#
# ############ Calculate SDRR of clean data #########################
#
# #RR_sec_detrended is in ms and std_dev will be in ms
# sdrr_curr=np.std(RR_sec_detrended_ms);
#print("SDRR after filtering and detrending in ms for " + rec_name + "is: " + str(sdrr_curr));
#################### PLOT histograms for each record ##############################################
# fig_hist,plot_hist=graphs.plotHistPercent(rec_name, RR_sec,100, "RR (sec)", "Percentage of total points", "RR interval histogram")
# fig_hist.savefig(output_folder+"hist_"+record+".png")
# plt.close();
################### Append feature for 1 record to a list of lists ##############################
all_features.append(feature_rec)
#nlm.plot_ctm(rec_name_array,ctm_list_list,radius_array)
#nlm.plot_dist(rec_name_array,dist_list_list,radius_array)
rw.write_value(global_vocab, output_folder, 'global_vocab.txt', 'w')
print(len(all_features))
#write to all_features to file
rw.write_value(all_features, output_folder, "all_features_readable.txt", 'w')
rw.write_features_to_file(all_features, output_folder,
"all_features_pickle.txt")
rw.write_features_to_file(global_vocab, output_folder,
"global_vocab_pickle.txt")
rw.write_features_to_file(rec_name_array, output_folder,
"rec_name_array_pickle.txt")
#plt.show()
# #RR_sec_detrended is in ms and std_dev will be in ms
# sdrr_curr=np.std(RR_sec_detrended_ms);
#print("SDRR after filtering and detrending in ms for " + rec_name + "is: " + str(sdrr_curr));
#################### PLOT histograms for each record ##############################################
# fig_hist,plot_hist=graphs.plotHistPercent(rec_name, RR_sec,100, "RR (sec)", "Percentage of total points", "RR interval histogram")
# fig_hist.savefig(output_folder+"hist_"+record+".png")
# plt.close();
################### Append feature for 1 record to a list of lists ##############################
all_features.append(feature_rec)
#nlm.plot_ctm(rec_name_array,ctm_list_list,radius_array)
#nlm.plot_dist(rec_name_array,dist_list_list,radius_array)
rw.write_value(global_vocab, output_folder, 'global_vocab.txt', 'w')
print(len(all_features))
#write to all_features to file
rw.write_value(all_features,output_folder,"all_features_readable.txt",'w')
rw.write_features_to_file(all_features,output_folder,"all_features_pickle.txt")
rw.write_features_to_file(global_vocab,output_folder,"global_vocab_pickle.txt")
rw.write_features_to_file(rec_name_array, output_folder, "rec_name_array_pickle.txt")
plt.show()
# cl.print_classification_report(y_test_report_rfecv_cv, y_predicted_report_rfecv_cv,['class 0', 'class 1'])
print("############################################")
folds=5
cv = StratifiedKFold(y_eval, n_folds=folds)
classifier = svm.SVC(kernel='linear', probability=True)
###################### Feature selection using RFECV only #################################################
only_feature_selection,index_arr_onlyfs=cl.select_optimal_features(X_cv_normalized_matrix,y_cv,classifier)
print("number of features selected only with rfecv: " +str(len(index_arr_onlyfs)))
index_num_fs_only,index_freq_fs_only=cl.sort_and_combine_feature_indices(index_arr_onlyfs)
print("index numbers are: " + str(index_num_fs_only))
rw.write_features_to_file(index_num_fs_only,output_folder,"rfecv_selected13_features.txt")
#print("index freq are: " + str(index_freq_fs_only))
####### print features selected by rfecv alone #########################################
rfecv_only_feature_arr=[]
for val in index_num_fs_only:
#print val
#print (inv_global_vocab[val])
rfecv_only_feature_arr.append(inv_global_vocab[val])
print("len of rfecv only features is: " +str(len(rfecv_only_feature_arr)))
np.savetxt(output_folder+"rfecv_only_features.txt",rfecv_only_feature_arr,fmt="%s",delimiter=',',newline='\n')
#######################################################################
#plt.figure()
folds = 5
cv = StratifiedKFold(y_eval, n_folds=folds)
classifier = svm.SVC(kernel='linear', probability=True)
###################### Feature selection using RFECV only #################################################
only_feature_selection, index_arr_onlyfs = cl.select_optimal_features(
X_cv_normalized_matrix, y_cv, classifier)
print("number of features selected only with rfecv: " +
str(len(index_arr_onlyfs)))
index_num_fs_only, index_freq_fs_only = cl.sort_and_combine_feature_indices(
index_arr_onlyfs)
print("index numbers are: " + str(index_num_fs_only))
rw.write_features_to_file(index_num_fs_only, output_folder,
"rfecv_selected13_features.txt")
#print("index freq are: " + str(index_freq_fs_only))
####### print features selected by rfecv alone #########################################
rfecv_only_feature_arr = []
for val in index_num_fs_only:
#print val
#print (inv_global_vocab[val])
rfecv_only_feature_arr.append(inv_global_vocab[val])
print("len of rfecv only features is: " + str(len(rfecv_only_feature_arr)))
np.savetxt(output_folder + "rfecv_only_features.txt",
rfecv_only_feature_arr,
fmt="%s",
delimiter=',',
newline='\n')
