add : image processing on jz

image_processing/build_dataset.py

+import argparse
 import glob
 import os
 import pandas as pd
@@ -154,12 +155,13 @@ def create_antibio_dataset(path='../data/label_raw/230804_strain_peptides_antibi
     return df
 
 
-def create_dataset():
+def create_dataset(bin_mz=1,tolerance=0.005,noise=1000,apex='apex',suffix='-d200'):
     """
     Create images from raw .mzML files and sort it in their corresponding class directory
     :return: None
     """
-    label = create_antibio_dataset(suffix='-d200')
+    label = create_antibio_dataset(suffix=suffix)
+    tolerance_str=str(tolerance)[2::]
     for path in glob.glob("../data/raw_data/**.wiff"):
         print(path)
         species = None
@@ -173,52 +175,44 @@ def create_dataset():
             name = label[label['path_aer'] == path.split("/")[-1]]['sample_name'].values[0]
             analyse = 'AER'
         if species is not None: #save image in species specific dir
-            directory_path_png = '../data/processed_data_wiff_clean_005_10000_apex/png_image/{}'.format(species)
-            directory_path_npy = '../data/processed_data_wiff_clean_005_10000_apex/npy_image/{}'.format(species)
+            directory_path_png = '../data/processed_data_wiff_clean_{}_{}_{}_{}/png_image/{}'.format(tolerance_str,noise,apex,bin_mz,species)
+            directory_path_npy = '../data/processed_data_wiff_clean_{}_{}_{}_{}/npy_image/{}'.format(tolerance_str,noise,apex,bin_mz,species)
             if not os.path.isdir(directory_path_png):
                 os.makedirs(directory_path_png)
             if not os.path.isdir(directory_path_npy):
                 os.makedirs(directory_path_npy)
             if not os.path.isfile(directory_path_png + "/" + name + '_' + analyse + '.png'):
-                try :
-                    mat = build_image_ms1_wiff_charge_filtered_apex_only(path, bin_mz=1,tolerance=0.005,noise=10000)
-                    mpimg.imsave(directory_path_png + "/" + name + '_' + analyse + '.png', mat)
-                    np.save(directory_path_npy + "/" + name + '_' + analyse + '.npy', mat)
-                    print('image create')
-                except:
-                    print(name +' couldnt be laoded')
-
-    #reiterate for other kind of raw file
-    label = create_antibio_dataset(suffix='_100vW_100SPD')
-    for path in glob.glob("../data/raw_data/**.wiff"):
-        print(path)
-        species = None
-        if path.split("/")[-1] in label['path_ana'].values:
-            species = label[label['path_ana'] == path.split("/")[-1]]['species'].values[0]
-            name = label[label['path_ana'] == path.split("/")[-1]]['sample_name'].values[0]
-            analyse = 'ANA'
-        elif path.split("/")[-1] in label['path_aer'].values:
-            species = label[label['path_aer'] == path.split("/")[-1]]['species'].values[0]
-            name = label[label['path_aer'] == path.split("/")[-1]]['sample_name'].values[0]
-            analyse = 'AER'
-        if species is not None:
-            directory_path_png = '../data/processed_data_wiff_clean_005_10000_apex/png_image/{}'.format(species)
-            directory_path_npy = '../data/processed_data_wiff_clean_005_10000_apex/npy_image/{}'.format(species)
-            if not os.path.isdir(directory_path_png):
-                os.makedirs(directory_path_png)
-            if not os.path.isdir(directory_path_npy):
-                os.makedirs(directory_path_npy)
-            if not os.path.isfile(directory_path_png + "/" + name + '_' + analyse + '.png'):
-                try :
-                    mat = build_image_ms1_wiff_charge_filtered_apex_only(path, bin_mz=1,tolerance=0.005,noise=10000)
-                    mpimg.imsave(directory_path_png + "/" + name + '_' + analyse + '.png', mat)
-                    np.save(directory_path_npy + "/" + name + '_' + analyse + '.npy', mat)
-                    print('image create')
-                except:
-                    print(name +' couldnt be laoded')
-
+                if apex == 'apex':
+                    try :
+                        mat = build_image_ms1_wiff_charge_filtered_apex_only(path, bin_mz=bin_mz,tolerance=tolerance,noise=noise)
+                        mpimg.imsave(directory_path_png + "/" + name + '_' + analyse + '.png', mat)
+                        np.save(directory_path_npy + "/" + name + '_' + analyse + '.npy', mat)
+                        print('image create')
+                    except:
+                        print(name +' couldnt be loaded')
+                else :
+                    try :
+                        mat = build_image_ms1_wiff_charge_filtered(path, bin_mz=bin_mz,tolerance=tolerance,noise=noise)
+                        mpimg.imsave(directory_path_png + "/" + name + '_' + analyse + '.png', mat)
+                        np.save(directory_path_npy + "/" + name + '_' + analyse + '.npy', mat)
+                        print('image create')
+                    except:
+                        print(name +' couldnt be loaded')
+
+def load_args_dataset():
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument('--noise', type=float, default=1000.)
+    parser.add_argument('--tolerance', type=float, default=0.005)
+    parser.add_argument('--mz_bin', type=float, default=1.)
+    parser.add_argument('--apex', type=str, default='apex')
+    args = parser.parse_args()
+
+    return args
 
 if __name__ =='__main__' :
-    create_dataset()
+    args = load_args_dataset()
+    create_dataset(noise=args.noise, tolerance=args.tolerance, bin_mz=args.mz_bin, apex=args.apex, suffix='-d200')
+    create_dataset(noise=args.noise, tolerance=args.tolerance, bin_mz=args.mz_bin, apex=args.apex, suffix='_100vW_100SPD')
 
     #KLEAER-12-AER-d200.wiff problème
\ No newline at end of file

image_processing/image_comparison.py

+import numpy as np
+import matplotlib.pyplot as plt
+import matplotlib as mpl
+import matplotlib.colors
+
+def compare_image(img_path,ref_path):
+    img = np.load(img_path)
+    img = np.log(img+1)
+    img = img/img.max()
+
+    ref = np.load(ref_path)
+
+    am1 = np.ones_like(img) # Find data to colour special
+    am1 = np.ma.masked_where(ref==0, am1)  # Mask the data we are not colouring
+
+
+    # Colourmaps for each special colour to place. The left-hand colour (black) is
+    # not used because all black pixels are masked. The right-hand colour (red or
+    # green) is used because it represents the highest z-value of the mask matrices
+    cm1 = mpl.colors.ListedColormap(['black', 'green'])
+    cm2 = mpl.colors.ListedColormap(['black', 'red'])
+
+    fig = plt.figure()  # Make a new figure
+    ax = fig.add_subplot(111)  # Add subplot to that figure, get ax
+
+    # Plot the original data. We'll overlay the specially-coloured data
+    ax.imshow(img, aspect='auto', cmap='inferno', vmin=0, vmax=1,interpolation='nearest')
+
+    # Plot the first mask. Values we wanted to colour (`a<0.3`) are masked, so they
+    # do not show up. The values that do show up are coloured using the `cm1` colour
+    # map. Since the range is constrained to `vmin=0, vmax=1` and a value of
+    # `cm2==True` corresponds to a 1, the top value of `cm1` is applied to all such
+    # pixels, thereby colouring them red.
+    ax.imshow(am1, aspect='auto', cmap=cm1, vmin=0, vmax=1,interpolation='nearest',alpha=0.4);
+
+    plt.savefig('test.png')
+
+if __name__ == '__main__':
+    # img_path = '../data/processed_data_wiff_clean_005_10000_apex/npy_image/all data/Citrobacter portucalensis/CITPOR1_ANA.npy'
+    img_path = '../data/processed_data_wiff/npy_image/all data/Citrobacter portucalensis/CITPOR1_ANA.npy'
+    ref_path = '../image_ref/img_ref_aligned/Citrobacter portucalensis.npy'
+    compare_image(img_path,ref_path)
\ No newline at end of file