def pre_featsel(X, y, method, thr=95, dist_function=None, thr_method='robust'):
'''
INPUT
X : data ([n_samps x n_feats] matrix)
y : class labels
method : distance measure: 'pearson', 'bhattacharyya', 'welcht', ''
if method == '', will use dist_function
thr : percentile distance threshold
dist_function :
thr_method : method for thresholding: 'none', 'robust', 'ranking'
OUTPUT
m : distance measure (thresholded or not)
'''
#pre feature selection, measuring distances
#Pearson correlation
if method == 'pearson':
au.log.info('Calculating Pearson correlation')
m = np.abs(pearson_correlation(X, y))
#Bhattacharyya distance
elif method == 'bhattacharyya':
au.log.info('Calculating Bhattacharyya distance')
m = bhattacharyya_dist(X, y)
#Welch's t-test
elif method == 'welcht':
au.log.info("Calculating Welch's t-test")
m = welch_ttest(X, y)
elif method == '':
au.log.info("Calculating distance between data and class labels")
#http://docs.scipy.org/doc/scipy/reference/spatial.distance.html
m = distance_computation(X, y, dist_function)
#if all distance values are 0
if not m.any():
au.log.info(
"No differences between groups have been found. Are you sure you want to continue?"
)
return m
#threshold data
if thr_method != 'none':
if thr_method == 'robust':
mt = au.robust_range_threshold(m, thr)
elif thr_method == 'percentile':
mt = au.percentile_threshold(m, thr)
elif thr_method == 'rank':
mt = au.rank_threshold(m, thr)
return mt
return m
def pre_featsel (X, y, method, thr=95, dist_function=None, thr_method='robust'):
'''
INPUT
X : data ([n_samps x n_feats] matrix)
y : class labels
method : distance measure: 'pearson', 'bhattacharyya', 'welcht', ''
if method == '', will use dist_function
thr : percentile distance threshold
dist_function :
thr_method : method for thresholding: 'none', 'robust', 'ranking'
OUTPUT
m : distance measure (thresholded or not)
'''
#pre feature selection, measuring distances
#Pearson correlation
if method == 'pearson':
au.log.info ('Calculating Pearson correlation')
m = np.abs(pearson_correlation (X, y))
#Bhattacharyya distance
elif method == 'bhattacharyya':
au.log.info ('Calculating Bhattacharyya distance')
m = bhattacharyya_dist (X, y)
#Welch's t-test
elif method == 'welcht':
au.log.info ("Calculating Welch's t-test")
m = welch_ttest (X, y)
elif method == '':
au.log.info ("Calculating distance between data and class labels")
#http://docs.scipy.org/doc/scipy/reference/spatial.distance.html
m = distance_computation(X, y, dist_function)
#if all distance values are 0
if not m.any():
au.log.info("No differences between groups have been found. Are you sure you want to continue?")
return m
#threshold data
if thr_method != 'none':
if thr_method == 'robust':
mt = au.robust_range_threshold (m, thr)
elif thr_method == 'percentile':
mt = au.percentile_threshold (m, thr)
elif thr_method == 'rank':
mt = au.rank_threshold (m, thr)
return mt
return m
def apply_distance_threshold(distances, thr, method='robust'):
if method == 'robust': return au.robust_range_threshold(distances, thr)
elif method == 'rank': return au.rank_threshold(distances, thr)
elif method == 'percentile': return au.percentile_threshold(distances, thr)
def apply_distance_threshold (distances, thr, method='robust'):
if method == 'robust': return au.robust_range_threshold (distances, thr)
elif method == 'rank': return au.rank_threshold (distances, thr)
elif method == 'percentile': return au.percentile_threshold (distances, thr)