search

spmcodes / Codecademy_Project

Capstone Project of Machine Learning Fundamentals
0 stars 0 forks source link

What is profiles_clean? #1

Open mackenzieyoung opened 5 years ago

mackenzieyoung commented 5 years ago

https://github.com/spmcodes/Codecademy_Project/blob/ee8c62dbbc9a83bb1d05c2428aee5f4ed13ec34e/Codecademy_Project.ipynb#L21

I'm not sure what the profiles_clean CSV is. It's best to clean your data within your code, so anyone who has your code and the original data can run your code and get the same results. The way it is now, I can't tell what you did to clean your data.

spmcodes commented 5 years ago

There were a lot of -1s in the income column and I was not able to replace it within the code. I replaced all of them with 30000 in the csv file. I would ideally desire to replace -1s with random numbers within the range 20000 to 1000000 or so. Tried various options but was not able to do it. Appreciate your help in this.