krishnakartik1 / lstm-footballmatchwinner Goto Github PK
View Code? Open in Web Editor NEWThis repository contains the code for a conference paper "Predicting the football match winner using LSTM model of Recurrent Neural Networks" that we wrote
This repository contains the code for a conference paper "Predicting the football match winner using LSTM model of Recurrent Neural Networks" that we wrote
Hi, I'm currently looking into this project and it would be very nice to be able to play around with it. However, this isn't going so well since I don't know which versions of the libraries were used during the project. Could you provide me with this information?
how can i use it to predict a new game? i do not know the new game data.
There is something i do not quite understand. When you append last standings, you actually assign to "playing_statistics_4" and all others below "playing_statistics_3".
Shouldnt it be 3 to 3, 4 to 4, etc. ?
playing_statistics_2 = get_last(playing_statistics_2, Standings, "15")
playing_statistics_3 = get_last(playing_statistics_3, Standings, "14")
playing_statistics_4 = get_last(playing_statistics_3, Standings, "13")
playing_statistics_5 = get_last(playing_statistics_3, Standings, "12")
playing_statistics_6 = get_last(playing_statistics_3, Standings, "11")
playing_statistics_7 = get_last(playing_statistics_3, Standings, "10")
playing_statistics_8 = get_last(playing_statistics_3, Standings, "9")
When creating training and test datasets you have used the following code
x_train, y_train = dataTrain.iloc[:,:28].values,dataTrain.iloc[:,28:].values
x_train=np.reshape(x_train,(1860,28,1))
x_test, y_test = dataTest.iloc[:,:28].values,dataTest.iloc[:,28:].values
x_test=np.reshape(x_test,(800,28,1))
dataTrain.iloc[:,:28]
this is completely wrong. You are still passing the original FTR column(Which is actually the current match result), which is the 0th column.
It should've been dataTrain.iloc[:,1:28]
instead
The correct version would've been as described below
x_train, y_train = dataTrain.iloc[:,1:28].values,dataTrain.iloc[:,28:].values
x_train=np.reshape(x_train,(1860,27,1))
x_test, y_test = dataTest.iloc[:,1:28].values,dataTest.iloc[:,28:].values
x_test=np.reshape(x_test,(800,27,1))
When modified correctly it only gives 54% accuracy.
Hence the results produced are completely misleading.
I have tried running through dataCleaning.ipynb and I am not getting quite the same end csv file as you did. And with my new csv there also isn't good prediction percentage in LSTM.ipynb. I also tried fixing what I thought was wrong with dataCleaning file, but no luck. Is there any chance you can share the original code you used for cleaning up the data, so you got such good end results?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.