Created
March 28, 2023 18:06
-
-
Save PlethoraChutney/fa6166e8da4448f01ed40c8cfb74797e to your computer and use it in GitHub Desktop.
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
#!/usr/bin/env python | |
import numpy as np | |
import pandas as pd | |
import umap | |
import sys | |
import matplotlib.pyplot as plt | |
import seaborn as sns | |
from sklearn.preprocessing import StandardScaler | |
from cryosparc.dataset import Dataset | |
sns.set(style = 'white') | |
# load the dataset and just select components and UID | |
particles = Dataset.load(sys.argv[1]) | |
components = [x for x in particles.fields() if 'component' in x and 'value' in x] | |
components.insert(0, 'uid') | |
df = pd.DataFrame({x: particles[x] for x in components}) | |
if sys.argv[2] == 'subset': | |
df = df.sample(10000) | |
just_components = df[components[1:]].values | |
scaled_components = StandardScaler().fit_transform(just_components) | |
reducer = umap.UMAP() | |
embedding = reducer.fit_transform(scaled_components) | |
plt.scatter( | |
embedding[:, 0], | |
embedding[:, 1]) | |
plt.gca().set_aspect('equal', 'datalim') | |
plt.title('UMAP projection of 3DVA dataset', fontsize=24) | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment