Heart Disease Prediction - Data Every Day

Hi guys, welcome back to Data Every Day!
On today's episode, we are looking at a dataset of patients' medical records and trying to predict if a given patient will have heart disease or not. We will be using logistic regression, support vector machine, and neural network models to make our predictions.
Here is a link to the Kaggle dataset:
www.kaggle.com...
And here is a link to my notebook from the video:
www.kaggle.com...
Thanks so much for watching! If you enjoyed today's episode, be sure to subscribe and hit the bell for more content!
See you all tomorrow! :)

[@akhilaabhijith2185]

This was of great help, thank you

[@gcdatkin]

Thanks so much, Akhila!

[@madhusudan4420]

Great video Bro

[@chash_games]

Very helpful thanks

[@namansrivastava375]

Sir what if we have to take input from user and then predict about the disease... please share how to convert into that type of model

[@Mohamm-ed]

Really great video thanks for your effor

[@gcdatkin]

Thank you!

[@pinakunadkat1384]

Can you do this in weka?

[@azrflourish9032]

great video! I've got a qstn~ Why one-hot encoding process is needed ??

[@azrflourish9032]

Actually, I am new in machine learning and I can't manage what the exact purpose of every single processes ㅠ.ㅠ :D

[@gcdatkin]

Great question! At the end of the day, a model is really just a function that takes in some numeric input and spits out a numeric output.
For categorical variables/inputs, we need a way to convert them into numeric form.
One-hot encoding accomplishes this. It's a lossless way of encoding the information contained in a categorical input.

[@sachinsd4663]

Me and friends were doing cardiac arrhythmias prediction ..
Is this the same one bro?

[@gcdatkin]

I don't think so. This one is specifically for heart disease. You can view the dataset I used here:
www.kaggle.com/ronitf/heart-disease-uci

[@jamespaladin607]

Is chest pain a type of pain or is it a level of pain? If it is a level of pain then it would not be nominal. Agree?

[@gcdatkin]

Correct. Since the information provided about the features is a bit vague, I tested out each categorical feature as both ordinal and nominal to see what made the models perform best. The combination I have in the video was the best I could find.

[@trees5351]

How would you calculate the recall_score or f1 score?

[@gcdatkin]

Do you mean what's the formula or how can we do it with code?

[@jamespaladin607]

think ST is systolic blood pressure

[@gcdatkin]

Ah, thanks!

[@pinakunadkat1384]

Hey