def create_edges(self, input_file_dir, input_file_name, output_file_name):
storage = StorageFactory().get_storage(type='tab_storage', subdir='store',
storage_location=input_file_dir)
dataset = Dataset(in_storage = storage, id_name = ['stop_id','sch_time'], in_table_name = input_file_name)
n = dataset.size()
trip_ids = dataset.get_attribute("stop_id")
unique_trip_ids = unique(trip_ids)
source_list = list()
target_list = list()
time_list = list()
for trip in unique_trip_ids:
idx = where(dataset.get_attribute("stop_id") == trip)[0]
nodes = dataset.get_attribute_by_index("node_id", idx)
times = dataset.get_attribute_by_index("sch_time", idx)
for inode in range(nodes.size-1):
source_list.append(nodes[inode])
target_list.append(nodes[inode+1])
time_list.append(times[inode+1] - times[inode])
storage = StorageFactory().get_storage('dict_storage')
storage.write_table(table_name='edges',
table_data={
'edge_id': arange(len(source_list))+1,
'source': array(source_list), #type=int64), # <<<< OUTPUT FIELD, USE array
'target': array(target_list), #type=int64), # <<<< OUTPUT FIELD, USE array
'cost': array(time_list, dtype=int32)
}
)
edges = Dataset(in_storage=storage, in_table_name='edges', id_name = "edge_id")
edges.write_dataset(attributes = ["source", "target", "cost"], out_storage = storage, out_table_name = output_file_name)
def create_edges(self, input_file_dir, input_file_name, output_file_name):
storage = StorageFactory().get_storage(type='tab_storage',
subdir='store',
storage_location=input_file_dir)
dataset = Dataset(in_storage=storage,
id_name=['stop_id', 'sch_time'],
in_table_name=input_file_name)
n = dataset.size()
trip_ids = dataset.get_attribute("stop_id")
unique_trip_ids = unique(trip_ids)
source_list = list()
target_list = list()
time_list = list()
for trip in unique_trip_ids:
idx = where(dataset.get_attribute("stop_id") == trip)[0]
nodes = dataset.get_attribute_by_index("node_id", idx)
times = dataset.get_attribute_by_index("sch_time", idx)
for inode in range(nodes.size - 1):
source_list.append(nodes[inode])
target_list.append(nodes[inode + 1])
time_list.append(times[inode + 1] - times[inode])
storage = StorageFactory().get_storage('dict_storage')
storage.write_table(
table_name='edges',
table_data={
'edge_id': arange(len(source_list)) + 1,
'source': array(
source_list), #type=int64), # <<<< OUTPUT FIELD, USE array
'target': array(
target_list), #type=int64), # <<<< OUTPUT FIELD, USE array
'cost': array(time_list, dtype=int32)
})
edges = Dataset(in_storage=storage,
in_table_name='edges',
id_name="edge_id")
edges.write_dataset(attributes=["source", "target", "cost"],
out_storage=storage,
out_table_name=output_file_name)
def test_flt_dataset(self):
import opus_core
from opus_core.store.flt_storage import flt_storage
attribute = 'little_endian'
location = os.path.join(opus_core.__path__[0], 'data', 'flt')
storage = flt_storage(storage_location=location)
ds = Dataset(in_storage=storage, id_name=attribute, in_table_name='endians')
self.assertAlmostEqual(11.0, ds.get_attribute_by_index(attribute, 0))
self.assertEqual(None, ds.get_attribute_header(attribute))
