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 or float
cls._entry(path, 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.
sc = spark_context()
if os.path.isdir(path):
res = XRdd(sc.pickleFile(path))
metadata_path = os.path.join(path, '_metadata')
with open(metadata_path) as f:
dtype = pickle.load(f)
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))
else:
res = res.map(lambda x: dtype(x))
cls._exit()
return cls(res, dtype)
def load_from_iterable(cls, values, dtype, ignore_cast_failure):
"""
Load RDD from values given by iterable.
Note
----
Values must not only be iterable, but also it must support len and __getitem__
Modifies the existing RDD: does not return a new XArray.
"""
cls._entry(values, dtype, ignore_cast_failure)
dtype = dtype or None
sc = spark_context()
try:
if len(values) == 0:
cls._exit()
return XArrayImpl(XRdd(sc.parallelize([])), dtype)
dtype = dtype or infer_type_of_list(values[0:100])
except TypeError:
# get here if values does not support len or __getitem
pass
if dtype is None:
# try iterating and see if we get something
cpy = copy.copy(values)
for val in cpy:
dtype = infer_type_of_list([val])
break
if dtype is None:
raise TypeError('Cannot determine types.')
def do_cast(x, dtype, ignore_cast_failure):
if is_missing(x): return x
if type(x) == dtype:
return x
try:
return dtype(x)
except (ValueError, TypeError):
# TODO: this does not seem to cach as it should
return None if ignore_cast_failure else ValueError
raw_rdd = XRdd(sc.parallelize(values))
rdd = raw_rdd.map(lambda x: do_cast(x, dtype, ignore_cast_failure))
if not ignore_cast_failure:
errs = len(rdd.filter(lambda x: x is ValueError).take(1)) == 1
if errs: raise ValueError
cls._exit()
return cls(rdd, dtype)