def manager(**args):
db_nums = list(enumerate(['users', 'response', 'state', 'key_to_path', 'path_to_key', 'tasks']))
logging.debug(db_nums)
args.update(dict((y + '_db', redis.StrictRedis(host=args['redis_address'], port=args['redis_port'], db=x))
for x, y in db_nums))
logging.debug(args)
sp = lambda x: ROOT + '/static_private/' + x
# Used if we want to use a specific data connection instead of creating one, by setting to None
# data connections can be disallowed (useful if one is not needed)
try:
if args['data_connection']:
args['data_source'] = data_source_from_uri(args['data'], data_connection=args['data_connection'])
else:
args['data_source'] = None
except KeyError:
args['data_source'] = data_source_from_uri(args['data'])
if args['type'] == 'image_class':
m = mturk_vision.AMTImageClassManager(index_path=sp('image_label.html'),
config_path=sp('image_class_config.js'),
**args)
elif args['type'] == 'image_qa':
m = mturk_vision.AMTImageQAManager(index_path=sp('image_qa.html'),
config_path=sp('image_qa_config.js'),
**args)
else:
raise ValueError('Unknown type[%s]' % args['type'])
if args['sync']:
m.sync()
return m
def test_dir(self):
import tempfile
import shutil
import os
temp_dir = None
try:
temp_dir = tempfile.mkdtemp()
for x in xrange(100):
d = os.path.join(temp_dir, str(x))
try:
os.mkdir(d)
except OSError:
pass
for y in range(10):
open(os.path.join(d, 'colfam1:col%d' % y),
'w').write(str(x))
ds = data_sources.DirectoryDataSource({'mydata': 'colfam1:col0'},
temp_dir)
print list(ds.rows())
print list(ds.columns(list(ds.rows())[0]))
print list(ds.column_values(list(ds.rows())[0]))
print[(x, list(y)) for x, y in ds.row_columns()]
print[(x, dict(y)) for x, y in ds.row_column_values()]
print ds.uri
ds = data_sources.data_source_from_uri(ds.uri)
print list(ds.rows())
print list(ds.columns(list(ds.rows())[0]))
print list(ds.column_values(list(ds.rows())[0]))
print[(x, list(y)) for x, y in ds.row_columns()]
print[(x, dict(y)) for x, y in ds.row_column_values()]
print ds.uri
finally:
if temp_dir is not None:
shutil.rmtree(temp_dir)
def test_hbase(self):
import hadoopy_hbase
client = hadoopy_hbase.connect()
try:
client.createTable('testtable',
[hadoopy_hbase.ColumnDescriptor('colfam1:')])
except:
pass
for x in xrange(100):
client.mutateRow('testtable', str(x), [
hadoopy_hbase.Mutation(column='colfam1:col%d' % y,
value=str(x)) for y in range(10)
])
ds = data_sources.HBaseDataSource({'mydata': 'colfam1:col0'},
'testtable')
print list(ds.rows())
print list(ds.columns(list(ds.rows())[0]))
print list(ds.column_values(list(ds.rows())[0]))
print[(x, list(y)) for x, y in ds.row_columns()]
print[(x, dict(y)) for x, y in ds.row_column_values()]
print ds.uri
ds = data_sources.data_source_from_uri(ds.uri)
print list(ds.rows())
print list(ds.columns(list(ds.rows())[0]))
print list(ds.column_values(list(ds.rows())[0]))
print[(x, list(y)) for x, y in ds.row_columns()]
print[(x, dict(y)) for x, y in ds.row_column_values()]
print ds.uri
def manager(**args):
db_nums = list(enumerate(['users', 'response', 'state', 'key_to_path', 'path_to_key', 'tasks']))
logging.debug(db_nums)
args.update(dict((y + '_db', redis.StrictRedis(host=args['redis_address'], port=args['redis_port'], db=x))
for x, y in db_nums))
logging.debug(args)
sp = lambda x: ROOT + '/static_private/' + x
args['data_source'] = data_source_from_uri(args['data'])
if args['type'] == 'image_class':
m = mturk_vision.AMTImageClassManager(index_path=sp('image_label.html'),
config_path=sp('image_class_config.js'),
**args)
elif args['type'] == 'image_qa':
m = mturk_vision.AMTImageQAManager(index_path=sp('image_qa.html'),
config_path=sp('image_qa_config.js'),
**args)
else:
raise ValueError('Unknown type[%s]' % args['type'])
if args['sync']:
m.sync()
return m
import hadoopy_hbase
client = hadoopy_hbase.connect()
try:
client.createTable('testtable', [hadoopy_hbase.ColumnDescriptor('colfam1:')])
except:
pass
for x in xrange(100):
client.mutateRow('testtable', str(x), [hadoopy_hbase.Mutation(column='colfam1:col%d' % y, value=str(x)) for y in range(10)])
ds = data_sources.HBaseDataSource({'mydata': 'colfam1:col0'}, 'testtable')
print list(ds.rows())
print list(ds.columns(list(ds.rows())[0]))
print list(ds.column_values(list(ds.rows())[0]))
print [(x, list(y)) for x, y in ds.row_columns()]
print [(x, dict(y)) for x, y in ds.row_column_values()]
print ds.uri
ds = data_sources.data_source_from_uri(ds.uri)
print list(ds.rows())
print list(ds.columns(list(ds.rows())[0]))
print list(ds.column_values(list(ds.rows())[0]))
print [(x, list(y)) for x, y in ds.row_columns()]
print [(x, dict(y)) for x, y in ds.row_column_values()]
print ds.uri
def test_dir(self):
import tempfile
import shutil
import os
temp_dir = None
try:
temp_dir = tempfile.mkdtemp()
for x in xrange(100):
import numpy as np
y = str(np.fromstring(y, dtype=np.double).tolist())
elif conv == 'str':
pass
elif conv == 'image':
import base64
y = '<img src="data:image/jpeg;base64,%s" />' % base64.b64encode(y)
else:
raise ValueError('Unsupported: ' + conv)
render_columns.append([x, y])
except KeyError:
render_columns.append([x, str(len(y))])
render_rows.append(row + ' | ' + ' '.join([x + '|' + y for x, y in render_columns]))
return '<br>'.join(render_rows)
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Serve data source visualization")
parser.add_argument('data_source')
parser.add_argument('--port',
default='8080')
parser.add_argument('--rows', default=10, type=int)
parser.add_argument('--convert', action='append')
ARGS = parser.parse_args()
print(ARGS.convert)
CONVERT = {}
if ARGS.convert:
CONVERT = dict(x.split('=', 1) for x in ARGS.convert)
DATA = data_sources.data_source_from_uri(ARGS.data_source)
bottle.run(host='0.0.0.0', port=ARGS.port, server='gevent')
(dataset._name, start_time, hdfs_file_cnt))
hdfs_buf.append(x)
if len(hdfs_buf) >= 100:
try:
hadoopy.writetb(
'spatial_queries/input/%s/%f/%d.tb.seq' %
(dataset._name, start_time, hdfs_file_cnt), hdfs_buf)
except IOError, e:
print('Got IOError, skipping')
print(e)
hdfs_file_cnt += 1
hdfs_buf = []
if hdfs_buf:
hadoopy.writetb(
'spatial_queries/input/%s/%f/%d.tb.seq' %
(dataset._name, start_time, hdfs_file_cnt), hdfs_buf)
print('NumClasses[%d]' % len(classes))
print('Classes: %r' % classes)
if __name__ == '__main__':
dataset = vision_data.MSRC()
classes = msrc_classes
if 1:
from data_sources import data_source_from_uri
from sun397_dataset import SUN397
uri = 'hbase://localhost:9090/images?image=data:image_320>=feat:masks_gt'
dataset = SUN397(data_source_from_uri(uri))
classes = json.load(open('classes.js'))
write_texton_hadoop(dataset, classes)
yield str(image_num), (image, label_points)
hdfs_file_cnt = 0
hdfs_buf = []
start_time = time.time()
for x in make_data():
print('spatial_queries/input/%s/%f/%d.tb.seq' % (dataset._name, start_time, hdfs_file_cnt))
hdfs_buf.append(x)
if len(hdfs_buf) >= 100:
try:
hadoopy.writetb('spatial_queries/input/%s/%f/%d.tb.seq' % (dataset._name, start_time, hdfs_file_cnt), hdfs_buf)
except IOError, e:
print('Got IOError, skipping')
print(e)
hdfs_file_cnt += 1
hdfs_buf = []
if hdfs_buf:
hadoopy.writetb('spatial_queries/input/%s/%f/%d.tb.seq' % (dataset._name, start_time, hdfs_file_cnt), hdfs_buf)
print('NumClasses[%d]' % len(classes))
print('Classes: %r' % classes)
if __name__ == '__main__':
dataset = vision_data.MSRC()
classes = msrc_classes
if 1:
from data_sources import data_source_from_uri
from sun397_dataset import SUN397
uri = 'hbase://localhost:9090/images?image=data:image_320>=feat:masks_gt'
dataset = SUN397(data_source_from_uri(uri))
classes = json.load(open('classes.js'))
write_texton_hadoop(dataset, classes)
