-
Notifications
You must be signed in to change notification settings - Fork 0
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
Optimize Feature Engineering Part 2 #9
Conversation
* Applied scalar multiplication to vector * Used indexing technique * Transformed from float64 to float32
This is an expected behavior (confirmed by Chaozhong), but not sure why. We can ignore this anyway. |
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.
a minor comment. thanks for doing this.
for i in range(0, max_iter): | ||
Fs = np.append(Fs, F, axis=1) | ||
F = alpha * nn @ Fs[:, [i]] + fY | ||
F = nn @ (alpha * Fs[:, [i]]) + (1 - alpha) * y |
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.
any benefit for using (1 - alpha) * y
instead of using fY
?
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.
any benefit for using
(1 - alpha) * y
instead of usingfY
?
I thought it adds intuitiveness to the equation, and no drawbacks on speed.
Because I used float32 instead of float64, for the purpose of speed optimization, but not necessary. It only improves 30s. |
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.
Clear all good
Changed Output
There's subtle change on outputs, but I think they are ignorable.
Reduced the running time
Before:
After: