In [4]:

    

%matplotlib inline
import re
import mia
import os.path
import numpy as np
from sklearn import manifold, decomposition


    

In [52]:

    

image_directory = '/Volumes/Seagate/MammoData/pngs'
masks_directory = '/Volumes/Seagate/MammoData/masks'

name_regex = re.compile(r"p(\d{3}-\d{3}-\d{5})-([a-z]{2})\.png")

img_names, patient_id, views, sides = [], [], [], []
for img_path, msk_path in mia.io_tools.iterate_directory(image_directory, masks_directory):
    name = os.path.basename(img_path)
    img_names.append(name)
    m = re.match(name_regex, name)
    num = m.group(1).replace('-', '')
    view, side = m.group(2)
    views.append(view)
    sides.append(side)
    patient_id.append(int(num))
    
feature_matrix = np.load('../raw_images.npy')


    

    




---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-52-ee707b6db428> in <module>()
      5 
      6 img_names, patient_id, views, sides = [], [], [], []
----> 7 for img_path, msk_path in mia.io_tools.iterate_directory(image_directory, masks_directory):
      8     name = os.path.basename(img_path)
      9     img_names.append(name)

/Users/samuel/git/major-project/src/mia/io_tools.pyc in iterate_directory(directory, mask_directory)
     16     :returns: iterator to the image paths in the directory
     17     """
---> 18     check_is_directory(directory)
     19 
     20     for img_name in os.listdir(directory):

/Users/samuel/git/major-project/src/mia/io_tools.pyc in check_is_directory(directory)
     51     """
     52     if not os.path.isdir(directory):
---> 53         raise ValueError("%s is not a directory" % directory)
     54 
     55 

ValueError: /Volumes/Seagate/MammoData/pngs is not a directory

In [6]:

    

df = pd.DataFrame(feature_matrix, index=img_names)
md = pd.DataFrame(np.array([patient_id, views, sides]).T, columns=['patient_id', 'view', 'side'], index=img_names)
md = mia.reduction.add_BIRADS_class(md, '../data/BIRADS.csv')


    

In [86]:

    

X = df.as_matrix()


    

    
Out[86]:





array([ 0.,  0.,  0., ...,  0.,  0.,  0.])

In [87]:

    

pca = decomposition.PCA(n_components=10)
X = pca.fit_transform(X)


    

    
Out[87]:





array([-44.03278639, -20.10827969,   7.64452451,  18.33399668,
        15.12215433,  -1.65562797,   2.37125881,  -1.20035446,
        10.02527258,  -5.16636072])

In [90]:

    

tsne = manifold.TSNE(n_components=2, perplexity=50, early_exaggeration=2.0, verbose=2,  learning_rate=300.0)
y = tsne.fit_transform(X)


    

    




[t-SNE] Computing pairwise distances...
[t-SNE] Computed conditional probabilities for sample 360 / 360
[t-SNE] Mean sigma: 23.230741
[t-SNE] Iteration 10: error = 4.6092650, gradient norm = 0.0930863
[t-SNE] Iteration 20: error = 3.5026420, gradient norm = 0.0795287
[t-SNE] Iteration 30: error = 3.6462744, gradient norm = 0.0785828
[t-SNE] Iteration 40: error = 3.5836784, gradient norm = 0.0726549
[t-SNE] Iteration 45: did not make any progress during the last 30 episodes. Finished.
[t-SNE] Iteration 50: error = 3.1309570, gradient norm = 0.0667554
[t-SNE] Iteration 60: error = 3.6121856, gradient norm = 0.0821283
[t-SNE] Iteration 70: error = 3.5110685, gradient norm = 0.0771007
[t-SNE] Iteration 78: did not make any progress during the last 30 episodes. Finished.
[t-SNE] Error after 78 iterations with early exaggeration: 3.563292
[t-SNE] Iteration 80: error = 0.7780572, gradient norm = 0.0213501
[t-SNE] Iteration 90: error = 0.5158594, gradient norm = 0.0085724
[t-SNE] Iteration 100: error = 0.4807104, gradient norm = 0.0027211
[t-SNE] Iteration 110: error = 0.4744094, gradient norm = 0.0008895
[t-SNE] Iteration 120: error = 0.4724821, gradient norm = 0.0005412
[t-SNE] Iteration 130: error = 0.4713123, gradient norm = 0.0005568
[t-SNE] Iteration 140: error = 0.4707005, gradient norm = 0.0004141
[t-SNE] Iteration 150: error = 0.4704620, gradient norm = 0.0003834
[t-SNE] Iteration 160: error = 0.4703361, gradient norm = 0.0003739
[t-SNE] Iteration 170: error = 0.4702641, gradient norm = 0.0003694
[t-SNE] Iteration 180: error = 0.4702221, gradient norm = 0.0003670
[t-SNE] Iteration 190: error = 0.4701973, gradient norm = 0.0003655
[t-SNE] Iteration 200: error = 0.4701825, gradient norm = 0.0003646
[t-SNE] Iteration 210: error = 0.4701738, gradient norm = 0.0003641
[t-SNE] Iteration 220: error = 0.4701685, gradient norm = 0.0003637
[t-SNE] Iteration 230: error = 0.4701654, gradient norm = 0.0003635
[t-SNE] Iteration 240: error = 0.4701635, gradient norm = 0.0003634
[t-SNE] Iteration 248: error difference 0.000000. Finished.
[t-SNE] Error after 248 iterations: 0.470163

In [92]:

    

%matplotlib qt
mapping = pd.DataFrame(y, index=md.index.values)
mia.plotting.plot_scatter_2d(mapping, columns=[0,1], labels=md['class'])


    

In [440]:

    

mapping['class'] = md['class']
mia.io_tools.dump_mapping_to_json(mapping, columns=[0,1], output_file="../mapping_viz/data.json")