def read_udfs(pickleSer, infile, eval_type):
num_udfs = read_int(infile)
udfs = {}
call_udf = []
for i in range(num_udfs):
arg_offsets, udf = read_single_udf(pickleSer, infile, eval_type)
udfs['f%d' % i] = udf
args = ["a[%d]" % o for o in arg_offsets]
call_udf.append("f%d(%s)" % (i, ", ".join(args)))
# Create function like this:
# lambda a: (f0(a0), f1(a1, a2), f2(a3))
# 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.
mapper_str = "lambda a: (%s)" % (", ".join(call_udf))
mapper = eval(mapper_str, udfs)
func = lambda _, it: map(mapper, it)
if eval_type in (PythonEvalType.SQL_SCALAR_PANDAS_UDF,
PythonEvalType.SQL_GROUPED_MAP_PANDAS_UDF):
timezone = utf8_deserializer.loads(infile)
ser = ArrowStreamPandasSerializer(timezone)
else:
ser = BatchedSerializer(PickleSerializer(), 100)
# 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)
ser = ArrowStreamPandasSerializer(timezone)
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
def _create_from_pandas_with_arrow(self, pdf, schema, timezone):
"""
Create a DataFrame from a given pandas.DataFrame by slicing it into partitions, converting
to Arrow data, then sending to the JVM to parallelize. If a schema is passed in, the
data types will be used to coerce the data in Pandas to Arrow conversion.
"""
from distutils.version import LooseVersion
from pyspark.serializers import ArrowStreamPandasSerializer
from pyspark.sql.types import from_arrow_type, to_arrow_type, TimestampType
from pyspark.sql.utils import require_minimum_pandas_version, \
require_minimum_pyarrow_version
require_minimum_pandas_version()
require_minimum_pyarrow_version()
from pandas.api.types import is_datetime64_dtype, is_datetime64tz_dtype
import pyarrow as pa
# Create the Spark schema from list of names passed in with Arrow types
if isinstance(schema, (list, tuple)):
if LooseVersion(pa.__version__) < LooseVersion("0.12.0"):
temp_batch = pa.RecordBatch.from_pandas(pdf[0:100], preserve_index=False)
arrow_schema = temp_batch.schema
else:
arrow_schema = pa.Schema.from_pandas(pdf, preserve_index=False)
struct = StructType()
for name, field in zip(schema, arrow_schema):
struct.add(name, from_arrow_type(field.type), nullable=field.nullable)
schema = struct
# Determine arrow types to coerce data when creating batches
if isinstance(schema, StructType):
arrow_types = [to_arrow_type(f.dataType) for f in schema.fields]
elif isinstance(schema, DataType):
raise ValueError("Single data type %s is not supported with Arrow" % str(schema))
else:
# Any timestamps must be coerced to be compatible with Spark
arrow_types = [to_arrow_type(TimestampType())
if is_datetime64_dtype(t) or is_datetime64tz_dtype(t) else None
for t in pdf.dtypes]
# Slice the DataFrame to be batched
step = -(-len(pdf) // self.sparkContext.defaultParallelism) # round int up
pdf_slices = (pdf[start:start + step] for start in xrange(0, len(pdf), step))
# Create list of Arrow (columns, type) for serializer dump_stream
arrow_data = [[(c, t) for (_, c), t in zip(pdf_slice.iteritems(), arrow_types)]
for pdf_slice in pdf_slices]
jsqlContext = self._wrapped._jsqlContext
safecheck = self._wrapped._conf.arrowSafeTypeConversion()
col_by_name = True # col by name only applies to StructType columns, can't happen here
ser = ArrowStreamPandasSerializer(timezone, safecheck, col_by_name)
def reader_func(temp_filename):
return self._jvm.PythonSQLUtils.readArrowStreamFromFile(jsqlContext, temp_filename)
def create_RDD_server():
return self._jvm.ArrowRDDServer(jsqlContext)
# Create Spark DataFrame from Arrow stream file, using one batch per partition
jrdd = self._sc._serialize_to_jvm(arrow_data, ser, reader_func, create_RDD_server)
jdf = self._jvm.PythonSQLUtils.toDataFrame(jrdd, schema.json(), jsqlContext)
df = DataFrame(jdf, self._wrapped)
df._schema = schema
return df