def run(self): """ 03-30-05 06-30-05 more complex data grouping via which_column_list and group_size_list if both lists are of length 2, 2-level grouping. --db_connect() --get_go_no2depth() --data_fetch() --group_data() if self.stat_table_fname: --prediction_space_output() """ self.init() (conn, curs) = db_connect(self.hostname, self.dbname, self.schema) from codense.common import get_go_no2depth self.go_no2depth = get_go_no2depth(curs) self.data_fetch(curs, self.table, self.mcl_table, self.gene_table) local_prediction_space2attr = self.group_data(self.prediction_data,key_column=self.which_column_list[0], group_size=self.group_size_list[0]) for key, unit in local_prediction_space2attr.iteritems(): if len(self.which_column_list)>1 and len(self.group_size_list)>1: local_prediction_space2attr_2 = self.group_data(unit, key_column=self.which_column_list[1], group_size=self.group_size_list[1]) for key2, unit2 in local_prediction_space2attr_2.iteritems(): self.prediction_space2attr[(key,key2)] = unit2 else: self.prediction_space2attr[(key,)] = unit stat_table_f = open(self.stat_table_fname, 'w') self.prediction_space_output(stat_table_f, self.prediction_space2attr)
def dstruc_loadin(self, curs): """ 03-14-05 remove the distance loading part """ sys.stderr.write("Loading Data STructure...\n") from codense.common import get_known_genes_dict, get_go_no2go_id,\ get_go_no2term_id, get_go_no2depth, get_go_term_id2go_no, \ get_go_term_id2depth self.known_genes_dict = get_known_genes_dict(curs) self.go_no2go_id = get_go_no2go_id(curs) self.go_no2term_id = get_go_no2term_id(curs) self.go_no2depth = get_go_no2depth(curs) self.go_term_id2go_no = get_go_term_id2go_no(curs) self.go_term_id2depth = get_go_term_id2depth(curs) sys.stderr.write("Done\n")
def prepare_gene_no2go_no(self, curs): """ 04-15-05 different from get_gene_no2go_no, the value is a set. 04-27-05 only depth ==5 """ sys.stderr.write("Preparing gene_no2go_no...") #from codense.common import get_gene_no2go_no, get_go_no2depth go_no2depth = get_go_no2depth(curs) gene_no2go_no = get_gene_no2go_no(curs) gene_no2go_no_set = {} for gene_no,go_no_list in gene_no2go_no.iteritems(): gene_no2go_no_set[gene_no] = Set() for go_no in go_no_list: if go_no2depth[go_no] == 5: gene_no2go_no_set[gene_no].add(go_no) sys.stderr.write("Done.\n") return gene_no2go_no_set
def get_gene_no2go_no_list(self, curs, depth=5): """ 04-03-05 get the mapping between gene_no and its associated functions given the depth.(unknown's depth is 2, so all these genes are known genes. the fact is used in _connectivity2homogeneity()) """ from codense.common import get_go_no2depth go_no2depth = get_go_no2depth(curs) if self.debug: print "length of go_no2depth is %s" % len(go_no2depth) # codes below similar to get_gene_no2go_no of codense.common, but different. sys.stderr.write("Getting gene_no2go_no (go_no depth:%s) ..." % depth) gene_no2go_no = {} curs.execute("select gene_no,go_functions from gene") rows = curs.fetchall() for row in rows: go_functions_list = row[1][1:-1].split(",") # don't forget to transform the data type to integer. go_functions_list = map(int, go_functions_list) if self.debug: print "gene is %s" % row[0] print "go_functions_list is %s" % row[1] for go_no in go_functions_list: go_no_depth = go_no2depth.get(go_no) if self.debug: print "go_no %s depth: %s" % (go_no, go_no_depth) raw_input("pause:") if go_no_depth == depth: if row[0] not in gene_no2go_no: gene_no2go_no[row[0]] = [] gene_no2go_no[row[0]].append(go_no) sys.stderr.write("Done\n") return gene_no2go_no
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