

In [ ]:

    
FEATURES_PATH = '../code/data/roi_features/features.csv'  # use your own path

import numpy as np
import matplotlib
matplotlib.use('AGG')  # avoid some error in matplotlib, delete this line if the following doesn't work
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
import jgraph as ig
%matplotlib inline

# DATA description (column description)
# 0. class label [0=cocaine | 1=control | 2=fear]
# 1. brain number
# 2. roi number
# 3. roi position X
# 4. roi position Y
# 5. roi position Z
# 6. roi mean
# 7. roi std
# 8. Haralick feature - Energy
# 9. Haralick feature - Entropy
# 10. Haralick feature - Correlation
# 11. Haralick feature - Contrast
# 12. Haralick feature - Variance
# 13. Haralick feature - SumMean
# 14. Haralick feature - Inertia
# 15. Haralick feature - Cluster Shade
# 16. Haralick feature - Cluster tendency
# 17. Haralick feature - Homogeneity
# 18. Haralick feature - MaxProbability
# 19. Haralick feature - Inverse Variance
fields = ['label','nbrain','nroi','roix','roiy','roiy','mean','std','energy','entropy','correlation','contrast','variance',
          'summean','inertia','cluster shade','cluster tendency','homogeneity','maxProbability','inverse variance']
data = np.genfromtxt(FEATURES_PATH, delimiter=",", dtype=np.float32)# the features data have been pre-processed and merged

brain_nums = np.unique(data[:,1])
roi_nums = np.unique(data[:,2])

# preview - print brain numbers
print brain_nums

# preview - print roi numbers
print roi_nums

print data.shape
More analysis on ROI features

Setup
