def test_nested(spark_session):
# data = [[dict(a=1, b=[3, 4], d=1.0)], [json.dumps(dict(b=[30, "40"]))]]
# df = SparkDataFrame(data, "a:{a:str,b:[int]}")
# a = df.as_array(type_safe=True)
# assert [[dict(a="1", b=[3, 4])], [dict(a=None, b=[30, 40])]] == a
data = [[[10, 20]]]
sdf = spark_session.createDataFrame(data, to_spark_schema("a:[int]"))
df = SparkDataFrame(sdf)
assert data == df.as_array(type_safe=False)
assert data == df.as_array(type_safe=True)
assert data == list(df.as_array_iterable(type_safe=False))
assert data == list(df.as_array_iterable(type_safe=True))
data = [[dict(b=[30, 40])]]
sdf = spark_session.createDataFrame(data,
to_spark_schema("a:{a:str,b:[int]}"))
df = SparkDataFrame(sdf)
a = df.as_array(type_safe=False)
assert [[dict(a=None, b=[30, 40])]] == a
a = df.as_array(type_safe=True)
assert [[dict(a=None, b=[30, 40])]] == a
a = list(df.as_array_iterable(type_safe=False))
assert [[dict(a=None, b=[30, 40])]] == a
a = list(df.as_array_iterable(type_safe=True))
assert [[dict(a=None, b=[30, 40])]] == a
def to_df(
self, df: Any, schema: Any = None, metadata: Any = None
) -> SparkDataFrame:
"""Convert a data structure to :class:`~fugue_spark.dataframe.SparkDataFrame`
:param data: :class:`~fugue.dataframe.dataframe.DataFrame`,
:class:`spark:pyspark.sql.DataFrame`, :class:`spark:pyspark.RDD`,
pandas DataFrame or list or iterable of arrays
:param schema: |SchemaLikeObject| or :class:`spark:pyspark.sql.types.StructType`
defaults to None.
:param metadata: |ParamsLikeObject|, defaults to None
:return: engine compatible dataframe
:Notice:
* if the input is already :class:`~fugue_spark.dataframe.SparkDataFrame`,
it should return itself
* For :class:`~spark:pyspark.RDD`, list or iterable of arrays,
``schema`` must be specified
* When ``schema`` is not None, a potential type cast may happen to ensure
the dataframe's schema.
* all other methods in the engine can take arbitrary dataframes and
call this method to convert before doing anything
"""
if isinstance(df, DataFrame):
assert_or_throw(
schema is None and metadata is None,
ValueError("schema and metadata must be None when df is a DataFrame"),
)
if isinstance(df, SparkDataFrame):
return df
if any(pa.types.is_struct(t) for t in df.schema.types):
sdf = self.spark_session.createDataFrame(
df.as_array(type_safe=True), to_spark_schema(df.schema)
)
else:
sdf = self.spark_session.createDataFrame(
df.as_pandas(), to_spark_schema(df.schema)
)
return SparkDataFrame(sdf, df.schema, df.metadata)
if isinstance(df, ps.DataFrame):
return SparkDataFrame(
df, None if schema is None else to_schema(schema), metadata
)
if isinstance(df, RDD):
assert_arg_not_none(schema, "schema")
sdf = self.spark_session.createDataFrame(df, to_spark_schema(schema))
return SparkDataFrame(sdf, to_schema(schema), metadata)
if isinstance(df, pd.DataFrame):
sdf = self.spark_session.createDataFrame(df)
return SparkDataFrame(sdf, schema, metadata)
# use arrow dataframe here to handle nulls in int cols
adf = ArrowDataFrame(df, to_schema(schema))
sdf = self.spark_session.createDataFrame(
adf.as_array(), to_spark_schema(adf.schema)
)
return SparkDataFrame(sdf, adf.schema, metadata)
def test_schema_conversion(spark_session):
def test(expr):
assert to_schema(to_spark_schema(expr)) == expr
test("a:int,b:long,c:[int],d:datetime,e:date,f:decimal(3,4),g:str")
test("a:{a:[int],b:[str]}")
# test("a:[{a:int}]") TODO: this is not supported by spark, should we support?
s = to_spark_schema(to_spark_schema("a:int"))
assert to_spark_schema(s) is s
df = spark_session.createDataFrame([[1]], schema=to_spark_schema("a:int"))
assert to_schema(to_spark_schema(df)) == "a:int"
assert to_schema(df) == "a:int"
assert to_schema(dict(a=str)) == "a:str"
def _load_csv(self, p: List[str], columns: Any = None, **kwargs: Any) -> DataFrame:
kw = ParamDict(kwargs)
infer_schema = kw.get("infer_schema", False)
if infer_schema:
kw["inferSchema"] = True
if "infer_schema" in kw:
del kw["infer_schema"]
header = str(kw.get_or_none("header", object)).lower()
if "header" in kw:
del kw["header"]
reader = self._session.read.format("csv")
reader.options(**kw)
if header == "true":
reader.option("header", "true")
if columns is None:
return SparkDataFrame(reader.load(p))
if isinstance(columns, list): # column names
return SparkDataFrame(reader.load(p)[columns])
schema = Schema(columns)
return SparkDataFrame(reader.load(p)[schema.names], schema)
if header in ["false", "none"]:
reader.option("header", "false")
if columns is None:
raise InvalidOperationError("columns must be set if without header")
if isinstance(columns, list): # column names
sdf = reader.load(p)
inferred = to_schema(sdf)
renames = [f"{k} AS {v}" for k, v in zip(inferred.names, columns)]
return SparkDataFrame(sdf.selectExpr(*renames))
schema = Schema(columns)
sdf = reader.schema(to_spark_schema(schema)).load(p)
return SparkDataFrame(sdf, schema)
else:
raise NotImplementedError(f"{header} is not supported")
def even_repartition(session: SparkSession, df: ps.DataFrame, num: int,
cols: List[Any]) -> ps.DataFrame:
if num == 1:
return _single_repartition(df)
if len(cols) == 0:
if num == 0:
return df
rdd = (_zipWithIndex(df.rdd).partitionBy(
num, lambda k: k).mapPartitions(_to_rows))
return session.createDataFrame(rdd, df.schema)
else:
keys = df.select(*cols).distinct()
krdd = _zipWithIndex(keys.rdd, True)
new_schema = to_spark_schema(
to_schema(df.schema).extract(cols) +
f"{_PARTITION_DUMMY_KEY}:long")
idx = session.createDataFrame(krdd, new_schema)
if num <= 0:
idx = idx.persist()
num = idx.count()
idf = (df.alias("df").join(idx.alias("idx"), on=cols,
how="inner").select(_PARTITION_DUMMY_KEY,
"df.*"))
def _to_kv(rows: Iterable[Any]) -> Iterable[Any]: # pragma: no cover
for row in rows:
yield (row[0], row[1:])
rdd = (idf.rdd.mapPartitions(_to_kv).partitionBy(
num, lambda k: k).mapPartitions(_to_rows))
return session.createDataFrame(rdd, df.schema)
def _df(data, schema=None, metadata=None):
session = SparkSession.builder.getOrCreate()
if schema is not None:
pdf = PandasDataFrame(data, to_schema(schema), metadata)
return session.createDataFrame(pdf.native, to_spark_schema(schema))
else:
return session.createDataFrame(data)
def _map_by_pandas_udf(
self,
df: DataFrame,
map_func: Callable[[PartitionCursor, LocalDataFrame], LocalDataFrame],
output_schema: Any,
partition_spec: PartitionSpec,
metadata: Any = None,
on_init: Optional[Callable[[int, DataFrame], Any]] = None,
) -> DataFrame:
df = self.to_df(self.repartition(df, partition_spec))
output_schema = Schema(output_schema)
input_schema = df.schema
on_init_once: Any = (
None
if on_init is None
else RunOnce(
on_init, lambda *args, **kwargs: to_uuid(id(on_init), id(args[0]))
)
)
def _udf(
dfs: Iterable[pd.DataFrame],
) -> Iterable[pd.DataFrame]: # pragma: no cover
def get_dfs() -> Iterable[LocalDataFrame]:
for df in dfs:
if df.shape[0] > 0:
yield PandasDataFrame(
df.reset_index(drop=True),
input_schema,
pandas_df_wrapper=True,
)
input_df = LocalDataFrameIterableDataFrame(get_dfs(), input_schema)
if input_df.empty:
return PandasDataFrame([], output_schema).as_pandas()
if on_init_once is not None:
on_init_once(0, input_df)
cursor = partition_spec.get_cursor(input_schema, 0)
cursor.set(input_df.peek_array(), 0, 0)
output_df = map_func(cursor, input_df)
if isinstance(output_df, LocalDataFrameIterableDataFrame):
for res in output_df.native:
yield res.as_pandas()
else:
yield output_df.as_pandas()
df = self.to_df(df)
sdf = df.native.mapInPandas(_udf, schema=to_spark_schema(output_schema))
return SparkDataFrame(sdf, metadata=metadata)
def df(self,
data: Any = None,
schema: Any = None,
metadata: Any = None) -> SparkDataFrame:
session = SparkSession.builder.getOrCreate()
if data is None:
df = None
else:
if schema is not None:
pdf = PandasDataFrame(data, to_schema(schema), metadata)
df = session.createDataFrame(pdf.native,
to_spark_schema(schema))
else:
try:
df = session.createDataFrame(data)
except Exception:
raise FugueDataFrameInitError("schema error")
return SparkDataFrame(df, schema, metadata)
def _group_map_by_pandas_udf(
self,
df: DataFrame,
map_func: Callable[[PartitionCursor, LocalDataFrame], LocalDataFrame],
output_schema: Any,
partition_spec: PartitionSpec,
metadata: Any = None,
on_init: Optional[Callable[[int, DataFrame], Any]] = None,
) -> DataFrame:
presort = partition_spec.presort
presort_keys = list(presort.keys())
presort_asc = list(presort.values())
output_schema = Schema(output_schema)
input_schema = df.schema
on_init_once: Any = (
None
if on_init is None
else RunOnce(
on_init, lambda *args, **kwargs: to_uuid(id(on_init), id(args[0]))
)
)
def _udf(pdf: Any) -> pd.DataFrame: # pragma: no cover
if pdf.shape[0] == 0:
return PandasDataFrame([], output_schema).as_pandas()
if len(presort_keys) > 0:
pdf = pdf.sort_values(presort_keys, ascending=presort_asc)
input_df = PandasDataFrame(
pdf.reset_index(drop=True), input_schema, pandas_df_wrapper=True
)
if on_init_once is not None:
on_init_once(0, input_df)
cursor = partition_spec.get_cursor(input_schema, 0)
cursor.set(input_df.peek_array(), 0, 0)
output_df = map_func(cursor, input_df)
return output_df.as_pandas()
df = self.to_df(df)
gdf = df.native.groupBy(*partition_spec.partition_by)
sdf = gdf.applyInPandas(_udf, schema=to_spark_schema(output_schema))
return SparkDataFrame(sdf, metadata=metadata)
def test(expr):
assert to_schema(to_spark_schema(expr)) == expr
