def node_cluster_stat(index, parameter_list): """ 08-14-05 """ index = int(index) #08-14-05 convert it to integer form, cause it's transferred as a string from cluster_stat import cluster_stat hostname, dbname, schema, source_table, output, gene_table, \ gene_table_commit, OffsetLimitList, debug = parameter_list target_table = 'cluster_stat' offset, limit = OffsetLimitList[index] output = '%s.%s'%(output, index) uniformity = 0 min_node_size = 0 min_node_depth = 5 bonferroni = 0 commit = 0 report = 0 log = 0 wu = 1 if debug: sys.stderr.write("Index: %s; Offset: %s; Limit: %s\n"%(index, offset, limit)) instance = cluster_stat(hostname, dbname, schema, source_table, target_table, \ offset, limit, output, bonferroni, report, log, wu, commit, uniformity, \ min_node_size, min_node_depth) instance.run() del instance depth_cut_off = 5 dir_files = output leave_one_out = 1 wu = 1 report = 0 commit = gene_table_commit subgraph_cut_off = 0 debug = 0 new_table = 0 recurrence_gap_size = 2 connectivity_gap_size = 2 instance = gene_stat(hostname, dbname, schema, target_table, source_table, \ leave_one_out, wu, report, depth_cut_off, dir_files, commit, gene_table, \ subgraph_cut_off, debug, new_table, recurrence_gap_size, connectivity_gap_size) instance.run() del instance return output
def run(self): """ 08-14-05 """ communicator = MPI.world.duplicate() fake_no_of_nodes = int((communicator.size-1)*times_nodes) #NOTICE: fake_no_of_nodes is used to enlarge(or shrink) the actual number of nodes, #to balance the amount of work on each node OffsetLimitList = Numeric.zeros((fake_no_of_nodes,2), Numeric.Int) if communicator.rank == 0: (conn, curs) = db_connect(self.hostname, self.dbname, self.schema) OffsetLimitList = self.createOffsetLimitList(curs, self.source_table, fake_no_of_nodes) OffsetLimitList = Numeric.array(OffsetLimitList, Numeric.Int) #transform it into Numeric array to broadcast() if self.commit: #08-14-05 create the gene_table instance = gene_stat() instance.createGeneTable(curs, self.gene_table) curs.execute('end') if self.debug: sys.stderr.write("OffsetLimitList: %s"%repr(OffsetLimitList)) del conn, curs communicator.broadcast(OffsetLimitList, 0) #share the OffsetLimitList mpi_synchronize(communicator) job_list = range(len(OffsetLimitList)) #corresponding to the indices in the OffsetLimitList parameter_list =[self.hostname, self.dbname, self.schema, self.source_table, self.output, \ self.gene_table, self.commit, OffsetLimitList, self.debug] if self.debug: sys.stderr.write("The common parameter_list is %s.\n"%repr(parameter_list)) of_name_list = mpi_schedule_jobs(communicator, job_list, node_cluster_stat, parameter_list, self.debug) mpi_synchronize(communicator) #collecting 08-14-05 not really necessary, but just to make the number of files small if communicator.rank==0: netmine_wrapper_instance = netmine_wrapper() netmine_wrapper_instance.collect_and_merge_output(of_name_list, self.output)
def run(self): """ 09-05-05 10-23-05 create views from old schema result goes to the new schema's p_gene_table (input_node) --db_connect() --form_schema_tables() --form_schema_tables() --get_gene_no2go_no_set() --get_go_no2depth() (pass data to computing_node) (computing_node) (take data from other nodes, 0 and size-1) (judge_node) --gene_stat() --db_connect() --gene_p_map_redundancy() (output_node) --db_connect() --form_schema_tables() --form_schema_tables() --MpiPredictionFilter() --MpiPredictionFilter_instance.createGeneTable() --get_go_no2edge_counter_list()(if necessary) (pass go_no2edge_counter_list to computing_node) (input_node) --fetch_cluster_block() (computing_node) --get_no_of_unknown_genes() --node_fire_handler() --cleanup_handler() --judge_node() --gene_stat_instance.(match functions) --output_node() --output_node_handler() --MpiPredictionFilter_instance.submit_to_p_gene_table() """ communicator = MPI.world.duplicate() node_rank = communicator.rank if node_rank == 0: (conn, curs) = db_connect(self.hostname, self.dbname, self.schema) """ #01-02-06 old_schema_instance = form_schema_tables(self.input_fname) new_schema_instance = form_schema_tables(self.jnput_fname) """ gene_no2go_no = get_gene_no2go_no_set(curs) gene_no2go_no_pickle = cPickle.dumps(gene_no2go_no, -1) #-1 means use the highest protocol go_no2depth = get_go_no2depth(curs) go_no2depth_pickle = cPickle.dumps(go_no2depth, -1) go_no2gene_no_set = get_go_no2gene_no_set(curs) go_no2gene_no_set_pickle = cPickle.dumps(go_no2gene_no_set, -1) for node in range(1, communicator.size-2): #send it to the computing_node communicator.send(gene_no2go_no_pickle, node, 0) communicator.send(go_no2depth_pickle, node, 0) communicator.send(go_no2gene_no_set_pickle, node, 0) elif node_rank<=communicator.size-3: #WATCH: last 2 nodes are not here. data, source, tag = communicator.receiveString(0, 0) gene_no2go_no = cPickle.loads(data) #take the data data, source, tag = communicator.receiveString(0, 0) go_no2depth = cPickle.loads(data) data, source, tag = communicator.receiveString(0, 0) go_no2gene_no_set = cPickle.loads(data) data, source, tag = communicator.receiveString(communicator.size-1, 0) #from the last node go_no2edge_counter_list = cPickle.loads(data) #choose a functor for recurrence_array functor_dict = {0: None, 1: lambda x: int(x>=self.recurrence_x), 2: lambda x: math.pow(x, self.recurrence_x)} functor = functor_dict[self.recurrence_x_type] elif node_rank == communicator.size-2: #judge node gene_stat_instance = gene_stat(depth_cut_off=self.depth) (conn, curs) = db_connect(self.hostname, self.dbname, self.schema) gene_stat_instance.dstruc_loadin(curs) from gene_p_map_redundancy import gene_p_map_redundancy node_distance_class = gene_p_map_redundancy() elif node_rank==communicator.size-1: #establish connection before pursuing (conn, curs) = db_connect(self.hostname, self.dbname, self.schema) """ #01-02-06, input and output are all directed to files old_schema_instance = form_schema_tables(self.input_fname) new_schema_instance = form_schema_tables(self.jnput_fname) MpiPredictionFilter_instance = MpiPredictionFilter() MpiPredictionFilter_instance.view_from_table(curs, old_schema_instance.splat_table, new_schema_instance.splat_table) MpiPredictionFilter_instance.view_from_table(curs, old_schema_instance.mcl_table, new_schema_instance.mcl_table) MpiPredictionFilter_instance.view_from_table(curs, old_schema_instance.pattern_table, new_schema_instance.pattern_table) if self.new_table: MpiPredictionFilter_instance.createGeneTable(curs, new_schema_instance.p_gene_table) """ if self.go_no2edge_counter_list_fname: go_no2edge_counter_list = cPickle.load(open(self.go_no2edge_counter_list_fname,'r')) else: if self.eg_d_type==2: go_no2edge_counter_list = None else: gene_no2go_no = get_gene_no2go_no_set(curs) go_no2edge_counter_list = get_go_no2edge_counter_list(curs, gene_no2go_no, self.edge_type2index) go_no2edge_counter_list_pickle = cPickle.dumps(go_no2edge_counter_list, -1) for node in range(1, communicator.size-2): #send it to the computing_node communicator.send(go_no2edge_counter_list_pickle, node, 0) mpi_synchronize(communicator) free_computing_nodes = range(1,communicator.size-2) #exclude the last node if node_rank == 0: """ curs.execute("DECLARE crs CURSOR FOR SELECT id, vertex_set, edge_set, no_of_edges,\ connectivity, unknown_gene_ratio, recurrence_array, d_matrix from %s"%(old_schema_instance.pattern_table)) """ self.counter = 0 #01-02-06 counter is used as id reader = csv.reader(open(self.input_fname, 'r'), delimiter='\t') parameter_list = [reader] input_node(communicator, parameter_list, free_computing_nodes, self.message_size, \ self.report, input_handler=self.input_handler) del reader elif node_rank in free_computing_nodes: no_of_unknown_genes = get_no_of_unknown_genes(gene_no2go_no) GradientScorePrediction_instance = GradientScorePrediction(gene_no2go_no, go_no2gene_no_set, go_no2depth, \ go_no2edge_counter_list, no_of_unknown_genes, self.depth, self.min_layer1_associated_genes, \ self.min_layer1_ratio, self.min_layer2_associated_genes, self.min_layer2_ratio, self.exponent, \ self.score_list, self.max_layer, self.norm_exp, self.eg_d_type, self.debug) parameter_list = [GradientScorePrediction_instance, functor] computing_node(communicator, parameter_list, self.node_fire_handler, self.cleanup_handler, self.report) elif node_rank == communicator.size-2: self.judge_node(communicator, curs, gene_stat_instance, node_distance_class) elif node_rank==communicator.size-1: #01-02-06 output goes to plain file, not database writer = csv.writer(open(self.jnput_fname, 'w'), delimiter='\t') parameter_list = [writer] output_node(communicator, free_computing_nodes, parameter_list, self.output_node_handler, self.report) del writer