def MKNN_init(self):
#setting up configuration
GraphClusterer_WI_semisupervised.configdata.do_config()
GraphClusterer_WI_semisupervised.configdata.data_dir
logger = GraphClusterer_WI_semisupervised.configdata.logger
logger.debug("Debugging from inside MKNN_init method")
#setting up the input matrices
#Create SM and SM_orig
GraphClusterer_WI_semisupervised.graphdata.create_SM_from_relfile(
GraphClusterer_WI_semisupervised.configdata.inp_rel_file)
#Expand SM
GraphClusterer_WI_semisupervised.graphdata.setup_expanded_SM(
GraphClusterer_WI_semisupervised.configdata.nhops,
GraphClusterer_WI_semisupervised.configdata.inp_rel_file)
#Create Edge Objects
GraphClusterer_WI_semisupervised.graphdata.create_edge_objects()
#self.helper.print_dict(GraphClusterer.graphdata.edge_dict)
#self.helper.print_set(GraphClusterer.graphdata.node_dict[1].node_edges_dict[EdgeType.secondary])
#print(GraphClusterer.graphdata.edge_dict[011].edge_id)
#Initialize all K evaluation objects for both phases
self.phase1_allKevaluationdata = AllKEvaluationData(
self.configdata, 1) #1 for phase=1
self.phase2_allKevaluationdata = AllKEvaluationData(
self.configdata, 2) #2 for phase=2
def clusterone_init(self):
#setting up configuration
GraphClusterer_Clusterone_semisupervised.configdata.do_config()
GraphClusterer_Clusterone_semisupervised.configdata.data_dir
logger = GraphClusterer_Clusterone_semisupervised.configdata.logger
logger.debug("Debugging from inside MKNN_init method")
GraphClusterer_Clusterone_semisupervised.graphdata = GraphData_Clusterone_Gene(
GraphClusterer_Clusterone_semisupervised.configdata.GO_TYPE,
GraphClusterer_Clusterone_semisupervised.configdata.GO_SIZE,
GraphClusterer_Clusterone_semisupervised.configdata.GO_SIM_TYPE,
GraphClusterer_Clusterone_semisupervised.configdata.go_obo_file,
GraphClusterer_Clusterone_semisupervised.configdata.gene_syn_file)
#Create SM and SM_orig
GraphClusterer_Clusterone_semisupervised.graphdata.create_SM_from_relfile(
GraphClusterer_Clusterone_semisupervised.configdata.inp_rel_file)
#Expansion step not needed here as in MKNN
GraphClusterer_Clusterone_semisupervised.graphdata.setup_SM_GO_1(
GraphClusterer_Clusterone_semisupervised.configdata.inp_rel_file,
GraphClusterer_Clusterone_semisupervised.configdata.gene2go_file)
#Create edge objects
GraphClusterer_Clusterone_semisupervised.graphdata.create_edge_objects(
)
#Initialize all K evaluation objects for both phases
self.phase1_allKevaluationdata = AllKEvaluationData(
self.configdata, 1) #1 for phase=1
self.phase2_allKevaluationdata = AllKEvaluationData(
self.configdata, 2) #2 for phase=2
def clusterone_init(self):
#setting up configuration
GraphClusterer_Clusterone_CP_Overlapping.configdata.do_config()
GraphClusterer_Clusterone_CP_Overlapping.configdata.data_dir
logger = GraphClusterer_Clusterone_CP_Overlapping.configdata.logger
logger.debug("Debugging from inside MKNN_init method.")
#Create SM and SM_orig
GraphClusterer_Clusterone_CP_Overlapping.graphdata.create_SM_from_relfile(GraphClusterer_Clusterone_CP_Overlapping.configdata.inp_rel_file)
#Expansion step not needed here as in MKNN
#Create edge objects
GraphClusterer_Clusterone_CP_Overlapping.graphdata.create_edge_objects()
#Initialize all K evaluation objects for both phases
self.phase1_allKevaluationdata = AllKEvaluationData(self.configdata, 1) #1 for phase=1
self.phase2_allKevaluationdata = AllKEvaluationData(self.configdata, 2) #2 for phase=2
class GraphClusterer_WI_semisupervised(object):
CODE_DIR = '/Users/divya/work/repo/Dissertation'
#CODE_DIR = '/Users/divya/Documents/Dissertation/Dissertation'
DATA_DIR = '/Users/divya/Documents/input/Dissertation/data'
LOG_DIR = '/Users/divya/Documents/logs/Dissertation'
configdata = ConfigData(CODE_DIR, DATA_DIR, LOG_DIR)
#graphdata = GraphData_Gene(GO_SIM_TYPE)
graphdata = None
def __init__(self, K):
self.phase1data = None
self.phase2data = None
self.phase1_allKevaluationdata = None
self.phase2_allKevaluationdata = None
self.helper = MKNN_Helper()
#self.GO_SIM_TYPE = 'BP'
##############################################################
#1. Initialize MKNN
#2. As a wrapper, call MKNN_worker for different values of K
##############################################################
def MKNN_worker_wrapper(self):
#GraphClusterer.configdata.logger.info("Initialization phase of GMKNN begins")
self.MKNN_init()
GraphClusterer_WI_semisupervised.configdata.logger.info(
"Initialization phase of GMKNN ends.")
GraphClusterer_WI_semisupervised.configdata.logger.info(
"Working of G-MKNN begins")
GraphClusterer_WI_semisupervised.configdata.logger.info(
"Running G-MKNN for different values of K.")
K_range = list(
range(
(int)(GraphClusterer_WI_semisupervised.configdata.K_min),
(int)(GraphClusterer_WI_semisupervised.configdata.K_max) + 1))
for K in K_range:
GraphClusterer_WI_semisupervised.configdata.logger.info(
"Running G-MKNN for the value of K: ")
GraphClusterer_WI_semisupervised.configdata.logger.info(K)
#Call MKNN_worker for the value of K
self.MKNN_worker(K)
#(CL_List_P2, CL_List_P1, SM, SM_orig, num_clusters_P2, num_clusters_P1, num_nodes) = MKNN_worker(K, max_num_clusters, SM, SM_orig, num_nodes, node_codes, currentdate_str, dataset_name, eval_results_dir, log)
#Plot evaluation measures for all values of K for phase 1
self.phase1_allKevaluationdata.plot_evaluation_measures_for_all_K()
#Plot evaluation measures for all values of K for phase 2
self.phase2_allKevaluationdata.plot_evaluation_measures_for_all_K()
############################################
#Set up configuration
#Set up the input matrices for the algorithm
############################################
def MKNN_init(self):
#setting up configuration
GraphClusterer_WI_semisupervised.configdata.do_config()
GraphClusterer_WI_semisupervised.configdata.data_dir
logger = GraphClusterer_WI_semisupervised.configdata.logger
logger.debug("Debugging from inside MKNN_init method")
#Instantiate GraphData_Gene
GraphClusterer_WI_semisupervised.graphdata = GraphData_Gene(
GraphClusterer_WI_semisupervised.configdata.GO_TYPE,
GraphClusterer_WI_semisupervised.configdata.GO_SIZE,
GraphClusterer_WI_semisupervised.configdata.GO_SIM_TYPE,
GraphClusterer_WI_semisupervised.configdata.go_obo_file,
GraphClusterer_WI_semisupervised.configdata.gene_syn_file)
#setting up the input matrices
#Create SM and SM_orig
GraphClusterer_WI_semisupervised.graphdata.create_SM_from_relfile(
GraphClusterer_WI_semisupervised.configdata.inp_rel_file)
#Expand SM
#GraphClusterer_WI_semisupervised.graphdata.setup_expanded_SM(GraphClusterer_WI_semisupervised.configdata.nhops, GraphClusterer_WI_semisupervised.configdata.inp_rel_file)
#Setup GOsim based SM_GO
#GraphClusterer_WI_semisupervised.graphdata.setup_SM_GO(GraphClusterer_WI_semisupervised.configdata.inp_rel_file, GraphClusterer_WI_semisupervised.configdata.gene2go_file)
GraphClusterer_WI_semisupervised.graphdata.setup_SM_GO_1(
GraphClusterer_WI_semisupervised.configdata.inp_rel_file,
GraphClusterer_WI_semisupervised.configdata.gene2go_file)
#Create Edge Objects
GraphClusterer_WI_semisupervised.graphdata.create_edge_objects()
#self.helper.print_dict(GraphClusterer.graphdata.edge_dict)
#self.helper.print_set(GraphClusterer.graphdata.node_dict[1].node_edges_dict[EdgeType.secondary])
#print(GraphClusterer.graphdata.edge_dict[011].edge_id)
#Initialize all K evaluation objects for both phases
self.phase1_allKevaluationdata = AllKEvaluationData(
self.configdata, 1) #1 for phase=1
self.phase2_allKevaluationdata = AllKEvaluationData(
self.configdata, 2) #2 for phase=2
print("MKNN_Init phase complete.")
#############################
#Run MKNN for one value of K
#############################
def MKNN_worker(self, K):
self.phase1data = Phase1Data_WI_Gene(
GraphClusterer_WI_semisupervised.graphdata,
GraphClusterer_WI_semisupervised.configdata, K)
self.MKNN_Phase1()
self.phase2data = Phase2Data_WI_Gene(
GraphClusterer_WI_semisupervised.graphdata,
GraphClusterer_WI_semisupervised.configdata, K,
self.phase1data.cnodes_dict, self.phase1data.next_cluster_label,
self.phase1data.num_clusters)
self.MKNN_Phase2()
def MKNN_Phase1(self):
#Initialize Phase 1
self.phase1data.initialize_phase()
#self.helper.print_list(self.phase1data.graphdata.node_dict[10].MKNN_list)
#print('Degree')
#print((self.phase1data.graphdata.node_dict[10].degree))
#print('CI_list')
#self.helper.print_list(self.phase1data.cluster_initiator_list)
#self.helper.convert_list_ids_to_codes(self.graphdata, self.phase1data.cluster_initiator_list)
#print((self.phase1data.graphdata.CI_list[0]))
#Execute Phase 1
self.phase1data.execute_phase()
#Visualize Phase 1 results
self.phase1data.visualize_phase()
#Evaluate phase
self.phase1data.evaluate_phase()
self.phase1_allKevaluationdata.add_evaluation_for_K(
self.phase1data.phase1_evaluation_data)
print("MKNN_Phase1 complete.")
def MKNN_Phase2(self):
#Initialize phase 2
self.phase2data.initialize_phase()
#self.helper.print_list(self.phase2data.c_SM)
#self.helper.print_list(self.phase2data.c_SM_sort)
#Execute phase 2
self.phase2data.execute_phase()
#Visualize phase
self.phase2data.visualize_phase()
#Evaluate Phase
self.phase2data.evaluate_phase()
self.phase2_allKevaluationdata.add_evaluation_for_K(
self.phase2data.phase2_evaluation_data)
#self.helper.print_list(self.phase2data.phase2_evaluation_data.gold_standard_CL_list)
self.helper.print_list(
self.phase2data.phase2_evaluation_data.contingency_matrix)
print("sensitivity:")
print(self.phase2data.phase2_evaluation_data.sensitivity)
print("PPV")
print(self.phase2data.phase2_evaluation_data.PPV)
print("accuracy")
print(self.phase2data.phase2_evaluation_data.accuracy)