Merge branch '11-installation-instructions' into 'main'

Fix EDA Errors

Closes #11

See merge request !8

EDA.py

@@ -2,60 +2,74 @@ from sklearn.decomposition import PCA
 from math import ceil
 import numpy as np
 import matplotlib.pyplot as plt
+from tqdm import tqdm
 
-def find_mean_img(full_mat, title):
-    """[summary]
+def find_mean_img(full_mat):
+    """Calculates and plots the mean of each pixel in an image matrix.
 
     Args:
-        full_mat ([type]): [description]
-        title ([type]): [description]
+        full_mat (np.ndarray): Vectorized array of the image matrix.
+        title (String): Name of the title for the plot.
 
     Returns:
-        [type]: [description]
+        matplotlib.plt: A plot of the the mean pixels for each disease category.
     """
+    cols = 4
+    rows = len(full_mat)//cols + 1
+    
+    fig = plt.figure(figsize = (12,6))
+
+    for i, mat in zip(range(0,len(full_mat)),full_mat):
     # calculate the average
-    mean_img = np.mean(full_mat, axis = 0)
+        mean_img = np.mean(full_mat[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}')
+        mean_img = mean_img.reshape((200, 150))
+        ax = fig.add_subplot(rows, cols,i+1)
+        ax.imshow(mean_img, vmin=0, vmax=255, cmap='Greys_r')
+        ax.set_title('Average ' + mat)
         plt.axis('off')
-    plt.show()
-    return mean_img
 
-def eigenimages(full_mat, title, n_comp = 0.7, size = (300,225)):
-    """[summary]
+    plt.tight_layout()
     
-    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]
+def plot_pca(pca, title, size = (200, 150)):
+    """Plots each decomposed PCA image and labels the amount of variability for each image.
 
     Args:
-        pca ([type]): [description]
-        size (tuple, optional): [description]. Defaults to (300,225).
+        pca (sklearn PCA object): A fitted PCA object.
+        title (String): Title of the plot.
+        size (tuple, optional): Shape of the image matrix. Defaults to (300,225).
     """
     # plot eigen images in a grid
     n = pca.n_components_
+    print('Number of PC in ' + title + ':', n)
     fig = plt.figure(figsize=(8, 8))
+    fig.suptitle('PCA Components of ' + title)
     r = int(n**.5)
     c = ceil(n/ r) 
     for i in range(n):
-        ax = fig.add_subplot(r, c, i + 1, xticks = [], yticks = [])
+        ax = fig.add_subplot(r, c, i + 1)
         ax.imshow(pca.components_[i].reshape(size), 
                   cmap='Greys_r')
+        ax.set_title("Variance " + "{0:.2f}%".format(pca.explained_variance_ratio_[i] * 100) )
         plt.axis('off')
+        plt.tight_layout()
+
     plt.show()
+
+
+def eigenimages(full_mat,n_comp = 0.7, size = (200, 150)):
+    """Creates creates and fits a PCA estimator from sklearn.
+
+    Args:
+        full_mat (np.ndarray): A vectorized array of images.
+        n_comp (float, optional): Percentage of desired variability. Defaults to 0.7.
+        size (tuple, optional): Shape of the image matrix. Defaults to (300,225).
+
+    Returns:
+        sklearn PCA object: Fitted PCA model.
+    """
+    # fit PCA to describe n_comp * variability in the class
+    pca = PCA(n_components = n_comp, whiten = True)
+    pca.fit(full_mat)
+
+    return pca

data_processing.py

@@ -4,6 +4,7 @@ import pandas as pd
 import tensorflow as tf
 from tensorflow.keras.preprocessing import image
 import numpy as np
+from tqdm import tqdm
 
 
 def load_sort_data(meta_filename = str, image_folder = str, output_folder = str):
@@ -23,13 +24,13 @@ def load_sort_data(meta_filename = str, image_folder = str, output_folder = str)
     labels = metadata['dx'].unique()
     label_images = []
     
-    for i in labels:
+    for i in tqdm(labels):
         if os.path.exists(dest_dir + str(i) + '/'):
             shutil.rmtree(dest_dir + str(i) + '/')
         os.mkdir(dest_dir + str(i) + '/')
         sample = metadata[metadata['dx'] == i]['image_id']
         label_images.extend(sample)
-        for id in label_images:
+        for id in tqdm(label_images):
             shutil.copyfile((data_dir + image_folder + '/' + id + '.jpg'), (dest_dir + i + '/' + id + '.jpg'))
         label_images = []
     
@@ -39,7 +40,7 @@ def transform(path, size = (300, 225)):
     # create a list of images
     img_list = [fn for fn in os.listdir(path) if fn.endswith('.jpg')]
     #iterating over each .jpg
-    for fn in img_list:
+    for fn in tqdm(img_list):
         fp = path + '/' + fn
         current_image = image.load_img(fp, target_size = size, 
                                     color_mode = 'grayscale')

requirements.txt

@@ -2,3 +2,4 @@ numpy>=1.21.5
 pandas>=1.3.5
 tensorflow>=2.8.0
 matplotlib>=3.3.2
+tqdm>=4.*
\ No newline at end of file