In [2]:

    

%matplotlib qt
import pandas as pd
import numpy as np
import mia


    

In [3]:

    

hologic = pd.DataFrame.from_csv("/Volumes/Seagate/mmp_data/2015-04-16/real-lines.csv")
hologic_blobs = pd.DataFrame.from_csv("/Volumes/Seagate/mmp_data/2015-04-01/hologic.csv")
phantom = pd.DataFrame.from_csv("/Volumes/Seagate/mmp_data/2015-04-16/phantom-lines.csv")
phantom_blobs = pd.DataFrame.from_csv("/Volumes/Seagate/mmp_data/2015-04-14/synthetics1-blobs.csv")


    

In [4]:

    

hologic_meta = mia.analysis.create_hologic_meta_data(hologic, "/Volumes/Seagate/mmp_data/meta_data/BIRADS.csv")
phantom_meta = mia.analysis.create_synthetic_meta_data(phantom, "/Volumes/Seagate/mmp_data/meta_data/synthetic_meta_data_cleaned.csv")
phantom_meta.index.name = 'img_name'


    

In [5]:

    

hologic_labels = hologic_meta.drop_duplicates().BIRADS
phantom_labels = phantom_meta['VBD.1']

# class_labels = mia.analysis.remove_duplicate_index(hologic_labels)
class_labels = pd.concat([hologic_labels, phantom_labels])
class_labels.index.name = "img_name"
labels = mia.analysis.remove_duplicate_index(class_labels)[0]


    

In [6]:

    

hologic_line_features = mia.analysis.features_from_lines(hologic)
hologic_line_features.fillna(hologic_line_features.mean(), inplace=True)

hologic_blob_features = mia.analysis.features_from_blobs(hologic_blobs)

phantom_line_features = mia.analysis.features_from_lines(phantom)
phantom_line_features.fillna(phantom_line_features.mean(), inplace=True)

phantom_blob_features = mia.analysis.features_from_blobs(phantom_blobs)


    

In [7]:

    

syn_feature_meta = mia.analysis.remove_duplicate_index(phantom_meta)
phantom_line_features['phantom_name'] = syn_feature_meta.phantom_name.tolist()
phantom_line_features_subset = mia.analysis.create_random_subset(phantom_line_features, 'phantom_name')
phantom_blob_features_subset = phantom_blob_features.loc[phantom_line_features_subset.index]


    

In [9]:

    

line_features = pd.concat([hologic_line_features, phantom_line_features])
blob_features = pd.concat([hologic_blob_features, phantom_blob_features])
features = blob_features.join(line_features, rsuffix='_line')
# assert features.shape[0] == 366
features.head()


    

    
Out[9]:






  

    

      

      
blob_count
      
avg_radius
      
std_radius
      
min_radius
      
max_radius
      
small_radius_count
      
med_radius_count
      
large_radius_count
      
density
      
lower_radius_qt
      
...
      
75%
      
count
      
kurtosis
      
max
      
mean
      
min
      
phantom_name
      
skew
      
std
      
upper_dist_count_line
    
  
  

    

      
p214-010-60001-cl.png
      
  56
      
 22.121831
      
 22.923389
      
 8
      
 128.000000
      
  52
      
 1
      
 3
      
 52.940812
      
 8
      
...
      
 137.25
      
  72
      
 26.793023
      
 1744
      
 161.791667
      
 1
      
 NaN
      
 4.786025
      
 245.194659
      
 16
    
    

      
p214-010-60001-cr.png
      
  78
      
 19.054538
      
 17.506086
      
 8
      
  90.509668
      
  68
      
 4
      
 6
      
 40.749811
      
 8
      
...
      
 152.00
      
  57
      
 50.202367
      
 3494
      
 176.421053
      
 1
      
 NaN
      
 6.905092
      
 460.921203
      
 13
    
    

      
p214-010-60001-ml.png
      
  98
      
 20.011191
      
 21.876304
      
 8
      
 128.000000
      
  90
      
 3
      
 5
      
 42.644057
      
 8
      
...
      
 210.50
      
  72
      
 13.937538
      
 1662
      
 200.708333
      
 1
      
 NaN
      
 3.484285
      
 296.524822
      
 19
    
    

      
p214-010-60001-mr.png
      
 139
      
 15.309764
      
 15.307860
      
 8
      
 128.000000
      
 136
      
 1
      
 2
      
 38.287439
      
 8
      
...
      
 192.25
      
  74
      
 22.429202
      
 2522
      
 203.459459
      
 1
      
 NaN
      
 4.309621
      
 371.688380
      
 16
    
    

      
p214-010-60005-cl.png
      
  97
      
 20.132590
      
 23.255605
      
 8
      
 181.019336
      
  94
      
 2
      
 1
      
 41.456308
      
 8
      
...
      
 170.75
      
 114
      
  9.028130
      
  911
      
 143.184211
      
 1
      
 NaN
      
 2.667624
      
 152.914376
      
 36
    
  

5 rows × 24 columns

In [16]:

    

selected_features = blob_features.copy()
# selected_features.drop(['skew', 'kurtosis', 'min'], inplace=True, axis=1)
mapping = mia.analysis.isomap(selected_features, n_components=2)


    

In [52]:

    

mapping.to_csv("/Volumes/Seagate/mmp_data/2015-04-16/lines-mapping.csv")


    

In [ ]:

    

left = hologic_line_features[mapping[0] < 0]
right = hologic_line_features[mapping[0] >=0]

left.describe() - right.describe()


    

In [ ]:

    

phantom_line_features_subset.describe() - hologic_line_features.describe()


    

In [18]:

    

def plot_mapping(m):
    hologic_map = m.loc[hologic_line_features.index]
    phantom_map = m.loc[phantom_line_features.index]

    hol_labels = labels[hologic_map.index]
    syn_labels = labels[phantom_map.index]

    ax = mia.plotting.plot_scatter_2d(hologic_map, labels=hol_labels, s=20)
    ax = mia.plotting.plot_scatter_2d(phantom_map, labels=syn_labels, ax=ax, marker='^', s=50)

plot_mapping(mapping)


    

In [ ]:

    

selected_features.to_csv("/Volumes/Seagate/mmp_data/features.csv")
mapping.to_csv("/Volumes/Seagate/mmp_data/mapping.csv")


    

In [ ]:

    

mapping = pd.DataFrame.from_csv("/Volumes/Seagate/mmp_data/2015-04-01/both_shape_mapping.csv")
plot_mapping(mapping)


    

In [45]:

    

m = selected_features.copy()
m['class'] = labels
m.drop(['25%', 'upper_dist_count'], inplace=True, axis=1)
pd.tools.plotting.radviz(m, 'class')


    

    
Out[45]:





<matplotlib.axes._subplots.AxesSubplot at 0x11ca64350>