Last active
March 18, 2020 20:16
-
-
Save rpryzant/2e0d5fec5915ba0e27edf6b644e291a0 to your computer and use it in GitHub Desktop.
Util functions for computing and removing principal components
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from sklearn.decomposition import TruncatedSVD | |
def compute_pc(X,npc=1): | |
""" | |
Compute the principal components. | |
X: numpy array [data, features] | |
npc: num principal components | |
""" | |
svd = TruncatedSVD(n_components=npc, n_iter=7, random_state=0) | |
svd.fit(X) | |
return svd.components_ | |
def remove_pc(X, npc=1, pc=None): | |
""" | |
Remove the projection on the principal components | |
X: numpy array [data, features] | |
npc: num principal components | |
pc (optional): direction to project and flatten on | |
returns: out[i, :] is the data point after removing its projection | |
""" | |
if pc is None: | |
pc = compute_pc(X, npc) | |
if npc==1: | |
out = X - X.dot(pc.transpose()) * pc | |
else: | |
out = X - X.dot(pc.transpose()).dot(pc) | |
return out |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment