def main():
hsic_lasso = HSICLasso()
hsic_lasso.input("../tests/test_data/matlab_data.mat")
#max_neighbors=0 means that we only use the HSIC Lasso features to plot heatmap
hsic_lasso.regression(5, max_neighbors=0)
#Compute linkage
hsic_lasso.linkage()
#Run Hierarchical clustering
# Features are clustered by using HSIC scores
# Samples are clusterd by using Euclid distance
hsic_lasso.plot_heatmap()
- MODE: regression or classification.
- HL_SELECT: number of features to select.
- HL_B: size of the block.
- HL_M: number of permutations.
Output files:
- features_hl.npy: numpy array with the 0-based index of
the selected features.
'''
import numpy as np
from pyHSICLasso import HSICLasso
hl = HSICLasso()
np.random.seed(0)
hl.X_in = np.load("${X_TRAIN}").T
hl.Y_in = np.load("${Y_TRAIN}").T
hl.Y_in = np.expand_dims(hl.Y_in, 0)
hl.featname = np.load("${FEATNAMES}")
try:
hl.${MODE}($HL_SELECT, B = $HL_B, M = $HL_M, max_neighbors = 50)
except MemoryError:
import sys, traceback
traceback.print_exc()
np.save('features_hl.npy', np.array([]))
sys.exit(77)
hl.linkage()
hl.plot_dendrogram()
hl.plot_heatmap()