def cli_main():
log_file = 'stdout' # auto-name the log file
log_level = ''
utils.start_logging(log_file=log_file, log_level='INFO',
verbose=False) # start logging
opts = parse_arguments()
count_silent_mutations(opts)
def run(args):
logname = os.path.basename(__file__) + '.log'
utils.start_logging(filename=logname, level=args.log)
localtime = utils.getCurrentTimeAsAscii()
t0 = time.time()
msg = os.path.basename(__file__) + ' script starts at %s.' % localtime
print msg
logging.info(msg)
connection, cursor = utils.connectToDB(args.dbname, args.dbuser, args.dbpass, args.dbhost, args.dbport)
(returnOk, vertices, minZ, maxZ, avgZ, numpoints) = create_cut_out(cursor, args.las, args.output, args.itemid, args.buffer, args.concave)
if returnOk:
# Create CSV with vertices of footprint
footoutput = args.output + '_footprint.csv'
logging.info('Creating CSV %s with vertices of concave hull of footprint' % footoutput)
fpOutput = open(footoutput, 'w')
for point in vertices:
point.append(str(avgZ))
fpOutput.write(','.join(point) + '\n')
fpOutput.close()
logging.info('#Points: %d' % numpoints)
elapsed_time = time.time() - t0
msg = 'Finished. Total elapsed time: %.02f seconds. See %s' % (elapsed_time, logname)
print(msg)
logging.info(msg)
def run(opts):
# Start logging
logname = os.path.splitext(os.path.basename(__file__))[0] + '.log'
utils.start_logging(filename=logname, level=opts.log)
localtime = utils.getCurrentTimeAsAscii()
t0 = time.time()
msg = os.path.basename(__file__) + ' script starts at %s.' % localtime
print msg
logging.info(msg)
# database connection
connection, cursor = utils.connectToDB(opts.dbname, opts.dbuser,
opts.dbpass, opts.dbhost,
opts.dbport)
if opts.itemid == '?':
utils.listRawDataItems(cursor)
return
elif opts.itemid == '' or opts.itemid == '!':
query = """
SELECT raw_data_item_id,abs_path,background
FROM RAW_DATA_ITEM JOIN ITEM USING (item_id) JOIN RAW_DATA_ITEM_PC USING (raw_data_item_id)
WHERE raw_data_item_id NOT IN (
SELECT raw_data_item_id FROM POTREE_DATA_ITEM_PC)"""
# Get the list of items that are not converted yet (we sort by background to have the background converted first)
raw_data_items, num_raw_data_items = utils.fetchDataFromDB(
cursor, query)
for (rawDataItemId, absPath, isBackground) in raw_data_items:
if opts.itemid == '':
levels = getNumLevels(opts, isBackground)
createPOTree(cursor, rawDataItemId, opts.potreeDir, levels)
else:
m = '\t'.join((str(rawDataItemId), absPath))
print m
logging.info(m)
else:
for rawDataItemId in opts.itemid.split(','):
rows, num_rows = utils.fetchDataFromDB(
cursor,
'SELECT background FROM RAW_DATA_ITEM JOIN ITEM USING (item_id) WHERE raw_data_item_id = %s',
[int(rawDataItemId)])
if num_rows == 0:
logging.error('There is not a raw data item with id %d' %
int(rawDataItemId))
return
isBackground = rows[0][0]
levels = getNumLevels(opts, isBackground)
createPOTree(cursor, int(rawDataItemId), opts.potreeDir, levels)
# close DB connection
utils.closeConnectionDB(connection, cursor)
elapsed_time = time.time() - t0
msg = 'Finished. Total elapsed time: %.02f seconds. See %s' % (
elapsed_time, logname)
print(msg)
logging.info(msg)
def run(args):
logname = os.path.basename(__file__) + '.log'
utils.start_logging(filename=logname, level=args.log)
# connect to the DB
connection, cursor = utils.connectToDB(args.dbname, args.dbuser, args.dbpass, args.dbhost, args.dbport)
itemIds = None
if args.itemid != '':
itemIds = args.itemid.split(',')
utils.listRawDataItems(cursor, itemIds)
def run(args):
# start logging
logname = os.path.splitext(os.path.basename(__file__))[0] + '.log'
utils.start_logging(filename=logname, level=utils.DEFAULT_LOG_LEVEL)
localtime = utils.getCurrentTimeAsAscii()
t0 = time.time()
msg = os.path.basename(__file__) + ' script starts at %s.' %localtime
print msg
logging.info(msg)
# connect to the DB
connection, cursor = utils.connectToDB(args.dbname, args.dbuser, args.dbpass, args.dbhost, args.dbport)
itemIds = []
if args.itemid == '':
data,num = utils.fetchDataFromDB(cursor, 'SELECT item_id FROM ITEM WHERE NOT background')
for (itemId,) in data:
itemIds.append(itemId)
else:
itemIds = args.itemid.split(',')
# close the conection to the DB
utils.closeConnectionDB(connection, cursor)
# Create queues
itemsQueue = multiprocessing.Queue() # The queue of tasks (queries)
resultsQueue = multiprocessing.Queue() # The queue of results
for itemId in itemIds:
itemsQueue.put(int(itemId))
for i in range(args.cores): #we add as many None jobs as numUsers to tell them to terminate (queue is FIFO)
itemsQueue.put(None)
procs = []
# We start numUsers users processes
for i in range(args.cores):
procs.append(multiprocessing.Process(target=runChild,
args=(i, itemsQueue, resultsQueue, args.las, args.dbname, args.dbuser, args.dbpass, args.dbhost, args.dbport)))
procs[-1].start()
for i in range(len(itemIds)):
[procIndex, itemId] = resultsQueue.get()
# wait for all users to finish their execution
for i in range(args.cores):
procs[i].join()
# measure elapsed time
elapsed_time = time.time() - t0
msg = 'Finished. Total elapsed time: %.02f seconds. See %s' % (elapsed_time, logname)
print(msg)
logging.info(msg)
def run(opts):
# Start logging
#logname = os.path.basename(__file__) + '.log'
logname = os.path.splitext(os.path.basename(__file__))[0] + '.log'
utils.start_logging(filename=logname, level=opts.log)
localtime = utils.getCurrentTimeAsAscii()
t0 = time.time()
msg = os.path.basename(__file__) + ' script starts at %s.' % localtime
print msg
logging.info(msg)
# database connection
connection, cursor = utils.connectToDB(opts.dbname, opts.dbuser,
opts.dbpass, opts.dbhost,
opts.dbport)
if opts.itemid == '?':
utils.listRawDataItems(cursor)
return
elif opts.itemid == '' or opts.itemid == '!':
query = """
SELECT raw_data_item_id, abs_path
FROM RAW_DATA_ITEM JOIN ITEM USING (item_id)
WHERE NOT background AND raw_data_item_id NOT IN (
SELECT raw_data_item_id FROM OSG_DATA_ITEM_PC_SITE
UNION
SELECT raw_data_item_id FROM OSG_DATA_ITEM_MESH
UNION
SELECT raw_data_item_id FROM OSG_DATA_ITEM_PICTURE)"""
# Get the list of items that are not converted yet (we sort by background to have the background converted first)
raw_data_items, num_raw_data_items = utils.fetchDataFromDB(
cursor, query)
for (rawDataItemId, absPath) in raw_data_items:
if opts.itemid == '':
createOSG(cursor, rawDataItemId, opts.osgDir)
else:
m = '\t'.join((str(rawDataItemId), absPath))
print m
logging.info(m)
else:
for rawDataItemId in opts.itemid.split(','):
createOSG(cursor, int(rawDataItemId), opts.osgDir)
# close DB connection
utils.closeConnectionDB(connection, cursor)
elapsed_time = time.time() - t0
msg = 'Finished. Total elapsed time: %.02f seconds. See %s' % (
elapsed_time, logname)
print(msg)
logging.info(msg)
def run(opts):
# Start logging
logname = os.path.splitext(os.path.basename(__file__))[0] + '.log'
utils.start_logging(filename=logname, level=opts.log)
localtime = utils.getCurrentTimeAsAscii()
t0 = time.time()
msg = os.path.basename(__file__) + ' script starts at %s.' % localtime
print msg
logging.info(msg)
# database connection
connection, cursor = utils.connectToDB(opts.dbname, opts.dbuser,
opts.dbpass, opts.dbhost,
opts.dbport)
if opts.itemid == '?':
utils.listRawDataItems(cursor)
return
elif opts.itemid == '' or opts.itemid == '!':
query = """
SELECT raw_data_item_id,abs_path,background
FROM RAW_DATA_ITEM JOIN ITEM USING (item_id) JOIN RAW_DATA_ITEM_PC USING (raw_data_item_id)
WHERE raw_data_item_id NOT IN (
SELECT raw_data_item_id FROM POTREE_DATA_ITEM_PC)"""
# Get the list of items that are not converted yet (we sort by background to have the background converted first)
raw_data_items, num_raw_data_items = utils.fetchDataFromDB(cursor, query)
for (rawDataItemId,absPath,isBackground) in raw_data_items:
if opts.itemid == '' :
levels = getNumLevels(opts, isBackground)
createPOTree(cursor, rawDataItemId, opts.potreeDir, levels)
else:
m = '\t'.join((str(rawDataItemId),absPath))
print m
logging.info(m)
else:
for rawDataItemId in opts.itemid.split(','):
rows,num_rows = utils.fetchDataFromDB(cursor, 'SELECT background FROM RAW_DATA_ITEM JOIN ITEM USING (item_id) WHERE raw_data_item_id = %s', [int(rawDataItemId)])
if num_rows == 0:
logging.error('There is not a raw data item with id %d' % int(rawDataItemId))
return
isBackground = rows[0][0]
levels = getNumLevels(opts, isBackground)
createPOTree(cursor, int(rawDataItemId), opts.potreeDir, levels)
# close DB connection
utils.closeConnectionDB(connection, cursor)
elapsed_time = time.time() - t0
msg = 'Finished. Total elapsed time: %.02f seconds. See %s' % (elapsed_time, logname)
print(msg)
logging.info(msg)
def run(args):
logname = os.path.basename(__file__) + '.log'
utils.start_logging(filename=logname, level=args.log)
# connect to the DB
connection, cursor = utils.connectToDB(args.dbname, args.dbuser,
args.dbpass, args.dbhost,
args.dbport)
itemIds = None
if args.itemid != '':
itemIds = args.itemid.split(',')
utils.listRawDataItems(cursor, itemIds)
def main():
parser = argparse.ArgumentParser(description='Migrate from Melange to Quark.') # noqa
parser.add_argument('-v', '--verbose', action='store_true', default=False,
help='Log to stdout and to file.', dest='verbose')
parser.add_argument('-c', '--clear', action='store_true', default=False,
help='Clear logs before running.', dest='clearlogs')
arguments = parser.parse_args()
start_logging(verbose=arguments.verbose)
if arguments.clearlogs:
clear_logs()
melange_session = loadSession(melange.engine)
neutron_session = loadSession(neutron.engine)
migration = Obligator(melange_session, neutron_session)
migration.migrate()
def run(opts):
# Start logging
#logname = os.path.basename(__file__) + '.log'
logname = os.path.splitext(os.path.basename(__file__))[0] + '.log'
utils.start_logging(filename=logname, level=opts.log)
localtime = utils.getCurrentTimeAsAscii()
t0 = time.time()
msg = os.path.basename(__file__) + ' script starts at %s.' % localtime
print msg
logging.info(msg)
# database connection
connection, cursor = utils.connectToDB(opts.dbname, opts.dbuser,
opts.dbpass, opts.dbhost,
opts.dbport)
if opts.itemid == '?':
utils.listRawDataItems(cursor)
return
elif opts.itemid == '' or opts.itemid == '!':
query = """
SELECT raw_data_item_id, abs_path
FROM RAW_DATA_ITEM JOIN ITEM USING (item_id)
WHERE NOT background AND raw_data_item_id NOT IN (
SELECT raw_data_item_id FROM OSG_DATA_ITEM_PC_SITE
UNION
SELECT raw_data_item_id FROM OSG_DATA_ITEM_MESH
UNION
SELECT raw_data_item_id FROM OSG_DATA_ITEM_PICTURE)"""
# Get the list of items that are not converted yet (we sort by background to have the background converted first)
raw_data_items, num_raw_data_items = utils.fetchDataFromDB(cursor, query)
for (rawDataItemId, absPath) in raw_data_items:
if opts.itemid == '':
createOSG(cursor, rawDataItemId, opts.osgDir)
else:
m = '\t'.join((str(rawDataItemId),absPath))
print m
logging.info(m)
else:
for rawDataItemId in opts.itemid.split(','):
createOSG(cursor, int(rawDataItemId), opts.osgDir)
# close DB connection
utils.closeConnectionDB(connection, cursor)
elapsed_time = time.time() - t0
msg = 'Finished. Total elapsed time: %.02f seconds. See %s' % (elapsed_time, logname)
print(msg)
logging.info(msg)
def run(opts):
# set logging level
global logger
#logname = os.path.basename(__file__) + '.log'
logname = os.path.splitext(os.path.basename(__file__))[0] + '.log'
logger = utils.start_logging(filename=logname, level=opts.log)
localtime = utils.getCurrentTimeAsAscii()
t0 = time.time()
msg = os.path.basename(__file__) + ' script starts at %s.' % localtime
print msg
logger.info(msg)
opts.file = opts.file.rstrip('/')
# check if all required options are specified
check_required_options(opts)
# check if the required directory structure exists
check_directory_structure(opts.data)
# check input data
check_input_data(opts)
# define target directory
TARGETDIR = define_create_target_dir(opts)
# copy the data to the target directory
copy_data(opts, TARGETDIR)
elapsed_time = time.time() - t0
msg = 'Finished. Total elapsed time: %.02f seconds. See %s' % (
elapsed_time, logname)
print(msg)
logger.info(msg)
def run(opts):
# set logging level
global logger
#logname = os.path.basename(__file__) + '.log'
logname = os.path.splitext(os.path.basename(__file__))[0] + '.log'
logger = utils.start_logging(filename=logname, level=opts.log)
localtime = utils.getCurrentTimeAsAscii()
t0 = time.time()
msg = os.path.basename(__file__) + ' script starts at %s.' % localtime
print msg
logger.info(msg)
opts.file = opts.file.rstrip('/')
# check if all required options are specified
check_required_options(opts)
# check if the required directory structure exists
check_directory_structure(opts.data)
# check input data
check_input_data(opts)
# define target directory
TARGETDIR = define_create_target_dir(opts)
# copy the data to the target directory
copy_data(opts, TARGETDIR)
elapsed_time = time.time() - t0
msg = 'Finished. Total elapsed time: %.02f seconds. See %s' % (elapsed_time, logname)
print(msg)
logger.info(msg)
def run(opts):
# Set logging
#logname = os.path.splitext(os.path.basename(opts.sql))[0] + '.log'
logname = os.path.basename(opts.sql) + '.log'
utils.start_logging(filename=logname, level=opts.log)
localtime = utils.getCurrentTimeAsAscii()
t0 = time.time()
msg = os.path.basename(__file__) + ' script starts at %s.' %localtime
print msg
logging.info(msg)
os.system('createdb ' + utils.postgresConnectString(opts.dbname, opts.dbuser, opts.dbpass, opts.dbhost, opts.dbport, True))
connection, cursor = utils.connectToDB(opts.dbname, opts.dbuser, opts.dbpass, opts.dbhost, opts.dbport)
msg = 'Adding PostGIS extension'
logging.info(msg)
#print msg
cursor.execute("CREATE EXTENSION POSTGIS")
connection.commit()
success_loading = utils.load_sql_file(cursor, opts.sql)
msg = 'Granting relevant permissions'
logging.info(msg)
#print msg
if success_loading:
cursor.execute("select tablename from pg_tables where schemaname = 'public'")
tablesNames = cursor.fetchall()
for (tableName,) in tablesNames:
cursor.execute('GRANT SELECT ON ' + tableName + ' TO public')
for tableName in ('ITEM', 'ITEM_OBJECT', 'OSG_LOCATION', 'OSG_LABEL', 'OSG_CAMERA', 'OSG_ITEM_CAMERA', 'OSG_ITEM_OBJECT'):
cursor.execute( 'GRANT SELECT,INSERT,UPDATE,DELETE ON ' + tableName + ' TO public')
connection.commit()
connection.close()
msg = 'Finished. Total elapsed time %.02f seconds. See %s' % ((time.time() - t0), logname)
logging.info(msg)
print msg
def __init__(self):
results = self._cli_parser()
global logger
logger = utils.start_logging(os.path.join(os.path.expanduser("~"),
'wrfpy.log'))
if results['init']:
self._create_directory_structure(results['suitename'],
results['basedir'])
elif results['create']:
self._create_cylc_config(results['suitename'],
results['basedir'])
def main():
parser = argparse.ArgumentParser(
description='Migrate from Melange to Quark.') # noqa
parser.add_argument('-v',
'--verbose',
action='store_true',
default=False,
help='Log to stdout and to file.',
dest='verbose')
parser.add_argument('-c',
'--clear',
action='store_true',
default=False,
help='Clear logs before running.',
dest='clearlogs')
arguments = parser.parse_args()
start_logging(verbose=arguments.verbose)
if arguments.clearlogs:
clear_logs()
melange_session = loadSession(melange.engine)
neutron_session = loadSession(neutron.engine)
migration = Obligator(melange_session, neutron_session)
migration.migrate()
def main(argv=None):
if not argv:
argv = sys.argv[1:]
parser = argparse.ArgumentParser(description='Run bot to maintain issues.')
parser.add_argument('--config', action="store", help='Configuration file')
parser.add_argument('--logging-config',
action="store",
help='Logging configuration file')
parser.add_argument('--user', action="store", help='Github user')
parser.add_argument('--token', action="store", help='Github token')
parser.add_argument('--repo', action="store", help='Repository')
parser.add_argument('--label',
action="store",
help='Add this label to issues when closing')
parser.add_argument(
'--test',
action="store_true",
help='Print actions that would be taken but do not modify repository')
args = parser.parse_args(argv)
config = get_config(args.config)
if args.user:
config["user"] = args.user
if args.token:
config["token"] = args.token
if args.repo:
config["repo"] = args.repo
if args.logging_config:
config["logging-config"] = args.logging_config
if args.test:
config["test"] = True
if args.label:
config["label"] = args.label
if "label" not in config:
config["label"] = None
start_logging(config)
process_issues(config)
def __init__(self, input_dir, dest_dir):
global logger
logger = utils.start_logging('translate.log') # create log file
self.input_dir = input_dir
self.dest_dir = dest_dir
self.database = 'translate.db' # hardcode database name for now
try:
with open(self.database) as file:
pass # file exists and is readable, nothing else to do
except IOError as e:
# file does not exist OR no read permissions
# create database if not existing
self._create_database()
# read yandex api key from file
self._read_yandex_api_key('yandex_key') # TODO: hardcode for now
self._yandex_connect(self.api_key)
def main():
pymysql.install_as_MySQLdb()
logger, start_time = start_logging('update_db_from_jira')
try:
mode = "prod"
Session, engine = create_db_session(mode)
session = Session()
jira_data_by_pr = JiraDataByProject(logger, session)
project_data_mp = jira_data_by_pr.get_web_mp_data("DBIOSCA")
project_data_web = jira_data_by_pr.get_web_mp_data("DBSBOLW")
project_data_ufs = jira_data_by_pr.get_ufs_data("LINEUP")
release_db = UpdateReleaseDB(logger, session)
release_db.update_mp_web_db(project_data_mp)
release_db.update_mp_web_db(project_data_web)
release_db.update_ufs_db(project_data_ufs)
except Exception as ex:
print(ex)
finally:
update_time = datetime.datetime.now().replace(
microsecond=0) - start_time
logger.info(f"End of DB updating. Update time: {str(update_time)}")
session.close()
def __init__(self, wrfpy_config=False):
global logger
wrfpy_dir = os.environ['HOME']
logger = utils.start_logging(os.path.join(wrfpy_dir, 'wrfpy.log'))
if not wrfpy_config:
try:
# get CYLC_SUITE_DEF_PATH environment variable
wrfpy_dir = os.environ['CYLC_SUITE_DEF_PATH']
except KeyError:
# default back to user home dir in case CYLC is not used
wrfpy_dir = os.environ['HOME']
# config.json needs to be in base of wrfpy_dir
self.configfile = os.path.join(wrfpy_dir, 'config.json')
else:
self.configfile = wrfpy_config
try:
logger.debug('Checking if configuration file exists: %s' %self.configfile)
utils.check_file_exists(self.configfile)
except IOError:
# create config file
self._create_empty_config()
# TODO: exit and notify user to manually edit config file
# read json config file
self._read_json()
def run(args):
# set logging level
global logger
global connection
global cursor
logname = os.path.basename(__file__) + '.log'
logger = utils.start_logging(filename=logname, level=args.log)
localtime = utils.getCurrentTimeAsAscii()
msg = os.path.basename(__file__) + ' script starts at %s.' % localtime
print msg
logger.info(msg)
# start timer
t0 = time.time()
# connect to the DB
connection, cursor = utils.connectToDB(args.dbname, args.dbuser,
args.dbpass, args.dbhost,
args.dbport)
if args.itemid == '?':
utils.listRawDataItems(cursor)
return
else:
for rawDataItemId in args.itemid.split(','):
# fetch the abs_path
abs_paths = fetch_abs_path(rawDataItemId)
msg = 'Abs path fetched: %s' % abs_paths
print msg
logger.info(msg)
# fetch the potree abs_paths
abs_potree_paths, num_potree = fetch_potree_abs_paths(
rawDataItemId)
msg = '%s abs potree paths fetched %s' % (num_potree,
abs_potree_paths)
print msg
logger.info(msg)
# fetch the nexus abs_paths
abs_nexus_paths, num_nexus = fetch_nexus_abs_paths(rawDataItemId)
msg = '%s abs nexus paths fetched %s' % (num_nexus,
abs_nexus_paths)
print msg
logger.info(msg)
# fetch the OSG abs_paths PC
abs_osg_pc_paths, num_osg_pc = fetch_osg_abs_paths_pc(
rawDataItemId)
msg = '%s abs OSG paths for PC fetched: %s' % (num_osg_pc,
abs_osg_pc_paths)
print msg
logger.info(msg)
# fetch the OSG abs_paths mesh
abs_osg_mesh_paths, num_osg_mesh = fetch_osg_abs_paths_mesh(
rawDataItemId)
msg = '%s abs OSG paths for meshes fetched: %s' % (
num_osg_mesh, abs_osg_mesh_paths)
print msg
logger.info(msg)
# fetch the OSG abs_paths picture
abs_osg_picture_paths, num_osg_picture = fetch_osg_abs_paths_picture(
rawDataItemId)
msg = '%s abs OSG paths for pictures fetched: %s' % (
num_osg_picture, abs_osg_picture_paths)
print msg
logger.info(msg)
# fetch the OSG abs_paths PC BG
abs_osg_pc_bg_paths, num_osg_pc_bg = fetch_osg_abs_paths_pc_bg(
rawDataItemId)
msg = '%s abs OSG paths for PC BG fetched: %s' % (
num_osg_pc_bg, abs_osg_pc_bg_paths)
print msg
logger.info(msg)
# remove the files related to the above absolute paths
for abs_paths_to_remove in (abs_paths, abs_potree_paths,
abs_nexus_paths, abs_osg_pc_paths,
abs_osg_mesh_paths,
abs_osg_picture_paths,
abs_osg_pc_bg_paths):
remove_data(abs_paths_to_remove)
msg = 'Removed data locations related to raw data item %s (%s)!' % (
rawDataItemId, abs_paths[0])
print msg
logger.info(msg)
# measure elapsed time
elapsed_time = time.time() - t0
msg = 'Finished. Total elapsed time: %.02f seconds. See %s' % (
elapsed_time, logname)
print(msg)
logger.info(msg)
def run(opts):
global logger
# Define logger and start logging
#logname = os.path.basename(opts.output) + '.log'
logname = os.path.splitext(os.path.basename(__file__))[0] + '.log'
logger = utils.start_logging(filename=logname, level=opts.log)
localtime = utils.getCurrentTimeAsAscii()
t0 = time.time()
msg = os.path.basename(__file__) + ' script starts at %s.' % localtime
print msg
logger.info(msg)
if not opts.output.endswith(".conf.xml"):
logger.error('The output file must end with .conf.xml')
raise IOError('The output file must end with .conf.xml')
# Create python postgres connection
global cursor
connection, cursor = utils.connectToDB(opts.dbname, opts.dbuser,
opts.dbpass, opts.dbhost,
opts.dbport)
# Check that provided background is in DB
query = """
SELECT OSG_DATA_ITEM_PC_BACKGROUND.abs_path,srid
FROM OSG_DATA_ITEM_PC_BACKGROUND JOIN RAW_DATA_ITEM USING (raw_data_item_id)"""
rows, num_rows = utils.fetchDataFromDB(cursor, query)
backGroundAbsPath = None
backgroundSRID = None
for (bgAbsPath, bgSRID) in rows:
if opts.background == os.path.basename(bgAbsPath):
backGroundAbsPath = bgAbsPath
backgroundSRID = bgSRID
if backGroundAbsPath == None:
errorMsg = 'Background ' + opts.background + ' is not found'
logger.error(errorMsg)
raise Exception(errorMsg)
# Get the root object: the OSG configuration
rootObject = viewer_conf_api.osgRCconfiguration()
# set version
rootObject.set_version("0.2")
# Add all the different XML of the active objects
# (we add distinct since the boundings will share XMLs)
query = """
SELECT DISTINCT xml_abs_path
FROM OSG_DATA_ITEM ORDER BY xml_abs_path"""
rows, num_rows = utils.fetchDataFromDB(cursor, query)
for (xmlPath, ) in rows:
if xmlPath.count(opts.osg) == 0:
logger.error('Mismatch between given OSG data directory ' +
'and DB content')
rootObject.add_objectLibrary(
viewer_conf_api.objectLibrary(
url=os.path.relpath(xmlPath, opts.osg)))
# Add the object library with the boundings
rootObject.add_objectLibrary(
viewer_conf_api.objectLibrary(url=utils.BOUNDINGS_XML_RELATIVE))
# Add the cameras that are in the DB
cameras = viewer_conf_api.cameras()
query = """
SELECT osg_camera_name, srid, x, y, z, h, p, r
FROM OSG_CAMERA JOIN OSG_LOCATION USING (osg_location_id)"""
rows, num_rows = utils.fetchDataFromDB(cursor, query)
for (name, srid, x, y, z, h, p, r) in rows:
if (srid is not None) and (srid == bgSRID):
x, y, z = getOSGPosition(x, y, z, srid)
else:
x, y, z = getOSGPosition(x, y, z)
cameras.add_camera(
viewer_conf_api.camera(name=name, x=x, y=y, z=z, h=h, p=p, r=r))
# Add Default cameras for the items that have no camera in the DB
query = """
SELECT
item_id, ST_SRID(geom), st_x(st_centroid(geom)), st_y(st_centroid(geom)), min_z + ((max_z - min_z) / 2)
FROM ITEM WHERE NOT background AND geom IS NOT null AND item_id NOT IN (
SELECT DISTINCT item_id FROM OSG_ITEM_CAMERA
) ORDER BY item_id"""
rows, numitems = utils.fetchDataFromDB(cursor, query)
for (itemId, srid, x, y, z) in rows:
# only call getOSGPosition if [x,y,z] are not None
# should item_id = -1 be added?
if all(position is not None for position in [x, y, z]) and itemId > 0:
if (srid is not None) and (srid == bgSRID):
x, y, z = getOSGPosition(x, y, z, srid)
else:
x, y, z = getOSGPosition(x, y, z)
cameras.add_camera(
viewer_conf_api.camera(name=utils.DEFAULT_CAMERA_PREFIX +
str(itemId),
x=x,
y=y,
z=z))
rootObject.set_cameras(cameras)
# Add the XML content of the preferences
rootObject.set_preferences(viewer_conf_api.parseString(DEFAULT_PREFENCES))
attributes = viewer_conf_api.attributes()
# Use generic method to fill all properties.
# We need the name in the XML, the column name in the DB and
# the table name in the DB
for property in utils.ATTRIBUTES_ORDER:
(cName, tName) = utils.ATTRIBUTES[property]
elements = getattr(viewer_conf_api, property + 's')()
# We need to call the columns and tables with extra "" because
# they were created from the Access DB
# utils.dbExecute(cursor, 'SELECT "' + cName + '" FROM "' + tName + '"')
utils.dbExecute(cursor, 'SELECT ' + cName + ' FROM ' + tName)
for (element, ) in cursor:
getattr(elements,
'add_' + property)(getattr(viewer_conf_api,
property)(name=element))
getattr(attributes, 'set_' + property + 's')(elements)
rootObject.set_attributes(attributes)
# Add all the static objects, i.e. the OSG from the background
# Add the static object for the background
staticObjects = viewer_conf_api.staticObjects()
staticObjects.add_staticObject(
viewer_conf_api.staticObject(url=os.path.relpath(
glob.glob(backGroundAbsPath + '/' + utils.OSG_DATA_PREFIX +
'.osgb')[0], opts.osg)))
# Add hardcode DOME
staticObjects.add_staticObject(
viewer_conf_api.staticObject(url=utils.DOMES_OSG_RELATIVE))
rootObject.set_staticObjects(staticObjects)
# Add the 5 different layers of active objects
activeObjects = viewer_conf_api.activeObjects()
# First we add points, meshes and pcitures which are related to
# the active_objects_sites
layersData = [('points', 'OSG_DATA_ITEM_PC_SITE', utils.AO_TYPE_PC),
('photos', 'OSG_DATA_ITEM_PICTURE', utils.AO_TYPE_PIC),
('meshes', 'OSG_DATA_ITEM_MESH', utils.AO_TYPE_MESH)]
for (layerName, tableName, inType) in layersData:
layer = viewer_conf_api.layer(name=layerName)
query = """
SELECT item_id, raw_data_item_id, OSG_LOCATION.srid, x, y, z, xs, ys, zs, h, p, r, cast_shadow
FROM """ + tableName + """ JOIN OSG_DATA_ITEM USING (osg_data_item_id)
JOIN OSG_LOCATION USING (osg_location_id)
JOIN RAW_DATA_ITEM USING (raw_data_item_id)
ORDER BY item_id"""
rows, numitems = utils.fetchDataFromDB(cursor, query)
for (itemId, rawDataItemId, srid, x, y, z, xs, ys, zs, h, p, r,
castShadow) in rows:
# only call getOSGPosition if [x,y,z] are not None
if all(position is not None for position in [x, y, z]):
if (srid is not None) and (srid == bgSRID):
x, y, z = getOSGPosition(x, y, z, srid)
else:
x, y, z = getOSGPosition(x, y, z)
uniqueName = utils.codeOSGActiveObjectUniqueName(
cursor, inType, rawDataItemId)
activeObject = viewer_conf_api.activeObject(prototype=uniqueName,
uniqueName=uniqueName)
setting = viewer_conf_api.setting(
x=x,
y=y,
z=z,
xs=xs,
ys=ys,
zs=zs,
h=h,
p=p,
r=r,
castShadow=(1 if castShadow else 0))
activeObject.set_setting(setting)
layer.add_activeObject(activeObject)
activeObjects.add_layer(layer)
# Add the boundings
layer = viewer_conf_api.layer(name='boundings')
# We first add the boundings that are currently in the DB
query = """
SELECT item_id, object_number, x, y, z, xs, ys, zs, h, p, r, OSG_LOCATION.cast_shadow, srid
FROM OSG_ITEM_OBJECT JOIN OSG_LOCATION USING (osg_location_id)
ORDER BY item_id,object_number"""
osgItemObjects, numOsgItemObjects = utils.fetchDataFromDB(cursor, query)
# osgItemObjects is (itemId, objectNumber, x, y, z, xs, ys, zs, h, p, r, castShadow, srid)
# Now we add Default OSG data items for the objects that are not in OSG_ITEM_OBJECT table
query = """
SELECT item_id,object_number
FROM item_object
WHERE (item_id,object_number) NOT IN (SELECT item_id,object_number FROM OSG_ITEM_OBJECT)
ORDER BY item_id,object_number"""
objects, num_objects = utils.fetchDataFromDB(cursor, query)
for (itemId, objectNumber) in objects:
srid = None
(x, y, z) = (0, 0, 0)
(xs, ys, zs) = (1, 1, 1)
query = """
SELECT ST_SRID(geom), st_x(st_centroid(geom)), st_y(st_centroid(geom)), min_z + ((max_z - min_z) / 2),
st_xmax(geom)-st_xmin(geom) as dx, st_ymax(geom)-st_ymin(geom) as dy, (max_z - min_z) as dz
FROM ITEM
WHERE item_id = %s and geom is not %s"""
queryArgs = [itemId, None]
footprints, num_footprints = utils.fetchDataFromDB(
cursor, query, queryArgs)
if num_footprints:
(srid, x, y, z, xs, ys, zs) = footprints[0]
if xs == 0: xs = 1
if ys == 0: ys = 1
if zs == 0: zs = 1
osgItemObjects.append(
[itemId, objectNumber, x, y, z, xs, ys, zs, 0, 0, 0, False, srid])
# Now let's add them to the XML
for (itemId, objectNumber, x, y, z, xs, ys, zs, h, p, r, castShadow,
srid) in osgItemObjects:
# only call getOSGPosition if [x,y,z] are not None
if all(position is not None for position in [x, y, z]) and itemId > 0:
if (srid is not None) and (srid == bgSRID):
x, y, z = getOSGPosition(x, y, z, srid)
else:
x, y, z = getOSGPosition(x, y, z)
uniqueName = utils.codeOSGActiveObjectUniqueName(
cursor,
utils.AO_TYPE_OBJ,
itemId=itemId,
objectId=objectNumber)
proto = "Bounding Box"
activeObject = viewer_conf_api.activeObject(prototype=proto,
uniqueName=uniqueName)
setting = viewer_conf_api.setting(
x=x,
y=y,
z=z,
xs=xs,
ys=ys,
zs=zs,
h=h,
p=p,
r=r,
castShadow=(1 if castShadow else 0))
activeObject.set_setting(setting)
layer.add_activeObject(activeObject)
activeObjects.add_layer(layer)
# Add the labels
layer = viewer_conf_api.layer(name='labels')
utils.dbExecute(
cursor, 'SELECT osg_label_name, text, red, green, blue, ' +
'rotate_screen, outline, font, srid, x, y, z, xs, ys, zs, h, ' +
'p, r, cast_shadow FROM OSG_LABEL INNER JOIN ' +
'OSG_LOCATION ON OSG_LABEL.osg_location_id=' +
'OSG_LOCATION.osg_location_id')
rows = cursor.fetchall()
for (name, text, red, green, blue, rotatescreen, outline, font, srid, x, y,
z, xs, ys, zs, h, p, r, castShadow) in rows:
proto = "labelPrototype"
uniqueName = utils.codeOSGActiveObjectUniqueName(cursor,
utils.AO_TYPE_LAB,
labelName=name)
if (srid is not None) and (srid == bgSRID):
x, y, z = getOSGPosition(x, y, z, srid)
else:
x, y, z = getOSGPosition(x, y, z)
activeObject = viewer_conf_api.activeObject(
prototype=proto,
uniqueName=uniqueName,
labelText=text,
labelColorRed=red,
labelColorGreen=green,
labelColorBlue=blue,
labelRotateScreen=rotatescreen,
outline=outline,
Font=font)
setting = viewer_conf_api.setting(x=x,
y=y,
z=z,
xs=xs,
ys=ys,
zs=zs,
h=h,
p=p,
r=r,
castShadow=(1 if castShadow else 0))
activeObject.set_setting(setting)
layer.add_activeObject(activeObject)
activeObjects.add_layer(layer)
rootObject.set_activeObjects(activeObjects)
# Create the XML
rootObject.export(open(opts.output, 'w'), 0)
elapsed_time = time.time() - t0
msg = 'Finished. Total elapsed time: %.02f seconds. See %s' % (
elapsed_time, logname)
print(msg)
logger.info(msg)
def run(args):
# set logging level
global logger
global connection
global cursor
logname = os.path.basename(__file__) + '.log'
logger = utils.start_logging(filename=logname, level=args.log)
localtime = utils.getCurrentTimeAsAscii()
msg = os.path.basename(__file__) + ' script starts at %s.' % localtime
print msg
logger.info(msg)
# start timer
t0 = time.time()
# connect to the DB
connection, cursor = utils.connectToDB(args.dbname, args.dbuser, args.dbpass, args.dbhost, args.dbport)
if args.itemid == '?':
utils.listRawDataItems(cursor)
return
else:
for rawDataItemId in args.itemid.split(','):
# fetch the abs_path
abs_paths = fetch_abs_path(rawDataItemId)
msg = 'Abs path fetched: %s' % abs_paths
print msg
logger.info(msg)
# fetch the potree abs_paths
abs_potree_paths, num_potree = fetch_potree_abs_paths(rawDataItemId)
msg = '%s abs potree paths fetched %s' %(num_potree, abs_potree_paths)
print msg
logger.info(msg)
# fetch the nexus abs_paths
abs_nexus_paths, num_nexus = fetch_nexus_abs_paths(rawDataItemId)
msg = '%s abs nexus paths fetched %s' %(num_nexus, abs_nexus_paths)
print msg
logger.info(msg)
# fetch the OSG abs_paths PC
abs_osg_pc_paths, num_osg_pc = fetch_osg_abs_paths_pc(rawDataItemId)
msg = '%s abs OSG paths for PC fetched: %s' %(num_osg_pc, abs_osg_pc_paths)
print msg
logger.info(msg)
# fetch the OSG abs_paths mesh
abs_osg_mesh_paths, num_osg_mesh = fetch_osg_abs_paths_mesh(rawDataItemId)
msg = '%s abs OSG paths for meshes fetched: %s' %(num_osg_mesh, abs_osg_mesh_paths)
print msg
logger.info(msg)
# fetch the OSG abs_paths picture
abs_osg_picture_paths, num_osg_picture = fetch_osg_abs_paths_picture(rawDataItemId)
msg = '%s abs OSG paths for pictures fetched: %s' %(num_osg_picture, abs_osg_picture_paths)
print msg
logger.info(msg)
# fetch the OSG abs_paths PC BG
abs_osg_pc_bg_paths, num_osg_pc_bg = fetch_osg_abs_paths_pc_bg(rawDataItemId)
msg = '%s abs OSG paths for PC BG fetched: %s' %(num_osg_pc_bg, abs_osg_pc_bg_paths)
print msg
logger.info(msg)
# remove the files related to the above absolute paths
for abs_paths_to_remove in (abs_paths, abs_potree_paths, abs_nexus_paths, abs_osg_pc_paths, abs_osg_mesh_paths, abs_osg_picture_paths, abs_osg_pc_bg_paths):
remove_data(abs_paths_to_remove)
msg = 'Removed data locations related to raw data item %s (%s)!' % (rawDataItemId, abs_paths[0])
print msg
logger.info(msg)
# measure elapsed time
elapsed_time = time.time() - t0
msg = 'Finished. Total elapsed time: %.02f seconds. See %s' % (elapsed_time, logname)
print(msg)
logger.info(msg)
def run(args):
global logger
global offsetX
global offsetY
global offsetZ
logname = os.path.basename(args.output) + '.log'
logger = utils.start_logging(filename=logname, level=args.log)
# start logging
localtime = utils.getCurrentTimeAsAscii()
msg = __file__ + ' script logging start at %s' % localtime
print msg
logger.info(msg)
t0 = time.time()
# connect to DB and get a cursor
connection, cursor = utils.connectToDB(args.dbname, args.dbuser,
args.dbpass, args.dbhost)
# We assume the osg location is relative
# We need to make it absolute by adding the offset of the background with srid as provided
query = """
SELECT C.offset_x, C.offset_y, C.offset_z
FROM raw_data_item A, raw_data_item_pc B, osg_data_item_pc_background C
WHERE A.raw_data_item_id = B.raw_data_item_id AND
B.raw_data_item_id = C.raw_data_item_id AND
A.srid = %s"""
queryArgs = [
args.srid,
]
backgroundOffsets, num_backgrounds = utils.fetchDataFromDB(
cursor, query, queryArgs)
if num_backgrounds:
(offsetX, offsetY, offsetZ) = backgroundOffsets[0]
# get all items
query = 'SELECT item_id, ST_ASGEOJSON(geom), min_z, max_z FROM item WHERE NOT background ORDER BY item_id'
sites, num_sites = utils.fetchDataFromDB(cursor, query)
data = []
for (itemId, itemGeom, minz, maxz) in sites:
# Generate the JSON data for this item
dataSite = {}
dataSite["id"] = itemId
if itemGeom != None:
dataSite["footprint"] = json.loads(itemGeom)['coordinates']
dataSite["footprint_altitude"] = [minz, maxz]
addThumbnail(cursor, itemId, dataSite)
addSiteMetaData(cursor, itemId, dataSite)
addPointCloud(cursor, itemId, dataSite, args.srid)
addMeshes(cursor, itemId, dataSite, args.srid)
addObjectsMetaData(cursor, itemId, dataSite, args.srid)
data.append(dataSite)
# close the Db connection
utils.closeConnectionDB(connection, cursor)
# save the data into JSON file
save2JSON(args.output, data)
elapsed_time = time.time() - t0
msg = 'Finished. Total elapsed time: %.02f seconds. See %s' % (
elapsed_time, logname)
print(msg)
logger.info(msg)
self.cursor.execute("SELECT timestep FROM steps WHERE pass=(?)", (False,))
# first timestep that didn't finish yet
date = self.cursor.fetchone()[0]
# assume all tasks are completed successfully: update all tasks
self.cursor.execute("UPDATE tasks SET get_boundary=(?) WHERE timestep=(?)", (True, date))
self.cursor.execute("UPDATE tasks SET wps=(?) WHERE timestep=(?)", (True, date))
self.cursor.execute("UPDATE tasks SET wrf=(?) WHERE timestep=(?)", (True, date))
# get all tasks
self.cursor.execute("SELECT * FROM tasks WHERE timestep=(?)", (date,))
tasks = self.cursor.fetchall()
# verify all tasks were completed successfully: set timestep to pass
if all(item is True for item in tasks[0][1:]): # all subtasks completed
self.cursor.execute("UPDATE steps SET pass=(?) WHERE timestep=(?)", (True, date))
# commit changes
self.connection.commit()
if __name__ == "__main__":
global logger
logger = utils.start_logging("test.log")
db = database()
db._new_database()
# db._connect_to_database()
start_date = datetime.datetime(2014, 07, 16, 0)
end_date = datetime.datetime(2014, 07, 20, 0)
db.create_list_datetimes(start_date, end_date, nhours=1)
db.testcode()
# db._add_timesteps_to_db()
db._close_connection()
exit()
def run(args):
logname = os.path.basename(args.input) + '.log'
utils.start_logging(filename=logname, level=args.log)
localtime = utils.getCurrentTimeAsAscii()
t0 = time.time()
msg = os.path.basename(__file__) + ' script starts at %s.' % localtime
print msg
logging.info(msg)
logging.info('Checking validity of SQL file')
# Check that beginning of the file does not contain a create database statement
if os.popen('head -500 ' + args.input +
' | grep "CREATE DATABASE"').read().count("CREATE DATABASE"):
msg = "You must remove CREATE DATABASE statement from the SQL file"
print msg
logging.error(msg)
return
# Check that ther are not defaults in TIMESTAMPS that would cause errors
if os.popen('grep "TIMESTAMP DEFAULT" ' +
args.input).read().count("TIMESTAMP DEFAULT"):
msg = "You must remove any DEFAULT value of any TIMESTAMP column"
print msg
logging.error(msg)
return
# Check that ther are not index creations
if os.popen('grep "INDEX" ' + args.input).read().count("INDEX"):
msg = "You must remove any INDEX creation"
print msg
logging.error(msg)
return
if os.popen("""grep '"' """ + args.input).read().count('"'):
msg = 'You must remove any double quote (")'
print msg
logging.error(msg)
dangerousWords = []
for line in open(args.input, 'r').read().split('\n'):
if not line.startswith('--'):
for word in line.split():
if word.count('"') == 1:
dangerousWords.append(word)
if len(dangerousWords):
msg = 'Also, before removing all ", take care of table and column names that would be incorrect when removing ".\n If any of the following is a table or column name please be sure that it does not have white spaces: ' + ','.join(
dangerousWords)
print msg
logging.error(msg)
return
return
# Establish connection with DB
connection, cursor = utils.connectToDB(args.dbname, args.dbuser,
args.dbpass, args.dbhost,
args.dbport)
# First we drop all tables in attribute
logging.info("Dropping all previous attribute tables")
for tablename in ('tbl2_site_relation', 'tbl2_object_depression',
'tbl2_object_decoration', 'tbl2_object_material',
'tbl1_object', 'tbl1_site'):
cursor.execute('DROP TABLE IF EXISTS ' + tablename + ' CASCADE')
connection.commit()
# First we need to drop the previous constraints in tbl1_site and tbl1_object
# logging.info("Dropping constraints in tbl1_site and tbl1_object tables")
# for tablename in ('tbl1_site','tbl1_object'):
# cursor.execute("select constraint_name from information_schema.table_constraints where table_name=%s", [tablename,])
# constraintNames = cursor.fetchall()
# for (constraintName, ) in constraintNames:
# cursor.execute('ALTER TABLE ' + tablename + ' DROP CONSTRAINT %s CASCADE', [constraintName,])
# connection.commit()
# This script will drop all attribute tables and create them again
logging.info('Executing SQL file %s' % args.input)
#utils.load_sql_file(cursor, args.input)
connParams = utils.postgresConnectString(args.dbname, args.dbuser,
args.dbpass, args.dbhost,
args.dbport, True)
logFile = os.path.basename(args.input) + '.log'
command = 'psql ' + connParams + ' -f ' + args.input + ' &> ' + logFile
logging.info(command)
os.system(command)
#Check errors
if os.popen('cat ' + logFile + ' | grep ERROR').read().count("ERROR"):
msg = 'There was some errors in the data loading. Please see log ' + logFile
print msg
logging.error(msg)
return
# Set select permissions to all new tables
logging.info('Granting select permissions to all tables')
cursor.execute(
"select tablename from pg_tables where schemaname = 'public'")
tablesNames = cursor.fetchall()
for (tableName, ) in tablesNames:
cursor.execute('GRANT SELECT ON ' + tableName + ' TO public')
# We check that the added Sites and Objects are also in Data Management part of the DB
# All sites in tbl1_site must have an entry in ITEM
logging.info(
'Adding items in attribute data that are missing in ITEM table')
query = 'SELECT site_id from tbl1_site WHERE site_id NOT IN (SELECT item_id FROM item)'
sites, num_sites = utils.fetchDataFromDB(cursor, query)
for (siteId, ) in sites:
utils.dbExecute(
cursor, "INSERT INTO ITEM (item_id, background) VALUES (%s,%s)",
[siteId, False])
utils.dbExecute(
cursor,
"INSERT INTO ITEM_OBJECT (item_id, object_number) VALUES (%s,%s)",
[siteId, utils.ITEM_OBJECT_NUMBER_ITEM])
# All objects in tbl1_object must also be in ITEM_OBJECT
logging.info(
'Adding items objects in attribute data that are missing in ITEM_OBJECT table'
)
query = 'SELECT site_id,object_id from tbl1_object WHERE (site_id,object_id) NOT IN (SELECT item_id,object_number FROM item_object)'
sites_objects, num_sites_objects = utils.fetchDataFromDB(cursor, query)
for (siteId, objectId) in sites_objects:
utils.dbExecute(
cursor,
"INSERT INTO ITEM_OBJECT (item_id, object_number) VALUES (%s,%s)",
[siteId, objectId])
#We add again the constraints that link management and attribute data
logging.info('Adding constraints between attribute and items')
cursor.execute("""ALTER TABLE tbl1_object
ADD FOREIGN KEY (site_id, object_id)
REFERENCES ITEM_OBJECT (item_id, object_number)
ON UPDATE NO ACTION
ON DELETE NO ACTION""")
connection.commit()
cursor.execute("""ALTER TABLE tbl1_site
ADD FOREIGN KEY (site_id)
REFERENCES ITEM (item_id)
ON UPDATE NO ACTION
ON DELETE NO ACTION""")
connection.commit()
elapsed_time = time.time() - t0
msg = 'Finished. Total elapsed time: %.02f seconds. See %s' % (
elapsed_time, logname)
print(msg)
logging.info(msg)
logger.info('creating {F} gene infomation ...'.format(F=F))
gencode_codon_list(F, 'db/cancergene_pos_list.txt')
hin.close()
df = pd.read_table("db/cancergene_pos_list.txt", sep='\s+', header=None)
incomp_IDs = df[(df[4].astype(str).str.len() == 1) | (df[4].astype(str).str.len() == 2)][1].unique()
df = df[~df[1].isin(incomp_IDs)]
del df[1]
df = df.drop_duplicates()
df.to_csv('db/cancergene_pos_list_filtered.txt', sep = ' ', header =False, index=False)
# sort
hout = open('db/cancergene_pos_list_final.txt', 'w')
s_ret = subprocess.call(["sort", "-k1", 'db/cancergene_pos_list_filtered.txt'], stdout = hout)
if s_ret != 0:
print >> sys.stderr, "Error in sorting merged junction file"
sys.exit(1)
hin.close()
hout.close()
if __name__ == "__main__":
log_file = 'stdout' # auto-name the log file
log_level = ''
utils.start_logging(log_file=log_file,
log_level='INFO',
verbose=False) # start logging
main()
import config
import utils
import time
import json
import logging
import pandas as pd
import textrazor
TABLE_NAME = 'ARTICLES_538'
NUMBER_OF_RECORDS = 499
now_str = time.strftime('%Y%m%d_%H%M%S')
filename_log = 'log/' + now_str + 'get_textrazor_json.txt'
utils.start_logging(filename_log)
logging.info('*' * 30 + '\nGET Text_Razor JSON - START\n' + '*' * 30)
# get data
# ----------------------------------------------------------------
conn = utils.create_connection('scraping538.db')
query = "SELECT * FROM ARTICLES_538 WHERE TEXTRAZOR_JSON_SAVED = 0 LIMIT {a}".format(
a=NUMBER_OF_RECORDS)
articles_all = pd.read_sql(query, con=conn)
logging.info('Number of records (for which to get the JSON): {a}'.format(
a=articles_all.shape[0]))
# text razor config
textrazor.api_key = config.TEXT_RAZOR_API_KEY
client = textrazor.TextRazor(extractors=[
'entailments', 'relations', 'dependency-trees', "entities", "topics",
"words", "phrases"
])
def db_preparation_main():
#start logging
log_file = 'stdout' # auto-name the log file
log_level = ''
utils.start_logging(log_file=log_file, log_level='INFO',
verbose=False) # start logging
# change directory to db/
if not os.path.exists('db/'):
os.mkdir('db/')
os.chdir('db/')
#####
# make necessary bed files using annot_utils
#####
logger.info('making annot_utils files...')
# make refseq gene coding bed file (refseq)
annot_utils.coding.make_coding_info("gencode_coding.bed.gz", "gencode",
"hg19", False, True)
annot_utils.gene.make_gene_info("gencode_gene.bed.gz", "gencode", "hg19",
False, True)
logger.info('finished making annot_utils files...')
# get trinucleotide context for each bed line
# hack to index the FASTA file
fa = pysam.Fastafile(
'/home/w3varann/genomon_pipeline-2.4.0/database/GRCh37/GRCh37.fa')
# gencode dictionary
hin = gzip.open(
'/home/ysaito/bin/annot_utils-0.2.1/annot_utils/data/hg19/wgEncodeGencodeCompV19.txt.gz',
'r')
ID_dict = {}
for line in hin:
F = line.rstrip('\n').split('\t')
gene = str(F[12])
genID = F[1]
ID_dict[genID] = str(gene)
hin.close()
######
# Average Expression Data
######
logger.info('reading in expression data...')
expr_dict = {}
with open("../input_db/CCLE_avg_exp.txt") as handle:
# skip comment line(s)
comment_line = handle.readline()
header = handle.readline()
for line in handle:
F = line.rstrip('\n').split('\t')
# consider genes with multiple transcripts
if F[0] in expr_dict.keys():
expr_dict[F[0]] = str(F[1]) + ":" + str(expr_dict[F[0]])
else:
expr_dict[F[0]] = F[1]
handle.close()
# get average expression for genes with multiple transcripts
for k, v in expr_dict.items():
if ":" in v:
v_list = [float(n) for n in v.split(':')]
expr_dict[k] = sum(v_list) / len(v_list)
# get median expression of all genes
all_median_expr = np.nanmedian([float(v) for v in expr_dict.values()])
logger.info('finished reading in expression data')
######
# Average Replication Time Data (for gene)
######
logger.info('reading in replication_time data...')
# skip comment line(s)
with open("../input_db/replication_time.txt") as hIN:
first_line = next(hIN)
if first_line.startswith('#'):
skip_rows = 1 if first_line.startswith('#') else 0
hIN.close()
# read in data frame
rep_df = pd.read_table("../input_db/replication_time.txt",
sep='\t',
skiprows=skip_rows)
# make dictionary
rep_dict = rep_df.set_index('gene')['replication_time'].to_dict()
######
# Average Replication Time Data (for position)
######
# skip comment line(s)
with open("../input_db/replication_time_position.txt") as hIN:
first_line = next(hIN)
if first_line.startswith('#'):
skip_rows = 1 if first_line.startswith('#') else 0
hIN.close()
# read in data frame
rep_pos_df = pd.read_table("../input_db/replication_time_position.txt",
sep='\t',
skiprows=skip_rows)
rep_pos_df['chr_start'] = rep_pos_df['chr'].astype(
str) + ':' + rep_pos_df['start'].astype(str)
# make dictionary
rep_pos_dict = rep_pos_df.set_index(
'chr_start')['replication_time'].to_dict()
# get averaage replication time of all position
all_median_rep_time = np.nanmedian(
[float(v) for v in rep_pos_dict.values()])
logger.info('finished reading in replication_time data')
######
# Fill in missing replication time data and expression data
######
logger.info(
'filling in missing replication time data and expression data...')
with gzip.open('gencode_gene.bed.gz') as hIN:
for line in hIN:
F = line.rstrip('\n').split('\t')
chrom = F[0].replace('chr', '')
if chrom not in chroms:
continue
gene_start = int(F[1])
gene_end = int(F[2])
gene_mid_pos = (gene_start + gene_end) / 2
gene = ID_dict[F[3]]
if gene not in rep_dict.keys():
gene_mid_pos_floor = int(
math.floor(gene_mid_pos / 100000) * 100000 + 1)
pos = chrom + ':' + str(gene_mid_pos_floor)
if pos in rep_pos_dict.keys():
rep_dict[gene] = rep_pos_dict[chrom + ':' +
str(gene_mid_pos_floor)]
else:
rep_dict[gene] = all_median_rep_time
if gene not in expr_dict.keys():
expr_dict[gene] = all_median_expr
hIN.close()
logger.info(
'finished filling in missing replication time data and expression data'
)
######
# get trinucleotide context
######
logger.info('getting trinucleotide context...')
gencode_df = pd.read_table("gencode_coding.bed.gz",
names=('chr', 'start', 'end', 'ID', 'type',
'strand'))
# select only coding
gencode_df = gencode_df[(gencode_df['type'] == 'coding') |
(gencode_df['type'] == 'intron')]
gencode_df['gene'] = gencode_df['ID'].map(ID_dict)
# sort by ID
gencode_df = gencode_df.sort_index(by=['ID', 'chr', 'start', 'end'])
#remove chrY
gencode_df = gencode_df[gencode_df['chr'] != 'chrY']
gencode_df.to_csv("gencode_coding.modified.bed",
sep='\t',
header=False,
index=False)
pos_to_context = open("merged_pos_to_context.txt", 'w')
with open("gencode_coding.modified.bed", 'r') as hin:
for line in hin:
F = line.rstrip('\n').split('\t')
chrom = F[0].replace('chr', '')
if chrom not in chroms:
continue
start = int(F[1])
end = int(F[2])
length = end - start
ID = F[3]
gene = F[6]
if F[4] == "coding":
for i in range(length):
strand = F[5]
pos = start + i
try:
# 0-based
nucs = fa.fetch(reference=chrom,
start=pos - 1,
end=pos + 2).upper()
if nucs[1] == 'G':
strand = strand_pairing[strand]
nucs = utils.rev_seq(nucs)
if nucs[1] == 'A':
strand = strand_pairing[strand]
nucs = utils.rev_seq(nucs)
except Exception as inst:
logger.debug("{0}: {1}".format(type(inst), inst.args))
if 'N' not in nucs:
print >> pos_to_context, '\t'.join([
gene, chrom + ':' + str(pos), strand, nucs,
str(expr_dict[gene]),
str(rep_dict[gene])
])
if F[4] == "intron":
for pos in (start, start + 1, end - 2, end - 1):
strand = F[5]
try:
# 0-based
nucs = fa.fetch(reference=chrom,
start=pos - 1,
end=pos + 2).upper()
if nucs[1] == 'G':
strand = strand_pairing[strand]
nucs = utils.rev_seq(nucs)
if nucs[1] == 'A':
strand = strand_pairing[strand]
nucs = utils.rev_seq(nucs)
except Exception as inst:
logger.debug("{0}: {1}".format(type(inst), inst.args))
if 'N' not in nucs:
print >> pos_to_context, '\t'.join([
gene, chrom + ':' + str(pos), strand, nucs,
str(expr_dict[gene]),
str(rep_dict[gene])
])
hin.close()
pos_to_context.close()
logger.info('finished getting trinucleotide context')
# sort
hout = open('merged_pos_to_context_sorted.txt', 'w')
s_ret = subprocess.call(["sort", "-k2", "merged_pos_to_context.txt"],
stdout=hout)
hout.close()
# sometimes, multiple genes share same genome as coding regions.
#chr1 367658 368597 OR4F16(NM_001005277) coding +
#chr1 367658 368597 OR4F29(NM_001005221) coding +
# in these cases, we use higher expression.
#concern: is there any genomic position which diffrent genes on different strands share? --> we checked the posssibility and there was no position like that.
rep_pos_df = pd.read_table("merged_pos_to_context_sorted.txt",
sep='\t',
names=('gene', 'pos', 'strand', 'trinucleotide',
'expression', 'replication_time'))
del rep_pos_df['gene']
rep_pos_df = rep_pos_df.drop_duplicates()
rep_pos_df.to_csv("merged_pos_to_context_duplicate_dropped.txt",
sep='\t',
header=False,
index=False)
# top expression
tmp_pos = ""
tmp_exp = 0
hout = open("merged_pos_to_context_duplicate_dropped2.txt", "w")
with open("merged_pos_to_context_duplicate_dropped.txt", 'r') as hin:
for line in hin:
F = line.rstrip('\n').split('\t')
if tmp_pos != F[0] and tmp_pos != "":
print >> hout, '\t'.join(
[tmp_pos, tmp_strand, tmp_trinuc, tmp_exp, tmp_rep_time])
tmp_pos = F[0]
tmp_strand = F[1]
tmp_trinuc = F[2]
tmp_exp = F[3]
tmp_rep_time = F[4]
continue
tmp_pos = F[0]
tmp_strand = F[1]
tmp_trinuc = F[2]
if F[3] > tmp_exp:
tmp_exp = F[3]
tmp_rep_time = F[4]
print >> hout, '\t'.join(
[tmp_pos, tmp_strand, tmp_trinuc, tmp_exp, tmp_rep_time])
hin.close()
hout.close()
rep_pos_df = pd.read_table("merged_pos_to_context_duplicate_dropped2.txt",
sep='\t',
names=('pos', 'strand', 'trinucleotide',
'expression', 'replication_time'))
rep_pos_df['replication_time'] = rep_pos_df['replication_time'].fillna(
all_median_rep_time)
rep_pos_df['exp_group'], exp_bins = pd.qcut(
rep_pos_df['expression'].astype(float),
15,
labels=[
'exp_class1', 'exp_class2', 'exp_class3', 'exp_class4',
'exp_class5', 'exp_class6', 'exp_class7', 'exp_class8',
'exp_class9', 'exp_class10', 'exp_class11', 'exp_class12',
'exp_class13', 'exp_class14', 'exp_class15'
],
retbins=True)
rep_pos_df['rep_group'], rep_bins = pd.qcut(
rep_pos_df['replication_time'].astype(float),
15,
labels=[
'rep_class1', 'rep_class2', 'rep_class3', 'rep_class4',
'rep_class5', 'rep_class6', 'rep_class7', 'rep_class8',
'rep_class9', 'rep_class10', 'rep_class11', 'rep_class12',
'rep_class13', 'rep_class14', 'rep_class15'
],
retbins=True)
rep_pos_df['class'] = rep_pos_df['exp_group'].str.cat(
rep_pos_df['rep_group'], sep='_')
rep_pos_df.to_csv("merged_pos_to_context_class.txt",
sep='\t',
header=False,
index=False)
print "exp bins"
print exp_bins
print "rep bins"
print rep_bins
######
# output
######
# output
f = open('CCLE_avg_exp_output.txt', 'w')
for k, v in sorted(expr_dict.items()):
f.write('{0}\t{1}\n'.format(k, v))
f.close()
f2 = open('replication_time_output.txt', 'w')
for k, v in sorted(rep_dict.items()):
if v == 'NaN':
rep_dict[k] = all_avg_rep_time
f2.write('{0}\t{1}\n'.format(k, v))
f2.close()
def run(opts):
global logger
# Define logger and start logging
#logname = os.path.basename(opts.output) + '.log'
logname = os.path.splitext(os.path.basename(__file__))[0] + '.log'
logger = utils.start_logging(filename=logname, level=opts.log)
localtime = utils.getCurrentTimeAsAscii()
t0 = time.time()
msg = os.path.basename(__file__) + ' script starts at %s.' % localtime
print msg
logger.info(msg)
if not opts.output.endswith(".conf.xml"):
logger.error('The output file must end with .conf.xml')
raise IOError('The output file must end with .conf.xml')
# Create python postgres connection
global cursor
connection, cursor = utils.connectToDB(opts.dbname, opts.dbuser,
opts.dbpass, opts.dbhost,
opts.dbport)
# Check that provided background is in DB
query = """
SELECT OSG_DATA_ITEM_PC_BACKGROUND.abs_path,srid
FROM OSG_DATA_ITEM_PC_BACKGROUND JOIN RAW_DATA_ITEM USING (raw_data_item_id)"""
rows, num_rows = utils.fetchDataFromDB(cursor, query)
backGroundAbsPath = None
backgroundSRID = None
for (bgAbsPath,bgSRID) in rows:
if opts.background == os.path.basename(bgAbsPath):
backGroundAbsPath = bgAbsPath
backgroundSRID = bgSRID
if backGroundAbsPath == None:
errorMsg = 'Background ' + opts.background + ' is not found'
logger.error(errorMsg)
raise Exception(errorMsg)
# Get the root object: the OSG configuration
rootObject = viewer_conf_api.osgRCconfiguration()
# set version
rootObject.set_version("0.2")
# Add all the different XML of the active objects
# (we add distinct since the boundings will share XMLs)
query = """
SELECT DISTINCT xml_abs_path
FROM OSG_DATA_ITEM ORDER BY xml_abs_path"""
rows, num_rows = utils.fetchDataFromDB(cursor, query)
for (xmlPath,) in rows:
if xmlPath.count(opts.osg) == 0:
logger.error('Mismatch between given OSG data directory ' +
'and DB content')
rootObject.add_objectLibrary(viewer_conf_api.objectLibrary
(url=os.path.relpath(xmlPath, opts.osg)))
# Add the object library with the boundings
rootObject.add_objectLibrary(viewer_conf_api.objectLibrary
(url=utils.BOUNDINGS_XML_RELATIVE))
# Add the cameras that are in the DB
cameras = viewer_conf_api.cameras()
query = """
SELECT osg_camera_name, srid, x, y, z, h, p, r
FROM OSG_CAMERA JOIN OSG_LOCATION USING (osg_location_id)"""
rows, num_rows = utils.fetchDataFromDB(cursor, query)
for (name, srid, x, y, z, h, p, r) in rows:
if (srid is not None) and (srid == bgSRID):
x, y, z = getOSGPosition(x, y, z, srid)
else:
x, y, z = getOSGPosition(x, y, z)
cameras.add_camera(viewer_conf_api.camera
(name=name, x=x, y=y, z=z, h=h, p=p, r=r))
# Add Default cameras for the items that have no camera in the DB
query = """
SELECT
item_id, ST_SRID(geom), st_x(st_centroid(geom)), st_y(st_centroid(geom)), min_z + ((max_z - min_z) / 2)
FROM ITEM WHERE NOT background AND geom IS NOT null AND item_id NOT IN (
SELECT DISTINCT item_id FROM OSG_ITEM_CAMERA
) ORDER BY item_id"""
rows, numitems = utils.fetchDataFromDB(cursor, query)
for (itemId, srid, x, y, z) in rows:
# only call getOSGPosition if [x,y,z] are not None
# should item_id = -1 be added?
if all(position is not None for position in [x,y,z]) and itemId>0:
if (srid is not None) and (srid == bgSRID):
x, y, z = getOSGPosition(x, y, z, srid)
else:
x, y, z = getOSGPosition(x, y, z)
cameras.add_camera(viewer_conf_api.camera
(name=utils.DEFAULT_CAMERA_PREFIX + str(itemId),
x=x, y=y, z=z))
rootObject.set_cameras(cameras)
# Add the XML content of the preferences
rootObject.set_preferences(viewer_conf_api.parseString(DEFAULT_PREFENCES))
attributes = viewer_conf_api.attributes()
# Use generic method to fill all properties.
# We need the name in the XML, the column name in the DB and
# the table name in the DB
for property in utils.ATTRIBUTES_ORDER:
(cName, tName) = utils.ATTRIBUTES[property]
elements = getattr(viewer_conf_api, property + 's')()
# We need to call the columns and tables with extra "" because
# they were created from the Access DB
# utils.dbExecute(cursor, 'SELECT "' + cName + '" FROM "' + tName + '"')
utils.dbExecute(cursor, 'SELECT ' + cName + ' FROM ' + tName)
for (element,) in cursor:
getattr(elements, 'add_' + property)(getattr(
viewer_conf_api, property)(name=element))
getattr(attributes, 'set_' + property + 's')(elements)
rootObject.set_attributes(attributes)
# Add all the static objects, i.e. the OSG from the background
# Add the static object for the background
staticObjects = viewer_conf_api.staticObjects()
staticObjects.add_staticObject(viewer_conf_api.staticObject
(url=os.path.relpath(
glob.glob(backGroundAbsPath + '/' + utils.OSG_DATA_PREFIX + '.osgb')[0],
opts.osg)))
# Add hardcode DOME
staticObjects.add_staticObject(viewer_conf_api.staticObject
(url=utils.DOMES_OSG_RELATIVE))
rootObject.set_staticObjects(staticObjects)
# Add the 5 different layers of active objects
activeObjects = viewer_conf_api.activeObjects()
# First we add points, meshes and pcitures which are related to
# the active_objects_sites
layersData = [('points', 'OSG_DATA_ITEM_PC_SITE', utils.AO_TYPE_PC),
('photos', 'OSG_DATA_ITEM_PICTURE', utils.AO_TYPE_PIC),
('meshes', 'OSG_DATA_ITEM_MESH', utils.AO_TYPE_MESH)]
for (layerName, tableName, inType) in layersData:
layer = viewer_conf_api.layer(name=layerName)
query = """
SELECT item_id, raw_data_item_id, OSG_LOCATION.srid, x, y, z, xs, ys, zs, h, p, r, cast_shadow
FROM """ + tableName + """ JOIN OSG_DATA_ITEM USING (osg_data_item_id)
JOIN OSG_LOCATION USING (osg_location_id)
JOIN RAW_DATA_ITEM USING (raw_data_item_id)
ORDER BY item_id"""
rows, numitems = utils.fetchDataFromDB(cursor, query)
for (itemId, rawDataItemId, srid, x, y, z, xs, ys, zs, h, p, r, castShadow) in rows:
# only call getOSGPosition if [x,y,z] are not None
if all(position is not None for position in [x,y,z]):
if (srid is not None) and (srid == bgSRID):
x, y, z = getOSGPosition(x, y, z, srid)
else:
x, y, z = getOSGPosition(x, y, z)
uniqueName = utils.codeOSGActiveObjectUniqueName(cursor, inType, rawDataItemId)
activeObject = viewer_conf_api.activeObject(prototype=uniqueName,
uniqueName=uniqueName)
setting = viewer_conf_api.setting(
x=x, y=y, z=z, xs=xs, ys=ys, zs=zs, h=h, p=p, r=r,
castShadow=(1 if castShadow else 0))
activeObject.set_setting(setting)
layer.add_activeObject(activeObject)
activeObjects.add_layer(layer)
# Add the boundings
layer = viewer_conf_api.layer(name='boundings')
# We first add the boundings that are currently in the DB
query = """
SELECT item_id, object_number, x, y, z, xs, ys, zs, h, p, r, OSG_LOCATION.cast_shadow, srid
FROM OSG_ITEM_OBJECT JOIN OSG_LOCATION USING (osg_location_id)
ORDER BY item_id,object_number"""
osgItemObjects, numOsgItemObjects = utils.fetchDataFromDB(cursor, query)
# osgItemObjects is (itemId, objectNumber, x, y, z, xs, ys, zs, h, p, r, castShadow, srid)
# Now we add Default OSG data items for the objects that are not in OSG_ITEM_OBJECT table
query = """
SELECT item_id,object_number
FROM item_object
WHERE (item_id,object_number) NOT IN (SELECT item_id,object_number FROM OSG_ITEM_OBJECT)
ORDER BY item_id,object_number"""
objects, num_objects = utils.fetchDataFromDB(cursor, query)
for (itemId, objectNumber) in objects:
srid = None
(x,y,z) = (0,0,0)
(xs,ys,zs) = (1,1,1)
query = """
SELECT ST_SRID(geom), st_x(st_centroid(geom)), st_y(st_centroid(geom)), min_z + ((max_z - min_z) / 2),
st_xmax(geom)-st_xmin(geom) as dx, st_ymax(geom)-st_ymin(geom) as dy, (max_z - min_z) as dz
FROM ITEM
WHERE item_id = %s and geom is not %s"""
queryArgs = [itemId, None]
footprints, num_footprints = utils.fetchDataFromDB(cursor, query, queryArgs)
if num_footprints:
(srid, x, y, z, xs, ys, zs) = footprints[0]
if xs == 0: xs = 1
if ys == 0: ys = 1
if zs == 0: zs = 1
osgItemObjects.append([itemId, objectNumber, x, y, z, xs, ys, zs, 0, 0, 0, False, srid])
# Now let's add them to the XML
for (itemId, objectNumber, x, y, z, xs, ys, zs, h, p, r, castShadow, srid) in osgItemObjects:
# only call getOSGPosition if [x,y,z] are not None
if all(position is not None for position in [x,y,z]) and itemId>0:
if (srid is not None) and (srid == bgSRID):
x, y, z = getOSGPosition(x, y, z, srid)
else:
x, y, z = getOSGPosition(x, y, z)
uniqueName = utils.codeOSGActiveObjectUniqueName(cursor, utils.AO_TYPE_OBJ, itemId = itemId, objectId = objectNumber)
proto = "Bounding Box"
activeObject = viewer_conf_api.activeObject(prototype=proto,
uniqueName=uniqueName)
setting = viewer_conf_api.setting(
x=x, y=y, z=z, xs=xs, ys=ys, zs=zs, h=h, p=p, r=r,
castShadow=(1 if castShadow else 0))
activeObject.set_setting(setting)
layer.add_activeObject(activeObject)
activeObjects.add_layer(layer)
# Add the labels
layer = viewer_conf_api.layer(name='labels')
utils.dbExecute(cursor, 'SELECT osg_label_name, text, red, green, blue, ' +
'rotate_screen, outline, font, srid, x, y, z, xs, ys, zs, h, ' +
'p, r, cast_shadow FROM OSG_LABEL INNER JOIN ' +
'OSG_LOCATION ON OSG_LABEL.osg_location_id=' +
'OSG_LOCATION.osg_location_id')
rows = cursor.fetchall()
for (name, text, red, green, blue, rotatescreen, outline, font, srid, x, y, z, xs, ys, zs, h, p, r, castShadow) in rows:
proto = "labelPrototype"
uniqueName = utils.codeOSGActiveObjectUniqueName(cursor, utils.AO_TYPE_LAB, labelName = name)
if (srid is not None) and (srid == bgSRID):
x, y, z = getOSGPosition(x, y, z, srid)
else:
x, y, z = getOSGPosition(x, y, z)
activeObject = viewer_conf_api.activeObject(
prototype=proto, uniqueName=uniqueName, labelText=text,
labelColorRed=red, labelColorGreen=green, labelColorBlue=blue,
labelRotateScreen=rotatescreen, outline=outline, Font=font)
setting = viewer_conf_api.setting(
x=x, y=y, z=z, xs=xs, ys=ys, zs=zs, h=h, p=p, r=r,
castShadow=(1 if castShadow else 0))
activeObject.set_setting(setting)
layer.add_activeObject(activeObject)
activeObjects.add_layer(layer)
rootObject.set_activeObjects(activeObjects)
# Create the XML
rootObject.export(open(opts.output, 'w'), 0)
elapsed_time = time.time() - t0
msg = 'Finished. Total elapsed time: %.02f seconds. See %s' % (elapsed_time, logname)
print(msg)
logger.info(msg)
def parse_arguments():
# make a parser
info = 'Evaluates cancer driver gene methods'
parent_parser = argparse.ArgumentParser(description=info)
# logging arguments
parent_parser.add_argument('-ll', '--log-level',
type=str,
action='store',
default='',
help='Write a log file (--log-level=DEBUG for debug mode, '
'--log-level=INFO for info mode)')
parent_parser.add_argument('-l', '--log',
type=str,
action='store',
default='stdout',
help='Path to log file. (accepts "stdout")')
parent_parser.add_argument('-v', '--verbose',
action='store_true',
default=False,
help='Flag for more verbose log output')
# add subparsers
subparsers = parent_parser.add_subparsers(title='Sub-commands', dest='kind')
parser_pipeline = subparsers.add_parser('pipeline',
help='Run all sub-commands evaluating methods',
description='Run all sub-commands evaluating methods')
parser_split = subparsers.add_parser('split_mutations',
help='Splits mutations in a MAF-like format into two random halves',
description='Splits mutations in a MAF-like format into two random halves. '
'Each split maintains the proportion of samples in each cancer type.')
parser_cgc = subparsers.add_parser('list_overlap',
help='Evaluate the overlap of significant genes with the Cancer Gene Census (CGC)',
description='Evaluate the overlap of significant genes with the Cancer Gene Census (CGC)')
parser_ovlp = subparsers.add_parser('method_overlap',
help='Counts the number of methods that find specific genes significant',
description='Counts the number of methods that find specific genes significant')
parser_pval = subparsers.add_parser('pvalue',
help='Examine the p-value distribution',
description='Examine the p-value distribution')
parser_signif = subparsers.add_parser('num_signif',
help='Examine the number of significant genes',
description='Examine the number of significant genes')
help_info = 'Evaluate method consistency'
parser_consis = subparsers.add_parser('consistency',
help=help_info,
description='Evaluate method consistency')
# program arguments
for i, parser in enumerate([parser_pipeline, parser_split, parser_cgc, parser_ovlp,
parser_pval, parser_signif, parser_consis]):
# group of parameters
major_parser = parser.add_argument_group(title='Major options')
advance_parser = parser.add_argument_group(title='Advanced options')
if i != 1 and i != 6:
help_str = 'directory containing results from methods on full data'
major_parser.add_argument('-i', '--input-dir',
type=str, default=None,
help=help_str)
elif i == 1:
help_str = 'Mutation file to split'
major_parser.add_argument('-m', '--mutations',
type=str, required=True,
help=help_str)
help_str = 'Configuration file (YAML format)'
major_parser.add_argument('-config', '--config',
type=str, default=None,
help=help_str)
help_str = 'output directory'
major_parser.add_argument('-o', '--output',
type=str, default=None,
help=help_str)
if i == 0:
list_parser = major_parser.add_mutually_exclusive_group(required=True)
help_str = 'Path to Cancer Gene Census file'
list_parser.add_argument('-c', '--cgc',
type=str, default=None,
help=help_str)
help_str = 'Custom driver gene list'
list_parser.add_argument('-g', '--gene-list',
type=str, default=None,
help=help_str)
help_str = ('Minimum number of methods finding a gene significant to '
'not include that gene\' p-value (Default: 3)')
major_parser.add_argument('-m', '--min',
type=int, default=3,
help=help_str)
help_str = 'Directory containing the consistency results'
major_parser.add_argument('-consis-dir', '--consistency-dir',
type=str, required=True,
help=help_str)
help_str = 'Q-value threshold for significance (Default: 0.1)'
advance_parser.add_argument('-q', '--qvalue',
type=float, default=.1,
help=help_str)
help_str = 'Ranking depth to consider for consistency (Default: 100)'
advance_parser.add_argument('-d', '--depth',
type=int, default=100,
help=help_str)
help_str = 'Generate plots examining evaluation (Default: False)'
advance_parser.add_argument('-p', '--plot',
action='store_true', default=False,
help=help_str)
if i == 1:
help_str = ('Column name containing sample IDs (Default: checks '
'"Tumor_Sample_Barcode" or "Tumor_Sample")')
advance_parser.add_argument('-s', '--sample-col',
type=str,
help=help_str)
help_str = 'Number of iterations to randomly split data (Default: 10)'
advance_parser.add_argument('-n', '--number',
type=int, default=10,
help=help_str)
elif i == 2:
list_parser = major_parser.add_mutually_exclusive_group(required=True)
help_str = 'Path to Cancer Gene Census file'
list_parser.add_argument('-c', '--cgc',
type=str, default=None,
help=help_str)
help_str = 'Custom driver gene list'
list_parser.add_argument('-g', '--gene-list',
type=str, default=None,
help=help_str)
help_str = 'Q-value threshold for significance (Default: 0.1)'
advance_parser.add_argument('-q', '--qvalue',
type=float, default=.1,
help=help_str)
help_str = 'Generate plots examining evaluation (Default: False)'
advance_parser.add_argument('-p', '--plot',
action='store_true', default=False,
help=help_str)
elif i == 3:
help_str = 'Q-value threshold for significance (Default: 0.1)'
advance_parser.add_argument('-q', '--qvalue',
type=float, default=.1,
help=help_str)
help_str = 'Generate plots examining evaluation (Default: False)'
advance_parser.add_argument('-p', '--plot',
action='store_true', default=False,
help=help_str)
elif i == 4:
help_str = ('Minimum number of methods finding a gene significant to '
'not include that gene\' p-value (Default: 3)')
major_parser.add_argument('-m', '--min',
type=int, default=3,
help=help_str)
help_str = ('Path to Cancer Gene Census file (optional). Additionaly '
'removes genes from the CGC.')
major_parser.add_argument('-c', '--cgc',
type=str, default=None,
help=help_str)
help_str = 'Generate plots examining evaluation (Default: False)'
advance_parser.add_argument('-p', '--plot',
action='store_true', default=False,
help=help_str)
elif i == 5:
help_str = 'Q-value threshold for significance (Default: 0.1)'
advance_parser.add_argument('-q', '--qvalue',
type=float, default=.1,
help=help_str)
help_str = 'Generate plots examining evaluation (Default: False)'
advance_parser.add_argument('-p', '--plot',
action='store_true', default=False,
help=help_str)
elif i == 6:
help_str = 'Directory containing the consistency results'
major_parser.add_argument('-consis-dir', '--consistency-dir',
type=str, required=True,
help=help_str)
help_str = 'Ranking depth to consider for consistency (Default: 100)'
advance_parser.add_argument('-d', '--depth',
type=int, default=100,
help=help_str)
help_str = 'Generate plots examining evaluation (Default: False)'
advance_parser.add_argument('-p', '--plot',
action='store_true', default=False,
help=help_str)
args = parent_parser.parse_args()
# handle logging
if args.log_level or args.log:
if args.log:
log_file = args.log
else:
log_file = '' # auto-name the log file
else:
log_file = os.devnull
log_level = args.log_level
utils.start_logging(log_file=log_file,
log_level=log_level,
verbose=args.verbose) # start logging
opts = vars(args)
# log user entered command
#logger.info('Version: {0}'.format(prob2020.__version__))
logger.info('Command: {0}'.format(' '.join(sys.argv)))
return opts
"""
Functions for training estimators, performing cross validation, and making predictions
"""
__author__ = 'Bryan Gregory'
__email__ = '*****@*****.**'
__date__ = '11-19-2013'
#Internal modules
import utils
#Start logger to record all info, warnings, and errors to Logs/logfile.log
log = utils.start_logging(__name__)
import ml_metrics
#External modules
import time
from datetime import datetime
from sklearn import (metrics, cross_validation, linear_model, preprocessing)
from sklearn.externals import joblib
import numpy as np
from scipy import sparse
from scipy.sparse import coo_matrix, hstack, vstack
#-----Run Cross Validation Steps-----#
def cross_validate(model, settings, dfTrn_Segment, dfTest_Segment):
#Combine the train and test feature matrices and create targets
mtxTrn, mtxTest, mtxTrnTarget, mtxTestTarget = combine_features(model, dfTrn_Segment, dfTest_Segment)
#Run CV
if settings['cv_method'] in ['march','april','list_split']:
cv_preds = cross_validate_temporal(mtxTrn,mtxTest,mtxTrnTarget.ravel(),mtxTestTarget.ravel(),model)
if settings['cv_method'] in ['kfold']:
cv_preds = cross_validate_kfold(mtxTrn,mtxTest,mtxTrnTarget.ravel(),mtxTestTarget.ravel(),model)
def run(args):
# start logging
logname = os.path.splitext(os.path.basename(__file__))[0] + '.log'
utils.start_logging(filename=logname, level=utils.DEFAULT_LOG_LEVEL)
localtime = utils.getCurrentTimeAsAscii()
t0 = time.time()
msg = os.path.basename(__file__) + ' script starts at %s.' % localtime
print msg
logging.info(msg)
# connect to the DB
connection, cursor = utils.connectToDB(args.dbname, args.dbuser,
args.dbpass, args.dbhost,
args.dbport)
itemIds = []
if args.itemid == '':
data, num = utils.fetchDataFromDB(
cursor, 'SELECT item_id FROM ITEM WHERE NOT background')
for (itemId, ) in data:
itemIds.append(itemId)
else:
itemIds = args.itemid.split(',')
# close the conection to the DB
utils.closeConnectionDB(connection, cursor)
# Create queues
itemsQueue = multiprocessing.Queue() # The queue of tasks (queries)
resultsQueue = multiprocessing.Queue() # The queue of results
for itemId in itemIds:
itemsQueue.put(int(itemId))
for i in range(
args.cores
): #we add as many None jobs as numUsers to tell them to terminate (queue is FIFO)
itemsQueue.put(None)
procs = []
# We start numUsers users processes
for i in range(args.cores):
procs.append(
multiprocessing.Process(
target=runChild,
args=(i, itemsQueue, resultsQueue, args.las, args.dbname,
args.dbuser, args.dbpass, args.dbhost, args.dbport)))
procs[-1].start()
for i in range(len(itemIds)):
[procIndex, itemId] = resultsQueue.get()
# wait for all users to finish their execution
for i in range(args.cores):
procs[i].join()
# measure elapsed time
elapsed_time = time.time() - t0
msg = 'Finished. Total elapsed time: %.02f seconds. See %s' % (
elapsed_time, logname)
print(msg)
logging.info(msg)
def run(args):
global logger
global connection
global cursor
# start logging
logname = os.path.basename(args.input) + '.log'
logger = utils.start_logging(filename=logname,
level=utils.DEFAULT_LOG_LEVEL)
localtime = utils.getCurrentTimeAsAscii()
t0 = time.time()
msg = os.path.basename(__file__) + ' script starts at %s.' % localtime
print msg
logger.info(msg)
if not os.path.isfile(args.input):
msg = "Input file is not found!"
print msg
logger.error(msg)
return
# connect to the DB
connection, cursor = utils.connectToDB(args.dbname, args.dbuser,
args.dbpass, args.dbhost,
args.dbport)
if args.input.endswith('shp'):
prjFile = args.input.replace('shp', 'prj')
if not os.path.isfile(prjFile):
msg = "Input PRJ file is not found!"
print msg
logger.error(msg)
return
sqlFile = os.path.basename(args.input).replace('shp', 'sql')
shp2psql = 'shp2pgsql -s ' + str(getEPSG(
prjFile)) + ' -c ' + args.input + ' sites_geoms_temp > ' + sqlFile
print shp2psql
logger.info(shp2psql)
os.system(shp2psql)
else:
sqlFile = args.input
for line in open(sqlFile, 'r').read().split('\n'):
if line.count('CREATE TABLE'):
if line.count('sites_geoms_temp') == 0:
msg = "The table in the SQL file must be named sites_geom_temp. Replace the table name to sites_geoms_temp!"
print msg
logger.error(msg)
return
# clean the temp table if exsisted
clean_temp_table(args)
# load the table sites_geoms_temp from the SQL file ot the DB
success_loading = utils.load_sql_file(cursor, sqlFile)
if args.input.endswith('shp'):
os.system('rm -rf ' + sqlFile)
if success_loading:
# check if the SITES table is empty, then change the type of the geom field
update_geom_col_type(cursor)
# find the lists of new IDs and list of overlapping IDs
no_item_well_temp_ids, both_in_item_and_temp_ids = find_lists(cursor)
# insert the object geometries per site for the sites not in item, but in the sites_geoms_temp table
update_geometries(no_item_well_temp_ids, True)
# update the union of object geometries per site for the sites both in item and sites_geoms_temp table
update_geometries(both_in_item_and_temp_ids, False)
# clean the temp table
clean_temp_table(args)
# close the conection to the DB
utils.closeConnectionDB(connection, cursor)
# measure elapsed time
elapsed_time = time.time() - t0
msg = 'Finished. Total elapsed time: %.02f seconds. See %s' % (
elapsed_time, logname)
print(msg)
logger.info(msg)
return
from __future__ import division
import Microbial_com_modeling as mcm
from Microbial_com_modeling import IntegrationError
import multiprocess
import numpy as np
import statsmodels
import multiprocessing as mp
import time
import logging
from utils import start_logging, save_json
import json
import os
import matplotlib.pyplot as plt
import seaborn as sns
logger = start_logging(log_file=True)
old_settings = np.seterr(all='raise')
start_time = time.time()
def draw_plot(directory, fname):
sns.set_context("talk")
with open("{}/{}.json".format(directory, fname)) as json_file:
data = json.load(json_file)
sensitivity = np.array(data["sensitivity"])
specificity = np.array(data["specificity"])
value_range = np.array(data["value_range"])
def run(args):
global logger
global offsetX
global offsetY
global offsetZ
logname = os.path.basename(args.output) + '.log'
logger = utils.start_logging(filename=logname, level=args.log)
# start logging
localtime = utils.getCurrentTimeAsAscii()
msg = __file__ + ' script logging start at %s'% localtime
print msg
logger.info(msg)
t0 = time.time()
# connect to DB and get a cursor
connection, cursor = utils.connectToDB(args.dbname, args.dbuser, args.dbpass, args.dbhost)
# We assume the osg location is relative
# We need to make it absolute by adding the offset of the background with srid as provided
query = """
SELECT C.offset_x, C.offset_y, C.offset_z
FROM raw_data_item A, raw_data_item_pc B, osg_data_item_pc_background C
WHERE A.raw_data_item_id = B.raw_data_item_id AND
B.raw_data_item_id = C.raw_data_item_id AND
A.srid = %s"""
queryArgs = [args.srid,]
backgroundOffsets, num_backgrounds = utils.fetchDataFromDB(cursor, query, queryArgs)
if num_backgrounds:
(offsetX,offsetY,offsetZ) = backgroundOffsets[0]
# get all items
query = 'SELECT item_id, ST_ASGEOJSON(geom), min_z, max_z FROM item WHERE NOT background ORDER BY item_id'
sites, num_sites = utils.fetchDataFromDB(cursor, query)
data = []
for (itemId, itemGeom, minz, maxz) in sites:
# Generate the JSON data for this item
dataSite = {}
dataSite["id"] = itemId
if itemGeom != None:
dataSite["footprint"] = json.loads(itemGeom)['coordinates']
dataSite["footprint_altitude"] = [minz,maxz]
addThumbnail(cursor, itemId, dataSite)
addSiteMetaData(cursor, itemId, dataSite)
addPointCloud(cursor, itemId, dataSite, args.srid)
addMeshes(cursor, itemId, dataSite, args.srid)
addObjectsMetaData(cursor, itemId, dataSite, args.srid)
data.append(dataSite)
# close the Db connection
utils.closeConnectionDB(connection, cursor)
# save the data into JSON file
save2JSON(args.output, data)
elapsed_time = time.time() - t0
msg = 'Finished. Total elapsed time: %.02f seconds. See %s' % (elapsed_time, logname)
print(msg)
logger.info(msg)
from __future__ import unicode_literals
import sys
import os
import tweepy
from utils import (
start_logging,
upload_media,
)
import logging
log = logging.getLogger(__name__)
start_logging()
auth = tweepy.OAuthHandler(os.environ['TWITTER_CONSUMER_KEY'], os.environ['TWITTER_CONSUMER_SECRET'])
auth.set_access_token(os.environ['TWITTER_ACCESS_TOKEN'], os.environ['TWITTER_ACCESS_TOKEN_SECRET'])
api = tweepy.API(auth)
media_id = upload_media(api, sys.argv[1])
log.info('media_id = %s', media_id)
import logging
import utils
import time
import sqlite3
import pandas as pd
now_str = time.strftime('%Y%m%d_%H%M%S')
FILENAME_lOG = 'log/' + now_str + 'report_integration.txt'
utils.start_logging(FILENAME_lOG)
logging.info('*'*30 + '\nINTEGRATION START\n' + '*'*30)
# INPUTS
TABLE_NAME = 'ARTICLES_538'
STAGING_TABLE = 'S_ARTICLES_538'
# Get data
# ----------------------------------------------------------------
conn = utils.create_connection('scraping538.db')
query = "SELECT * FROM " + STAGING_TABLE + " WHERE PROCESSED = 0"
data = pd.read_sql(query, con=conn)
data.drop("PROCESSED", axis=1, inplace=True)
# Clean data
# ----------------------------------------------------------------
# date
data['date'] = pd.to_datetime(data['date'])
data.rename(columns={"date": "DATE"}, inplace=True)
# date_hour
def items_to_upload():
for item in config:
if not config[item].get('processed'):
yield item
def mark_as_processed(item, post_id):
debug("Updating config for " + item)
config.reload()
config[item]['processed'] = 1
config[item]['post id'] = post_id
config[item]['posted on'] = str(datetime.now())
config.write()
def main():
for item in items_to_upload():
debug('=' * 60)
filename = utils.download(item)
post_id = posterous.post(title=config[item]['title'],
tags=config[item]['tags'],
media=filename)
mark_as_processed(item, post_id)
if __name__ == "__main__":
utils.start_logging(__file__)
main()
# first timestep that didn't finish yet
date = self.cursor.fetchone()[0]
# assume all tasks are completed successfully: update all tasks
self.cursor.execute("UPDATE tasks SET get_boundary=(?) WHERE timestep=(?)", (True,date,))
self.cursor.execute("UPDATE tasks SET wps=(?) WHERE timestep=(?)", (True,date,))
self.cursor.execute("UPDATE tasks SET wrf=(?) WHERE timestep=(?)", (True,date,))
# get all tasks
self.cursor.execute("SELECT * FROM tasks WHERE timestep=(?)", (date,))
tasks = self.cursor.fetchall()
# verify all tasks were completed successfully: set timestep to pass
if all(item is True for item in tasks[0][1:]): # all subtasks completed
self.cursor.execute("UPDATE steps SET pass=(?) WHERE timestep=(?)",
(True,date,))
# commit changes
self.connection.commit()
if __name__=="__main__":
global logger
logger = utils.start_logging('test.log')
db = database()
db._new_database()
#db._connect_to_database()
start_date = datetime.datetime(2014,07,16,0)
end_date = datetime.datetime(2014,07,20,0)
db.create_list_datetimes(start_date, end_date, nhours=1)
db.testcode()
#db._add_timesteps_to_db()
db._close_connection()
exit()
def _archive_output(self, current_time, thours, domain):
'''
rename unipost.exe output to wrfpost_d0${domain}_time.grb and archive
'''
import shutil
# verify that domain is an int
if not isinstance(domain, int):
message = 'domain id should be an integer'
logger.error(message)
raise IOError(message)
# define original and destination filename
origname = 'WRFPRS%02d.tm00' %thours
outname = 'wrfpost_d%02d_%s.grb' %(domain, current_time)
# rename file and move to archive dir
shutil.move(os.path.join(config['post_dir'], origname),
os.path.join(config['upp_archive_dir'], outname))
# check if file is indeed archived
utils.check_file_exists(os.path.join(config['upp_archive_dir'], outname))
if __name__ == "__main__":
logger = utils.start_logging('test.log')
postprocess = upp()
wrfout_files = glob.glob(os.path.join(config['wrf_run_dir'], 'wrfout_d01*'))
postprocess.run_unipost_file(wrfout_files[0], use_t0=True)
[postprocess.run_unipost_file(f) for f in wrfout_files[1:]]
#postprocess.run_unipost_file(
# '/home/WUR/haren009/sources/WRFV3/run/wrfout_d01_2014-07-16_00:00:00')
def run(opts):
# Define logging and start logging
logname = os.path.basename(opts.config) + '.log'
utils.start_logging(filename=logname, level=opts.log)
localtime = utils.getCurrentTimeAsAscii()
t0 = time.time()
msg = os.path.basename(__file__) + ' script starts at %s.' % localtime
print msg
logging.info(msg)
# Parse xml configuration file
data = ET.parse(opts.config).getroot()
# Database connection
connection, cursor = utils.connectToDB(opts.dbname, opts.dbuser, opts.dbpass, opts.dbhost, opts.dbport)
# get offset and srid of the background defined in the conf file
(bgOffsetX, bgOffsetY, bgOffsetZ, bgSRID) = getBackgroundOffset(data, cursor)
bgOffset = (bgOffsetX, bgOffsetY, bgOffsetZ)
# Process updates
updateAOS = data.xpath('//*[@status="updated"]')
# loop over all updates found in the xml config file
for ao in updateAOS:
#(aoType, proto, uniqueName, siteId, activeobjectId, objectNumber) = \
#getDetails(ao)
uniqueName = ao.get('uniqueName')
(aoType, itemId, rawDataItemId, objectId, labelName) = utils.decodeOSGActiveObjectUniqueName(cursor, uniqueName)
if aoType == None:
msg = 'Ignoring operation on %s. Could not decode uniqueName' % uniqueName
print msg
logging.warning(msg)
else:
# check if the object is in the DB
osgLocationId = getOSGLocationId(cursor, aoType, labelName, itemId, objectId, rawDataItemId)
if osgLocationId != None:
# update the DB with the information in the xml config file
if aoType == utils.AO_TYPE_LAB:
# Some other params may have changed in the label
msg = 'Updating label %s' % labelName
print msg
logging.info(msg)
deleteOSG(cursor, aoType, labelName)
osgLocationId = insertOSGLocation(cursor, ao.getchildren()[0], bgSRID, bgOffset)
insertDB(cursor, 'OSG_LABEL', ('osg_label_name', 'osg_location_id', 'text', 'red', 'green', 'blue', 'rotate_screen', 'outline', 'font'),
(labelName, osgLocationId, ao.get('labelText'),
ao.get('labelColorRed'), ao.get('labelColorGreen'), ao.get('labelColorBlue'),
ao.get('labelRotateScreen'), ao.get('outline'), ao.get('Font')))
else:
msg = 'Updating OSG location %d from %s' % (osgLocationId, uniqueName)
print msg
logging.info(msg)
updateOSGLocation(cursor, osgLocationId, ao.getchildren()[0], bgSRID, bgOffset)
else:
if aoType == utils.AO_TYPE_OBJ:
# It is a bounding that has been moved and it is not currently in the DB. Let's insert it!
msg = 'Insert missing OSG_ITEM_OBJECT (%s,%s)' % (itemId, objectId)
print msg
logging.info(msg)
osgLocationId = insertOSGLocation(cursor, ao.getchildren()[0], bgSRID, bgOffset)
insertDB(cursor, 'OSG_ITEM_OBJECT', ('item_id', 'object_number', 'osg_location_id'), (itemId, objectId, osgLocationId))
else:
# log error if object is not found in DB
msg = 'Update not possible. OSG_ITEM_OBJECT from %s not found in DB' % uniqueName
print msg
logging.error(msg)
# Process deletes (only possible for site objects)
deleteAOS = data.xpath('//*[@status="deleted"]')
# loop over all deletes found in the xml config file
for ao in deleteAOS:
uniqueName = ao.get('uniqueName')
(aoType, itemId, rawDataItemId, objectId, labelName) = utils.decodeOSGActiveObjectUniqueName(cursor, uniqueName)
if aoType==None:
msg = 'Ignoring operation on %s. Could not decode uniqueName' % uniqueName
print msg
logging.warning(msg)
else:
if aoType in (utils.AO_TYPE_OBJ, utils.AO_TYPE_LAB):
# check if the object is in the DB
osgLocationId = getOSGLocationId(cursor, aoType, labelName, itemId, objectId)
if osgLocationId != None:
# Delete the OSG-related entries from the DB
msg = 'Deleting OSG related entries for %s' % uniqueName
print msg
logging.info(msg)
deleteOSG(cursor, aoType, labelName, itemId, objectId)
else:
# log error if object is not found in DB
msg = 'Not possible to delete. OSG_ITEM_OBJECT from %s not found in DB. Maybe already deleted?' % uniqueName
print msg
logging.warning(msg)
else:
# log error if trying to delete a non-site object
msg = 'Ignoring delete in %s: Meshes, pictures and PCs can not be deleted' % uniqueName
print msg
logging.error(msg)
# Process new objects (only possible for site objects)
newAOS = data.xpath('//*[@status="new"]')
# loop over all new objects found in the xml config file
for ao in newAOS:
uniqueName = ao.get('uniqueName')
(aoType, itemId, rawDataItemId, objectId, labelName) = utils.decodeOSGActiveObjectUniqueName(cursor, uniqueName)
if aoType==None:
msg = 'Ignoring operation on %s. Could not decode uniqueName' % uniqueName
print msg
logging.warning(msg)
else:
if aoType in (utils.AO_TYPE_OBJ, utils.AO_TYPE_LAB):
# check if the object is in the DBbesafe i
osgLocationId = getOSGLocationId(cursor, aoType, labelName, itemId, objectId)
if osgLocationId != None:
# log error if the new object is already in the DB
msg = 'OSG_ITEM_OBJECT from %s already in DB. Ignoring add' % uniqueName
print msg
logging.warning(msg)
else:
osgLocationId = insertOSGLocation(cursor, ao.getchildren()[0], bgSRID, bgOffset)
if aoType == utils.AO_TYPE_OBJ:
# add object to the DB
if objectId == utils.ITEM_OBJECT_NUMBER_ITEM:
msg = 'Adding missing ITEM %s' % objectId
print msg
logging.info(msg)
insertDB(cursor, 'ITEM', ('item_id', 'background'), (itemId, False))
msg = 'Adding ITEM_OBJECT (%d,%d)' % (itemId, objectId)
print msg
logging.info(msg)
insertDB(cursor, 'ITEM_OBJECT', ('item_id', 'object_number'), (itemId, objectId))
insertDB(cursor, 'OSG_ITEM_OBJECT', ('item_id', 'object_number', 'osg_location_id'), (itemId, objectId, osgLocationId))
else:
# add label to the DB
msg = 'Adding label %s' % uniqueName
print msg
logging.info(msg)
insertDB(cursor, 'OSG_LABEL', ('osg_label_name', 'osg_location_id', 'text', 'red', 'green', 'blue', 'rotate_screen', 'outline', 'font'),
(labelName, osgLocationId, ao.get('labelText'),
ao.get('labelColorRed'), ao.get('labelColorGreen'), ao.get('labelColorBlue'),
ao.get('labelRotateScreen'), ao.get('outline'), ao.get('Font')))
else:
# log error if trying to add a non-site object
msg = 'Ignoring new in %s: Meshes, pictures and PCs can not be added' % uniqueName
print msg
logging.error(msg)
# Process the cameras (the DEF CAMs are added for all objects and can not be deleted or updated)
cameras = data.xpath('//camera[not(starts-with(@name,"' + utils.DEFAULT_CAMERA_PREFIX + '"))]')
# Delete all previous cameras and related entries
deleteCameras(cursor)
# add all cameras
for camera in cameras:
name = camera.get('name')
itemId = None
if name.count(utils.USER_CAMERA):
try:
itemId = int(name[name.index(utils.USER_CAMERA) + len(utils.USER_CAMERA):].split('_')[0])
except:
msg = 'Incorrect name %s for a ITEM camera' % name
print msg
logging.warn(msg)
itemId = None
msg = 'Adding camera %s' % name
print msg
logging.info(msg)
osgLocationId = insertOSGLocation(cursor, camera, bgSRID, bgOffset)
insertDB(cursor, 'OSG_CAMERA', ('osg_camera_name', 'osg_location_id'), (name, osgLocationId))
if itemId != None:
insertDB(cursor, 'OSG_ITEM_CAMERA', ('item_id', 'osg_camera_name'), (itemId, name))
# close DB connection
utils.closeConnectionDB(connection, cursor)
elapsed_time = time.time() - t0
msg = 'Finished. Total elapsed time: %.02f seconds. See %s' % (elapsed_time, logname)
print(msg)
logging.info(msg)
'''
check if outputdir exists and create if not
'''
if not os.path.exists(self.outputdir):
os.makedirs(self.outputdir)
if __name__ == "__main__":
# define argument menu
description = 'Get data KNMI reference stations'
parser = argparse.ArgumentParser(description=description)
# fill argument groups
parser.add_argument('-o', '--outputdir', help='Data output directory',
default=os.path.join(os.getcwd(),'KNMI'),
required=False)
parser.add_argument('-s', '--stationid', help='Station id',
default='', required=False, action='store')
parser.add_argument('-c', '--csvfile', help='CSV data file',
required=True, action='store')
parser.add_argument('-k', '--keep', help='Keep downloaded files',
required=False, action='store_true')
parser.add_argument('-l', '--log', help='Log level',
choices=utils.LOG_LEVELS_LIST,
default=utils.DEFAULT_LOG_LEVEL)
# extract user entered arguments
opts = parser.parse_args()
# define logger
logname = os.path.basename(__file__) + '.log'
logger = utils.start_logging(filename=logname, level=opts.log)
# process data
get_knmi_reference_data(opts)
def cli_main():
log_file = 'stdout' # auto-name the log file
log_level = ''
utils.start_logging(log_file=log_file, log_level='INFO',
verbose=False) # start logging
parse_arguments()