EDA.py

from sklearn.decomposition import PCA
from math import ceil
import numpy as np
import matplotlib.pyplot as plt

def find_mean_img(full_mat, title):
    """[summary]

    Args:
        full_mat ([type]): [description]
        title ([type]): [description]

    Returns:
        [type]: [description]
    """
    # calculate the average
    mean_img = np.mean(full_mat, axis = 0)
    # reshape it back to a matrix
    mean_img = mean_img.reshape((300,225))
    plt.imshow(mean_img, vmin=0, vmax=255, cmap='Greys_r')
    plt.title(f'Average {title}')
    plt.axis('off')
    plt.show()
    return mean_img

def eigenimages(full_mat, title, n_comp = 0.7, size = (300,225)):
    """[summary]

    Args:
        full_mat ([type]): [description]
        title ([type]): [description]
        n_comp (float, optional): [description]. Defaults to 0.7.
        size (tuple, optional): [description]. Defaults to (300,225).

    Returns:
        [type]: [description]
    """
    # fit PCA to describe n_comp * variability in the class
    pca = PCA(n_components = n_comp, whiten = True)
    pca.fit(full_mat)
    print('Number of PC: ', pca.n_components_)
    return pca
  
def plot_pca(pca, size = (300,225)):
    """[summary]

    Args:
        pca ([type]): [description]
        size (tuple, optional): [description]. Defaults to (300,225).
    """
    # plot eigenimages in a grid
    n = pca.n_components_
    fig = plt.figure(figsize=(8, 8))
    r = int(n**.5)
    c = ceil(n/ r)
    for i in range(n):
        ax = fig.add_subplot(r, c, i + 1, xticks = [], yticks = [])
        ax.imshow(pca.components_[i].reshape(size), 
                  cmap='Greys_r')
    plt.axis('off')
    plt.show()