In [1]:

    

%matplotlib qt
import mia
import pandas as pd
import numpy as np
import re
import random
import matplotlib.pyplot as plt
from pandas.tools import plotting


    

In [9]:

    

batch1 = pd.DataFrame.from_csv('/Volumes/Seagate/2015-03-26/batch1_blobs.csv')
batch2 = pd.DataFrame.from_csv('/Volumes/Seagate/2015-03-26/batch2_blobs.csv')

hologic = pd.concat([batch1, batch2])
hologic.index = hologic.img_name
hologic.head()


    

    
Out[9]:






  

    

      

      
x
      
y
      
radius
      
img_name
    
    

      
img_name
      

      

      

      

    
  
  

    

      
p214-010-60001-cl.png
      
 1842
      
 546
      
 128.000000
      
 p214-010-60001-cl.png
    
    

      
p214-010-60001-cl.png
      
 1482
      
 424
      
 128.000000
      
 p214-010-60001-cl.png
    
    

      
p214-010-60001-cl.png
      
 1355
      
 386
      
 128.000000
      
 p214-010-60001-cl.png
    
    

      
p214-010-60001-cl.png
      
 2072
      
 658
      
  45.254834
      
 p214-010-60001-cl.png
    
    

      
p214-010-60001-cl.png
      
 1955
      
 737
      
  45.254834
      
 p214-010-60001-cl.png
    
  

In [10]:

    

hologic.drop('img_name', axis=1, inplace=True)


    

In [8]:

    

hologic_meta_path = '/Volumes/Seagate/2015-03-26/BIRADS.csv'
hologic_meta = mia.analysis.create_hologic_meta_data(hologic, hologic_meta_path)
hologic_meta.head()


    

    
Out[8]:






  

    

      

      
patient_id
      
side
      
view
      
img_name
      
BIRADS
      
img_number
    
    

      
img_name
      

      

      

      

      

      

    
  
  

    

      
p214-010-60001-cl.png
      
 21401060001
      
 c
      
 l
      
 p214-010-60001-cl.png
      
 3
      
 1
    
    

      
p214-010-60001-cl.png
      
 21401060001
      
 c
      
 l
      
 p214-010-60001-cl.png
      
 3
      
 1
    
    

      
p214-010-60001-cl.png
      
 21401060001
      
 c
      
 l
      
 p214-010-60001-cl.png
      
 3
      
 1
    
    

      
p214-010-60001-cl.png
      
 21401060001
      
 c
      
 l
      
 p214-010-60001-cl.png
      
 3
      
 1
    
    

      
p214-010-60001-cl.png
      
 21401060001
      
 c
      
 l
      
 p214-010-60001-cl.png
      
 3
      
 1
    
  

In [11]:

    

flt = hologic['radius']>30.0

mia.plotting.plot_scatter_3d(hologic[flt], hologic.columns, hologic_meta[flt].BIRADS)


    

In [ ]:

    

mapping = mia.analysis.tSNE(hologic[flt], verbose=2)


    

    




[t-SNE] Computing pairwise distances...
[t-SNE] Computed conditional probabilities for sample 1000 / 9263
[t-SNE] Computed conditional probabilities for sample 2000 / 9263
[t-SNE] Computed conditional probabilities for sample 3000 / 9263
[t-SNE] Computed conditional probabilities for sample 4000 / 9263
[t-SNE] Computed conditional probabilities for sample 5000 / 9263
[t-SNE] Computed conditional probabilities for sample 6000 / 9263
[t-SNE] Computed conditional probabilities for sample 7000 / 9263
[t-SNE] Computed conditional probabilities for sample 8000 / 9263
[t-SNE] Computed conditional probabilities for sample 9000 / 9263
[t-SNE] Computed conditional probabilities for sample 9263 / 9263