def _handle_raw_fname(self, raw_fname, column_names=None):
"""
Handle result of upload_file
:param raw_fname: A raw key
:return: Part of the H2OFrame constructor.
"""
# perform the parse setup
setup = h2o.parse_setup(raw_fname)
# blocking parse, first line is always a header (since "we" wrote the data out)
parse = h2o.parse(setup, H2OFrame.py_tmp_key(), first_line_is_header=1)
# a hack to get the column names correct since "parse" does not provide them
if column_names and not parse["columnNames"]:
cols = column_names
else:
cols = parse['columnNames']
# set the rows
rows = parse['rows']
# set the vector keys
veckeys = parse['vecKeys']
# create a new vec[] array
self._vecs = H2OVec.new_vecs(zip(cols, veckeys), rows)
# print some information on the *uploaded* data
print "Uploaded", raw_fname, "into cluster with", \
rows, "rows and", len(cols), "cols"
print
def _handle_text_key(self, text_key, column_names): """ Handle result of upload_file :param test_key: A key pointing to raw text to be parsed :return: Part of the H2OFrame constructor. """ # perform the parse setup setup = h2o.parse_setup(text_key) # blocking parse, first line is always a header (since "we" wrote the data out) parse = h2o.parse(setup, H2OFrame.py_tmp_key(), first_line_is_header=1) # a hack to get the column names correct since "parse" does not provide them cols = parse['column_names'] if parse["column_names"] else ["C" + str(x) for x in range(1,len(parse['vec_ids'])+1)] # set the rows rows = parse['rows'] # set the vector keys veckeys = parse['vec_ids'] # create a new vec[] array self._vecs = H2OVec.new_vecs(zip(cols, veckeys), rows) # print some information on the *uploaded* data print "Uploaded", text_key, "into cluster with", rows, "rows and", len(cols), "cols"
def __init__(self, python_obj=None, local_fname=None, remote_fname=None, vecs=None, text_key=None):
"""
Create a new H2OFrame object by passing a file path or a list of H2OVecs.
If `remote_fname` is not None, then a REST call will be made to import the
data specified at the location `remote_fname`. This path is relative to the
H2O cluster, NOT the local Python process
If `local_fname` is not None, then the data is not imported into the H2O cluster
at the time of object creation.
If `python_obj` is not None, then an attempt to upload the python object to H2O
will be made. A valid python object has type `list`, or `dict`.
For more information on the structure of the input for the various native python
data types ("native" meaning non-H2O), please see the general documentation for
this object.
:param python_obj: A "native" python object - list, dict, tuple.
:param local_fname: A local path to a data source. Data is python-process-local.
:param remote_fname: A remote path to a data source. Data is cluster-local.
:param vecs: A list of H2OVec objects.
:param text_key: A raw key resulting from an upload_file.
:return: An instance of an H2OFrame object.
"""
self.local_fname = local_fname
self.remote_fname = remote_fname
self._vecs = None
if python_obj is not None: # avoids the truth value of an array is ambiguous err
self._upload_python_object(python_obj)
return
# Import the data into H2O cluster
if remote_fname:
rawkey = h2o.import_file(remote_fname)
setup = h2o.parse_setup(rawkey)
parse = h2o.parse(setup, H2OFrame.py_tmp_key()) # create a new key
veckeys = parse['vec_ids']
rows = parse['rows']
cols = parse['column_names'] if parse["column_names"] else ["C" + str(x) for x in range(1,len(veckeys)+1)]
self._vecs = H2OVec.new_vecs(zip(cols, veckeys), rows)
print "Imported", remote_fname, "into cluster with", rows, "rows and", len(cols), "cols"
# Read data locally into python process
elif local_fname:
with open(local_fname, 'rb') as csvfile:
self._vecs = []
for name in csvfile.readline().split(','):
self._vecs.append(H2OVec(name.rstrip(), Expr([])))
for row in csv.reader(csvfile):
for i, data in enumerate(row):
self._vecs[i].append(data)
print "Imported", local_fname, "into local python process"
# Construct from an array of Vecs already passed in
elif vecs:
vlen = len(vecs[0])
for v in vecs:
if not isinstance(v, H2OVec):
raise ValueError("Not a list of Vecs")
if len(v) != vlen:
raise ValueError("Vecs not the same size: " + str(vlen) + " != " + str(len(v)))
self._vecs = vecs
elif text_key:
self._handle_text_key(text_key, None)
else:
raise ValueError("Frame made from CSV file or an array of Vecs only")