Remove potential chronological bias

datasets/raise/split_and_compare_prnus_of_subgroups.py

@@ -5,6 +5,8 @@ from tqdm import tqdm
 from utils import denoise
 from skimage import img_as_float
 import sys
+import os
+from random import shuffle
 
 sys.path.insert(0, '../../algorithms/distance/')
 
@@ -12,19 +14,19 @@ from rms_diff import rmsDiffNumpy
 
 NUMBER_OF_SUBGROUPS = 1
 DENOISER = 'wavelet'
-
 IMAGES_FOLDER = 'flat-field/TIF'
-imagesFileNames = os.listdir(IMAGES_FOLDER)
-numberOfImagesPerSubgroup = len(imagesFileNames) // NUMBER_OF_SUBGROUPS
 
-# 1
+imagesFileNames = os.listdir(IMAGES_FOLDER)
+# To not have a bias (chronological for instance) when split to make subgroups.
+shuffle(imagesFileNames)
+numberOfImagesPerSubgroup = len(imagesFileNames) // NUMBER_OF_SUBGROUPS
 numberOfImagesThresholds = range(numberOfImagesPerSubgroup, numberOfImagesPerSubgroup + 1)
 
-# Assume random image order to not introduce a bias.
 subgroupsPrnuEstimatesNpArray = []
-for subgroupIndex in range(NUMBER_OF_SUBGROUPS):
+for subgroupIndex in tqdm(range(NUMBER_OF_SUBGROUPS), 'Subgroup'):
     imagesPrnuEstimateNpArray = []
-    for imageFileName in tqdm(imagesFileNames[numberOfImagesPerSubgroup * subgroupIndex : numberOfImagesPerSubgroup * (subgroupIndex + 1)]):
+    subgroupImagesFileNames = imagesFileNames[numberOfImagesPerSubgroup * subgroupIndex : numberOfImagesPerSubgroup * (subgroupIndex + 1)]
+    for imageFileName in tqdm(subgroupImagesFileNames, f'Image of subgroup {subgroupIndex}'):
         imagePath = f'{IMAGES_FOLDER}/{imageFileName}'
         imagePil = Image.open(imagePath)
         imageNpArray = img_as_float(np.array(imagePil))
@@ -39,7 +41,7 @@ for subgroupIndex in range(NUMBER_OF_SUBGROUPS):
     subgroupsPrnuEstimatesNpArray += [subgroupPrnuEstimateNpArray]
 
 rmss = []
-for numberOfImagesIndex, numberOfImages in enumerate(numberOfImagesThresholds):
+for numberOfImagesIndex in range(len(numberOfImagesThresholds)):
     rms = rmsDiffNumpy(subgroupsPrnuEstimatesNpArray[0][numberOfImagesIndex], subgroupsPrnuEstimatesNpArray[1][numberOfImagesIndex])
     rmss += [rms]