def _python(self):
"""gets frame backend as _PythonFrame, causes conversion if it is current not"""
if self._is_scala:
logger.info("frame._python reference: converting frame backend from Scala to Python")
# convert Scala Frame to a PythonFrame"""
scala_schema = self._frame.schema()
java_rdd = self._tc.sc._jvm.org.trustedanalytics.sparktk.frame.internal.rdd.PythonJavaRdd.scalaToPython(self._frame.rdd())
python_schema = schema_to_python(self._tc.sc, scala_schema)
python_rdd = RDD(java_rdd, self._tc.sc)
# If schema contains matrix datatype, then apply type_coercer to convert list[list] to numpy ndarray
map_python_rdd = schema_is_coercible(python_rdd, list(python_schema))
self._frame = PythonFrame(map_python_rdd, python_schema)
else:
logger.info("frame._python reference: frame already has a python backend")
return self._frame
def _scala(self):
"""gets frame backend as Scala Frame, causes conversion if it is current not"""
if self._is_python:
logger.info("frame._scala reference: converting frame backend from Python to Scala")
# If schema contains matrix dataype,
# then apply type_coercer_pymlib to convert ndarray to pymlib DenseMatrix for serialization purpose at java
self._frame.rdd = schema_is_coercible(self._frame.rdd, list(self._frame.schema), True)
# convert PythonFrame to a Scala Frame"""
scala_schema = schema_to_scala(self._tc.sc, self._frame.schema)
scala_rdd = self._tc.sc._jvm.org.trustedanalytics.sparktk.frame.internal.rdd.PythonJavaRdd.pythonToScala(self._frame.rdd._jrdd, scala_schema)
self._frame = self._create_scala_frame(self._tc.sc, scala_rdd, scala_schema)
else:
logger.info("frame._scala reference: frame already has a scala backend")
return self._frame
def _python(self):
"""gets frame backend as _PythonFrame, causes conversion if it is current not"""
if self._is_scala:
logger.info("frame._python reference: converting frame backend from Scala to Python")
# convert Scala Frame to a PythonFrame"""
scala_schema = self._frame.schema()
java_rdd = self._tc.sc._jvm.org.trustedanalytics.sparktk.frame.internal.rdd.PythonJavaRdd.scalaToPython(self._frame.rdd())
python_schema = schema_to_python(self._tc.sc, scala_schema)
python_rdd = RDD(java_rdd, self._tc.sc)
# If schema contains matrix datatype, then apply type_coercer to convert list[list] to numpy ndarray
map_python_rdd = schema_is_coercible(python_rdd, list(python_schema))
self._frame = PythonFrame(map_python_rdd, python_schema)
else:
logger.info("frame._python reference: frame already has a python backend")
return self._frame
def _scala(self):
"""gets frame backend as Scala Frame, causes conversion if it is current not"""
if self._is_python:
logger.info("frame._scala reference: converting frame backend from Python to Scala")
# If schema contains matrix dataype,
# then apply type_coercer_pymlib to convert ndarray to pymlib DenseMatrix for serialization purpose at java
self._frame.rdd = schema_is_coercible(self._frame.rdd, list(self._frame.schema), True)
# convert PythonFrame to a Scala Frame"""
scala_schema = schema_to_scala(self._tc.sc, self._frame.schema)
scala_rdd = self._tc.sc._jvm.org.trustedanalytics.sparktk.frame.internal.rdd.PythonJavaRdd.pythonToScala(self._frame.rdd._jrdd, scala_schema)
self._frame = self._create_scala_frame(self._tc.sc, scala_rdd, scala_schema)
else:
logger.info("frame._scala reference: frame already has a scala backend")
return self._frame
def __init__(self, tc, source, schema=None, validate_schema=False):
"""(Private constructor -- use tc.frame.create or other methods available from the TkContext)"""
self._tc = tc
if self._is_scala_frame(source):
self._frame = source
elif self._is_scala_rdd(source):
scala_schema = schema_to_scala(tc.sc, schema)
self._frame = self._create_scala_frame(tc.sc, source, scala_schema)
elif self._is_scala_dataframe(source):
self._frame = self._create_scala_frame_from_scala_dataframe(
tc.sc, source)
elif isinstance(source, DataFrame):
self._frame = self._create_scala_frame_from_scala_dataframe(
tc.sc, source._jdf)
elif isinstance(source, PythonFrame):
self._frame = source
else:
if not isinstance(source, RDD):
if not isinstance(source, list) or (len(source) > 0 and any(
not isinstance(row, (list, tuple)) for row in source)):
raise TypeError(
"Invalid data source. The data parameter must be a 2-dimensional list (list of row data) or an RDD."
)
inferred_schema = False
if isinstance(schema, list):
if all(isinstance(item, basestring) for item in schema):
# check if schema is just a list of column names (versus string and data type tuples)
schema = self._infer_schema(source, schema)
inferred_schema = True
elif not all(
isinstance(item, tuple) and len(item) == 2
and isinstance(item[0], basestring)
for item in schema):
raise TypeError(
"Invalid schema. Expected a list of tuples (str, type) with the column name and data type, but received type %s."
% type(schema))
# check for duplicate column names
column_names = [col[0] for col in schema]
duplicate_column_names = set([
col for col in column_names
if column_names.count(col) > 1
])
if len(duplicate_column_names) > 0:
raise ValueError(
"Invalid schema, column names cannot be duplicated: %s"
% ", ".join(duplicate_column_names))
elif schema is None:
schema = self._infer_schema(source)
inferred_schema = True
else:
# Schema is not a list or None
raise TypeError(
"Invalid schema type: %s. Expected a list of tuples (str, type) with the column name and data type."
% type(schema))
for item in schema:
if not self._is_supported_datatype(item[1]):
if inferred_schema:
raise TypeError(
"The %s data type was found when inferring the schema, and it is not a "
"supported data type. Instead, specify a schema that uses a supported data "
"type, and enable validate_schema so that the data is converted to the proper "
"data type.\n\nInferred schema: %s\n\nSupported data types: %s"
% (str(item[1]), str(schema), dtypes.dtypes))
else:
raise TypeError(
"Invalid schema. %s is not a supported data type.\n\nSupported data types: %s"
% (str(item[1]), dtypes.dtypes))
source = tc.sc.parallelize(source)
if schema and validate_schema:
# Validate schema by going through the data and checking the data type and attempting to parse it
validate_schema_result = self.validate_pyrdd_schema(
source, schema)
source = validate_schema_result.validated_rdd
logger.debug(
"%s values were unable to be parsed to the schema's data type."
% validate_schema_result.bad_value_count)
# If schema contains matrix datatype, then apply type_coercer to convert list[list] to numpy ndarray
map_source = schema_is_coercible(source, list(schema))
self._frame = PythonFrame(map_source, schema)
def __init__(self, tc, source, schema=None, validate_schema=False):
"""(Private constructor -- use tc.frame.create or other methods available from the TkContext)"""
self._tc = tc
if self._is_scala_frame(source):
self._frame = source
elif self._is_scala_rdd(source):
scala_schema = schema_to_scala(tc.sc, schema)
self._frame = self._create_scala_frame(tc.sc, source, scala_schema)
elif self._is_scala_dataframe(source):
self._frame = self._create_scala_frame_from_scala_dataframe(tc.sc, source)
elif isinstance(source, DataFrame):
self._frame = self._create_scala_frame_from_scala_dataframe(tc.sc, source._jdf)
elif isinstance(source, PythonFrame):
self._frame = source
else:
if not isinstance(source, RDD):
if not isinstance(source, list) or (len(source) > 0 and any(not isinstance(row, (list, tuple)) for row in source)):
raise TypeError("Invalid data source. The data parameter must be a 2-dimensional list (list of row data) or an RDD.")
inferred_schema = False
if isinstance(schema, list):
if all(isinstance(item, basestring) for item in schema):
# check if schema is just a list of column names (versus string and data type tuples)
schema = self._infer_schema(source, schema)
inferred_schema = True
elif not all(isinstance(item, tuple) and
len(item) == 2 and
isinstance(item[0], basestring) for item in schema):
raise TypeError("Invalid schema. Expected a list of tuples (str, type) with the column name and data type, but received type %s." % type(schema))
# check for duplicate column names
column_names = [col[0] for col in schema]
duplicate_column_names = set([col for col in column_names if column_names.count(col) > 1])
if len(duplicate_column_names) > 0:
raise ValueError("Invalid schema, column names cannot be duplicated: %s" % ", ".join(duplicate_column_names))
elif schema is None:
schema = self._infer_schema(source)
inferred_schema = True
else:
# Schema is not a list or None
raise TypeError("Invalid schema type: %s. Expected a list of tuples (str, type) with the column name and data type." % type(schema))
for item in schema:
if not self._is_supported_datatype(item[1]):
if inferred_schema:
raise TypeError("The %s data type was found when inferring the schema, and it is not a "
"supported data type. Instead, specify a schema that uses a supported data "
"type, and enable validate_schema so that the data is converted to the proper "
"data type.\n\nInferred schema: %s\n\nSupported data types: %s" %
(str(item[1]), str(schema), dtypes.dtypes))
else:
raise TypeError("Invalid schema. %s is not a supported data type.\n\nSupported data types: %s" %
(str(item[1]), dtypes.dtypes))
source = tc.sc.parallelize(source)
if schema and validate_schema:
# Validate schema by going through the data and checking the data type and attempting to parse it
validate_schema_result = self.validate_pyrdd_schema(source, schema)
source = validate_schema_result.validated_rdd
logger.debug("%s values were unable to be parsed to the schema's data type." % validate_schema_result.bad_value_count)
# If schema contains matrix datatype, then apply type_coercer to convert list[list] to numpy ndarray
map_source = schema_is_coercible(source, list(schema))
self._frame = PythonFrame(map_source, schema)
