def run(self):
## prepare a log file
fid = open(os.path.join(self.config.log['data'],'createdb.log'),'wa')
writer = csv.writer(fid)
def push_out(line):
writer.writerow([line])
print(line)
push_out(sys.argv[0])
push_out(time.asctime())
push_out("Getting ready to create database...")
## conect to the database
session,engine = db_connect(verbose=False)
Base.metadata.drop_all(engine)
Base.metadata.create_all(engine)
push_out("Creating database with...")
for t in Base.metadata.sorted_tables:
push_out("\t"+t.name)
## determine file sizes
timeStart = time.time()
push_out("determining filesizes...")
idmapCount,geneInfoCount = get_file_sizes()
push_out("extracting taxa list...")
totalAnnotations = get_total_annotations()
push_out("...extraction time: %s"%time.strftime('%H:%M:%S',time.gmtime(time.time()-timeStart)))
## taxa table
push_out("Populating the database taxa table")
timeStr,addedStr = populate_taxon_table(engine)
push_out(timeStr)
push_out(addedStr)
## gene table
push_out("Populating the database with %s genes"%(geneInfoCount))
timeStr,addedStr = populate_gene_table(geneInfoCount,session,engine)
push_out(timeStr)
push_out(addedStr)
## uniprot table
push_out("Populating the database with %s uniprot entries"%(idmapCount))
timeStr,addedStr = populate_uniprot_table(idmapCount,session,engine)
push_out(timeStr)
push_out(addedStr)
## populate the go-terms
push_out("Populating the database with for go terms...")
timeStr,addedStr = populate_go_terms(engine)
push_out(timeStr)
push_out(addedStr)
## populate the go-annotations
push_out("Populating the database with for go annotations...")
timeStr,addedStr,ignored = populate_go_annotations(totalAnnotations,session,engine)
push_out(timeStr)
push_out(addedStr)
push_out("There were %s uniprot annotations ignored"%str(ignored[0]))
push_out("There were %s gene annotations ignored"%str(ignored[1]))
print_db_summary()
fid.close()
http://www.sqlalchemy.org/trac/wiki/UsageRecipes/SchemaDisplay
"""
### make imports
import sys, os, re
from DatabaseTables import Base, Taxon, Gene, Uniprot
from DatabaseTools import db_connect
try:
from sqlalchemy_schemadisplay import create_schema_graph
createGraph = True
except:
createGraph = False
## conect to the database
session, engine = db_connect(verbose=False)
## test the 'Taxon' table
testID = '7227'
query = session.query(Taxon).filter_by(ncbi_id=testID).first()
if query == None:
print "ERROR: init taxon not found."
sys.exit()
if int(query.ncbi_id) != int(testID):
print "ERROR: Bad match to taxon id"
print query.ncbi_id, testID
if query.name != "Drosophila melanogaster":
print "ERROR: Bad match to taxon name"
http://www.sqlalchemy.org/trac/wiki/UsageRecipes/SchemaDisplay
"""
### make imports
import sys,os,re
from DatabaseTables import Base,Taxon,Gene,Uniprot
from DatabaseTools import db_connect
try:
from sqlalchemy_schemadisplay import create_schema_graph
createGraph = True
except:
createGraph = False
## conect to the database
session,engine = db_connect(verbose=False)
## test the 'Taxon' table
testID = '7227'
query = session.query(Taxon).filter_by(ncbi_id=testID).first()
if query == None:
print("ERROR: init taxon not found.")
sys.exit()
if int(query.ncbi_id) != int(testID):
print("ERROR: Bad match to taxon id")
print(query.ncbi_id,testID)
if query.name != "Drosophila melanogaster":
print("ERROR: Bad match to taxon name")
