def total(): check_dic() csv_dealer.csv_deal_to_file("./data/training_csv/",no_total=1,to_addr="./data/training_csv_cut") csv_dealer.csv_deal_to_file('./data/test_csv/',no_total=1,to_addr='./data/test_csv_cut') csv_dealer.csv_deal_to_file('./data/final_test/',no_total=1,to_addr='./data/final_test_cut') mat_list = nmf_sklearn.generate_new_mat_list('./data/training_csv') total_mat = csv_dealer.mat_list_to_total(mat_list) np.savetxt("./data/total.csv", total_mat, delimiter=',', fmt="%f") w, h = nmf_sklearn.nmf_sklearn(3,total_mat) K_Means.k_means(w,250,new_file_addr='./data/class_list.txt') probability.run() get_Sit.run() cal_f1.run()
def apply_algorithm(self, alg_name, training_vectors, test_vectors_clean, test_vectors_anomalous): """Applies the specified algorithm onto the feature sets. """ if alg_name == 'lof': result_clean, result_anomalous, result_training = LOF.local_outlier_detection(training_vectors, test_vectors_clean, test_vectors_anomalous) elif alg_name == 'svm': result_clean, result_anomalous, result_training = SVM.one_class_svm(training_vectors, test_vectors_clean, test_vectors_anomalous) elif alg_name == 'dbscan': result_clean,result_anomalous, result_training = DBSCAN.dbscan(training_vectors,test_vectors_clean,test_vectors_anomalous) elif alg_name == 'kmeans': result_clean,result_anomalous, result_training = K_Means.k_means(training_vectors,test_vectors_clean,test_vectors_anomalous) else: raise NameError("Invalid Algorithm Name") return result_clean,result_anomalous, result_training
output.close() print 'Parameters saved to ' + filenames['params'] + '.pkl' ######################################################### print 'Initiating K-Means...' k_results=list() for i in range(numRounds): start=datetime.now() iGenerations=qk_rounds_genNum[i] numInits=np.int(iGenerations*numOracles*initsPercentage) k_centroids,k_assignment,k_timings,k_intertia=K_Means.k_means(mixture,numClusters,numInits) k_results.append([k_centroids,k_assignment,k_timings,k_intertia]) round=(datetime.now() - start).total_seconds() print float(i+1)*100/numRounds,'%\t','round ', i,':',round,'s - estimated:',(float(numRounds-1)-i)*round,'s / ',(float(numRounds-1)-i)*round/60,'m' print 'Preparing K-Means data structures...' k_rounds=dict() k_rounds['centroids']=list() k_rounds['assignment']=list() k_rounds['times']=list() k_rounds['inertia']=list() for i in range(numRounds): k_rounds['centroids'].append(k_results[i][0])
from sklearn import datasets import K_Means, Plot blobs = datasets.make_blobs()[0] centers, clusters, colors, color_labels = K_Means.k_means(blobs, 3) Plot.plot(blobs, centers, colors, color_labels)
pickle.dump(params, output) output.close() print 'Parameters saved to ' + filenames['params'] + '.pkl' ######################################################### print 'Initiating K-Means...' print "Each round will have ", numInits, " K-Means initializations." k_results = list() for i in range(numRounds): start = datetime.now() k_centroids, k_assignment, k_timings, k_intertia = K_Means.k_means( mixture, numClusters, numInits) k_results.append([k_centroids, k_assignment, k_timings, k_intertia]) round = (datetime.now() - start).total_seconds() print float( i + 1 ) * 100 / numRounds, '%\t', 'round ', i, ':', round, 's - estimated:', ( float(numRounds - 1) - i) * round, 's / ', (float(numRounds - 1) - i) * round / 60, 'm' print 'Preparing K-Means data structures...' k_rounds = dict() k_rounds['centroids'] = list() k_rounds['assignment'] = list() k_rounds['times'] = list()