UBC-MDS / DSCI_522_Group-308_Used-Cars

This project attempts to build a regression model to predict price of used cars based on numerous features of the car
MIT License
2 stars 6 forks source link

Train/test/EDA scripts #36

Closed ksedivyhaley closed 4 years ago

ksedivyhaley commented 4 years ago

Train/Test scripts should take input and output paths as arguments. Use the same script format as download.py - define and call main().

Train and EDA scripts need tests.

pokrovskyy commented 4 years ago

Thanks for the feedback on train / test scripts - they were amended to accept some useful parameters.

However, what kind of tests do you expect to have for train script? It's quite stochastic due to its nature. The only meaningful thing I could think about is add some input handling, like non-existent data files / invalid split sizes etc. Is that what you meant? Thanks!

ksedivyhaley commented 4 years ago

The only meaningful thing I could think about is add some input handling, like non-existent data files / invalid split sizes etc. Is that what you meant?

That will do nicely!

pokrovskyy commented 4 years ago

Exactly! That’s what I’ve just done :) Thanks!

Sent from my iPhone

On Feb 1, 2020, at 07:52, ksedivyhaley notifications@github.com wrote:

The only meaningful thing I could think about is add some input handling, like non-existent data files / invalid split sizes etc. Is that what you meant?

That will do nicely!

— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.