def plot_similarity_array(self):
abs_corr_array = self.workflow.redundancy_method.similarity_array
op_id_name_map = self.map_op_id_name_mult_task(self.workflow.tasks)
names = hlp.ind_map_subset(
op_id_name_map[0], op_id_name_map[1],
self.workflow.redundancy_method.similarity_array_op_ids)
measures = np.zeros((2, len(names)))
tmp_ind = hlp.ismember(
self.workflow.redundancy_method.similarity_array_op_ids,
self.workflow.good_op_ids)
# -- number of problems for which each good performing feature has been calculated
measures[0, :] = (~self.workflow.stats_good_op[:, tmp_ind].mask).sum(
axis=0)
# -- z scored u-stat(for all features) for top features
stats_good_op_z_score = fap.normalise_masked_array(
self.workflow.stats_good_op_comb, axis=0, norm_type='zscore')[0]
measures[1, :] = stats_good_op_z_score[tmp_ind]
fiplt.plot_arr_dendrogram(abs_corr_array,
names,
max_dist_cluster=self.max_dist_cluster,
measures=measures)
def plot_similarity_array(self):
abs_corr_array = self.workflow.redundancy_method.similarity_array
op_id_name_map = self.map_op_id_name_mult_task(self.workflow.tasks)
names = hlp.ind_map_subset(op_id_name_map[0],op_id_name_map[1],self.workflow.redundancy_method.similarity_array_op_ids)
measures = np.zeros((2,len(names)))
tmp_ind = hlp.ismember(self.workflow.redundancy_method.similarity_array_op_ids,
self.workflow.good_op_ids)
# -- number of problems for which each good performing feature has been calculated
measures[0,:] = (~self.workflow.stats_good_op[:,tmp_ind].mask).sum(axis=0)
# -- z scored u-stat(for all features) for top features
stats_good_op_z_score = fap.normalise_masked_array(self.workflow.stats_good_op_comb, axis= 0,norm_type = 'zscore')[0]
measures[1,:] = stats_good_op_z_score[tmp_ind]
fiplt.plot_arr_dendrogram(abs_corr_array,names,max_dist_cluster=self.max_dist_cluster,measures = measures)
op_ref_HCTSA_path = '/home/philip/work/OperationImportanceProject/results/done/HCTSA_Beef.mat'
op, = mIO.read_from_mat_file(op_ref_HCTSA_path, ['Operations'],
is_from_old_matlab=True)
max_feat = 50
# -- calculate the correlation
abs_corr_array, sort_good_ind, all_classes_avg_good_norm = idtop.calc_perform_corr_mat(
all_classes_avg_good, norm='z-score', max_feat=max_feat)
# -- save the op id's in order of performance (first entry = best performance)
np.save(op_id_order_path, op_id_good[sort_good_ind])
# -- sort the permutation vector that would sort the data array containing the good operations only
np.save(sort_good_ind_path, sort_good_ind)
# -- extract the top feature names
names = hlp.ind_map_subset(op['id'], op['name'],
op_id_good[sort_good_ind][:max_feat])
# -- Calculate the measures to be plotted
problems_succ = (~all_classes_avg_good[:, sort_good_ind[:max_feat]].mask).sum(
axis=0)
u_stat_mean = all_classes_avg_good_norm[:,
sort_good_ind[:max_feat]].mean(axis=0)
measures = np.vstack((problems_succ, u_stat_mean))
fiplt.plot_arr_dendrogram(abs_corr_array, names, measures=measures)
plt.savefig('/home/philip/Desktop/tmp/figure_tmp/corr_array.png')
plt.show()
# -- load a reference HCTSA_loc.mat containing all op_ids
import modules.misc.PK_matlab_IO as mIO
op_ref_HCTSA_path = '/home/philip/work/OperationImportanceProject/results/done/HCTSA_Beef.mat'
op, = mIO.read_from_mat_file(op_ref_HCTSA_path,['Operations'],is_from_old_matlab = True)
max_feat = 50
# -- calculate the correlation
abs_corr_array,sort_good_ind,all_classes_avg_good_norm = idtop.calc_perform_corr_mat(all_classes_avg_good,norm='z-score', max_feat = max_feat)
# -- save the op id's in order of performance (first entry = best performance)
np.save(op_id_order_path,op_id_good[sort_good_ind])
# -- sort the permutation vector that would sort the data array containing the good operations only
np.save(sort_good_ind_path,sort_good_ind)
# -- extract the top feature names
names = hlp.ind_map_subset(op['id'], op['name'], op_id_good[sort_good_ind][:max_feat])
# -- Calculate the measures to be plotted
problems_succ = (~all_classes_avg_good[:,sort_good_ind[:max_feat]].mask).sum(axis=0)
u_stat_mean = all_classes_avg_good_norm[:,sort_good_ind[:max_feat]].mean(axis=0)
measures = np.vstack((problems_succ,u_stat_mean))
fiplt.plot_arr_dendrogram(abs_corr_array,names,measures = measures)
plt.savefig('/home/philip/Desktop/tmp/figure_tmp/corr_array.png')
plt.show()
