def read_udfs(pickleSer, infile, eval_type):
runner_conf = {}
if eval_type in (PythonEvalType.SQL_SCALAR_PANDAS_UDF,
PythonEvalType.SQL_COGROUPED_MAP_PANDAS_UDF,
PythonEvalType.SQL_SCALAR_PANDAS_ITER_UDF,
PythonEvalType.SQL_MAP_PANDAS_ITER_UDF,
PythonEvalType.SQL_GROUPED_MAP_PANDAS_UDF,
PythonEvalType.SQL_GROUPED_AGG_PANDAS_UDF,
PythonEvalType.SQL_WINDOW_AGG_PANDAS_UDF):
# Load conf used for pandas_udf evaluation
num_conf = read_int(infile)
for i in range(num_conf):
k = utf8_deserializer.loads(infile)
v = utf8_deserializer.loads(infile)
runner_conf[k] = v
# NOTE: if timezone is set here, that implies respectSessionTimeZone is True
timezone = runner_conf.get("spark.sql.session.timeZone", None)
safecheck = runner_conf.get(
"spark.sql.execution.pandas.arrowSafeTypeConversion",
"false").lower() == 'true'
# Used by SQL_GROUPED_MAP_PANDAS_UDF and SQL_SCALAR_PANDAS_UDF when returning StructType
assign_cols_by_name = runner_conf.get(
"spark.sql.legacy.execution.pandas.groupedMap.assignColumnsByName", "true")\
.lower() == "true"
if eval_type == PythonEvalType.SQL_COGROUPED_MAP_PANDAS_UDF:
ser = CogroupUDFSerializer(timezone, safecheck,
assign_cols_by_name)
else:
# Scalar Pandas UDF handles struct type arguments as pandas DataFrames instead of
# pandas Series. See SPARK-27240.
df_for_struct = (
eval_type == PythonEvalType.SQL_SCALAR_PANDAS_UDF
or eval_type == PythonEvalType.SQL_SCALAR_PANDAS_ITER_UDF
or eval_type == PythonEvalType.SQL_MAP_PANDAS_ITER_UDF)
ser = ArrowStreamPandasUDFSerializer(timezone, safecheck,
assign_cols_by_name,
df_for_struct)
else:
ser = BatchedSerializer(PickleSerializer(), 100)
num_udfs = read_int(infile)
is_scalar_iter = eval_type == PythonEvalType.SQL_SCALAR_PANDAS_ITER_UDF
is_map_iter = eval_type == PythonEvalType.SQL_MAP_PANDAS_ITER_UDF
if is_scalar_iter or is_map_iter:
if is_scalar_iter:
assert num_udfs == 1, "One SCALAR_ITER UDF expected here."
if is_map_iter:
assert num_udfs == 1, "One MAP_ITER UDF expected here."
arg_offsets, udf = read_single_udf(pickleSer,
infile,
eval_type,
runner_conf,
udf_index=0)
def func(_, iterator):
num_input_rows = [0]
def map_batch(batch):
udf_args = [batch[offset] for offset in arg_offsets]
num_input_rows[0] += len(udf_args[0])
if len(udf_args) == 1:
return udf_args[0]
else:
return tuple(udf_args)
iterator = map(map_batch, iterator)
result_iter = udf(iterator)
num_output_rows = 0
for result_batch, result_type in result_iter:
num_output_rows += len(result_batch)
assert is_map_iter or num_output_rows <= num_input_rows[0], \
"Pandas MAP_ITER UDF outputted more rows than input rows."
yield (result_batch, result_type)
if is_scalar_iter:
try:
next(iterator)
except StopIteration:
pass
else:
raise RuntimeError(
"SQL_SCALAR_PANDAS_ITER_UDF should exhaust the input "
"iterator.")
if is_scalar_iter and num_output_rows != num_input_rows[0]:
raise RuntimeError(
"The number of output rows of pandas iterator UDF should be "
"the same with input rows. The input rows number is %d but the "
"output rows number is %d." %
(num_input_rows[0], num_output_rows))
# profiling is not supported for UDF
return func, None, ser, ser
def extract_key_value_indexes(grouped_arg_offsets):
"""
Helper function to extract the key and value indexes from arg_offsets for the grouped and
cogrouped pandas udfs. See BasePandasGroupExec.resolveArgOffsets for equivalent scala code.
:param grouped_arg_offsets: List containing the key and value indexes of columns of the
DataFrames to be passed to the udf. It consists of n repeating groups where n is the
number of DataFrames. Each group has the following format:
group[0]: length of group
group[1]: length of key indexes
group[2.. group[1] +2]: key attributes
group[group[1] +3 group[0]]: value attributes
"""
parsed = []
idx = 0
while idx < len(grouped_arg_offsets):
offsets_len = grouped_arg_offsets[idx]
idx += 1
offsets = grouped_arg_offsets[idx:idx + offsets_len]
split_index = offsets[0] + 1
offset_keys = offsets[1:split_index]
offset_values = offsets[split_index:]
parsed.append([offset_keys, offset_values])
idx += offsets_len
return parsed
udfs = {}
call_udf = []
mapper_str = ""
if eval_type == PythonEvalType.SQL_GROUPED_MAP_PANDAS_UDF:
# Create function like this:
# lambda a: f([a[0]], [a[0], a[1]])
# We assume there is only one UDF here because grouped map doesn't
# support combining multiple UDFs.
assert num_udfs == 1
# See FlatMapGroupsInPandasExec for how arg_offsets are used to
# distinguish between grouping attributes and data attributes
arg_offsets, udf = read_single_udf(pickleSer,
infile,
eval_type,
runner_conf,
udf_index=0)
udfs['f'] = udf
parsed_offsets = extract_key_value_indexes(arg_offsets)
keys = ["a[%d]" % (o, ) for o in parsed_offsets[0][0]]
vals = ["a[%d]" % (o, ) for o in parsed_offsets[0][1]]
mapper_str = "lambda a: f([%s], [%s])" % (", ".join(keys),
", ".join(vals))
elif eval_type == PythonEvalType.SQL_COGROUPED_MAP_PANDAS_UDF:
# We assume there is only one UDF here because cogrouped map doesn't
# support combining multiple UDFs.
assert num_udfs == 1
arg_offsets, udf = read_single_udf(pickleSer,
infile,
eval_type,
runner_conf,
udf_index=0)
udfs['f'] = udf
parsed_offsets = extract_key_value_indexes(arg_offsets)
df1_keys = ["a[0][%d]" % (o, ) for o in parsed_offsets[0][0]]
df1_vals = ["a[0][%d]" % (o, ) for o in parsed_offsets[0][1]]
df2_keys = ["a[1][%d]" % (o, ) for o in parsed_offsets[1][0]]
df2_vals = ["a[1][%d]" % (o, ) for o in parsed_offsets[1][1]]
mapper_str = "lambda a: f([%s], [%s], [%s], [%s])" % (
", ".join(df1_keys), ", ".join(df1_vals), ", ".join(df2_keys),
", ".join(df2_vals))
else:
# Create function like this:
# lambda a: (f0(a[0]), f1(a[1], a[2]), f2(a[3]))
# In the special case of a single UDF this will return a single result rather
# than a tuple of results; this is the format that the JVM side expects.
for i in range(num_udfs):
arg_offsets, udf = read_single_udf(pickleSer,
infile,
eval_type,
runner_conf,
udf_index=i)
udfs['f%d' % i] = udf
args = ["a[%d]" % o for o in arg_offsets]
call_udf.append("f%d(%s)" % (i, ", ".join(args)))
mapper_str = "lambda a: (%s)" % (", ".join(call_udf))
mapper = eval(mapper_str, udfs)
func = lambda _, it: map(mapper, it)
# profiling is not supported for UDF
return func, None, ser, ser
def read_udfs(pickleSer, infile, eval_type):
runner_conf = {}
if eval_type in (PythonEvalType.SQL_SCALAR_PANDAS_UDF,
PythonEvalType.SQL_SCALAR_PANDAS_ITER_UDF,
PythonEvalType.SQL_MAP_PANDAS_ITER_UDF,
PythonEvalType.SQL_GROUPED_MAP_PANDAS_UDF,
PythonEvalType.SQL_GROUPED_AGG_PANDAS_UDF,
PythonEvalType.SQL_WINDOW_AGG_PANDAS_UDF):
# Load conf used for pandas_udf evaluation
num_conf = read_int(infile)
for i in range(num_conf):
k = utf8_deserializer.loads(infile)
v = utf8_deserializer.loads(infile)
runner_conf[k] = v
# NOTE: if timezone is set here, that implies respectSessionTimeZone is True
timezone = runner_conf.get("spark.sql.session.timeZone", None)
safecheck = runner_conf.get(
"spark.sql.execution.pandas.arrowSafeTypeConversion",
"false").lower() == 'true'
# Used by SQL_GROUPED_MAP_PANDAS_UDF and SQL_SCALAR_PANDAS_UDF when returning StructType
assign_cols_by_name = runner_conf.get(
"spark.sql.legacy.execution.pandas.groupedMap.assignColumnsByName", "true")\
.lower() == "true"
# Scalar Pandas UDF handles struct type arguments as pandas DataFrames instead of
# pandas Series. See SPARK-27240.
df_for_struct = (
eval_type == PythonEvalType.SQL_SCALAR_PANDAS_UDF
or eval_type == PythonEvalType.SQL_SCALAR_PANDAS_ITER_UDF
or eval_type == PythonEvalType.SQL_MAP_PANDAS_ITER_UDF)
ser = ArrowStreamPandasUDFSerializer(timezone, safecheck,
assign_cols_by_name,
df_for_struct)
else:
ser = BatchedSerializer(PickleSerializer(), 100)
num_udfs = read_int(infile)
is_scalar_iter = eval_type == PythonEvalType.SQL_SCALAR_PANDAS_ITER_UDF
is_map_iter = eval_type == PythonEvalType.SQL_MAP_PANDAS_ITER_UDF
if is_scalar_iter or is_map_iter:
if is_scalar_iter:
assert num_udfs == 1, "One SCALAR_ITER UDF expected here."
if is_map_iter:
assert num_udfs == 1, "One MAP_ITER UDF expected here."
arg_offsets, udf = read_single_udf(pickleSer,
infile,
eval_type,
runner_conf,
udf_index=0)
def func(_, iterator):
num_input_rows = [0]
def map_batch(batch):
udf_args = [batch[offset] for offset in arg_offsets]
num_input_rows[0] += len(udf_args[0])
if len(udf_args) == 1:
return udf_args[0]
else:
return tuple(udf_args)
iterator = map(map_batch, iterator)
result_iter = udf(iterator)
num_output_rows = 0
for result_batch, result_type in result_iter:
num_output_rows += len(result_batch)
assert is_map_iter or num_output_rows <= num_input_rows[0], \
"Pandas MAP_ITER UDF outputted more rows than input rows."
yield (result_batch, result_type)
if is_scalar_iter:
try:
next(iterator)
except StopIteration:
pass
else:
raise RuntimeError(
"SQL_SCALAR_PANDAS_ITER_UDF should exhaust the input "
"iterator.")
if is_scalar_iter and num_output_rows != num_input_rows[0]:
raise RuntimeError(
"The number of output rows of pandas iterator UDF should be "
"the same with input rows. The input rows number is %d but the "
"output rows number is %d." %
(num_input_rows[0], num_output_rows))
# profiling is not supported for UDF
return func, None, ser, ser
udfs = {}
call_udf = []
mapper_str = ""
if eval_type == PythonEvalType.SQL_GROUPED_MAP_PANDAS_UDF:
# Create function like this:
# lambda a: f([a[0]], [a[0], a[1]])
# We assume there is only one UDF here because grouped map doesn't
# support combining multiple UDFs.
assert num_udfs == 1
# See FlatMapGroupsInPandasExec for how arg_offsets are used to
# distinguish between grouping attributes and data attributes
arg_offsets, udf = read_single_udf(pickleSer,
infile,
eval_type,
runner_conf,
udf_index=0)
udfs['f'] = udf
split_offset = arg_offsets[0] + 1
arg0 = ["a[%d]" % o for o in arg_offsets[1:split_offset]]
arg1 = ["a[%d]" % o for o in arg_offsets[split_offset:]]
mapper_str = "lambda a: f([%s], [%s])" % (", ".join(arg0),
", ".join(arg1))
else:
# Create function like this:
# lambda a: (f0(a[0]), f1(a[1], a[2]), f2(a[3]))
# In the special case of a single UDF this will return a single result rather
# than a tuple of results; this is the format that the JVM side expects.
for i in range(num_udfs):
arg_offsets, udf = read_single_udf(pickleSer,
infile,
eval_type,
runner_conf,
udf_index=i)
udfs['f%d' % i] = udf
args = ["a[%d]" % o for o in arg_offsets]
call_udf.append("f%d(%s)" % (i, ", ".join(args)))
mapper_str = "lambda a: (%s)" % (", ".join(call_udf))
mapper = eval(mapper_str, udfs)
func = lambda _, it: map(mapper, it)
# profiling is not supported for UDF
return func, None, ser, ser
def read_udfs(pickleSer, infile, eval_type):
runner_conf = {}
if eval_type in (PythonEvalType.SQL_SCALAR_PANDAS_UDF,
PythonEvalType.SQL_GROUPED_MAP_PANDAS_UDF,
PythonEvalType.SQL_GROUPED_AGG_PANDAS_UDF,
PythonEvalType.SQL_WINDOW_AGG_PANDAS_UDF):
# Load conf used for pandas_udf evaluation
num_conf = read_int(infile)
for i in range(num_conf):
k = utf8_deserializer.loads(infile)
v = utf8_deserializer.loads(infile)
runner_conf[k] = v
# NOTE: if timezone is set here, that implies respectSessionTimeZone is True
timezone = runner_conf.get("spark.sql.session.timeZone", None)
safecheck = runner_conf.get(
"spark.sql.execution.pandas.arrowSafeTypeConversion",
"false").lower() == 'true'
# Used by SQL_GROUPED_MAP_PANDAS_UDF and SQL_SCALAR_PANDAS_UDF when returning StructType
assign_cols_by_name = runner_conf.get(
"spark.sql.legacy.execution.pandas.groupedMap.assignColumnsByName", "true")\
.lower() == "true"
# Scalar Pandas UDF handles struct type arguments as pandas DataFrames instead of
# pandas Series. See SPARK-27240.
df_for_struct = eval_type == PythonEvalType.SQL_SCALAR_PANDAS_UDF
ser = ArrowStreamPandasUDFSerializer(timezone, safecheck,
assign_cols_by_name,
df_for_struct)
else:
ser = BatchedSerializer(PickleSerializer(), 100)
num_udfs = read_int(infile)
udfs = {}
call_udf = []
mapper_str = ""
if eval_type == PythonEvalType.SQL_GROUPED_MAP_PANDAS_UDF:
# Create function like this:
# lambda a: f([a[0]], [a[0], a[1]])
# We assume there is only one UDF here because grouped map doesn't
# support combining multiple UDFs.
assert num_udfs == 1
# See FlatMapGroupsInPandasExec for how arg_offsets are used to
# distinguish between grouping attributes and data attributes
arg_offsets, udf = read_single_udf(pickleSer,
infile,
eval_type,
runner_conf,
udf_index=0)
udfs['f'] = udf
split_offset = arg_offsets[0] + 1
arg0 = ["a[%d]" % o for o in arg_offsets[1:split_offset]]
arg1 = ["a[%d]" % o for o in arg_offsets[split_offset:]]
mapper_str = "lambda a: f([%s], [%s])" % (", ".join(arg0),
", ".join(arg1))
else:
# Create function like this:
# lambda a: (f0(a[0]), f1(a[1], a[2]), f2(a[3]))
# In the special case of a single UDF this will return a single result rather
# than a tuple of results; this is the format that the JVM side expects.
for i in range(num_udfs):
arg_offsets, udf = read_single_udf(pickleSer,
infile,
eval_type,
runner_conf,
udf_index=i)
udfs['f%d' % i] = udf
args = ["a[%d]" % o for o in arg_offsets]
call_udf.append("f%d(%s)" % (i, ", ".join(args)))
mapper_str = "lambda a: (%s)" % (", ".join(call_udf))
mapper = eval(mapper_str, udfs)
func = lambda _, it: map(mapper, it)
# profiling is not supported for UDF
return func, None, ser, ser