parentheticals when combining various Antecedent Terms via a complex Rule when you may want to mix OR with AND.
    Give it a shot, I think that should meet your needs.
    Marceliwut
    @Marceliwut
    Hey @JDWarner -I have actually ended up using "the hard way" with nested fmin and fmax functions. Anyway thanks for your reply and most of all thanks for your work on this library. If you ever come to Cracow I owe you some sightseeing tour with local and beers. Thank you!