🏥 Challenge Chat: First Place Solution

Basic Needs Basic Rights Kenya - Tech4MentalHealth

Helping Kenya

$4 200 USD

Completed (over 5 years ago)

Skills you will learn

Classification

1244 joined

499 active

Info Data Chat Leaderboard

Start

Apr 26, 20

Jul 05, 20

Reveal

Jul 05, 20

Klai

First Place Solution

Connect · 28 Jul 2020, 10:57 · 13

Congratulations to all the winners

our model is an ensembling of 3 roberta base with different params !

also we did some functions for data augmentation which help our model to fit Drugs and Suicide Tweets !

github link: https://github.com/Klaimohelmi/Basic-Needs-Basic-Rights-Kenya---Tech4MentalHealth/blob/master/final_kernel_rank3.ipynb

Discussion 13 answers

Gozie

Freelance

Thanks Klai for sharing.

Congratulations!

28 Jul 2020, 11:06

Upvotes 0

Klai

you're welcome

replied to Gozie28 Jul 2020, 11:14

Upvotes 0

Lalit

Congratulations! Klai and Thank you for sharing your work.

0.32*sub1[e]+0.68*sub2[e] OR sub7['Drugs']*0.8+0.2*sub5['Drugs']

would you please explain, how you guys calculate these coefficients(0.32,0.68)?

28 Jul 2020, 11:36 (edited less than a minute later)

Upvotes 0

Hectogram

We assign weight of each model based on CV score. So one will give more weight on a model which "perform well". (Just a reminder, if you are choosing weights based on Public LB scores, then there is a chance that they will badly overfit.)

replied to Lalit28 Jul 2020, 11:47 (edited less than a minute later)

Upvotes 0

Lalit

CV score? where did you calculate that in your code? if you don't mind, could you share any blog or steps to calculate this or how to assign these coefficients?

replied to Hectogram28 Jul 2020, 12:12 (edited 1 minute later)

Upvotes 0

Hectogram

Look at this blog.

replied to Lalit28 Jul 2020, 13:56

Upvotes 0

Lalit

Thank you this is very helpful.

replied to Hectogram28 Jul 2020, 14:21

Upvotes 0

GBK

@Klai Congratulations!