New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Created scaffolding script #2
Conversation
Added a file called script-scaffolding.py that can be used as a basis for each classifier that we want to train. How training and test set are to be defined as well as the definition of the model have been left empty.
Updated script-scaffolding.py to include argument parser. Also corrected an error and added the nilearn cache to .gitignore.
Added a check if a feature file has already been saved and loads it if it exists.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Super!!! I have one small comment about the part where you extract the target vector... it is not necessary to iterate to extract the data since sklearn has been conceived to work with pandas dataframes. to extract the Y variable you can only do : Y=phenotypic["DX_GROUP"] and you will be able to use that in your model after. I can make the changes if you'd like
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks so much for this! A few questions that I'm not sure about so I won't request changes:
- If we're not plotting we don't need
%matplotlib inline
right? I have that in my script but maybe it isn't necessary - You did say subfolder
ABIDE_pcp
but maybe we specify that the super folder is callednilearn_data
?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I will later today add the code to remove half the matrix, and I will apply PCA so that we reduce the amount features used in our prediction models (while stile keeping 99% of explained variance)
|
@anproulx that sounds awesome! Maybe open an issue for that for the sake of transparency :) |
Added a file called script-scaffolding.py that can be used as a
basis for each classifier that we want to train. How training and
test set are to be defined as well as the definition of the model
have been left empty.
@anproulx @emilyemchen @guenounz Please check for errors