lblend / mann-eller-kvinne Goto Github PK

View Code? Open in Web Editor NEW

1.0 1.0 0.0 40.24 MB

🤵 En nettside som bruker maskinlæring til å gjette om du er mann eller kvinne basert på hva du skriver 💃

Home Page: https://mannellerkvinne.lblend.moe

License: GNU General Public License v3.0

Shell 2.28% Python 35.03% Dockerfile 0.60% PureBasic 62.09%

gender gender-classification machine-learning naive-bayes-classifier norge norsk norwegian reccurent-neural-network

mann-eller-kvinne's Introduction

Morn 👋

Hi there! I go by the name LBlend on the internet. I'm a student from Norway who is currently an undergraduate at the University of Oslo. I'm pursuing a degree in informatics, also known as computer science, and I'm looking to hone my skills and create cool/interesting projects!

Website (WIP) | LinkedIn | Discord

🇳🇴 Norwegian - Native
🇬🇧 English - Fluent
🇰🇷 Korean - A2/B1
🇪🇸 Spanish - A1/A2

Technologies

Familiar with

Technologies I have used extensively

Have dipped my toes into

Technologies that I have used, but not extensively

Scheme

Learning

Technologies that I am in the process of learning or want to do a project in

Potential future endeavors

Technologies that I want to take a look at in the future

APL

Config

Check out my dotfiles repo

mann-eller-kvinne's People

Contributors

Stargazers

Watchers

mann-eller-kvinne's Issues

Find a proper way to set dev api-url

The current soultion requires changing a line of code each time you want to switch it. We should have a .env config or something similar to set react environment variables when switching between dev and build. It might require installing additional dependencies (E.g. webpack or dotenv)

This article describes a couple ways of doing it:
https://trekinbami.medium.com/using-environment-variables-in-react-6b0a99d83cf5

Implement a logistic regression classifier

Take inspiration from the paper which the dataset we use originated from
https://aclanthology.org/2020.gebnlp-1.11.pdf

Resolve warnings produced by tensorflow when loading RNN

A bunch of warnings occur when loading the keras model. Not sure why, but it should either be resolved or suppressed

Specify lib versions for requirements.txt

This reduces the risk of incompatible installations. We already did this with numpy due to some bug
but ideally, we should do it for all of them

Move front end/backend into separate repos?

Perhaps it's more clean given that the programs can be run independently.
Wdyt?

Replace all NLTK with scikit-learn

NLTK is an old fashioned, awkward (imo). I think we should opt for a more modern classifier API. scikit learn is more modern and elegant. I think we should use this for the naive bayes (and possibly other) classifiers

Add Black formatting git hook / github action

Automatically format files with black

Add frontend switch to swap between classifiers

Add frontend switch to swap between classifiers. The switch should change the json field "clf" when calling the API.
Something along the lines of

{
    clf: switch ? 'rnn' : 'bayes'
    ...
}

Make config setup for hyperparameter tuning of deep model

We should use config files to manage hyperparameter tuning. Yaml is a pretty decent and readable format.
I'll be working on it as part of my mission to beat the bayes model.

Site crashes on load when using Safari on iOS

See vercel/next.js#8347 for a potential solution

API won't run due to Tensorflow error - NotImplementedEror: Cannot convert a symbolic Tensor to a numpy array.

What is wrong?

When trying to run the API, Tensorflow raises a NotImplementedError: Cannot convert a symbolic Tensor (bidirectional/forward_lstm/strided_slice:0) to a numpy array. This error may indicate that you're trying to pass a Tensor to a NumPy call, which is not supported

System info

OS: Ubuntu 20.04, x86
Release: 2.1.0

Use more semantic variable names and field names

Change names like "clf", "M", and "F" to more semantic and easy-to-understand names. It's not obvious to neither people reading the code nor consumers of the API what the values mean.

If we are going through with this, I want keep this change on hold until we've fully rewritten the backend. This makes it so that the finished rewrite will be a 3.0 release and this change the 4.0 release. This creates a consistent correlation between the version numbers of the frontend and the backend. Though, not a requirement it is good to keep it this way for now.

Add option for environment variables in docker compose

Fix CORS errors

Build Flask app in Docker image

consider using git submodules for corpus

Make rnn (or other) model to beat naïve bayes baseline

Turned out that the naive bayes model is still better than the rnn. This is unacceptable, and therefore we must tune hyperparameters and experiment so that it can outperform the baseline

Auto-publish prebuilt docker images to dockerhub/github

Front end crashes on any input

The site produces the following error:

Steps to reproduce

Type any chacter in the text field on the front page. Happens on both localhost and https://mannellerkvinne.lblend.moe/