Data analysis: The best library out there are pandas and scikit learn. Pandas helps you with finding patterns, using simple mathematics like mean, standard deviation, correlation matrix. You also have plotting features but just to help you visualize the pattern. As of scikit learn, is ML part which helps you in prediction even if that is necessary, for you, simple tasks like classification and regression.
Data visualization: You must be familiar with matplotlib, but I highly recommend plotting with plotly , since this is time Series Data. Other libraries I recommend are pygal or seaborn. Deep learning: Recurrent neural networks (RNN) are used to predict the next step , that the user would do. Recommended platform is tensorflow, with Keras on top of it., because it's cross platrform and has decent documentation. The first two can be done within 4-5 days at Max. Just go through documentation. The third may require at least a week and a maximum of two weeks. Hope this answer was helpful. On Wed 18 Oct, 2017, 21:30 , <chennaipy-requ...@python.org> wrote: > Send Chennaipy mailing list submissions to > chennaipy@python.org > > To subscribe or unsubscribe via the World Wide Web, visit > https://mail.python.org/mailman/listinfo/chennaipy > or, via email, send a message with subject or body 'help' to > chennaipy-requ...@python.org > > You can reach the person managing the list at > chennaipy-ow...@python.org > > When replying, please edit your Subject line so it is more specific > than "Re: Contents of Chennaipy digest..." > > > Today's Topics: > > 1. Time Series Analysis using Python (Akhil Mohan) > 2. Re: Time Series Analysis using Python (Venkatesh Umaashankar) > > > ---------------------------------------------------------------------- > > Message: 1 > Date: Tue, 17 Oct 2017 22:20:20 +0530 > From: Akhil Mohan <akhilmohan...@gmail.com> > To: Chennai Python User Group Mailing List <chennaipy@python.org> > Subject: [Chennaipy] Time Series Analysis using Python > Message-ID: > < > cadyudjtpfqy+akypasopvofbn9k_yz3lut9k4agzryy0bb9...@mail.gmail.com> > Content-Type: text/plain; charset="utf-8" > > Hi, > > As part of my PhD I have got some data from a subject for continuous 4 > weeks. The subject performs a task in the form of a computer game (2D ping > pong game developed using Unity 3D engine) and the information from sensors > are recorded continuously as a .txt file. This data from the sensors > (inertial sensors -IMU's) would be used to understand how well the player > has played the game and the time he/she took to move from one stage to > another. > > Now I want to make an analysis of the subject performance on a daily basis > (a graph representing the progress on a given task). I have done some basic > coding in python like 3D visualization, plotting etc. I am aware of certain > tools like SPSS or R who could do the same. So please provide me your > inputs (Should it be good to try it with python or try some other tools > would be the best for the same). > > Platform -- ?? > Time Needed -- ?? > Coding Expertise Needed -- ?? > > Thanks and Regards, > > -- > ------------------------------------------------- > Akhil Mohan (+91-7639168728) > Ph.D Scholar > IITM-CMC-SCTIMST > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: < > http://mail.python.org/pipermail/chennaipy/attachments/20171017/e6b0160e/attachment-0001.html > > > > ------------------------------ > > Message: 2 > Date: Tue, 17 Oct 2017 21:48:22 +0200 > From: Venkatesh Umaashankar <venkates...@gmail.com> > To: Chennai Python User Group Mailing List <chennaipy@python.org> > Subject: Re: [Chennaipy] Time Series Analysis using Python > Message-ID: <3d5a7722-fff6-4b3d-89d1-f732f5a60...@gmail.com> > Content-Type: text/plain; charset="utf-8" > > Hi Akhil, > Please reach me at my email. I work in the relevant area that you are > looking for and I could help you. > > Thanks > Venkatesh Umaashankar > 9444763417 > > ?Sent from TypeApp ? > > On 17 Oct 2017, 6:50 PM, at 6:50 PM, Akhil Mohan <akhilmohan...@gmail.com> > wrote: > >Hi, > > > >As part of my PhD I have got some data from a subject for continuous 4 > >weeks. The subject performs a task in the form of a computer game (2D > >ping > >pong game developed using Unity 3D engine) and the information from > >sensors > >are recorded continuously as a .txt file. This data from the sensors > >(inertial sensors -IMU's) would be used to understand how well the > >player > >has played the game and the time he/she took to move from one stage to > >another. > > > >Now I want to make an analysis of the subject performance on a daily > >basis > >(a graph representing the progress on a given task). I have done some > >basic > >coding in python like 3D visualization, plotting etc. I am aware of > >certain > >tools like SPSS or R who could do the same. So please provide me your > >inputs (Should it be good to try it with python or try some other tools > >would be the best for the same). > > > >Platform -- ?? > >Time Needed -- ?? > >Coding Expertise Needed -- ?? > > > >Thanks and Regards, > > > >-- > >------------------------------------------------- > >Akhil Mohan (+91-7639168728) > >Ph.D Scholar > >IITM-CMC-SCTIMST > > > > > >------------------------------------------------------------------------ > > > >_______________________________________________ > >Chennaipy mailing list > >Chennaipy@python.org > >https://mail.python.org/mailman/listinfo/chennaipy > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: < > http://mail.python.org/pipermail/chennaipy/attachments/20171017/ae6ce7f4/attachment-0001.html > > > > ------------------------------ > > Subject: Digest Footer > > _______________________________________________ > Chennaipy mailing list > Chennaipy@python.org > https://mail.python.org/mailman/listinfo/chennaipy > > > ------------------------------ > > End of Chennaipy Digest, Vol 50, Issue 6 > **************************************** >
_______________________________________________ Chennaipy mailing list Chennaipy@python.org https://mail.python.org/mailman/listinfo/chennaipy
