def transform_batch(
self, func: Callable[..., Union[pd.DataFrame, pd.Series]], *args: Any, **kwargs: Any
) -> DataFrameOrSeries:
"""
Transform chunks with a function that takes pandas DataFrame and outputs pandas DataFrame.
The pandas DataFrame given to the function is of a batch used internally. The length of
each input and output should be the same.
See also `Transform and apply a function
<https://koalas.readthedocs.io/en/latest/user_guide/transform_apply.html>`_.
.. note:: the `func` is unable to access to the whole input frame. pandas-on-Spark
internally splits the input series into multiple batches and calls `func` with each
batch multiple times. Therefore, operations such as global aggregations are impossible.
See the example below.
>>> # This case does not return the length of whole frame but of the batch internally
... # used.
... def length(pdf) -> ps.DataFrame[int]:
... return pd.DataFrame([len(pdf)] * len(pdf))
...
>>> df = ps.DataFrame({'A': range(1000)})
>>> df.pandas_on_spark.transform_batch(length) # doctest: +SKIP
c0
0 83
1 83
2 83
...
.. note:: this API executes the function once to infer the type which is
potentially expensive, for instance, when the dataset is created after
aggregations or sorting.
To avoid this, specify return type in ``func``, for instance, as below:
>>> def plus_one(x) -> ps.DataFrame[int, [float, float]]:
... return x + 1
If the return type is specified, the output column names become
`c0, c1, c2 ... cn`. These names are positionally mapped to the returned
DataFrame in ``func``.
To specify the column names, you can assign them in a NumPy compound type style
as below:
>>> def plus_one(x) -> ps.DataFrame[("index", int), [("a", float), ("b", float)]]:
... return x + 1
>>> pdf = pd.DataFrame({'a': [1, 2, 3], 'b': [3, 4, 5]})
>>> def plus_one(x) -> ps.DataFrame[
... (pdf.index.name, pdf.index.dtype), zip(pdf.dtypes, pdf.columns)]:
... return x + 1
Parameters
----------
func : function
Function to transform each pandas frame.
*args
Positional arguments to pass to func.
**kwargs
Keyword arguments to pass to func.
Returns
-------
DataFrame or Series
See Also
--------
DataFrame.pandas_on_spark.apply_batch: For row/columnwise operations.
Series.pandas_on_spark.transform_batch: transform the search as each pandas chunks.
Examples
--------
>>> df = ps.DataFrame([(1, 2), (3, 4), (5, 6)], columns=['A', 'B'])
>>> df
A B
0 1 2
1 3 4
2 5 6
>>> def plus_one_func(pdf) -> ps.DataFrame[int, [int, int]]:
... return pdf + 1
>>> df.pandas_on_spark.transform_batch(plus_one_func)
c0 c1
0 2 3
1 4 5
2 6 7
>>> def plus_one_func(pdf) -> ps.DataFrame[("index", int), [('A', int), ('B', int)]]:
... return pdf + 1
>>> df.pandas_on_spark.transform_batch(plus_one_func) # doctest: +NORMALIZE_WHITESPACE
A B
index
0 2 3
1 4 5
2 6 7
>>> def plus_one_func(pdf) -> ps.Series[int]:
... return pdf.B + 1
>>> df.pandas_on_spark.transform_batch(plus_one_func)
0 3
1 5
2 7
dtype: int64
You can also omit the type hints so pandas-on-Spark infers the return schema as below:
>>> df.pandas_on_spark.transform_batch(lambda pdf: pdf + 1)
A B
0 2 3
1 4 5
2 6 7
>>> (df * -1).pandas_on_spark.transform_batch(abs)
A B
0 1 2
1 3 4
2 5 6
Note that you should not transform the index. The index information will not change.
>>> df.pandas_on_spark.transform_batch(lambda pdf: pdf.B + 1)
0 3
1 5
2 7
Name: B, dtype: int64
You can also specify extra arguments as below.
>>> df.pandas_on_spark.transform_batch(lambda pdf, a, b, c: pdf.B + a + b + c, 1, 2, c=3)
0 8
1 10
2 12
Name: B, dtype: int64
"""
from pyspark.pandas.groupby import GroupBy
from pyspark.pandas.frame import DataFrame
from pyspark.pandas.series import first_series
from pyspark import pandas as ps
assert callable(func), "the first argument should be a callable function."
spec = inspect.getfullargspec(func)
return_sig = spec.annotations.get("return", None)
should_infer_schema = return_sig is None
should_retain_index = should_infer_schema
original_func = func
func = lambda o: original_func(o, *args, **kwargs)
def apply_func(pdf: pd.DataFrame) -> pd.DataFrame:
return func(pdf).to_frame()
def pandas_series_func(
f: Callable[[pd.DataFrame], pd.DataFrame], return_type: DataType
) -> "UserDefinedFunctionLike":
ff = f
@pandas_udf(returnType=return_type) # type: ignore[call-overload]
def udf(pdf: pd.DataFrame) -> pd.Series:
return first_series(ff(pdf))
return udf
if should_infer_schema:
# Here we execute with the first 1000 to get the return type.
# If the records were less than 1000, it uses pandas API directly for a shortcut.
log_advice(
"If the type hints is not specified for `transform_batch`, "
"it is expensive to infer the data type internally."
)
limit = ps.get_option("compute.shortcut_limit")
pdf = self._psdf.head(limit + 1)._to_internal_pandas()
transformed = func(pdf)
if not isinstance(transformed, (pd.DataFrame, pd.Series)):
raise ValueError(
"The given function should return a frame; however, "
"the return type was %s." % type(transformed)
)
if len(transformed) != len(pdf):
raise ValueError("transform_batch cannot produce aggregated results")
psdf_or_psser = ps.from_pandas(transformed)
if isinstance(psdf_or_psser, ps.Series):
psser = cast(ps.Series, psdf_or_psser)
field = psser._internal.data_fields[0].normalize_spark_type()
return_schema = StructType([field.struct_field])
output_func = GroupBy._make_pandas_df_builder_func(
self._psdf, apply_func, return_schema, retain_index=False
)
pudf = pandas_series_func(output_func, return_type=field.spark_type)
columns = self._psdf._internal.spark_columns
# TODO: Index will be lost in this case.
internal = self._psdf._internal.copy(
column_labels=psser._internal.column_labels,
data_spark_columns=[pudf(F.struct(*columns)).alias(field.name)],
data_fields=[field],
column_label_names=psser._internal.column_label_names,
)
return first_series(DataFrame(internal))
else:
psdf = cast(DataFrame, psdf_or_psser)
if len(pdf) <= limit:
# only do the short cut when it returns a frame to avoid
# operations on different dataframes in case of series.
return psdf
index_fields = [
field.normalize_spark_type() for field in psdf._internal.index_fields
]
data_fields = [field.normalize_spark_type() for field in psdf._internal.data_fields]
return_schema = StructType(
[field.struct_field for field in index_fields + data_fields]
)
self_applied: DataFrame = DataFrame(self._psdf._internal.resolved_copy)
output_func = GroupBy._make_pandas_df_builder_func(
self_applied, func, return_schema, retain_index=True # type: ignore[arg-type]
)
columns = self_applied._internal.spark_columns
pudf = pandas_udf( # type: ignore[call-overload]
output_func, returnType=return_schema
)
temp_struct_column = verify_temp_column_name(
self_applied._internal.spark_frame, "__temp_struct__"
)
applied = pudf(F.struct(*columns)).alias(temp_struct_column)
sdf = self_applied._internal.spark_frame.select(applied)
sdf = sdf.selectExpr("%s.*" % temp_struct_column)
return DataFrame(
psdf._internal.with_new_sdf(
spark_frame=sdf, index_fields=index_fields, data_fields=data_fields
)
)
else:
return_type = infer_return_type(original_func)
is_return_series = isinstance(return_type, SeriesType)
is_return_dataframe = isinstance(return_type, DataFrameType)
if not is_return_dataframe and not is_return_series:
raise TypeError(
"The given function should specify a frame or series as its type "
"hints; however, the return type was %s." % return_sig
)
if is_return_series:
field = InternalField(
dtype=cast(SeriesType, return_type).dtype,
struct_field=StructField(
name=SPARK_DEFAULT_SERIES_NAME,
dataType=cast(SeriesType, return_type).spark_type,
),
).normalize_spark_type()
return_schema = StructType([field.struct_field])
output_func = GroupBy._make_pandas_df_builder_func(
self._psdf, apply_func, return_schema, retain_index=False
)
pudf = pandas_series_func(output_func, return_type=field.spark_type)
columns = self._psdf._internal.spark_columns
internal = self._psdf._internal.copy(
column_labels=[None],
data_spark_columns=[pudf(F.struct(*columns)).alias(field.name)],
data_fields=[field],
column_label_names=None,
)
return first_series(DataFrame(internal))
else:
index_fields = cast(DataFrameType, return_type).index_fields
index_fields = [index_field.normalize_spark_type() for index_field in index_fields]
data_fields = [
field.normalize_spark_type()
for field in cast(DataFrameType, return_type).data_fields
]
normalized_fields = index_fields + data_fields
return_schema = StructType([field.struct_field for field in normalized_fields])
should_retain_index = len(index_fields) > 0
self_applied = DataFrame(self._psdf._internal.resolved_copy)
output_func = GroupBy._make_pandas_df_builder_func(
self_applied, func, return_schema, retain_index=should_retain_index # type: ignore[arg-type]
)
columns = self_applied._internal.spark_columns
pudf = pandas_udf( # type: ignore[call-overload]
output_func, returnType=return_schema
)
temp_struct_column = verify_temp_column_name(
self_applied._internal.spark_frame, "__temp_struct__"
)
applied = pudf(F.struct(*columns)).alias(temp_struct_column)
sdf = self_applied._internal.spark_frame.select(applied)
sdf = sdf.selectExpr("%s.*" % temp_struct_column)
index_spark_columns = None
index_names: Optional[List[Optional[Tuple[Any, ...]]]] = None
if should_retain_index:
index_spark_columns = [
scol_for(sdf, index_field.struct_field.name) for index_field in index_fields
]
if not any(
[
SPARK_INDEX_NAME_PATTERN.match(index_field.struct_field.name)
for index_field in index_fields
]
):
index_names = [
(index_field.struct_field.name,) for index_field in index_fields
]
internal = InternalFrame(
spark_frame=sdf,
index_names=index_names,
index_spark_columns=index_spark_columns,
index_fields=index_fields,
data_fields=data_fields,
)
return DataFrame(internal)
def transform_batch(self, func, *args, **kwargs) -> Union["DataFrame", "Series"]:
"""
Transform chunks with a function that takes pandas DataFrame and outputs pandas DataFrame.
The pandas DataFrame given to the function is of a batch used internally. The length of
each input and output should be the same.
See also `Transform and apply a function
<https://koalas.readthedocs.io/en/latest/user_guide/transform_apply.html>`_.
.. note:: the `func` is unable to access to the whole input frame. pandas-on-Spark
internally splits the input series into multiple batches and calls `func` with each
batch multiple times. Therefore, operations such as global aggregations are impossible.
See the example below.
>>> # This case does not return the length of whole frame but of the batch internally
... # used.
... def length(pdf) -> ps.DataFrame[int]:
... return pd.DataFrame([len(pdf)] * len(pdf))
...
>>> df = ps.DataFrame({'A': range(1000)})
>>> df.pandas_on_spark.transform_batch(length) # doctest: +SKIP
c0
0 83
1 83
2 83
...
.. note:: this API executes the function once to infer the type which is
potentially expensive, for instance, when the dataset is created after
aggregations or sorting.
To avoid this, specify return type in ``func``, for instance, as below:
>>> def plus_one(x) -> ps.DataFrame[float, float]:
... return x + 1
If the return type is specified, the output column names become
`c0, c1, c2 ... cn`. These names are positionally mapped to the returned
DataFrame in ``func``.
To specify the column names, you can assign them in a pandas friendly style as below:
>>> def plus_one(x) -> ps.DataFrame['a': float, 'b': float]:
... return x + 1
>>> pdf = pd.DataFrame({'a': [1, 2, 3], 'b': [3, 4, 5]})
>>> def plus_one(x) -> ps.DataFrame[zip(pdf.dtypes, pdf.columns)]:
... return x + 1
When the given function returns DataFrame and has the return type annotated, the
original index of the DataFrame will be lost and then a default index will be attached
to the result. Please be careful about configuring the default index. See also
`Default Index Type
<https://koalas.readthedocs.io/en/latest/user_guide/options.html#default-index-type>`_.
Parameters
----------
func : function
Function to transform each pandas frame.
*args
Positional arguments to pass to func.
**kwargs
Keyword arguments to pass to func.
Returns
-------
DataFrame or Series
See Also
--------
DataFrame.pandas_on_spark.apply_batch: For row/columnwise operations.
Series.pandas_on_spark.transform_batch: transform the search as each pandas chunks.
Examples
--------
>>> df = ps.DataFrame([(1, 2), (3, 4), (5, 6)], columns=['A', 'B'])
>>> df
A B
0 1 2
1 3 4
2 5 6
>>> def plus_one_func(pdf) -> ps.DataFrame[int, int]:
... return pdf + 1
>>> df.pandas_on_spark.transform_batch(plus_one_func)
c0 c1
0 2 3
1 4 5
2 6 7
>>> def plus_one_func(pdf) -> ps.DataFrame['A': int, 'B': int]:
... return pdf + 1
>>> df.pandas_on_spark.transform_batch(plus_one_func)
A B
0 2 3
1 4 5
2 6 7
>>> def plus_one_func(pdf) -> ps.Series[int]:
... return pdf.B + 1
>>> df.pandas_on_spark.transform_batch(plus_one_func)
0 3
1 5
2 7
dtype: int64
You can also omit the type hints so pandas-on-Spark infers the return schema as below:
>>> df.pandas_on_spark.transform_batch(lambda pdf: pdf + 1)
A B
0 2 3
1 4 5
2 6 7
>>> (df * -1).pandas_on_spark.transform_batch(abs)
A B
0 1 2
1 3 4
2 5 6
Note that you should not transform the index. The index information will not change.
>>> df.pandas_on_spark.transform_batch(lambda pdf: pdf.B + 1)
0 3
1 5
2 7
Name: B, dtype: int64
You can also specify extra arguments as below.
>>> df.pandas_on_spark.transform_batch(lambda pdf, a, b, c: pdf.B + a + b + c, 1, 2, c=3)
0 8
1 10
2 12
Name: B, dtype: int64
"""
from pyspark.pandas.groupby import GroupBy
from pyspark.pandas.frame import DataFrame
from pyspark.pandas.series import first_series
from pyspark import pandas as ps
assert callable(func), "the first argument should be a callable function."
spec = inspect.getfullargspec(func)
return_sig = spec.annotations.get("return", None)
should_infer_schema = return_sig is None
original_func = func
func = lambda o: original_func(o, *args, **kwargs)
names = self._psdf._internal.to_internal_spark_frame.schema.names
def pandas_concat(series):
# The input can only be a DataFrame for struct from Spark 3.0.
# This works around to make the input as a frame. See SPARK-27240
pdf = pd.concat(series, axis=1)
pdf.columns = names
return pdf
def apply_func(pdf):
return func(pdf).to_frame()
def pandas_extract(pdf, name):
# This is for output to work around a DataFrame for struct
# from Spark 3.0. See SPARK-23836
return pdf[name]
def pandas_series_func(f):
ff = f
return lambda *series: first_series(ff(*series))
def pandas_frame_func(f, field_name):
ff = f
return lambda *series: pandas_extract(ff(pandas_concat(series)), field_name)
if should_infer_schema:
# Here we execute with the first 1000 to get the return type.
# If the records were less than 1000, it uses pandas API directly for a shortcut.
limit = ps.get_option("compute.shortcut_limit")
pdf = self._psdf.head(limit + 1)._to_internal_pandas()
transformed = func(pdf)
if not isinstance(transformed, (pd.DataFrame, pd.Series)):
raise ValueError(
"The given function should return a frame; however, "
"the return type was %s." % type(transformed)
)
if len(transformed) != len(pdf):
raise ValueError("transform_batch cannot produce aggregated results")
psdf_or_psser = ps.from_pandas(transformed)
if isinstance(psdf_or_psser, ps.Series):
psser = cast(ps.Series, psdf_or_psser)
field = psser._internal.data_fields[0].normalize_spark_type()
return_schema = StructType([field.struct_field])
output_func = GroupBy._make_pandas_df_builder_func(
self._psdf, apply_func, return_schema, retain_index=False
)
pudf = pandas_udf( # type: ignore
returnType=field.spark_type, functionType=PandasUDFType.SCALAR
)(pandas_series_func(output_func))
columns = self._psdf._internal.spark_columns
# TODO: Index will be lost in this case.
internal = self._psdf._internal.copy(
column_labels=psser._internal.column_labels,
data_spark_columns=[pudf(F.struct(*columns)).alias(field.name)],
data_fields=[field],
column_label_names=psser._internal.column_label_names,
)
return first_series(DataFrame(internal))
else:
psdf = cast(DataFrame, psdf_or_psser)
if len(pdf) <= limit:
# only do the short cut when it returns a frame to avoid
# operations on different dataframes in case of series.
return psdf
index_fields = [
field.normalize_spark_type() for field in psdf._internal.index_fields
]
data_fields = [field.normalize_spark_type() for field in psdf._internal.data_fields]
return_schema = StructType(
[field.struct_field for field in index_fields + data_fields]
)
self_applied = DataFrame(self._psdf._internal.resolved_copy) # type: DataFrame
output_func = GroupBy._make_pandas_df_builder_func(
self_applied, func, return_schema, retain_index=True
)
columns = self_applied._internal.spark_columns
pudf = pandas_udf(returnType=return_schema, functionType=PandasUDFType.SCALAR)(
output_func
)
temp_struct_column = verify_temp_column_name(
self_applied._internal.spark_frame, "__temp_struct__"
)
applied = pudf(F.struct(*columns)).alias(temp_struct_column)
sdf = self_applied._internal.spark_frame.select(applied)
sdf = sdf.selectExpr("%s.*" % temp_struct_column)
return DataFrame(
psdf._internal.with_new_sdf(
spark_frame=sdf, index_fields=index_fields, data_fields=data_fields
)
)
else:
return_type = infer_return_type(original_func)
is_return_series = isinstance(return_type, SeriesType)
is_return_dataframe = isinstance(return_type, DataFrameType)
if not is_return_dataframe and not is_return_series:
raise TypeError(
"The given function should specify a frame or series as its type "
"hints; however, the return type was %s." % return_sig
)
if is_return_series:
field = InternalField(
dtype=cast(SeriesType, return_type).dtype,
struct_field=StructField(
name=SPARK_DEFAULT_SERIES_NAME,
dataType=cast(SeriesType, return_type).spark_type,
),
).normalize_spark_type()
return_schema = StructType([field.struct_field])
output_func = GroupBy._make_pandas_df_builder_func(
self._psdf, apply_func, return_schema, retain_index=False
)
pudf = pandas_udf( # type: ignore
returnType=field.spark_type, functionType=PandasUDFType.SCALAR
)(pandas_series_func(output_func))
columns = self._psdf._internal.spark_columns
internal = self._psdf._internal.copy(
column_labels=[None],
data_spark_columns=[pudf(F.struct(*columns)).alias(field.name)],
data_fields=[field],
column_label_names=None,
)
return first_series(DataFrame(internal))
else:
data_fields = [
field.normalize_spark_type()
for field in cast(DataFrameType, return_type).fields
]
return_schema = StructType([field.struct_field for field in data_fields])
self_applied = DataFrame(self._psdf._internal.resolved_copy)
output_func = GroupBy._make_pandas_df_builder_func(
self_applied, func, return_schema, retain_index=False
)
columns = self_applied._internal.spark_columns
pudf = pandas_udf(returnType=return_schema, functionType=PandasUDFType.SCALAR)(
output_func
)
temp_struct_column = verify_temp_column_name(
self_applied._internal.spark_frame, "__temp_struct__"
)
applied = pudf(F.struct(*columns)).alias(temp_struct_column)
sdf = self_applied._internal.spark_frame.select(applied)
sdf = sdf.selectExpr("%s.*" % temp_struct_column)
internal = InternalFrame(
spark_frame=sdf, index_spark_columns=None, data_fields=data_fields
)
return DataFrame(internal)
