import streamlit as st import numpy as np import matplotlib.pyplot as plt from matplotlib.widgets import Slider from scipy.ndimage import gaussian_filter from sklearn.decomposition import PCA # Dummy PCA Data - Replace with actual PCA-transformed data h, w, d = 100, 100, 4 # Example shape pc_data = np.random.rand(h, w, d) # Streamlit UI st.title("Interactive PCA Visualization") # Sliders for PC Weights pc1_weight = st.slider("PC1 Weight", -1.0, 1.0, 0.0, 0.02) pc2_weight = st.slider("PC2 Weight", -1.0, 1.0, 0.0, 0.02) pc3_weight = st.slider("PC3 Weight", -1.0, 1.0, 0.0, 0.02) pc4_weight = st.slider("PC4 Weight", -1.0, 1.0, 0.0, 0.02) # Generate Image composite_image = ( pc1_weight * pc_data[:, :, 0] + pc2_weight * pc_data[:, :, 1] + pc3_weight * pc_data[:, :, 2] + pc4_weight * pc_data[:, :, 3] ) composite_image = gaussian_filter(composite_image, sigma=1) # Display Image fig, ax = plt.subplots() ax.imshow(composite_image, cmap="gray") st.pyplot(fig)