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 pyspark.serializers import ArrowStreamSerializer, _create_batch
from pyspark.sql.types import from_arrow_schema, 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
# 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 Arrow record batches
safecheck = self._wrapped._conf.arrowSafeTypeConversion()
batches = [_create_batch([(c, t) for (_, c), t in zip(pdf_slice.iteritems(), arrow_types)],
timezone, safecheck)
for pdf_slice in pdf_slices]
# Create the Spark schema from the first Arrow batch (always at least 1 batch after slicing)
if isinstance(schema, (list, tuple)):
struct = from_arrow_schema(batches[0].schema)
for i, name in enumerate(schema):
struct.fields[i].name = name
struct.names[i] = name
schema = struct
jsqlContext = self._wrapped._jsqlContext
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(batches, ArrowStreamSerializer(), reader_func,
create_RDD_server)
jdf = self._jvm.PythonSQLUtils.toDataFrame(jrdd, schema.json(), jsqlContext)
df = DataFrame(jdf, self._wrapped)
df._schema = schema
return df
def _create_udf(f, returnType, evalType):
if evalType in (PythonEvalType.SQL_SCALAR_PANDAS_UDF,
PythonEvalType.SQL_GROUPED_MAP_PANDAS_UDF):
import inspect
from pyspark.sql.utils import require_minimum_pyarrow_version
require_minimum_pyarrow_version()
argspec = inspect.getargspec(f)
if evalType == PythonEvalType.SQL_SCALAR_PANDAS_UDF and len(argspec.args) == 0 and \
argspec.varargs is None:
raise ValueError(
"Invalid function: 0-arg pandas_udfs are not supported. "
"Instead, create a 1-arg pandas_udf and ignore the arg in your function."
)
if evalType == PythonEvalType.SQL_GROUPED_MAP_PANDAS_UDF and len(
argspec.args) != 1:
raise ValueError(
"Invalid function: pandas_udfs with function type GROUPED_MAP "
"must take a single arg that is a pandas DataFrame.")
# Set the name of the UserDefinedFunction object to be the name of function f
udf_obj = UserDefinedFunction(f,
returnType=returnType,
name=None,
evalType=evalType,
deterministic=True)
return udf_obj._wrapped()
def _create_udf(f, returnType, evalType):
if evalType in (PythonEvalType.SQL_SCALAR_PANDAS_UDF,
PythonEvalType.SQL_GROUPED_MAP_PANDAS_UDF,
PythonEvalType.SQL_GROUPED_AGG_PANDAS_UDF):
import inspect
from pyspark.sql.utils import require_minimum_pyarrow_version
require_minimum_pyarrow_version()
argspec = inspect.getargspec(f)
if evalType == PythonEvalType.SQL_SCALAR_PANDAS_UDF and len(argspec.args) == 0 and \
argspec.varargs is None:
raise ValueError(
"Invalid function: 0-arg pandas_udfs are not supported. "
"Instead, create a 1-arg pandas_udf and ignore the arg in your function."
)
if evalType == PythonEvalType.SQL_GROUPED_MAP_PANDAS_UDF and len(argspec.args) != 1:
raise ValueError(
"Invalid function: pandas_udfs with function type GROUPED_MAP "
"must take a single arg that is a pandas DataFrame."
)
# Set the name of the UserDefinedFunction object to be the name of function f
udf_obj = UserDefinedFunction(
f, returnType=returnType, name=None, evalType=evalType, deterministic=True)
return udf_obj._wrapped()
def _create_udf(f, returnType, evalType):
if evalType in (PythonEvalType.SQL_SCALAR_PANDAS_UDF,
PythonEvalType.SQL_SCALAR_PANDAS_ITER_UDF,
PythonEvalType.SQL_GROUPED_MAP_PANDAS_UDF,
PythonEvalType.SQL_GROUPED_AGG_PANDAS_UDF):
from pyspark.sql.utils import require_minimum_pyarrow_version
require_minimum_pyarrow_version()
argspec = _get_argspec(f)
if (evalType == PythonEvalType.SQL_SCALAR_PANDAS_UDF or
evalType == PythonEvalType.SQL_SCALAR_PANDAS_ITER_UDF) and \
len(argspec.args) == 0 and \
argspec.varargs is None:
raise ValueError(
"Invalid function: 0-arg pandas_udfs are not supported. "
"Instead, create a 1-arg pandas_udf and ignore the arg in your function."
)
if evalType == PythonEvalType.SQL_GROUPED_MAP_PANDAS_UDF \
and len(argspec.args) not in (1, 2):
raise ValueError(
"Invalid function: pandas_udfs with function type GROUPED_MAP "
"must take either one argument (data) or two arguments (key, data)."
)
# Set the name of the UserDefinedFunction object to be the name of function f
udf_obj = UserDefinedFunction(f,
returnType=returnType,
name=None,
evalType=evalType,
deterministic=True)
return udf_obj._wrapped()
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 pyspark.serializers import ArrowStreamSerializer, _create_batch
from pyspark.sql.types import from_arrow_schema, 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
# 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 Arrow record batches
batches = [_create_batch([(c, t) for (_, c), t in zip(pdf_slice.iteritems(), arrow_types)],
timezone)
for pdf_slice in pdf_slices]
# Create the Spark schema from the first Arrow batch (always at least 1 batch after slicing)
if isinstance(schema, (list, tuple)):
struct = from_arrow_schema(batches[0].schema)
for i, name in enumerate(schema):
struct.fields[i].name = name
struct.names[i] = name
schema = struct
jsqlContext = self._wrapped._jsqlContext
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(batches, ArrowStreamSerializer(), reader_func,
create_RDD_server)
jdf = self._jvm.PythonSQLUtils.toDataFrame(jrdd, schema.json(), jsqlContext)
df = DataFrame(jdf, self._wrapped)
df._schema = schema
return df
# limitations under the License.
#
"""
A simple example demonstrating Arrow in Spark.
Run with:
./bin/spark-submit examples/src/main/python/sql/arrow.py
"""
from __future__ import print_function
from pyspark.sql import SparkSession
from pyspark.sql.utils import require_minimum_pandas_version, require_minimum_pyarrow_version
require_minimum_pandas_version()
require_minimum_pyarrow_version()
def dataframe_with_arrow_example(spark):
# $example on:dataframe_with_arrow$
import numpy as np
import pandas as pd
# Enable Arrow-based columnar data transfers
spark.conf.set("spark.sql.execution.arrow.enabled", "true")
# Generate a Pandas DataFrame
pdf = pd.DataFrame(np.random.rand(100, 3))
# Create a Spark DataFrame from a Pandas DataFrame using Arrow
df = spark.createDataFrame(pdf)
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
# limitations under the License.
#
"""
A simple example demonstrating Arrow in Spark.
Run with:
./bin/spark-submit examples/src/main/python/sql/arrow.py
"""
from __future__ import print_function
from pyspark.sql import SparkSession
from pyspark.sql.utils import require_minimum_pandas_version, require_minimum_pyarrow_version
require_minimum_pandas_version()
require_minimum_pyarrow_version()
def dataframe_with_arrow_example(spark):
# $example on:dataframe_with_arrow$
import numpy as np
import pandas as pd
# Enable Arrow-based columnar data transfers
spark.conf.set("spark.sql.execution.arrow.enabled", "true")
# Generate a Pandas DataFrame
pdf = pd.DataFrame(np.random.rand(100, 3))
# Create a Spark DataFrame from a Pandas DataFrame using Arrow
df = spark.createDataFrame(pdf)
