Where communities thrive


  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
People
Activity
    Preeti
    @Leovarmak1_twitter
    Hello all, Preeti Sharma an Outreachy applicant this is my first time contributing to a large organization I'm really looking forward to contributing and collaborate in this project.
    Markus Löning
    @mloning
    Welcome @Leovarmak1_twitter :wave:
    OLUFUNMILAYO RUTH AFORIJIKU
    @olufunmiruth
    Hello everyone.. I am Olufunmi. I am an outreachy applicant. I am looking forward to contributing and learning. I am glad to be here.
    Markus Löning
    @mloning
    Welcome @olufunmiruth :wave:
    Anastasia Rizzo
    @arizzogithub
    Hello all, I am Ana, can't wait to join this project, good luck to everyone!
    Astha Jakher
    @Aexousia
    Hello, I am Astha, I'm really looking forward to contributing here! :)
    Markus Löning
    @mloning
    Hi there @arizzogithub and @Aexousia
    Ankita Priya
    @AnkitaxPriya
    Hello everyone! I am Ankita Priya, an Outreachy applicant pursuing Bachelor's degree in Computer Science Engineering at Birla Institute of Technology, Mesra, Ranchi, India. I am currently working on a research paper in the field of data science. I'm very new to the concept of "time series analysis" but I wish to learn about it. Having a basic knowledge of Python, I wish to contribute to the project "Extend classification API to handle time-constant variables and predict Covid-19 mortality risk". I'd be more than happy if you could guide me @mloning . Thanks.
    Riddhima Singh
    @riddhima:matrix.org
    [m]
    Hello everyone! I am Riddhima Singh from India.I am an Outreachy applicant. I am a sophomore at Indian Institute of Engineering Science and Technology,Shibpur.I have been working with python and its libraries for a couple of months. I have used scikit-learn previously for linear regression and logistics regression but time series analysis is a bit new to me but I can definetly learn it. I am new to open source as well hence it would be very helpful if the mentor could guide me to make a first contribution tso that I can get started.
    Riddhima Singh
    @riddhima:matrix.org
    [m]
    :point_up: Edit: Hello everyone! I am Riddhima Singh from India.I am an Outreachy applicant. I am a sophomore at Indian Institute of Engineering Science and Technology,Shibpur.I have been working with python and its libraries for a couple of months. I have used scikit-learn previously for linear regression and logistics regression but time series analysis is a bit new to me but I can definetly learn it. I am new to open source as well hence it would be very helpful if the mentor could guide me to make a first contribution so that I can get started.
    Guzal Bulatova
    @GuzalBulatova
    Hi there everybody, nice to meet you all!
    I'm Guzal. I'm studying object-oriented programming in Gothenburg. Very interested in Machine Learning and explore Python by myself. Looking forward to contribute to the classification API project :)
    Ifeanyi30
    @Ifeanyi30
    Hey guys! I am happy to be an outreachy applicant as it has given me the opportunity to learn as part of a community, thanks to @mloning for accepting this mentorship position and I look forward to your intellectual guidance.
    Sree Vidhya Isukapalli
    @vidhya830_twitter
    Hi, I am Vidhya , a CS undergraduate from India. I am outreachy aspirant experienced in python programming and open source. I have used scikit-learn in machine learning models. Looking forward to contribute here :)
    sonali945
    @sonali945
    Hello everyone, I am Sonali Gupta from India. I am an Outreachy applicant. I am a sophomore at Indian Institute of Technology Kanpur. I am glad to be here and looking forward to make my contribution.
    aishagurung
    @aishagurung
    Hey everyone, I am Aisha(Aishwarya) Gurung. I am from the city of Kathmandu in Nepal where the smogs are currently taking over. During this time I hope to stay inside and make contributions to the sktime community projects. I am very interested in ML and learning more about time series analysis. Stay safe and please send any good vibes and suggestions my way!
    Ifeanyi30
    @Ifeanyi30
    @mloning I have been working on this issue "alan-turing-institute/sktime#583", tried running the command "pip install -r build_tools/requirements.txt" but some packages could not be installed. What should I do?
    Ifeanyi30
    @Ifeanyi30
    @mloning I made a PR for this issue "alan-turing-institute/sktime#583" but the pre-commit package gives a the flask8 error without an actual error message. Can you help me out?
    jowallner
    @jowallner
    Hi everyone! Is there a workaround for the sktime-dl installation bug? I get the error message "cannot import name 'check_X_y' from 'sktime.utils.validation' " when trying to import "from sktime_dl.classifiers.deeplearning import CNNClassifier"
    Markus Löning
    @mloning
    @jowallner we're looking for some help with sktime-dl to bring it up to speed with sktime
    Abhipsha Das
    @chiral-carbon
    Hi! I am Abhipsha Das, an Outreachy applicant from India. I graduated last year and am interested in ML and applications of ML. I am proficient in Python and have experience in writing ML code. The sktime projects piqued my interest, so I look forward to contributing and working with everyone! :smile:
    Yash Lamba
    @yashlamba
    Hi @mloning, for alan-turing-institute/sktime#421 what way are we looking forward to? I think subclassing from statsmodel's theta model might be a better way because it won't break our current api implementation. I'll also look for issues with fit_trend if I find any.
    Markus Löning
    @mloning
    @yashlamba best to comment on the issue itself
    1 reply
    Mark Zurbruegg
    @Betaglutamate
    Hi I am a biology student at the University of Edinburgh and am looking into time series segmentation of bacterial growth curves. I see you guys have time series segmentation on your road map but as I understand it, it is not implemented yet?
    Markus Löning
    @mloning
    @Betaglutamate that's right, it's not implemented yet, do you have labelled data (supervised learning)?
    Nicolaj Noergaard Muehlbach
    @muhlbach
    Hi everyone! Quick question: For simulation purposes, I want to iteratively predict one-step ahead (fh=1) but with updated input data at each step. No refitting is needed. I see a few different ways to implement this, but I wanted to ask if there's a preferred way that could be implemented across all forecasting methods available via sktime? Thanks in advance!
    5 replies
    Guzal Bulatova
    @GuzalBulatova

    Side note for fellows who watch the tutorial (https://www.youtube.com/watch?v=wqQKFu41FIw&ab_channel=CodingTech):
    the sktime version available now is a bit different from the one in the video. Some functions shown in the tutorial notebook don't work anymore.

    It's better to follow along with the code published on github (https://github.com/alan-turing-institute/sktime/blob/main/examples/01_forecasting.ipynb)

    11 replies
    Mark Zurbruegg
    @Betaglutamate
    Hi @mloning thanks for replying. Right now I have about 600 time series recordings of bacterial growth. I am interested in identifying the period of exponential growth in these traces. I can annotate this manually quite easily. Do you have any suggestions of how I could use this data to then predict the exponential growth phase in my future traces?
    7 replies
    Ifeanyi30
    @Ifeanyi30
    Happy Easter guys
    1 reply
    Markus Löning
    @mloning
    Hi all, for those interested in the Outreachy program, we've posted some application info here: https://github.com/alan-turing-institute/sktime/wiki/Outreachy-2021
    Ifeanyi30
    @Ifeanyi30
    Hi @mloning I made another PR: alan-turing-institute/sktime#776 . I'd like you to review it
    I would also like to try out the issue: alan-turing-institute/sktime#729
    Markus Löning
    @mloning
    If you're interested in GSoC or Outreachy and want to ask some questions, you're very welcome to join our coffee chat on Thursday, 2:30pm BST https://turing-uk.zoom.us/j/99045960066?pwd=V1dOOUhGSVlFaFRpY0hqOVRzMXREUT09 - let me know if you have any questions in advance that I should discuss :)
    4 replies
    Riya Elizabeth John
    @Riyabelle25
    Hi guys, are there some mentors reviewing pre-proposals for GSoC? I mailed mine (google docs) last week, but didn't get a response, so got concerned (as the deadline for proposal submission is approaching)
    2 replies
    Markus Löning
    @mloning
    For those interested in GSoC, please make sure to upload your proposal drafts on the official GSoC platform too.
    Khoa Lai
    @imkhoa99
    image.png
    Khoa Lai
    @imkhoa99
    image.png
    Hi, thanks for the wonderful work!
    I'm trying to fit both time-series dataframe into the TimeSeriesForestClassifier model to classify detect synthetic data from real data. I ran into a problem: "Tabularization failed, it's possible that not all series were of equal length". I worked around by taking the same length subset of data and fit the model but still failed. I saw that someone managed to solve it by "tabularizing each column individually". I am wondering what does it mean? Or are there other reasons that might be causing the issue? Both of my data set are as above. Thanks!
    2 replies
    Yash Lamba
    @yashlamba
    Hi! So while framing my proposal around time series clustering, I came across https://github.com/alan-turing-institute/sktime/tree/uea_dev/sktime this branch. It already has most of the clustering utils and algorithms already implemented. @mloning, are we looking forward to merging this in the main branch? Most of the basics are already implemented so I'll probably have to reframe my proposal.
    Markus Löning
    @mloning
    For those applying to GSoC, we've sent out some feedback today to the submitted draft proposals - please let us know if we have missed you!
    7 replies
    SHREYA SINGH
    @SinghShreya05
    Hi everyone! I am Shreya. I am an Outreachy applicant. I have been previously contributing in opensource in Python, Deep learning, Natural language processing, and other tech-stack in my domain. Can anyone guide me to get started and share the link where I have to make contribution?
    MJimitater
    @MJimitater
    Hello Team, thank you for pushing ever forward with improvements! I saw the latest release is v0.5.3, I'd like to propose a fresh release with all the improvements, for convenient pip install usage. This would allow the broad community to take advantage of your great work! Thanks
    Markus Löning
    @mloning
    Hi @MJimitater thanks for feedback - we should be able to make a new release soon, there are still some PRs that we want to get merged first. Let me know if you're interested in contributing!
    Hi @SinghShreya05 yes you can find out more here: https://github.com/alan-turing-institute/sktime/wiki/Outreachy-2021
    Taiwo Owoseni
    @thayeylolu
    Hi Everyone. I want to extract features from a dataset and transform it. I am using RandomIntervalFeatureExtractor(n_intervals="sqrt", features=[np.mean, np.std, _slope]) to extract features but I don't know where to import _slope from. Kindly assist. Thank you :)
    1 reply
    Markus Löning
    @mloning
    For everyone applying to GSoC, please make sure you submit your final (not the draft) proposal before the deadline!
    Taiwo Owoseni
    @thayeylolu
    Hello everyone. I am currently having a challenge understanding how to transform a data frame with shape (114,1) to a nested data frame.
    3 replies
    Markus Löning
    @mloning
    For everyone applying to GSoC, please make sure you fill in the online form and submit your application on the GSoC platform, marking your proposal as final, before the deadline. More info here: https://github.com/alan-turing-institute/sktime/wiki/GSoC-2021
    Markus Löning
    @mloning
    If you want to learn more about the ROCKET time series classifier, check out this event: https://www.meetup.com/Berlin-Time-Series-Analysis-Meetup/events/276740583/
    Jason
    @jasondanger
    Hello everyone, I'm Jason Ding, a student in statistics major and I've learned time series analysis before. But I'm new to open source projects. Hoping to contribute and learn from GSOC.
    I'm working on time series regression task and I've got a question about the paper: is a casuality test needed before TSER doing regressions? Since each continuous sclar value may not directly result in the change in time series, I think this might be a good way to make the model more interpretable.
    2 replies
    Shreshtha
    @shreshtha48
    Hi! I submitted my draft for Gsoc this morning. I know it might be a bit late. If it's not too much trouble could the mentors please review it? I would appreciate any feedback that the mentors have!