def get_frame(frame_id):
if frame_id is None:
raise ValueError("frame_id must not be None")
res = H2OConnection.get_json("Frames/" + urllib.quote(frame_id))
res = res["frames"][0]
colnames = [v["label"] for v in res["columns"]]
veckeys = res["vec_ids"]
vecs = H2OVec.new_vecs(zip(colnames, veckeys), res["rows"])
return H2OFrame(vecs=vecs)
def get_frame(frame_id):
if frame_id is None:
raise ValueError("frame_id must not be None")
res = H2OConnection.get_json("Frames/"+urllib.quote(frame_id))
res = res["frames"][0]
colnames = [v["label"] for v in res["columns"]]
veckeys = res["vec_ids"]
vecs=H2OVec.new_vecs(zip(colnames, veckeys), res["rows"])
return H2OFrame(vecs=vecs)
def ifelse(test, yes, no):
"""
Semantically equivalent to R's ifelse.
Based on the booleans in the test vector, the output has the values of the yes and no
vectors interleaved (or merged together).
:param test: A "test" H2OFrame
:param yes: A "yes" H2OFrame
:param no: A "no" H2OFrame
:return: An H2OFrame
"""
test_a = None
yes_a = None
no_a = None
test_tmp = None
yes_tmp = None
no_tmp = None
if isinstance(test, bool): test_a = "%TRUE" if test else "%FALSE"
else:
if isinstance(test, H2OVec): test_tmp = test._expr.eager()
else: test_tmp = test.key()
test_a = "'" + test_tmp + "'"
if isinstance(yes, (int, float)): yes_a = "#{}".format(str(yes))
elif yes is None: yes_a = "#NaN"
else:
if isinstance(yes, H2OVec): yes_tmp = yes._expr.eager()
else: yes_tmp = yes.key()
yes_a = "'" + yes_tmp + "'"
if isinstance(no, (int, float)): no_a = "#{}".format(str(no))
elif no is None: no_a = "#NaN"
else:
if isinstance(no, H2OVec): no_tmp = no._expr.eager()
else: no_tmp = no.key()
no_a = "'" + no_tmp + "'"
tmp_key = H2OFrame.py_tmp_key()
expr = "(= !{} (ifelse {} {} {}))".format(tmp_key, test_a, yes_a, no_a)
rapids(expr)
j = frame(tmp_key) # Fetch the frame as JSON
fr = j['frames'][0] # Just the first (only) frame
rows = fr['rows'] # Row count
veckeys = fr['vec_ids'] # List of h2o vec keys
cols = fr['columns'] # List of columns
colnames = [col['label'] for col in cols]
vecs = H2OVec.new_vecs(zip(colnames, veckeys),
rows) # Peel the Vecs out of the returned Frame
removeFrameShallow(tmp_key)
if yes_tmp is not None: removeFrameShallow(str(yes_tmp))
if no_tmp is not None: removeFrameShallow(str(no_tmp))
if test_tmp is not None: removeFrameShallow(str(test_tmp))
return H2OFrame(vecs=vecs)
def ifelse(test,yes,no):
"""
Semantically equivalent to R's ifelse.
Based on the booleans in the test vector, the output has the values of the yes and no
vectors interleaved (or merged together).
:param test: A "test" H2OFrame
:param yes: A "yes" H2OFrame
:param no: A "no" H2OFrame
:return: An H2OFrame
"""
test_a=None
yes_a =None
no_a =None
test_tmp = None
yes_tmp = None
no_tmp = None
if isinstance(test, bool): test_a = "%TRUE" if test else "%FALSE"
else:
if isinstance(test,H2OVec): test_tmp = test._expr.eager()
else: test_tmp = test.key()
test_a = "'"+test_tmp+"'"
if isinstance(yes, (int,float)): yes_a = "#{}".format(str(yes))
elif yes is None: yes_a = "#NaN"
else:
if isinstance(yes,H2OVec): yes_tmp = yes._expr.eager()
else: yes_tmp = yes.key()
yes_a = "'"+yes_tmp+"'"
if isinstance(no, (int,float)): no_a = "#{}".format(str(no))
elif no is None: no_a = "#NaN"
else:
if isinstance(no,H2OVec): no_tmp = no._expr.eager()
else: no_tmp = no.key()
no_a = "'"+no_tmp+"'"
tmp_key = H2OFrame.py_tmp_key()
expr = "(= !{} (ifelse {} {} {}))".format(tmp_key,test_a,yes_a,no_a)
rapids(expr)
j = frame(tmp_key) # Fetch the frame as JSON
fr = j['frames'][0] # Just the first (only) frame
rows = fr['rows'] # Row count
veckeys = fr['vec_ids']# List of h2o vec keys
cols = fr['columns'] # List of columns
colnames = [col['label'] for col in cols]
vecs=H2OVec.new_vecs(zip(colnames, veckeys), rows) # Peel the Vecs out of the returned Frame
removeFrameShallow(tmp_key)
if yes_tmp is not None: removeFrameShallow(str(yes_tmp))
if no_tmp is not None: removeFrameShallow(str(no_tmp))
if test_tmp is not None: removeFrameShallow(str(test_tmp))
return H2OFrame(vecs=vecs)
def _simple_un_math_op(op, data):
"""
Element-wise math operations on H2OFrame and H2OVec
:param op: the math operation
:param data: the H2OFrame or H2OVec object to operate on.
:return: H2OFrame or H2oVec, with lazy operation
"""
if isinstance(data, H2OFrame):
return H2OFrame(
vecs=[_simple_un_math_op(op, vec) for vec in data._vecs])
if isinstance(data, H2OVec):
return H2OVec(data._name, Expr(op, left=data, length=len(data)))
raise ValueError, op + " only operates on H2OFrame or H2OVec objects"
def parse_raw(setup, id=None, first_line_is_header=(-1,0,1)): """ Used in conjunction with import_file and parse_setup in order to make alterations before parsing. :param setup: Result of h2o.parse_setup :param id: An optional id for the frame. :param first_line_is_header: -1,0,1 if the first line is to be used as the header :return: An H2OFrame object """ if id is None: id = H2OFrame.py_tmp_key() parsed = parse(setup, id, first_line_is_header) veckeys = parsed['vec_ids'] rows = parsed['rows'] cols = parsed['column_names'] if parsed["column_names"] else ["C" + str(x) for x in range(1,len(veckeys)+1)] vecs = H2OVec.new_vecs(zip(cols, veckeys), rows) return H2OFrame(vecs=vecs)
def rep_len(data, length_out):
if isinstance(data, (str, int)):
tmp_key = H2OFrame.py_tmp_key()
scaler = '#{}'.format(data) if isinstance(data, int) else '\"{}\"'.format(data)
expr = "(= !{} (rep_len {} {}))".format(tmp_key,scaler,'#{}'.format(length_out))
rapids(expr)
j = frame(tmp_key)
fr = j['frames'][0]
rows = fr['rows']
veckeys = fr['vec_ids']
cols = fr['columns']
colnames = [col['label'] for col in cols]
vecs=H2OVec.new_vecs(zip(colnames, veckeys), rows)
removeFrameShallow(tmp_key)
return H2OFrame(vecs=vecs)
return data.rep_len(length_out=length_out)
def parse_raw(setup, id=None, first_line_is_header=(-1, 0, 1)):
"""
Used in conjunction with import_file and parse_setup in order to make alterations before parsing.
:param setup: Result of h2o.parse_setup
:param id: An optional id for the frame.
:param first_line_is_header: -1,0,1 if the first line is to be used as the header
:return: An H2OFrame object
"""
if id is None: id = H2OFrame.py_tmp_key()
parsed = parse(setup, id, first_line_is_header)
veckeys = parsed['vec_ids']
rows = parsed['rows']
cols = parsed['column_names'] if parsed["column_names"] else [
"C" + str(x) for x in range(1,
len(veckeys) + 1)
]
vecs = H2OVec.new_vecs(zip(cols, veckeys), rows)
return H2OFrame(vecs=vecs)
def ls():
"""
List Keys on an H2O Cluster
:return: Returns a list of keys in the current H2O instance
"""
tmp_key = H2OFrame.py_tmp_key()
expr = "(= !{} (ls ))".format(tmp_key)
rapids(expr)
j = frame(tmp_key)
fr = j['frames'][0]
rows = fr['rows']
veckeys = fr['vec_ids']
cols = fr['columns']
colnames = [col['label'] for col in cols]
vecs=H2OVec.new_vecs(zip(colnames, veckeys), rows)
fr = H2OFrame(vecs=vecs)
print "First 10 Keys: "
fr.show()
return as_list(fr, use_pandas=False)
def ls():
"""
List Keys on an H2O Cluster
:return: Returns a list of keys in the current H2O instance
"""
tmp_key = H2OFrame.py_tmp_key()
expr = "(= !{} (ls ))".format(tmp_key)
rapids(expr)
j = frame(tmp_key)
fr = j['frames'][0]
rows = fr['rows']
veckeys = fr['vec_ids']
cols = fr['columns']
colnames = [col['label'] for col in cols]
vecs = H2OVec.new_vecs(zip(colnames, veckeys), rows)
fr = H2OFrame(vecs=vecs)
fr.setNames(["keys"])
print "First 10 Keys: "
fr.show()
return as_list(fr, use_pandas=False)
def cbind(left, right):
"""
:param left: H2OFrame or H2OVec
:param right: H2OFrame or H2OVec
:return: new H2OFrame with left|right cbinded
"""
# Check left and right data types
vecs = []
if isinstance(left, H2OFrame) and isinstance(right, H2OFrame):
vecs = left._vecs + right._vecs
elif isinstance(left, H2OFrame) and isinstance(right, H2OVec):
[vecs.append(vec) for vec in left._vecs]
vecs.append(right)
elif isinstance(left, H2OVec) and isinstance(right, H2OVec):
vecs = [left, right]
elif isinstance(left, H2OVec) and isinstance(right, H2OFrame):
vecs.append(left)
[vecs.append(vec) for vec in right._vecs]
else:
raise ValueError("left and right data must be H2OVec or H2OFrame")
names = [vec.name() for vec in vecs]
fr = H2OFrame.py_tmp_key()
cbind = "(= !" + fr + " (cbind %FALSE %"
cbind += " %".join([vec._expr.eager() for vec in vecs]) + "))"
rapids(cbind)
j = frame(fr)
fr = j['frames'][0]
rows = fr['rows']
vec_ids = fr['vec_ids']
cols = fr['columns']
colnames = [col['label'] for col in cols]
result = H2OFrame(vecs=H2OVec.new_vecs(zip(colnames, vec_ids), rows))
result.setNames(names)
return result
def cbind(left,right):
"""
:param left: H2OFrame or H2OVec
:param right: H2OFrame or H2OVec
:return: new H2OFrame with left|right cbinded
"""
# Check left and right data types
vecs = []
if isinstance(left,H2OFrame) and isinstance(right,H2OFrame):
vecs = left._vecs + right._vecs
elif isinstance(left,H2OFrame) and isinstance(right,H2OVec):
[vecs.append(vec) for vec in left._vecs]
vecs.append(right)
elif isinstance(left,H2OVec) and isinstance(right,H2OVec):
vecs = [left, right]
elif isinstance(left,H2OVec) and isinstance(right,H2OFrame):
vecs.append(left)
[vecs.append(vec) for vec in right._vecs]
else:
raise ValueError("left and right data must be H2OVec or H2OFrame")
names = [vec.name() for vec in vecs]
fr = H2OFrame.py_tmp_key()
cbind = "(= !" + fr + " (cbind %FALSE %"
cbind += " %".join([vec._expr.eager() for vec in vecs]) + "))"
rapids(cbind)
j = frame(fr)
fr = j['frames'][0]
rows = fr['rows']
vec_ids = fr['vec_ids']
cols = fr['columns']
colnames = [col['label'] for col in cols]
result = H2OFrame(vecs=H2OVec.new_vecs(zip(colnames, vec_ids), rows))
result.setNames(names)
return result
