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
def run(self):
"""
10-05-05
10-12-05
use max_layer to control whether to turn on the gradient or not
10-16-05
transformed to MPI version
if node_rank==0
--db_connect()
--form_schema_tables()
--form_schema_tables()
--get_gene_no2go_no_set()
--get_mcl_id2accuracy()
elif computing_node:
(prepare data)
elif output_node:
--db_connect()
--form_schema_tables()
--form_schema_tables()
--view_from_table()
--view_from_table()
--view_from_table()
--createGeneTable()
--mpi_synchronize()
if input_node:
--input_node()
--fetch_predictions()
elif computing_node:
--computing_node()
--node_fire()
--gradient_class()
elif output_node:
--output_node()
--output_node_handler()
--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)
old_schema_instance = form_schema_tables(self.input_fname)
new_schema_instance = form_schema_tables(self.jnput_fname)
gene_no2go = get_gene_no2go_no_set(curs)
gene_no2go_pickle = cPickle.dumps(gene_no2go, -1) #-1 means use the highest protocol
if self.max_layer:
crs_sentence = 'DECLARE crs CURSOR FOR SELECT p.p_gene_id, p.gene_no, p.go_no, p.is_correct, p.is_correct_l1, \
p.is_correct_lca, p.avg_p_value, p.no_of_clusters, p.cluster_array, p.p_value_cut_off, p.recurrence_cut_off, \
p.connectivity_cut_off, p.cluster_size_cut_off, p.unknown_cut_off, p.depth_cut_off, p.mcl_id, p.lca_list, \
p.vertex_gradient, p.edge_gradient, p2.vertex_set, p2.edge_set, p2.d_matrix, p2.recurrence_array from %s p, %s p2 where \
p.mcl_id=p2.id'%(old_schema_instance.p_gene_table, old_schema_instance.pattern_table)
else:
crs_sentence = "DECLARE crs CURSOR FOR SELECT p.p_gene_id, p.gene_no, p.go_no, p.is_correct, p.is_correct_l1, \
p.is_correct_lca, p.avg_p_value, p.no_of_clusters, p.cluster_array, p.p_value_cut_off, p.recurrence_cut_off, \
p.connectivity_cut_off, p.cluster_size_cut_off, p.unknown_cut_off, p.depth_cut_off, p.mcl_id, p.lca_list, p.vertex_gradient,\
p.edge_gradient, 'vertex_set', 'edge_set', 'd_matrix', 'recurrence_array' \
from %s p"%(old_schema_instance.p_gene_table)
#some placeholders 'vertex_set', 'edge_set', 'd_matrix' for prediction_attributes()
if self.acc_cut_off:
mcl_id2accuracy = self.get_mcl_id2accuracy(curs, old_schema_instance.p_gene_table, crs_sentence, self.is_correct_type)
else:
mcl_id2accuracy = None
mcl_id2accuracy_pickle = cPickle.dumps(mcl_id2accuracy, -1) #-1 means use the highest protocol
for node in range(1, communicator.size-1): #send it to the computing_node
communicator.send(gene_no2go_pickle, node, 0)
for node in range(1, communicator.size-1): #send it to the computing_node
communicator.send(mcl_id2accuracy_pickle, node, 0)
elif node_rank<=communicator.size-2: #exclude the last node
data, source, tag = communicator.receiveString(0, 0)
gene_no2go = cPickle.loads(data) #take the data
data, source, tag = communicator.receiveString(0, 0)
mcl_id2accuracy = cPickle.loads(data) #take the 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-1:
(conn, curs) = db_connect(self.hostname, self.dbname, self.schema)
old_schema_instance = form_schema_tables(self.input_fname)
new_schema_instance = form_schema_tables(self.jnput_fname)
self.view_from_table(curs, old_schema_instance.splat_table, new_schema_instance.splat_table)
self.view_from_table(curs, old_schema_instance.mcl_table, new_schema_instance.mcl_table)
self.view_from_table(curs, old_schema_instance.pattern_table, new_schema_instance.pattern_table)
self.createGeneTable(curs, new_schema_instance.p_gene_table)
mpi_synchronize(communicator)
if node_rank == 0:
self.input_node(communicator, curs, old_schema_instance, crs_sentence, self.size)
elif node_rank<=communicator.size-2: #exclude the last node
self.computing_node(communicator, gene_no2go, self.exponent, self.score_list, \
self.max_layer, self.norm_exp, self.eg_d_type, mcl_id2accuracy, self.acc_cut_off, functor)
elif node_rank==communicator.size-1:
parameter_list = [curs, new_schema_instance.p_gene_table]
free_computing_nodes = range(1,communicator.size-1)
output_node(communicator, free_computing_nodes, parameter_list, self.output_node_handler)
if self.commit:
curs.execute("end")
