def check_output_uri(uri):
dirname = os.path.dirname(uri)
if not fileio.exists(dirname):
fileio.make_dir(dirname)
if not fileio.exists(dirname):
raise ValueError(
'Output directory does not exist: {}'.format(dirname))
def check_input_uri(uri):
if "," in uri:
uri_list = uri.split(",")
else:
uri_list = [uri]
for path in uri_list:
if not fileio.exists(path):
raise ValueError("Input file does not exist: {}".format(path))
def check_input_uri(uri):
if ',' in uri:
uri_list = uri.split(',')
else:
uri_list = [uri]
for path in uri_list:
if not fileio.exists(path):
raise ValueError('Input file does not exist: {}'.format(path))
def load_autodetect(cls, path, dtype):
"""
Load from the given path.
This can be anything that spark will read from: local file or HDFS file.
It can also be a directory, and spark will read and concatenate them all.
"""
# Read the file as string
# Examine the first 100 lines, and cast if necessary to int, float, or datetime
cls._entry(path=path, dtype=dtype)
# If the path is a directory, then look for sarray-data file in the directory.
# If the path is a file, look for that file
# Use type inference to determine the element type.
# Passed-in dtype is always str and is ignored.
lineage = Lineage.init_array_lineage(path)
sc = CommonSparkContext.spark_context()
if os.path.isdir(path):
res = XRdd(sc.pickleFile(path))
metadata_path = os.path.join(path, '_metadata')
with fileio.open_file(metadata_path) as f:
dtype = pickle.load(f)
lineage_path = os.path.join(path, '_lineage')
if fileio.exists(lineage_path):
lineage = Lineage.load(lineage_path)
else:
res = XRdd(sc.textFile(path, use_unicode=False))
dtype = infer_type(res)
if dtype != str:
if dtype in (list, dict):
res = res.map(lambda x: ast.literal_eval(x))
elif dtype is datetime.datetime:
res = res.map(lambda x: date_parser.parse(x))
else:
res = res.map(lambda x: dtype(x))
return cls(res, dtype, lineage)
def load_autodetect(cls, path, dtype):
"""
Load from the given path.
This can be anything that spark will read from: local file or HDFS file.
It can also be a directory, and spark will read and concatenate them all.
"""
# Read the file as string
# Examine the first 100 lines, and cast if necessary to int, float, or datetime
cls._entry(path=path, dtype=dtype)
# If the path is a directory, then look for sarray-data file in the directory.
# If the path is a file, look for that file
# Use type inference to determine the element type.
# Passed-in dtype is always str and is ignored.
lineage = Lineage.init_array_lineage(path)
sc = CommonSparkContext.spark_context()
if os.path.isdir(path):
res = XRdd(sc.pickleFile(path))
metadata_path = os.path.join(path, '_metadata')
with fileio.open_file(metadata_path) as f:
dtype = pickle.load(f)
lineage_path = os.path.join(path, '_lineage')
if fileio.exists(lineage_path):
lineage = Lineage.load(lineage_path)
else:
res = XRdd(sc.textFile(path, use_unicode=False))
dtype = infer_type(res)
if dtype != str:
if dtype in (list, dict):
res = res.map(lambda x: ast.literal_eval(x))
elif dtype is datetime.datetime:
res = res.map(lambda x: date_parser.parse(x))
else:
res = res.map(lambda x: dtype(x))
return cls(res, dtype, lineage)
def check_output_uri(uri):
dirname = os.path.dirname(uri)
if not fileio.exists(dirname):
fileio.make_dir(dirname)
if not fileio.exists(dirname):
raise ValueError("Output directory does not exist: {}".format(dirname))