From d14410c6777e7de7f61e1957fab749da2793f4b8 Mon Sep 17 00:00:00 2001 From: Hyukjin Kwon Date: Thu, 23 Nov 2023 16:38:52 +0900 Subject: [PATCH] [SPARK-46048][PYTHON][CONNECT] Support DataFrame.groupingSets in Python Spark Connect ### What changes were proposed in this pull request? This PR adds `DataFrame.groupingSets` in Python Spark Connect. ### Why are the changes needed? For feature parity with non-Spark Connect. ### Does this PR introduce _any_ user-facing change? Yes, it adds the new API `DataFframe.groupingSets` in Python Spark Connect. ### How was this patch tested? Unittests were added. ### Was this patch authored or co-authored using generative AI tooling? No. Closes #43967 from HyukjinKwon/SPARK-46048. Authored-by: Hyukjin Kwon Signed-off-by: Hyukjin Kwon --- .../protobuf/spark/connect/relations.proto | 9 + .../spark/sql/connect/dsl/package.scala | 21 ++ .../connect/planner/SparkConnectPlanner.scala | 11 + .../planner/SparkConnectProtoSuite.scala | 12 ++ python/pyspark/sql/connect/dataframe.py | 39 ++++ python/pyspark/sql/connect/group.py | 16 +- python/pyspark/sql/connect/plan.py | 23 ++- .../sql/connect/proto/relations_pb2.py | 194 +++++++++--------- .../sql/connect/proto/relations_pb2.pyi | 36 ++++ python/pyspark/sql/dataframe.py | 1 - 10 files changed, 262 insertions(+), 100 deletions(-) diff --git a/connector/connect/common/src/main/protobuf/spark/connect/relations.proto b/connector/connect/common/src/main/protobuf/spark/connect/relations.proto index deb33978386d8..43f692671df72 100644 --- a/connector/connect/common/src/main/protobuf/spark/connect/relations.proto +++ b/connector/connect/common/src/main/protobuf/spark/connect/relations.proto @@ -327,12 +327,16 @@ message Aggregate { // (Optional) Pivots a column of the current `DataFrame` and performs the specified aggregation. Pivot pivot = 5; + // (Optional) List of values that will be translated to columns in the output DataFrame. + repeated GroupingSets grouping_sets = 6; + enum GroupType { GROUP_TYPE_UNSPECIFIED = 0; GROUP_TYPE_GROUPBY = 1; GROUP_TYPE_ROLLUP = 2; GROUP_TYPE_CUBE = 3; GROUP_TYPE_PIVOT = 4; + GROUP_TYPE_GROUPING_SETS = 5; } message Pivot { @@ -345,6 +349,11 @@ message Aggregate { // the distinct values of the column. repeated Expression.Literal values = 2; } + + message GroupingSets { + // (Required) Individual grouping set + repeated Expression grouping_set = 1; + } } // Relation of type [[Sort]]. diff --git a/connector/connect/server/src/main/scala/org/apache/spark/sql/connect/dsl/package.scala b/connector/connect/server/src/main/scala/org/apache/spark/sql/connect/dsl/package.scala index 5fd1a03538555..18c71ae4ace45 100644 --- a/connector/connect/server/src/main/scala/org/apache/spark/sql/connect/dsl/package.scala +++ b/connector/connect/server/src/main/scala/org/apache/spark/sql/connect/dsl/package.scala @@ -800,6 +800,27 @@ package object dsl { Relation.newBuilder().setAggregate(agg.build()).build() } + def groupingSets(groupingSets: Seq[Seq[Expression]], groupingExprs: Expression*)( + aggregateExprs: Expression*): Relation = { + val agg = Aggregate.newBuilder() + agg.setInput(logicalPlan) + agg.setGroupType(proto.Aggregate.GroupType.GROUP_TYPE_GROUPING_SETS) + for (groupingSet <- groupingSets) { + val groupingSetMsg = Aggregate.GroupingSets.newBuilder() + for (groupCol <- groupingSet) { + groupingSetMsg.addGroupingSet(groupCol) + } + agg.addGroupingSets(groupingSetMsg) + } + for (groupingExpr <- groupingExprs) { + agg.addGroupingExpressions(groupingExpr) + } + for (aggregateExpr <- aggregateExprs) { + agg.addAggregateExpressions(aggregateExpr) + } + Relation.newBuilder().setAggregate(agg.build()).build() + } + def except(otherPlan: Relation, isAll: Boolean): Relation = { Relation .newBuilder() diff --git a/connector/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala b/connector/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala index 4a0aa7e55898b..95c5acc803d49 100644 --- a/connector/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala +++ b/connector/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala @@ -2445,6 +2445,17 @@ class SparkConnectPlanner( aggregates = aggExprs, child = input) + case proto.Aggregate.GroupType.GROUP_TYPE_GROUPING_SETS => + val groupingSetsExprs = rel.getGroupingSetsList.asScala.toSeq.map { getGroupingSets => + getGroupingSets.getGroupingSetList.asScala.toSeq.map(transformExpression) + } + logical.Aggregate( + groupingExpressions = Seq( + GroupingSets( + groupingSets = groupingSetsExprs, + userGivenGroupByExprs = groupingExprs)), + aggregateExpressions = aliasedAgg, + child = input) case other => throw InvalidPlanInput(s"Unknown Group Type $other") } } diff --git a/connector/connect/server/src/test/scala/org/apache/spark/sql/connect/planner/SparkConnectProtoSuite.scala b/connector/connect/server/src/test/scala/org/apache/spark/sql/connect/planner/SparkConnectProtoSuite.scala index c54aa496c6672..0b27ccdbef89a 100644 --- a/connector/connect/server/src/test/scala/org/apache/spark/sql/connect/planner/SparkConnectProtoSuite.scala +++ b/connector/connect/server/src/test/scala/org/apache/spark/sql/connect/planner/SparkConnectProtoSuite.scala @@ -307,6 +307,18 @@ class SparkConnectProtoSuite extends PlanTest with SparkConnectPlanTest { comparePlans(connectPlan2, sparkPlan2) } + test("GroupingSets expressions") { + val connectPlan1 = + connectTestRelation.groupingSets(Seq(Seq("id".protoAttr), Seq.empty), "id".protoAttr)( + proto_min(proto.Expression.newBuilder().setLiteral(toLiteralProto(1)).build()) + .as("agg1")) + val sparkPlan1 = + sparkTestRelation + .groupingSets(Seq(Seq(Column("id")), Seq.empty), Column("id")) + .agg(min(lit(1)).as("agg1")) + comparePlans(connectPlan1, sparkPlan1) + } + test("Test as(alias: String)") { val connectPlan = connectTestRelation.as("target_table") val sparkPlan = sparkTestRelation.as("target_table") diff --git a/python/pyspark/sql/connect/dataframe.py b/python/pyspark/sql/connect/dataframe.py index c7b51205363f3..b3bec44428bf8 100644 --- a/python/pyspark/sql/connect/dataframe.py +++ b/python/pyspark/sql/connect/dataframe.py @@ -550,6 +550,45 @@ def cube(self, *cols: "ColumnOrName") -> "GroupedData": cube.__doc__ = PySparkDataFrame.cube.__doc__ + def groupingSets( + self, groupingSets: Sequence[Sequence["ColumnOrName"]], *cols: "ColumnOrName" + ) -> "GroupedData": + gsets: List[List[Column]] = [] + for grouping_set in groupingSets: + gset: List[Column] = [] + for c in grouping_set: + if isinstance(c, Column): + gset.append(c) + elif isinstance(c, str): + gset.append(self[c]) + else: + raise PySparkTypeError( + error_class="NOT_COLUMN_OR_STR", + message_parameters={ + "arg_name": "groupingSets", + "arg_type": type(c).__name__, + }, + ) + gsets.append(gset) + + gcols: List[Column] = [] + for c in cols: + if isinstance(c, Column): + gcols.append(c) + elif isinstance(c, str): + gcols.append(self[c]) + else: + raise PySparkTypeError( + error_class="NOT_COLUMN_OR_STR", + message_parameters={"arg_name": "cols", "arg_type": type(c).__name__}, + ) + + return GroupedData( + df=self, group_type="grouping_sets", grouping_cols=gcols, grouping_sets=gsets + ) + + groupingSets.__doc__ = PySparkDataFrame.groupingSets.__doc__ + @overload def head(self) -> Optional[Row]: ... diff --git a/python/pyspark/sql/connect/group.py b/python/pyspark/sql/connect/group.py index 7b71a43c11216..481b7981a151c 100644 --- a/python/pyspark/sql/connect/group.py +++ b/python/pyspark/sql/connect/group.py @@ -63,13 +63,20 @@ def __init__( grouping_cols: Sequence["Column"], pivot_col: Optional["Column"] = None, pivot_values: Optional[Sequence["LiteralType"]] = None, + grouping_sets: Optional[Sequence[Sequence["Column"]]] = None, ) -> None: from pyspark.sql.connect.dataframe import DataFrame assert isinstance(df, DataFrame) self._df = df - assert isinstance(group_type, str) and group_type in ["groupby", "rollup", "cube", "pivot"] + assert isinstance(group_type, str) and group_type in [ + "groupby", + "rollup", + "cube", + "pivot", + "grouping_sets", + ] self._group_type = group_type assert isinstance(grouping_cols, list) and all(isinstance(g, Column) for g in grouping_cols) @@ -83,6 +90,11 @@ def __init__( self._pivot_col = pivot_col self._pivot_values = pivot_values + self._grouping_sets: Optional[Sequence[Sequence["Column"]]] = None + if group_type == "grouping_sets": + assert grouping_sets is None or isinstance(grouping_sets, list) + self._grouping_sets = grouping_sets + def __repr__(self) -> str: # the expressions are not resolved here, # so the string representation can be different from vanilla PySpark. @@ -130,6 +142,7 @@ def agg(self, *exprs: Union[Column, Dict[str, str]]) -> "DataFrame": aggregate_cols=aggregate_cols, pivot_col=self._pivot_col, pivot_values=self._pivot_values, + grouping_sets=self._grouping_sets, ), session=self._df._session, ) @@ -171,6 +184,7 @@ def _numeric_agg(self, function: str, cols: Sequence[str]) -> "DataFrame": aggregate_cols=[_invoke_function(function, col(c)) for c in agg_cols], pivot_col=self._pivot_col, pivot_values=self._pivot_values, + grouping_sets=self._grouping_sets, ), session=self._df._session, ) diff --git a/python/pyspark/sql/connect/plan.py b/python/pyspark/sql/connect/plan.py index 607d1429a9efd..7d63f8714a937 100644 --- a/python/pyspark/sql/connect/plan.py +++ b/python/pyspark/sql/connect/plan.py @@ -778,10 +778,17 @@ def __init__( aggregate_cols: Sequence[Column], pivot_col: Optional[Column], pivot_values: Optional[Sequence[Any]], + grouping_sets: Optional[Sequence[Sequence[Column]]], ) -> None: super().__init__(child) - assert isinstance(group_type, str) and group_type in ["groupby", "rollup", "cube", "pivot"] + assert isinstance(group_type, str) and group_type in [ + "groupby", + "rollup", + "cube", + "pivot", + "grouping_sets", + ] self._group_type = group_type assert isinstance(grouping_cols, list) and all(isinstance(c, Column) for c in grouping_cols) @@ -795,12 +802,16 @@ def __init__( if group_type == "pivot": assert pivot_col is not None and isinstance(pivot_col, Column) assert pivot_values is None or isinstance(pivot_values, list) + elif group_type == "grouping_sets": + assert grouping_sets is None or isinstance(grouping_sets, list) else: assert pivot_col is None assert pivot_values is None + assert grouping_sets is None self._pivot_col = pivot_col self._pivot_values = pivot_values + self._grouping_sets = grouping_sets def plan(self, session: "SparkConnectClient") -> proto.Relation: from pyspark.sql.connect.functions import lit @@ -829,7 +840,15 @@ def plan(self, session: "SparkConnectClient") -> proto.Relation: plan.aggregate.pivot.values.extend( [lit(v).to_plan(session).literal for v in self._pivot_values] ) - + elif self._group_type == "grouping_sets": + plan.aggregate.group_type = proto.Aggregate.GroupType.GROUP_TYPE_GROUPING_SETS + assert self._grouping_sets is not None + for grouping_set in self._grouping_sets: + plan.aggregate.grouping_sets.append( + proto.Aggregate.GroupingSets( + grouping_set=[c.to_plan(session) for c in grouping_set] + ) + ) return plan diff --git a/python/pyspark/sql/connect/proto/relations_pb2.py b/python/pyspark/sql/connect/proto/relations_pb2.py index fc70cdea4021c..f79ee786afb91 100644 --- a/python/pyspark/sql/connect/proto/relations_pb2.py +++ b/python/pyspark/sql/connect/proto/relations_pb2.py @@ -35,7 +35,7 @@ DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile( - b'\n\x1dspark/connect/relations.proto\x12\rspark.connect\x1a\x19google/protobuf/any.proto\x1a\x1fspark/connect/expressions.proto\x1a\x19spark/connect/types.proto\x1a\x1bspark/connect/catalog.proto"\x9a\x19\n\x08Relation\x12\x35\n\x06\x63ommon\x18\x01 \x01(\x0b\x32\x1d.spark.connect.RelationCommonR\x06\x63ommon\x12)\n\x04read\x18\x02 \x01(\x0b\x32\x13.spark.connect.ReadH\x00R\x04read\x12\x32\n\x07project\x18\x03 \x01(\x0b\x32\x16.spark.connect.ProjectH\x00R\x07project\x12/\n\x06\x66ilter\x18\x04 \x01(\x0b\x32\x15.spark.connect.FilterH\x00R\x06\x66ilter\x12)\n\x04join\x18\x05 \x01(\x0b\x32\x13.spark.connect.JoinH\x00R\x04join\x12\x34\n\x06set_op\x18\x06 \x01(\x0b\x32\x1b.spark.connect.SetOperationH\x00R\x05setOp\x12)\n\x04sort\x18\x07 \x01(\x0b\x32\x13.spark.connect.SortH\x00R\x04sort\x12,\n\x05limit\x18\x08 \x01(\x0b\x32\x14.spark.connect.LimitH\x00R\x05limit\x12\x38\n\taggregate\x18\t \x01(\x0b\x32\x18.spark.connect.AggregateH\x00R\taggregate\x12&\n\x03sql\x18\n \x01(\x0b\x32\x12.spark.connect.SQLH\x00R\x03sql\x12\x45\n\x0elocal_relation\x18\x0b \x01(\x0b\x32\x1c.spark.connect.LocalRelationH\x00R\rlocalRelation\x12/\n\x06sample\x18\x0c \x01(\x0b\x32\x15.spark.connect.SampleH\x00R\x06sample\x12/\n\x06offset\x18\r \x01(\x0b\x32\x15.spark.connect.OffsetH\x00R\x06offset\x12>\n\x0b\x64\x65\x64uplicate\x18\x0e \x01(\x0b\x32\x1a.spark.connect.DeduplicateH\x00R\x0b\x64\x65\x64uplicate\x12,\n\x05range\x18\x0f \x01(\x0b\x32\x14.spark.connect.RangeH\x00R\x05range\x12\x45\n\x0esubquery_alias\x18\x10 \x01(\x0b\x32\x1c.spark.connect.SubqueryAliasH\x00R\rsubqueryAlias\x12>\n\x0brepartition\x18\x11 \x01(\x0b\x32\x1a.spark.connect.RepartitionH\x00R\x0brepartition\x12*\n\x05to_df\x18\x12 \x01(\x0b\x32\x13.spark.connect.ToDFH\x00R\x04toDf\x12U\n\x14with_columns_renamed\x18\x13 \x01(\x0b\x32!.spark.connect.WithColumnsRenamedH\x00R\x12withColumnsRenamed\x12<\n\x0bshow_string\x18\x14 \x01(\x0b\x32\x19.spark.connect.ShowStringH\x00R\nshowString\x12)\n\x04\x64rop\x18\x15 \x01(\x0b\x32\x13.spark.connect.DropH\x00R\x04\x64rop\x12)\n\x04tail\x18\x16 \x01(\x0b\x32\x13.spark.connect.TailH\x00R\x04tail\x12?\n\x0cwith_columns\x18\x17 \x01(\x0b\x32\x1a.spark.connect.WithColumnsH\x00R\x0bwithColumns\x12)\n\x04hint\x18\x18 \x01(\x0b\x32\x13.spark.connect.HintH\x00R\x04hint\x12\x32\n\x07unpivot\x18\x19 \x01(\x0b\x32\x16.spark.connect.UnpivotH\x00R\x07unpivot\x12\x36\n\tto_schema\x18\x1a \x01(\x0b\x32\x17.spark.connect.ToSchemaH\x00R\x08toSchema\x12\x64\n\x19repartition_by_expression\x18\x1b \x01(\x0b\x32&.spark.connect.RepartitionByExpressionH\x00R\x17repartitionByExpression\x12\x45\n\x0emap_partitions\x18\x1c \x01(\x0b\x32\x1c.spark.connect.MapPartitionsH\x00R\rmapPartitions\x12H\n\x0f\x63ollect_metrics\x18\x1d \x01(\x0b\x32\x1d.spark.connect.CollectMetricsH\x00R\x0e\x63ollectMetrics\x12,\n\x05parse\x18\x1e \x01(\x0b\x32\x14.spark.connect.ParseH\x00R\x05parse\x12\x36\n\tgroup_map\x18\x1f \x01(\x0b\x32\x17.spark.connect.GroupMapH\x00R\x08groupMap\x12=\n\x0c\x63o_group_map\x18 \x01(\x0b\x32\x19.spark.connect.CoGroupMapH\x00R\ncoGroupMap\x12\x45\n\x0ewith_watermark\x18! \x01(\x0b\x32\x1c.spark.connect.WithWatermarkH\x00R\rwithWatermark\x12\x63\n\x1a\x61pply_in_pandas_with_state\x18" \x01(\x0b\x32%.spark.connect.ApplyInPandasWithStateH\x00R\x16\x61pplyInPandasWithState\x12<\n\x0bhtml_string\x18# \x01(\x0b\x32\x19.spark.connect.HtmlStringH\x00R\nhtmlString\x12X\n\x15\x63\x61\x63hed_local_relation\x18$ \x01(\x0b\x32".spark.connect.CachedLocalRelationH\x00R\x13\x63\x61\x63hedLocalRelation\x12[\n\x16\x63\x61\x63hed_remote_relation\x18% \x01(\x0b\x32#.spark.connect.CachedRemoteRelationH\x00R\x14\x63\x61\x63hedRemoteRelation\x12\x8e\x01\n)common_inline_user_defined_table_function\x18& \x01(\x0b\x32\x33.spark.connect.CommonInlineUserDefinedTableFunctionH\x00R$commonInlineUserDefinedTableFunction\x12\x37\n\nas_of_join\x18\' \x01(\x0b\x32\x17.spark.connect.AsOfJoinH\x00R\x08\x61sOfJoin\x12\x30\n\x07\x66ill_na\x18Z \x01(\x0b\x32\x15.spark.connect.NAFillH\x00R\x06\x66illNa\x12\x30\n\x07\x64rop_na\x18[ \x01(\x0b\x32\x15.spark.connect.NADropH\x00R\x06\x64ropNa\x12\x34\n\x07replace\x18\\ \x01(\x0b\x32\x18.spark.connect.NAReplaceH\x00R\x07replace\x12\x36\n\x07summary\x18\x64 \x01(\x0b\x32\x1a.spark.connect.StatSummaryH\x00R\x07summary\x12\x39\n\x08\x63rosstab\x18\x65 \x01(\x0b\x32\x1b.spark.connect.StatCrosstabH\x00R\x08\x63rosstab\x12\x39\n\x08\x64\x65scribe\x18\x66 \x01(\x0b\x32\x1b.spark.connect.StatDescribeH\x00R\x08\x64\x65scribe\x12*\n\x03\x63ov\x18g \x01(\x0b\x32\x16.spark.connect.StatCovH\x00R\x03\x63ov\x12-\n\x04\x63orr\x18h \x01(\x0b\x32\x17.spark.connect.StatCorrH\x00R\x04\x63orr\x12L\n\x0f\x61pprox_quantile\x18i \x01(\x0b\x32!.spark.connect.StatApproxQuantileH\x00R\x0e\x61pproxQuantile\x12=\n\nfreq_items\x18j \x01(\x0b\x32\x1c.spark.connect.StatFreqItemsH\x00R\tfreqItems\x12:\n\tsample_by\x18k \x01(\x0b\x32\x1b.spark.connect.StatSampleByH\x00R\x08sampleBy\x12\x33\n\x07\x63\x61talog\x18\xc8\x01 \x01(\x0b\x32\x16.spark.connect.CatalogH\x00R\x07\x63\x61talog\x12\x35\n\textension\x18\xe6\x07 \x01(\x0b\x32\x14.google.protobuf.AnyH\x00R\textension\x12\x33\n\x07unknown\x18\xe7\x07 \x01(\x0b\x32\x16.spark.connect.UnknownH\x00R\x07unknownB\n\n\x08rel_type"\t\n\x07Unknown"[\n\x0eRelationCommon\x12\x1f\n\x0bsource_info\x18\x01 \x01(\tR\nsourceInfo\x12\x1c\n\x07plan_id\x18\x02 \x01(\x03H\x00R\x06planId\x88\x01\x01\x42\n\n\x08_plan_id"\xde\x03\n\x03SQL\x12\x14\n\x05query\x18\x01 \x01(\tR\x05query\x12\x34\n\x04\x61rgs\x18\x02 \x03(\x0b\x32\x1c.spark.connect.SQL.ArgsEntryB\x02\x18\x01R\x04\x61rgs\x12@\n\x08pos_args\x18\x03 \x03(\x0b\x32!.spark.connect.Expression.LiteralB\x02\x18\x01R\x07posArgs\x12O\n\x0fnamed_arguments\x18\x04 \x03(\x0b\x32&.spark.connect.SQL.NamedArgumentsEntryR\x0enamedArguments\x12>\n\rpos_arguments\x18\x05 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x0cposArguments\x1aZ\n\tArgsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x37\n\x05value\x18\x02 \x01(\x0b\x32!.spark.connect.Expression.LiteralR\x05value:\x02\x38\x01\x1a\\\n\x13NamedArgumentsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12/\n\x05value\x18\x02 \x01(\x0b\x32\x19.spark.connect.ExpressionR\x05value:\x02\x38\x01"\x97\x05\n\x04Read\x12\x41\n\x0bnamed_table\x18\x01 \x01(\x0b\x32\x1e.spark.connect.Read.NamedTableH\x00R\nnamedTable\x12\x41\n\x0b\x64\x61ta_source\x18\x02 \x01(\x0b\x32\x1e.spark.connect.Read.DataSourceH\x00R\ndataSource\x12!\n\x0cis_streaming\x18\x03 \x01(\x08R\x0bisStreaming\x1a\xc0\x01\n\nNamedTable\x12/\n\x13unparsed_identifier\x18\x01 \x01(\tR\x12unparsedIdentifier\x12\x45\n\x07options\x18\x02 \x03(\x0b\x32+.spark.connect.Read.NamedTable.OptionsEntryR\x07options\x1a:\n\x0cOptionsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01\x1a\x95\x02\n\nDataSource\x12\x1b\n\x06\x66ormat\x18\x01 \x01(\tH\x00R\x06\x66ormat\x88\x01\x01\x12\x1b\n\x06schema\x18\x02 \x01(\tH\x01R\x06schema\x88\x01\x01\x12\x45\n\x07options\x18\x03 \x03(\x0b\x32+.spark.connect.Read.DataSource.OptionsEntryR\x07options\x12\x14\n\x05paths\x18\x04 \x03(\tR\x05paths\x12\x1e\n\npredicates\x18\x05 \x03(\tR\npredicates\x1a:\n\x0cOptionsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01\x42\t\n\x07_formatB\t\n\x07_schemaB\x0b\n\tread_type"u\n\x07Project\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12;\n\x0b\x65xpressions\x18\x03 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x0b\x65xpressions"p\n\x06\x46ilter\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x37\n\tcondition\x18\x02 \x01(\x0b\x32\x19.spark.connect.ExpressionR\tcondition"\x95\x05\n\x04Join\x12+\n\x04left\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x04left\x12-\n\x05right\x18\x02 \x01(\x0b\x32\x17.spark.connect.RelationR\x05right\x12@\n\x0ejoin_condition\x18\x03 \x01(\x0b\x32\x19.spark.connect.ExpressionR\rjoinCondition\x12\x39\n\tjoin_type\x18\x04 \x01(\x0e\x32\x1c.spark.connect.Join.JoinTypeR\x08joinType\x12#\n\rusing_columns\x18\x05 \x03(\tR\x0cusingColumns\x12K\n\x0ejoin_data_type\x18\x06 \x01(\x0b\x32 .spark.connect.Join.JoinDataTypeH\x00R\x0cjoinDataType\x88\x01\x01\x1a\\\n\x0cJoinDataType\x12$\n\x0eis_left_struct\x18\x01 \x01(\x08R\x0cisLeftStruct\x12&\n\x0fis_right_struct\x18\x02 \x01(\x08R\risRightStruct"\xd0\x01\n\x08JoinType\x12\x19\n\x15JOIN_TYPE_UNSPECIFIED\x10\x00\x12\x13\n\x0fJOIN_TYPE_INNER\x10\x01\x12\x18\n\x14JOIN_TYPE_FULL_OUTER\x10\x02\x12\x18\n\x14JOIN_TYPE_LEFT_OUTER\x10\x03\x12\x19\n\x15JOIN_TYPE_RIGHT_OUTER\x10\x04\x12\x17\n\x13JOIN_TYPE_LEFT_ANTI\x10\x05\x12\x17\n\x13JOIN_TYPE_LEFT_SEMI\x10\x06\x12\x13\n\x0fJOIN_TYPE_CROSS\x10\x07\x42\x11\n\x0f_join_data_type"\xdf\x03\n\x0cSetOperation\x12\x36\n\nleft_input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\tleftInput\x12\x38\n\x0bright_input\x18\x02 \x01(\x0b\x32\x17.spark.connect.RelationR\nrightInput\x12\x45\n\x0bset_op_type\x18\x03 \x01(\x0e\x32%.spark.connect.SetOperation.SetOpTypeR\tsetOpType\x12\x1a\n\x06is_all\x18\x04 \x01(\x08H\x00R\x05isAll\x88\x01\x01\x12\x1c\n\x07\x62y_name\x18\x05 \x01(\x08H\x01R\x06\x62yName\x88\x01\x01\x12\x37\n\x15\x61llow_missing_columns\x18\x06 \x01(\x08H\x02R\x13\x61llowMissingColumns\x88\x01\x01"r\n\tSetOpType\x12\x1b\n\x17SET_OP_TYPE_UNSPECIFIED\x10\x00\x12\x19\n\x15SET_OP_TYPE_INTERSECT\x10\x01\x12\x15\n\x11SET_OP_TYPE_UNION\x10\x02\x12\x16\n\x12SET_OP_TYPE_EXCEPT\x10\x03\x42\t\n\x07_is_allB\n\n\x08_by_nameB\x18\n\x16_allow_missing_columns"L\n\x05Limit\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x14\n\x05limit\x18\x02 \x01(\x05R\x05limit"O\n\x06Offset\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x16\n\x06offset\x18\x02 \x01(\x05R\x06offset"K\n\x04Tail\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x14\n\x05limit\x18\x02 \x01(\x05R\x05limit"\xc6\x04\n\tAggregate\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x41\n\ngroup_type\x18\x02 \x01(\x0e\x32".spark.connect.Aggregate.GroupTypeR\tgroupType\x12L\n\x14grouping_expressions\x18\x03 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x13groupingExpressions\x12N\n\x15\x61ggregate_expressions\x18\x04 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x14\x61ggregateExpressions\x12\x34\n\x05pivot\x18\x05 \x01(\x0b\x32\x1e.spark.connect.Aggregate.PivotR\x05pivot\x1ao\n\x05Pivot\x12+\n\x03\x63ol\x18\x01 \x01(\x0b\x32\x19.spark.connect.ExpressionR\x03\x63ol\x12\x39\n\x06values\x18\x02 \x03(\x0b\x32!.spark.connect.Expression.LiteralR\x06values"\x81\x01\n\tGroupType\x12\x1a\n\x16GROUP_TYPE_UNSPECIFIED\x10\x00\x12\x16\n\x12GROUP_TYPE_GROUPBY\x10\x01\x12\x15\n\x11GROUP_TYPE_ROLLUP\x10\x02\x12\x13\n\x0fGROUP_TYPE_CUBE\x10\x03\x12\x14\n\x10GROUP_TYPE_PIVOT\x10\x04"\xa0\x01\n\x04Sort\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x39\n\x05order\x18\x02 \x03(\x0b\x32#.spark.connect.Expression.SortOrderR\x05order\x12 \n\tis_global\x18\x03 \x01(\x08H\x00R\x08isGlobal\x88\x01\x01\x42\x0c\n\n_is_global"\x8d\x01\n\x04\x44rop\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x33\n\x07\x63olumns\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x07\x63olumns\x12!\n\x0c\x63olumn_names\x18\x03 \x03(\tR\x0b\x63olumnNames"\xf0\x01\n\x0b\x44\x65\x64uplicate\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12!\n\x0c\x63olumn_names\x18\x02 \x03(\tR\x0b\x63olumnNames\x12\x32\n\x13\x61ll_columns_as_keys\x18\x03 \x01(\x08H\x00R\x10\x61llColumnsAsKeys\x88\x01\x01\x12.\n\x10within_watermark\x18\x04 \x01(\x08H\x01R\x0fwithinWatermark\x88\x01\x01\x42\x16\n\x14_all_columns_as_keysB\x13\n\x11_within_watermark"Y\n\rLocalRelation\x12\x17\n\x04\x64\x61ta\x18\x01 \x01(\x0cH\x00R\x04\x64\x61ta\x88\x01\x01\x12\x1b\n\x06schema\x18\x02 \x01(\tH\x01R\x06schema\x88\x01\x01\x42\x07\n\x05_dataB\t\n\x07_schema"H\n\x13\x43\x61\x63hedLocalRelation\x12\x12\n\x04hash\x18\x03 \x01(\tR\x04hashJ\x04\x08\x01\x10\x02J\x04\x08\x02\x10\x03R\x06userIdR\tsessionId"7\n\x14\x43\x61\x63hedRemoteRelation\x12\x1f\n\x0brelation_id\x18\x01 \x01(\tR\nrelationId"\x91\x02\n\x06Sample\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x1f\n\x0blower_bound\x18\x02 \x01(\x01R\nlowerBound\x12\x1f\n\x0bupper_bound\x18\x03 \x01(\x01R\nupperBound\x12.\n\x10with_replacement\x18\x04 \x01(\x08H\x00R\x0fwithReplacement\x88\x01\x01\x12\x17\n\x04seed\x18\x05 \x01(\x03H\x01R\x04seed\x88\x01\x01\x12/\n\x13\x64\x65terministic_order\x18\x06 \x01(\x08R\x12\x64\x65terministicOrderB\x13\n\x11_with_replacementB\x07\n\x05_seed"\x91\x01\n\x05Range\x12\x19\n\x05start\x18\x01 \x01(\x03H\x00R\x05start\x88\x01\x01\x12\x10\n\x03\x65nd\x18\x02 \x01(\x03R\x03\x65nd\x12\x12\n\x04step\x18\x03 \x01(\x03R\x04step\x12*\n\x0enum_partitions\x18\x04 \x01(\x05H\x01R\rnumPartitions\x88\x01\x01\x42\x08\n\x06_startB\x11\n\x0f_num_partitions"r\n\rSubqueryAlias\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x14\n\x05\x61lias\x18\x02 \x01(\tR\x05\x61lias\x12\x1c\n\tqualifier\x18\x03 \x03(\tR\tqualifier"\x8e\x01\n\x0bRepartition\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12%\n\x0enum_partitions\x18\x02 \x01(\x05R\rnumPartitions\x12\x1d\n\x07shuffle\x18\x03 \x01(\x08H\x00R\x07shuffle\x88\x01\x01\x42\n\n\x08_shuffle"\x8e\x01\n\nShowString\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x19\n\x08num_rows\x18\x02 \x01(\x05R\x07numRows\x12\x1a\n\x08truncate\x18\x03 \x01(\x05R\x08truncate\x12\x1a\n\x08vertical\x18\x04 \x01(\x08R\x08vertical"r\n\nHtmlString\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x19\n\x08num_rows\x18\x02 \x01(\x05R\x07numRows\x12\x1a\n\x08truncate\x18\x03 \x01(\x05R\x08truncate"\\\n\x0bStatSummary\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x1e\n\nstatistics\x18\x02 \x03(\tR\nstatistics"Q\n\x0cStatDescribe\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols"e\n\x0cStatCrosstab\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ol1\x18\x02 \x01(\tR\x04\x63ol1\x12\x12\n\x04\x63ol2\x18\x03 \x01(\tR\x04\x63ol2"`\n\x07StatCov\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ol1\x18\x02 \x01(\tR\x04\x63ol1\x12\x12\n\x04\x63ol2\x18\x03 \x01(\tR\x04\x63ol2"\x89\x01\n\x08StatCorr\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ol1\x18\x02 \x01(\tR\x04\x63ol1\x12\x12\n\x04\x63ol2\x18\x03 \x01(\tR\x04\x63ol2\x12\x1b\n\x06method\x18\x04 \x01(\tH\x00R\x06method\x88\x01\x01\x42\t\n\x07_method"\xa4\x01\n\x12StatApproxQuantile\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12$\n\rprobabilities\x18\x03 \x03(\x01R\rprobabilities\x12%\n\x0erelative_error\x18\x04 \x01(\x01R\rrelativeError"}\n\rStatFreqItems\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12\x1d\n\x07support\x18\x03 \x01(\x01H\x00R\x07support\x88\x01\x01\x42\n\n\x08_support"\xb5\x02\n\x0cStatSampleBy\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12+\n\x03\x63ol\x18\x02 \x01(\x0b\x32\x19.spark.connect.ExpressionR\x03\x63ol\x12\x42\n\tfractions\x18\x03 \x03(\x0b\x32$.spark.connect.StatSampleBy.FractionR\tfractions\x12\x17\n\x04seed\x18\x05 \x01(\x03H\x00R\x04seed\x88\x01\x01\x1a\x63\n\x08\x46raction\x12;\n\x07stratum\x18\x01 \x01(\x0b\x32!.spark.connect.Expression.LiteralR\x07stratum\x12\x1a\n\x08\x66raction\x18\x02 \x01(\x01R\x08\x66ractionB\x07\n\x05_seed"\x86\x01\n\x06NAFill\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12\x39\n\x06values\x18\x03 \x03(\x0b\x32!.spark.connect.Expression.LiteralR\x06values"\x86\x01\n\x06NADrop\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12\'\n\rmin_non_nulls\x18\x03 \x01(\x05H\x00R\x0bminNonNulls\x88\x01\x01\x42\x10\n\x0e_min_non_nulls"\xa8\x02\n\tNAReplace\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12H\n\x0creplacements\x18\x03 \x03(\x0b\x32$.spark.connect.NAReplace.ReplacementR\x0creplacements\x1a\x8d\x01\n\x0bReplacement\x12>\n\told_value\x18\x01 \x01(\x0b\x32!.spark.connect.Expression.LiteralR\x08oldValue\x12>\n\tnew_value\x18\x02 \x01(\x0b\x32!.spark.connect.Expression.LiteralR\x08newValue"X\n\x04ToDF\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12!\n\x0c\x63olumn_names\x18\x02 \x03(\tR\x0b\x63olumnNames"\xef\x01\n\x12WithColumnsRenamed\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x65\n\x12rename_columns_map\x18\x02 \x03(\x0b\x32\x37.spark.connect.WithColumnsRenamed.RenameColumnsMapEntryR\x10renameColumnsMap\x1a\x43\n\x15RenameColumnsMapEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01"w\n\x0bWithColumns\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x39\n\x07\x61liases\x18\x02 \x03(\x0b\x32\x1f.spark.connect.Expression.AliasR\x07\x61liases"\x86\x01\n\rWithWatermark\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x1d\n\nevent_time\x18\x02 \x01(\tR\teventTime\x12\'\n\x0f\x64\x65lay_threshold\x18\x03 \x01(\tR\x0e\x64\x65layThreshold"\x84\x01\n\x04Hint\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12\x39\n\nparameters\x18\x03 \x03(\x0b\x32\x19.spark.connect.ExpressionR\nparameters"\xc7\x02\n\x07Unpivot\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12+\n\x03ids\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x03ids\x12:\n\x06values\x18\x03 \x01(\x0b\x32\x1d.spark.connect.Unpivot.ValuesH\x00R\x06values\x88\x01\x01\x12\x30\n\x14variable_column_name\x18\x04 \x01(\tR\x12variableColumnName\x12*\n\x11value_column_name\x18\x05 \x01(\tR\x0fvalueColumnName\x1a;\n\x06Values\x12\x31\n\x06values\x18\x01 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x06valuesB\t\n\x07_values"j\n\x08ToSchema\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12/\n\x06schema\x18\x02 \x01(\x0b\x32\x17.spark.connect.DataTypeR\x06schema"\xcb\x01\n\x17RepartitionByExpression\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x42\n\x0fpartition_exprs\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x0epartitionExprs\x12*\n\x0enum_partitions\x18\x03 \x01(\x05H\x00R\rnumPartitions\x88\x01\x01\x42\x11\n\x0f_num_partitions"\xb5\x01\n\rMapPartitions\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x42\n\x04\x66unc\x18\x02 \x01(\x0b\x32..spark.connect.CommonInlineUserDefinedFunctionR\x04\x66unc\x12"\n\nis_barrier\x18\x03 \x01(\x08H\x00R\tisBarrier\x88\x01\x01\x42\r\n\x0b_is_barrier"\xfb\x04\n\x08GroupMap\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12L\n\x14grouping_expressions\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x13groupingExpressions\x12\x42\n\x04\x66unc\x18\x03 \x01(\x0b\x32..spark.connect.CommonInlineUserDefinedFunctionR\x04\x66unc\x12J\n\x13sorting_expressions\x18\x04 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x12sortingExpressions\x12<\n\rinitial_input\x18\x05 \x01(\x0b\x32\x17.spark.connect.RelationR\x0cinitialInput\x12[\n\x1cinitial_grouping_expressions\x18\x06 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x1ainitialGroupingExpressions\x12;\n\x18is_map_groups_with_state\x18\x07 \x01(\x08H\x00R\x14isMapGroupsWithState\x88\x01\x01\x12$\n\x0boutput_mode\x18\x08 \x01(\tH\x01R\noutputMode\x88\x01\x01\x12&\n\x0ctimeout_conf\x18\t \x01(\tH\x02R\x0btimeoutConf\x88\x01\x01\x42\x1b\n\x19_is_map_groups_with_stateB\x0e\n\x0c_output_modeB\x0f\n\r_timeout_conf"\x8e\x04\n\nCoGroupMap\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12W\n\x1ainput_grouping_expressions\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x18inputGroupingExpressions\x12-\n\x05other\x18\x03 \x01(\x0b\x32\x17.spark.connect.RelationR\x05other\x12W\n\x1aother_grouping_expressions\x18\x04 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x18otherGroupingExpressions\x12\x42\n\x04\x66unc\x18\x05 \x01(\x0b\x32..spark.connect.CommonInlineUserDefinedFunctionR\x04\x66unc\x12U\n\x19input_sorting_expressions\x18\x06 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x17inputSortingExpressions\x12U\n\x19other_sorting_expressions\x18\x07 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x17otherSortingExpressions"\xe5\x02\n\x16\x41pplyInPandasWithState\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12L\n\x14grouping_expressions\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x13groupingExpressions\x12\x42\n\x04\x66unc\x18\x03 \x01(\x0b\x32..spark.connect.CommonInlineUserDefinedFunctionR\x04\x66unc\x12#\n\routput_schema\x18\x04 \x01(\tR\x0coutputSchema\x12!\n\x0cstate_schema\x18\x05 \x01(\tR\x0bstateSchema\x12\x1f\n\x0boutput_mode\x18\x06 \x01(\tR\noutputMode\x12!\n\x0ctimeout_conf\x18\x07 \x01(\tR\x0btimeoutConf"\xf4\x01\n$CommonInlineUserDefinedTableFunction\x12#\n\rfunction_name\x18\x01 \x01(\tR\x0c\x66unctionName\x12$\n\rdeterministic\x18\x02 \x01(\x08R\rdeterministic\x12\x37\n\targuments\x18\x03 \x03(\x0b\x32\x19.spark.connect.ExpressionR\targuments\x12<\n\x0bpython_udtf\x18\x04 \x01(\x0b\x32\x19.spark.connect.PythonUDTFH\x00R\npythonUdtfB\n\n\x08\x66unction"\xb1\x01\n\nPythonUDTF\x12=\n\x0breturn_type\x18\x01 \x01(\x0b\x32\x17.spark.connect.DataTypeH\x00R\nreturnType\x88\x01\x01\x12\x1b\n\teval_type\x18\x02 \x01(\x05R\x08\x65valType\x12\x18\n\x07\x63ommand\x18\x03 \x01(\x0cR\x07\x63ommand\x12\x1d\n\npython_ver\x18\x04 \x01(\tR\tpythonVerB\x0e\n\x0c_return_type"\x88\x01\n\x0e\x43ollectMetrics\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12\x33\n\x07metrics\x18\x03 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x07metrics"\x84\x03\n\x05Parse\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x38\n\x06\x66ormat\x18\x02 \x01(\x0e\x32 .spark.connect.Parse.ParseFormatR\x06\x66ormat\x12\x34\n\x06schema\x18\x03 \x01(\x0b\x32\x17.spark.connect.DataTypeH\x00R\x06schema\x88\x01\x01\x12;\n\x07options\x18\x04 \x03(\x0b\x32!.spark.connect.Parse.OptionsEntryR\x07options\x1a:\n\x0cOptionsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01"X\n\x0bParseFormat\x12\x1c\n\x18PARSE_FORMAT_UNSPECIFIED\x10\x00\x12\x14\n\x10PARSE_FORMAT_CSV\x10\x01\x12\x15\n\x11PARSE_FORMAT_JSON\x10\x02\x42\t\n\x07_schema"\xdb\x03\n\x08\x41sOfJoin\x12+\n\x04left\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x04left\x12-\n\x05right\x18\x02 \x01(\x0b\x32\x17.spark.connect.RelationR\x05right\x12\x37\n\nleft_as_of\x18\x03 \x01(\x0b\x32\x19.spark.connect.ExpressionR\x08leftAsOf\x12\x39\n\x0bright_as_of\x18\x04 \x01(\x0b\x32\x19.spark.connect.ExpressionR\trightAsOf\x12\x36\n\tjoin_expr\x18\x05 \x01(\x0b\x32\x19.spark.connect.ExpressionR\x08joinExpr\x12#\n\rusing_columns\x18\x06 \x03(\tR\x0cusingColumns\x12\x1b\n\tjoin_type\x18\x07 \x01(\tR\x08joinType\x12\x37\n\ttolerance\x18\x08 \x01(\x0b\x32\x19.spark.connect.ExpressionR\ttolerance\x12.\n\x13\x61llow_exact_matches\x18\t \x01(\x08R\x11\x61llowExactMatches\x12\x1c\n\tdirection\x18\n \x01(\tR\tdirectionB6\n\x1eorg.apache.spark.connect.protoP\x01Z\x12internal/generatedb\x06proto3' + b'\n\x1dspark/connect/relations.proto\x12\rspark.connect\x1a\x19google/protobuf/any.proto\x1a\x1fspark/connect/expressions.proto\x1a\x19spark/connect/types.proto\x1a\x1bspark/connect/catalog.proto"\x9a\x19\n\x08Relation\x12\x35\n\x06\x63ommon\x18\x01 \x01(\x0b\x32\x1d.spark.connect.RelationCommonR\x06\x63ommon\x12)\n\x04read\x18\x02 \x01(\x0b\x32\x13.spark.connect.ReadH\x00R\x04read\x12\x32\n\x07project\x18\x03 \x01(\x0b\x32\x16.spark.connect.ProjectH\x00R\x07project\x12/\n\x06\x66ilter\x18\x04 \x01(\x0b\x32\x15.spark.connect.FilterH\x00R\x06\x66ilter\x12)\n\x04join\x18\x05 \x01(\x0b\x32\x13.spark.connect.JoinH\x00R\x04join\x12\x34\n\x06set_op\x18\x06 \x01(\x0b\x32\x1b.spark.connect.SetOperationH\x00R\x05setOp\x12)\n\x04sort\x18\x07 \x01(\x0b\x32\x13.spark.connect.SortH\x00R\x04sort\x12,\n\x05limit\x18\x08 \x01(\x0b\x32\x14.spark.connect.LimitH\x00R\x05limit\x12\x38\n\taggregate\x18\t \x01(\x0b\x32\x18.spark.connect.AggregateH\x00R\taggregate\x12&\n\x03sql\x18\n \x01(\x0b\x32\x12.spark.connect.SQLH\x00R\x03sql\x12\x45\n\x0elocal_relation\x18\x0b \x01(\x0b\x32\x1c.spark.connect.LocalRelationH\x00R\rlocalRelation\x12/\n\x06sample\x18\x0c \x01(\x0b\x32\x15.spark.connect.SampleH\x00R\x06sample\x12/\n\x06offset\x18\r \x01(\x0b\x32\x15.spark.connect.OffsetH\x00R\x06offset\x12>\n\x0b\x64\x65\x64uplicate\x18\x0e \x01(\x0b\x32\x1a.spark.connect.DeduplicateH\x00R\x0b\x64\x65\x64uplicate\x12,\n\x05range\x18\x0f \x01(\x0b\x32\x14.spark.connect.RangeH\x00R\x05range\x12\x45\n\x0esubquery_alias\x18\x10 \x01(\x0b\x32\x1c.spark.connect.SubqueryAliasH\x00R\rsubqueryAlias\x12>\n\x0brepartition\x18\x11 \x01(\x0b\x32\x1a.spark.connect.RepartitionH\x00R\x0brepartition\x12*\n\x05to_df\x18\x12 \x01(\x0b\x32\x13.spark.connect.ToDFH\x00R\x04toDf\x12U\n\x14with_columns_renamed\x18\x13 \x01(\x0b\x32!.spark.connect.WithColumnsRenamedH\x00R\x12withColumnsRenamed\x12<\n\x0bshow_string\x18\x14 \x01(\x0b\x32\x19.spark.connect.ShowStringH\x00R\nshowString\x12)\n\x04\x64rop\x18\x15 \x01(\x0b\x32\x13.spark.connect.DropH\x00R\x04\x64rop\x12)\n\x04tail\x18\x16 \x01(\x0b\x32\x13.spark.connect.TailH\x00R\x04tail\x12?\n\x0cwith_columns\x18\x17 \x01(\x0b\x32\x1a.spark.connect.WithColumnsH\x00R\x0bwithColumns\x12)\n\x04hint\x18\x18 \x01(\x0b\x32\x13.spark.connect.HintH\x00R\x04hint\x12\x32\n\x07unpivot\x18\x19 \x01(\x0b\x32\x16.spark.connect.UnpivotH\x00R\x07unpivot\x12\x36\n\tto_schema\x18\x1a \x01(\x0b\x32\x17.spark.connect.ToSchemaH\x00R\x08toSchema\x12\x64\n\x19repartition_by_expression\x18\x1b \x01(\x0b\x32&.spark.connect.RepartitionByExpressionH\x00R\x17repartitionByExpression\x12\x45\n\x0emap_partitions\x18\x1c \x01(\x0b\x32\x1c.spark.connect.MapPartitionsH\x00R\rmapPartitions\x12H\n\x0f\x63ollect_metrics\x18\x1d \x01(\x0b\x32\x1d.spark.connect.CollectMetricsH\x00R\x0e\x63ollectMetrics\x12,\n\x05parse\x18\x1e \x01(\x0b\x32\x14.spark.connect.ParseH\x00R\x05parse\x12\x36\n\tgroup_map\x18\x1f \x01(\x0b\x32\x17.spark.connect.GroupMapH\x00R\x08groupMap\x12=\n\x0c\x63o_group_map\x18 \x01(\x0b\x32\x19.spark.connect.CoGroupMapH\x00R\ncoGroupMap\x12\x45\n\x0ewith_watermark\x18! \x01(\x0b\x32\x1c.spark.connect.WithWatermarkH\x00R\rwithWatermark\x12\x63\n\x1a\x61pply_in_pandas_with_state\x18" \x01(\x0b\x32%.spark.connect.ApplyInPandasWithStateH\x00R\x16\x61pplyInPandasWithState\x12<\n\x0bhtml_string\x18# \x01(\x0b\x32\x19.spark.connect.HtmlStringH\x00R\nhtmlString\x12X\n\x15\x63\x61\x63hed_local_relation\x18$ \x01(\x0b\x32".spark.connect.CachedLocalRelationH\x00R\x13\x63\x61\x63hedLocalRelation\x12[\n\x16\x63\x61\x63hed_remote_relation\x18% \x01(\x0b\x32#.spark.connect.CachedRemoteRelationH\x00R\x14\x63\x61\x63hedRemoteRelation\x12\x8e\x01\n)common_inline_user_defined_table_function\x18& \x01(\x0b\x32\x33.spark.connect.CommonInlineUserDefinedTableFunctionH\x00R$commonInlineUserDefinedTableFunction\x12\x37\n\nas_of_join\x18\' \x01(\x0b\x32\x17.spark.connect.AsOfJoinH\x00R\x08\x61sOfJoin\x12\x30\n\x07\x66ill_na\x18Z \x01(\x0b\x32\x15.spark.connect.NAFillH\x00R\x06\x66illNa\x12\x30\n\x07\x64rop_na\x18[ \x01(\x0b\x32\x15.spark.connect.NADropH\x00R\x06\x64ropNa\x12\x34\n\x07replace\x18\\ \x01(\x0b\x32\x18.spark.connect.NAReplaceH\x00R\x07replace\x12\x36\n\x07summary\x18\x64 \x01(\x0b\x32\x1a.spark.connect.StatSummaryH\x00R\x07summary\x12\x39\n\x08\x63rosstab\x18\x65 \x01(\x0b\x32\x1b.spark.connect.StatCrosstabH\x00R\x08\x63rosstab\x12\x39\n\x08\x64\x65scribe\x18\x66 \x01(\x0b\x32\x1b.spark.connect.StatDescribeH\x00R\x08\x64\x65scribe\x12*\n\x03\x63ov\x18g \x01(\x0b\x32\x16.spark.connect.StatCovH\x00R\x03\x63ov\x12-\n\x04\x63orr\x18h \x01(\x0b\x32\x17.spark.connect.StatCorrH\x00R\x04\x63orr\x12L\n\x0f\x61pprox_quantile\x18i \x01(\x0b\x32!.spark.connect.StatApproxQuantileH\x00R\x0e\x61pproxQuantile\x12=\n\nfreq_items\x18j \x01(\x0b\x32\x1c.spark.connect.StatFreqItemsH\x00R\tfreqItems\x12:\n\tsample_by\x18k \x01(\x0b\x32\x1b.spark.connect.StatSampleByH\x00R\x08sampleBy\x12\x33\n\x07\x63\x61talog\x18\xc8\x01 \x01(\x0b\x32\x16.spark.connect.CatalogH\x00R\x07\x63\x61talog\x12\x35\n\textension\x18\xe6\x07 \x01(\x0b\x32\x14.google.protobuf.AnyH\x00R\textension\x12\x33\n\x07unknown\x18\xe7\x07 \x01(\x0b\x32\x16.spark.connect.UnknownH\x00R\x07unknownB\n\n\x08rel_type"\t\n\x07Unknown"[\n\x0eRelationCommon\x12\x1f\n\x0bsource_info\x18\x01 \x01(\tR\nsourceInfo\x12\x1c\n\x07plan_id\x18\x02 \x01(\x03H\x00R\x06planId\x88\x01\x01\x42\n\n\x08_plan_id"\xde\x03\n\x03SQL\x12\x14\n\x05query\x18\x01 \x01(\tR\x05query\x12\x34\n\x04\x61rgs\x18\x02 \x03(\x0b\x32\x1c.spark.connect.SQL.ArgsEntryB\x02\x18\x01R\x04\x61rgs\x12@\n\x08pos_args\x18\x03 \x03(\x0b\x32!.spark.connect.Expression.LiteralB\x02\x18\x01R\x07posArgs\x12O\n\x0fnamed_arguments\x18\x04 \x03(\x0b\x32&.spark.connect.SQL.NamedArgumentsEntryR\x0enamedArguments\x12>\n\rpos_arguments\x18\x05 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x0cposArguments\x1aZ\n\tArgsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x37\n\x05value\x18\x02 \x01(\x0b\x32!.spark.connect.Expression.LiteralR\x05value:\x02\x38\x01\x1a\\\n\x13NamedArgumentsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12/\n\x05value\x18\x02 \x01(\x0b\x32\x19.spark.connect.ExpressionR\x05value:\x02\x38\x01"\x97\x05\n\x04Read\x12\x41\n\x0bnamed_table\x18\x01 \x01(\x0b\x32\x1e.spark.connect.Read.NamedTableH\x00R\nnamedTable\x12\x41\n\x0b\x64\x61ta_source\x18\x02 \x01(\x0b\x32\x1e.spark.connect.Read.DataSourceH\x00R\ndataSource\x12!\n\x0cis_streaming\x18\x03 \x01(\x08R\x0bisStreaming\x1a\xc0\x01\n\nNamedTable\x12/\n\x13unparsed_identifier\x18\x01 \x01(\tR\x12unparsedIdentifier\x12\x45\n\x07options\x18\x02 \x03(\x0b\x32+.spark.connect.Read.NamedTable.OptionsEntryR\x07options\x1a:\n\x0cOptionsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01\x1a\x95\x02\n\nDataSource\x12\x1b\n\x06\x66ormat\x18\x01 \x01(\tH\x00R\x06\x66ormat\x88\x01\x01\x12\x1b\n\x06schema\x18\x02 \x01(\tH\x01R\x06schema\x88\x01\x01\x12\x45\n\x07options\x18\x03 \x03(\x0b\x32+.spark.connect.Read.DataSource.OptionsEntryR\x07options\x12\x14\n\x05paths\x18\x04 \x03(\tR\x05paths\x12\x1e\n\npredicates\x18\x05 \x03(\tR\npredicates\x1a:\n\x0cOptionsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01\x42\t\n\x07_formatB\t\n\x07_schemaB\x0b\n\tread_type"u\n\x07Project\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12;\n\x0b\x65xpressions\x18\x03 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x0b\x65xpressions"p\n\x06\x46ilter\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x37\n\tcondition\x18\x02 \x01(\x0b\x32\x19.spark.connect.ExpressionR\tcondition"\x95\x05\n\x04Join\x12+\n\x04left\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x04left\x12-\n\x05right\x18\x02 \x01(\x0b\x32\x17.spark.connect.RelationR\x05right\x12@\n\x0ejoin_condition\x18\x03 \x01(\x0b\x32\x19.spark.connect.ExpressionR\rjoinCondition\x12\x39\n\tjoin_type\x18\x04 \x01(\x0e\x32\x1c.spark.connect.Join.JoinTypeR\x08joinType\x12#\n\rusing_columns\x18\x05 \x03(\tR\x0cusingColumns\x12K\n\x0ejoin_data_type\x18\x06 \x01(\x0b\x32 .spark.connect.Join.JoinDataTypeH\x00R\x0cjoinDataType\x88\x01\x01\x1a\\\n\x0cJoinDataType\x12$\n\x0eis_left_struct\x18\x01 \x01(\x08R\x0cisLeftStruct\x12&\n\x0fis_right_struct\x18\x02 \x01(\x08R\risRightStruct"\xd0\x01\n\x08JoinType\x12\x19\n\x15JOIN_TYPE_UNSPECIFIED\x10\x00\x12\x13\n\x0fJOIN_TYPE_INNER\x10\x01\x12\x18\n\x14JOIN_TYPE_FULL_OUTER\x10\x02\x12\x18\n\x14JOIN_TYPE_LEFT_OUTER\x10\x03\x12\x19\n\x15JOIN_TYPE_RIGHT_OUTER\x10\x04\x12\x17\n\x13JOIN_TYPE_LEFT_ANTI\x10\x05\x12\x17\n\x13JOIN_TYPE_LEFT_SEMI\x10\x06\x12\x13\n\x0fJOIN_TYPE_CROSS\x10\x07\x42\x11\n\x0f_join_data_type"\xdf\x03\n\x0cSetOperation\x12\x36\n\nleft_input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\tleftInput\x12\x38\n\x0bright_input\x18\x02 \x01(\x0b\x32\x17.spark.connect.RelationR\nrightInput\x12\x45\n\x0bset_op_type\x18\x03 \x01(\x0e\x32%.spark.connect.SetOperation.SetOpTypeR\tsetOpType\x12\x1a\n\x06is_all\x18\x04 \x01(\x08H\x00R\x05isAll\x88\x01\x01\x12\x1c\n\x07\x62y_name\x18\x05 \x01(\x08H\x01R\x06\x62yName\x88\x01\x01\x12\x37\n\x15\x61llow_missing_columns\x18\x06 \x01(\x08H\x02R\x13\x61llowMissingColumns\x88\x01\x01"r\n\tSetOpType\x12\x1b\n\x17SET_OP_TYPE_UNSPECIFIED\x10\x00\x12\x19\n\x15SET_OP_TYPE_INTERSECT\x10\x01\x12\x15\n\x11SET_OP_TYPE_UNION\x10\x02\x12\x16\n\x12SET_OP_TYPE_EXCEPT\x10\x03\x42\t\n\x07_is_allB\n\n\x08_by_nameB\x18\n\x16_allow_missing_columns"L\n\x05Limit\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x14\n\x05limit\x18\x02 \x01(\x05R\x05limit"O\n\x06Offset\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x16\n\x06offset\x18\x02 \x01(\x05R\x06offset"K\n\x04Tail\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x14\n\x05limit\x18\x02 \x01(\x05R\x05limit"\xfe\x05\n\tAggregate\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x41\n\ngroup_type\x18\x02 \x01(\x0e\x32".spark.connect.Aggregate.GroupTypeR\tgroupType\x12L\n\x14grouping_expressions\x18\x03 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x13groupingExpressions\x12N\n\x15\x61ggregate_expressions\x18\x04 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x14\x61ggregateExpressions\x12\x34\n\x05pivot\x18\x05 \x01(\x0b\x32\x1e.spark.connect.Aggregate.PivotR\x05pivot\x12J\n\rgrouping_sets\x18\x06 \x03(\x0b\x32%.spark.connect.Aggregate.GroupingSetsR\x0cgroupingSets\x1ao\n\x05Pivot\x12+\n\x03\x63ol\x18\x01 \x01(\x0b\x32\x19.spark.connect.ExpressionR\x03\x63ol\x12\x39\n\x06values\x18\x02 \x03(\x0b\x32!.spark.connect.Expression.LiteralR\x06values\x1aL\n\x0cGroupingSets\x12<\n\x0cgrouping_set\x18\x01 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x0bgroupingSet"\x9f\x01\n\tGroupType\x12\x1a\n\x16GROUP_TYPE_UNSPECIFIED\x10\x00\x12\x16\n\x12GROUP_TYPE_GROUPBY\x10\x01\x12\x15\n\x11GROUP_TYPE_ROLLUP\x10\x02\x12\x13\n\x0fGROUP_TYPE_CUBE\x10\x03\x12\x14\n\x10GROUP_TYPE_PIVOT\x10\x04\x12\x1c\n\x18GROUP_TYPE_GROUPING_SETS\x10\x05"\xa0\x01\n\x04Sort\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x39\n\x05order\x18\x02 \x03(\x0b\x32#.spark.connect.Expression.SortOrderR\x05order\x12 \n\tis_global\x18\x03 \x01(\x08H\x00R\x08isGlobal\x88\x01\x01\x42\x0c\n\n_is_global"\x8d\x01\n\x04\x44rop\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x33\n\x07\x63olumns\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x07\x63olumns\x12!\n\x0c\x63olumn_names\x18\x03 \x03(\tR\x0b\x63olumnNames"\xf0\x01\n\x0b\x44\x65\x64uplicate\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12!\n\x0c\x63olumn_names\x18\x02 \x03(\tR\x0b\x63olumnNames\x12\x32\n\x13\x61ll_columns_as_keys\x18\x03 \x01(\x08H\x00R\x10\x61llColumnsAsKeys\x88\x01\x01\x12.\n\x10within_watermark\x18\x04 \x01(\x08H\x01R\x0fwithinWatermark\x88\x01\x01\x42\x16\n\x14_all_columns_as_keysB\x13\n\x11_within_watermark"Y\n\rLocalRelation\x12\x17\n\x04\x64\x61ta\x18\x01 \x01(\x0cH\x00R\x04\x64\x61ta\x88\x01\x01\x12\x1b\n\x06schema\x18\x02 \x01(\tH\x01R\x06schema\x88\x01\x01\x42\x07\n\x05_dataB\t\n\x07_schema"H\n\x13\x43\x61\x63hedLocalRelation\x12\x12\n\x04hash\x18\x03 \x01(\tR\x04hashJ\x04\x08\x01\x10\x02J\x04\x08\x02\x10\x03R\x06userIdR\tsessionId"7\n\x14\x43\x61\x63hedRemoteRelation\x12\x1f\n\x0brelation_id\x18\x01 \x01(\tR\nrelationId"\x91\x02\n\x06Sample\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x1f\n\x0blower_bound\x18\x02 \x01(\x01R\nlowerBound\x12\x1f\n\x0bupper_bound\x18\x03 \x01(\x01R\nupperBound\x12.\n\x10with_replacement\x18\x04 \x01(\x08H\x00R\x0fwithReplacement\x88\x01\x01\x12\x17\n\x04seed\x18\x05 \x01(\x03H\x01R\x04seed\x88\x01\x01\x12/\n\x13\x64\x65terministic_order\x18\x06 \x01(\x08R\x12\x64\x65terministicOrderB\x13\n\x11_with_replacementB\x07\n\x05_seed"\x91\x01\n\x05Range\x12\x19\n\x05start\x18\x01 \x01(\x03H\x00R\x05start\x88\x01\x01\x12\x10\n\x03\x65nd\x18\x02 \x01(\x03R\x03\x65nd\x12\x12\n\x04step\x18\x03 \x01(\x03R\x04step\x12*\n\x0enum_partitions\x18\x04 \x01(\x05H\x01R\rnumPartitions\x88\x01\x01\x42\x08\n\x06_startB\x11\n\x0f_num_partitions"r\n\rSubqueryAlias\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x14\n\x05\x61lias\x18\x02 \x01(\tR\x05\x61lias\x12\x1c\n\tqualifier\x18\x03 \x03(\tR\tqualifier"\x8e\x01\n\x0bRepartition\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12%\n\x0enum_partitions\x18\x02 \x01(\x05R\rnumPartitions\x12\x1d\n\x07shuffle\x18\x03 \x01(\x08H\x00R\x07shuffle\x88\x01\x01\x42\n\n\x08_shuffle"\x8e\x01\n\nShowString\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x19\n\x08num_rows\x18\x02 \x01(\x05R\x07numRows\x12\x1a\n\x08truncate\x18\x03 \x01(\x05R\x08truncate\x12\x1a\n\x08vertical\x18\x04 \x01(\x08R\x08vertical"r\n\nHtmlString\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x19\n\x08num_rows\x18\x02 \x01(\x05R\x07numRows\x12\x1a\n\x08truncate\x18\x03 \x01(\x05R\x08truncate"\\\n\x0bStatSummary\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x1e\n\nstatistics\x18\x02 \x03(\tR\nstatistics"Q\n\x0cStatDescribe\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols"e\n\x0cStatCrosstab\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ol1\x18\x02 \x01(\tR\x04\x63ol1\x12\x12\n\x04\x63ol2\x18\x03 \x01(\tR\x04\x63ol2"`\n\x07StatCov\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ol1\x18\x02 \x01(\tR\x04\x63ol1\x12\x12\n\x04\x63ol2\x18\x03 \x01(\tR\x04\x63ol2"\x89\x01\n\x08StatCorr\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ol1\x18\x02 \x01(\tR\x04\x63ol1\x12\x12\n\x04\x63ol2\x18\x03 \x01(\tR\x04\x63ol2\x12\x1b\n\x06method\x18\x04 \x01(\tH\x00R\x06method\x88\x01\x01\x42\t\n\x07_method"\xa4\x01\n\x12StatApproxQuantile\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12$\n\rprobabilities\x18\x03 \x03(\x01R\rprobabilities\x12%\n\x0erelative_error\x18\x04 \x01(\x01R\rrelativeError"}\n\rStatFreqItems\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12\x1d\n\x07support\x18\x03 \x01(\x01H\x00R\x07support\x88\x01\x01\x42\n\n\x08_support"\xb5\x02\n\x0cStatSampleBy\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12+\n\x03\x63ol\x18\x02 \x01(\x0b\x32\x19.spark.connect.ExpressionR\x03\x63ol\x12\x42\n\tfractions\x18\x03 \x03(\x0b\x32$.spark.connect.StatSampleBy.FractionR\tfractions\x12\x17\n\x04seed\x18\x05 \x01(\x03H\x00R\x04seed\x88\x01\x01\x1a\x63\n\x08\x46raction\x12;\n\x07stratum\x18\x01 \x01(\x0b\x32!.spark.connect.Expression.LiteralR\x07stratum\x12\x1a\n\x08\x66raction\x18\x02 \x01(\x01R\x08\x66ractionB\x07\n\x05_seed"\x86\x01\n\x06NAFill\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12\x39\n\x06values\x18\x03 \x03(\x0b\x32!.spark.connect.Expression.LiteralR\x06values"\x86\x01\n\x06NADrop\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12\'\n\rmin_non_nulls\x18\x03 \x01(\x05H\x00R\x0bminNonNulls\x88\x01\x01\x42\x10\n\x0e_min_non_nulls"\xa8\x02\n\tNAReplace\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04\x63ols\x18\x02 \x03(\tR\x04\x63ols\x12H\n\x0creplacements\x18\x03 \x03(\x0b\x32$.spark.connect.NAReplace.ReplacementR\x0creplacements\x1a\x8d\x01\n\x0bReplacement\x12>\n\told_value\x18\x01 \x01(\x0b\x32!.spark.connect.Expression.LiteralR\x08oldValue\x12>\n\tnew_value\x18\x02 \x01(\x0b\x32!.spark.connect.Expression.LiteralR\x08newValue"X\n\x04ToDF\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12!\n\x0c\x63olumn_names\x18\x02 \x03(\tR\x0b\x63olumnNames"\xef\x01\n\x12WithColumnsRenamed\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x65\n\x12rename_columns_map\x18\x02 \x03(\x0b\x32\x37.spark.connect.WithColumnsRenamed.RenameColumnsMapEntryR\x10renameColumnsMap\x1a\x43\n\x15RenameColumnsMapEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01"w\n\x0bWithColumns\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x39\n\x07\x61liases\x18\x02 \x03(\x0b\x32\x1f.spark.connect.Expression.AliasR\x07\x61liases"\x86\x01\n\rWithWatermark\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x1d\n\nevent_time\x18\x02 \x01(\tR\teventTime\x12\'\n\x0f\x64\x65lay_threshold\x18\x03 \x01(\tR\x0e\x64\x65layThreshold"\x84\x01\n\x04Hint\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12\x39\n\nparameters\x18\x03 \x03(\x0b\x32\x19.spark.connect.ExpressionR\nparameters"\xc7\x02\n\x07Unpivot\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12+\n\x03ids\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x03ids\x12:\n\x06values\x18\x03 \x01(\x0b\x32\x1d.spark.connect.Unpivot.ValuesH\x00R\x06values\x88\x01\x01\x12\x30\n\x14variable_column_name\x18\x04 \x01(\tR\x12variableColumnName\x12*\n\x11value_column_name\x18\x05 \x01(\tR\x0fvalueColumnName\x1a;\n\x06Values\x12\x31\n\x06values\x18\x01 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x06valuesB\t\n\x07_values"j\n\x08ToSchema\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12/\n\x06schema\x18\x02 \x01(\x0b\x32\x17.spark.connect.DataTypeR\x06schema"\xcb\x01\n\x17RepartitionByExpression\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x42\n\x0fpartition_exprs\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x0epartitionExprs\x12*\n\x0enum_partitions\x18\x03 \x01(\x05H\x00R\rnumPartitions\x88\x01\x01\x42\x11\n\x0f_num_partitions"\xb5\x01\n\rMapPartitions\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x42\n\x04\x66unc\x18\x02 \x01(\x0b\x32..spark.connect.CommonInlineUserDefinedFunctionR\x04\x66unc\x12"\n\nis_barrier\x18\x03 \x01(\x08H\x00R\tisBarrier\x88\x01\x01\x42\r\n\x0b_is_barrier"\xfb\x04\n\x08GroupMap\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12L\n\x14grouping_expressions\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x13groupingExpressions\x12\x42\n\x04\x66unc\x18\x03 \x01(\x0b\x32..spark.connect.CommonInlineUserDefinedFunctionR\x04\x66unc\x12J\n\x13sorting_expressions\x18\x04 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x12sortingExpressions\x12<\n\rinitial_input\x18\x05 \x01(\x0b\x32\x17.spark.connect.RelationR\x0cinitialInput\x12[\n\x1cinitial_grouping_expressions\x18\x06 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x1ainitialGroupingExpressions\x12;\n\x18is_map_groups_with_state\x18\x07 \x01(\x08H\x00R\x14isMapGroupsWithState\x88\x01\x01\x12$\n\x0boutput_mode\x18\x08 \x01(\tH\x01R\noutputMode\x88\x01\x01\x12&\n\x0ctimeout_conf\x18\t \x01(\tH\x02R\x0btimeoutConf\x88\x01\x01\x42\x1b\n\x19_is_map_groups_with_stateB\x0e\n\x0c_output_modeB\x0f\n\r_timeout_conf"\x8e\x04\n\nCoGroupMap\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12W\n\x1ainput_grouping_expressions\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x18inputGroupingExpressions\x12-\n\x05other\x18\x03 \x01(\x0b\x32\x17.spark.connect.RelationR\x05other\x12W\n\x1aother_grouping_expressions\x18\x04 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x18otherGroupingExpressions\x12\x42\n\x04\x66unc\x18\x05 \x01(\x0b\x32..spark.connect.CommonInlineUserDefinedFunctionR\x04\x66unc\x12U\n\x19input_sorting_expressions\x18\x06 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x17inputSortingExpressions\x12U\n\x19other_sorting_expressions\x18\x07 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x17otherSortingExpressions"\xe5\x02\n\x16\x41pplyInPandasWithState\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12L\n\x14grouping_expressions\x18\x02 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x13groupingExpressions\x12\x42\n\x04\x66unc\x18\x03 \x01(\x0b\x32..spark.connect.CommonInlineUserDefinedFunctionR\x04\x66unc\x12#\n\routput_schema\x18\x04 \x01(\tR\x0coutputSchema\x12!\n\x0cstate_schema\x18\x05 \x01(\tR\x0bstateSchema\x12\x1f\n\x0boutput_mode\x18\x06 \x01(\tR\noutputMode\x12!\n\x0ctimeout_conf\x18\x07 \x01(\tR\x0btimeoutConf"\xf4\x01\n$CommonInlineUserDefinedTableFunction\x12#\n\rfunction_name\x18\x01 \x01(\tR\x0c\x66unctionName\x12$\n\rdeterministic\x18\x02 \x01(\x08R\rdeterministic\x12\x37\n\targuments\x18\x03 \x03(\x0b\x32\x19.spark.connect.ExpressionR\targuments\x12<\n\x0bpython_udtf\x18\x04 \x01(\x0b\x32\x19.spark.connect.PythonUDTFH\x00R\npythonUdtfB\n\n\x08\x66unction"\xb1\x01\n\nPythonUDTF\x12=\n\x0breturn_type\x18\x01 \x01(\x0b\x32\x17.spark.connect.DataTypeH\x00R\nreturnType\x88\x01\x01\x12\x1b\n\teval_type\x18\x02 \x01(\x05R\x08\x65valType\x12\x18\n\x07\x63ommand\x18\x03 \x01(\x0cR\x07\x63ommand\x12\x1d\n\npython_ver\x18\x04 \x01(\tR\tpythonVerB\x0e\n\x0c_return_type"\x88\x01\n\x0e\x43ollectMetrics\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x12\n\x04name\x18\x02 \x01(\tR\x04name\x12\x33\n\x07metrics\x18\x03 \x03(\x0b\x32\x19.spark.connect.ExpressionR\x07metrics"\x84\x03\n\x05Parse\x12-\n\x05input\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x05input\x12\x38\n\x06\x66ormat\x18\x02 \x01(\x0e\x32 .spark.connect.Parse.ParseFormatR\x06\x66ormat\x12\x34\n\x06schema\x18\x03 \x01(\x0b\x32\x17.spark.connect.DataTypeH\x00R\x06schema\x88\x01\x01\x12;\n\x07options\x18\x04 \x03(\x0b\x32!.spark.connect.Parse.OptionsEntryR\x07options\x1a:\n\x0cOptionsEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01"X\n\x0bParseFormat\x12\x1c\n\x18PARSE_FORMAT_UNSPECIFIED\x10\x00\x12\x14\n\x10PARSE_FORMAT_CSV\x10\x01\x12\x15\n\x11PARSE_FORMAT_JSON\x10\x02\x42\t\n\x07_schema"\xdb\x03\n\x08\x41sOfJoin\x12+\n\x04left\x18\x01 \x01(\x0b\x32\x17.spark.connect.RelationR\x04left\x12-\n\x05right\x18\x02 \x01(\x0b\x32\x17.spark.connect.RelationR\x05right\x12\x37\n\nleft_as_of\x18\x03 \x01(\x0b\x32\x19.spark.connect.ExpressionR\x08leftAsOf\x12\x39\n\x0bright_as_of\x18\x04 \x01(\x0b\x32\x19.spark.connect.ExpressionR\trightAsOf\x12\x36\n\tjoin_expr\x18\x05 \x01(\x0b\x32\x19.spark.connect.ExpressionR\x08joinExpr\x12#\n\rusing_columns\x18\x06 \x03(\tR\x0cusingColumns\x12\x1b\n\tjoin_type\x18\x07 \x01(\tR\x08joinType\x12\x37\n\ttolerance\x18\x08 \x01(\x0b\x32\x19.spark.connect.ExpressionR\ttolerance\x12.\n\x13\x61llow_exact_matches\x18\t \x01(\x08R\x11\x61llowExactMatches\x12\x1c\n\tdirection\x18\n \x01(\tR\tdirectionB6\n\x1eorg.apache.spark.connect.protoP\x01Z\x12internal/generatedb\x06proto3' ) _builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, globals()) @@ -104,101 +104,103 @@ _TAIL._serialized_start = 6182 _TAIL._serialized_end = 6257 _AGGREGATE._serialized_start = 6260 - _AGGREGATE._serialized_end = 6842 - _AGGREGATE_PIVOT._serialized_start = 6599 - _AGGREGATE_PIVOT._serialized_end = 6710 - _AGGREGATE_GROUPTYPE._serialized_start = 6713 - _AGGREGATE_GROUPTYPE._serialized_end = 6842 - _SORT._serialized_start = 6845 - _SORT._serialized_end = 7005 - _DROP._serialized_start = 7008 - _DROP._serialized_end = 7149 - _DEDUPLICATE._serialized_start = 7152 - _DEDUPLICATE._serialized_end = 7392 - _LOCALRELATION._serialized_start = 7394 - _LOCALRELATION._serialized_end = 7483 - _CACHEDLOCALRELATION._serialized_start = 7485 - _CACHEDLOCALRELATION._serialized_end = 7557 - _CACHEDREMOTERELATION._serialized_start = 7559 - _CACHEDREMOTERELATION._serialized_end = 7614 - _SAMPLE._serialized_start = 7617 - _SAMPLE._serialized_end = 7890 - _RANGE._serialized_start = 7893 - _RANGE._serialized_end = 8038 - _SUBQUERYALIAS._serialized_start = 8040 - _SUBQUERYALIAS._serialized_end = 8154 - _REPARTITION._serialized_start = 8157 - _REPARTITION._serialized_end = 8299 - _SHOWSTRING._serialized_start = 8302 - _SHOWSTRING._serialized_end = 8444 - _HTMLSTRING._serialized_start = 8446 - _HTMLSTRING._serialized_end = 8560 - _STATSUMMARY._serialized_start = 8562 - _STATSUMMARY._serialized_end = 8654 - _STATDESCRIBE._serialized_start = 8656 - _STATDESCRIBE._serialized_end = 8737 - _STATCROSSTAB._serialized_start = 8739 - _STATCROSSTAB._serialized_end = 8840 - _STATCOV._serialized_start = 8842 - _STATCOV._serialized_end = 8938 - _STATCORR._serialized_start = 8941 - _STATCORR._serialized_end = 9078 - _STATAPPROXQUANTILE._serialized_start = 9081 - _STATAPPROXQUANTILE._serialized_end = 9245 - _STATFREQITEMS._serialized_start = 9247 - _STATFREQITEMS._serialized_end = 9372 - _STATSAMPLEBY._serialized_start = 9375 - _STATSAMPLEBY._serialized_end = 9684 - _STATSAMPLEBY_FRACTION._serialized_start = 9576 - _STATSAMPLEBY_FRACTION._serialized_end = 9675 - _NAFILL._serialized_start = 9687 - _NAFILL._serialized_end = 9821 - _NADROP._serialized_start = 9824 - _NADROP._serialized_end = 9958 - _NAREPLACE._serialized_start = 9961 - _NAREPLACE._serialized_end = 10257 - _NAREPLACE_REPLACEMENT._serialized_start = 10116 - _NAREPLACE_REPLACEMENT._serialized_end = 10257 - _TODF._serialized_start = 10259 - _TODF._serialized_end = 10347 - _WITHCOLUMNSRENAMED._serialized_start = 10350 - _WITHCOLUMNSRENAMED._serialized_end = 10589 - _WITHCOLUMNSRENAMED_RENAMECOLUMNSMAPENTRY._serialized_start = 10522 - _WITHCOLUMNSRENAMED_RENAMECOLUMNSMAPENTRY._serialized_end = 10589 - _WITHCOLUMNS._serialized_start = 10591 - _WITHCOLUMNS._serialized_end = 10710 - _WITHWATERMARK._serialized_start = 10713 - _WITHWATERMARK._serialized_end = 10847 - _HINT._serialized_start = 10850 - _HINT._serialized_end = 10982 - _UNPIVOT._serialized_start = 10985 - _UNPIVOT._serialized_end = 11312 - _UNPIVOT_VALUES._serialized_start = 11242 - _UNPIVOT_VALUES._serialized_end = 11301 - _TOSCHEMA._serialized_start = 11314 - _TOSCHEMA._serialized_end = 11420 - _REPARTITIONBYEXPRESSION._serialized_start = 11423 - _REPARTITIONBYEXPRESSION._serialized_end = 11626 - _MAPPARTITIONS._serialized_start = 11629 - _MAPPARTITIONS._serialized_end = 11810 - _GROUPMAP._serialized_start = 11813 - _GROUPMAP._serialized_end = 12448 - _COGROUPMAP._serialized_start = 12451 - _COGROUPMAP._serialized_end = 12977 - _APPLYINPANDASWITHSTATE._serialized_start = 12980 - _APPLYINPANDASWITHSTATE._serialized_end = 13337 - _COMMONINLINEUSERDEFINEDTABLEFUNCTION._serialized_start = 13340 - _COMMONINLINEUSERDEFINEDTABLEFUNCTION._serialized_end = 13584 - _PYTHONUDTF._serialized_start = 13587 - _PYTHONUDTF._serialized_end = 13764 - _COLLECTMETRICS._serialized_start = 13767 - _COLLECTMETRICS._serialized_end = 13903 - _PARSE._serialized_start = 13906 - _PARSE._serialized_end = 14294 + _AGGREGATE._serialized_end = 7026 + _AGGREGATE_PIVOT._serialized_start = 6675 + _AGGREGATE_PIVOT._serialized_end = 6786 + _AGGREGATE_GROUPINGSETS._serialized_start = 6788 + _AGGREGATE_GROUPINGSETS._serialized_end = 6864 + _AGGREGATE_GROUPTYPE._serialized_start = 6867 + _AGGREGATE_GROUPTYPE._serialized_end = 7026 + _SORT._serialized_start = 7029 + _SORT._serialized_end = 7189 + _DROP._serialized_start = 7192 + _DROP._serialized_end = 7333 + _DEDUPLICATE._serialized_start = 7336 + _DEDUPLICATE._serialized_end = 7576 + _LOCALRELATION._serialized_start = 7578 + _LOCALRELATION._serialized_end = 7667 + _CACHEDLOCALRELATION._serialized_start = 7669 + _CACHEDLOCALRELATION._serialized_end = 7741 + _CACHEDREMOTERELATION._serialized_start = 7743 + _CACHEDREMOTERELATION._serialized_end = 7798 + _SAMPLE._serialized_start = 7801 + _SAMPLE._serialized_end = 8074 + _RANGE._serialized_start = 8077 + _RANGE._serialized_end = 8222 + _SUBQUERYALIAS._serialized_start = 8224 + _SUBQUERYALIAS._serialized_end = 8338 + _REPARTITION._serialized_start = 8341 + _REPARTITION._serialized_end = 8483 + _SHOWSTRING._serialized_start = 8486 + _SHOWSTRING._serialized_end = 8628 + _HTMLSTRING._serialized_start = 8630 + _HTMLSTRING._serialized_end = 8744 + _STATSUMMARY._serialized_start = 8746 + _STATSUMMARY._serialized_end = 8838 + _STATDESCRIBE._serialized_start = 8840 + _STATDESCRIBE._serialized_end = 8921 + _STATCROSSTAB._serialized_start = 8923 + _STATCROSSTAB._serialized_end = 9024 + _STATCOV._serialized_start = 9026 + _STATCOV._serialized_end = 9122 + _STATCORR._serialized_start = 9125 + _STATCORR._serialized_end = 9262 + _STATAPPROXQUANTILE._serialized_start = 9265 + _STATAPPROXQUANTILE._serialized_end = 9429 + _STATFREQITEMS._serialized_start = 9431 + _STATFREQITEMS._serialized_end = 9556 + _STATSAMPLEBY._serialized_start = 9559 + _STATSAMPLEBY._serialized_end = 9868 + _STATSAMPLEBY_FRACTION._serialized_start = 9760 + _STATSAMPLEBY_FRACTION._serialized_end = 9859 + _NAFILL._serialized_start = 9871 + _NAFILL._serialized_end = 10005 + _NADROP._serialized_start = 10008 + _NADROP._serialized_end = 10142 + _NAREPLACE._serialized_start = 10145 + _NAREPLACE._serialized_end = 10441 + _NAREPLACE_REPLACEMENT._serialized_start = 10300 + _NAREPLACE_REPLACEMENT._serialized_end = 10441 + _TODF._serialized_start = 10443 + _TODF._serialized_end = 10531 + _WITHCOLUMNSRENAMED._serialized_start = 10534 + _WITHCOLUMNSRENAMED._serialized_end = 10773 + _WITHCOLUMNSRENAMED_RENAMECOLUMNSMAPENTRY._serialized_start = 10706 + _WITHCOLUMNSRENAMED_RENAMECOLUMNSMAPENTRY._serialized_end = 10773 + _WITHCOLUMNS._serialized_start = 10775 + _WITHCOLUMNS._serialized_end = 10894 + _WITHWATERMARK._serialized_start = 10897 + _WITHWATERMARK._serialized_end = 11031 + _HINT._serialized_start = 11034 + _HINT._serialized_end = 11166 + _UNPIVOT._serialized_start = 11169 + _UNPIVOT._serialized_end = 11496 + _UNPIVOT_VALUES._serialized_start = 11426 + _UNPIVOT_VALUES._serialized_end = 11485 + _TOSCHEMA._serialized_start = 11498 + _TOSCHEMA._serialized_end = 11604 + _REPARTITIONBYEXPRESSION._serialized_start = 11607 + _REPARTITIONBYEXPRESSION._serialized_end = 11810 + _MAPPARTITIONS._serialized_start = 11813 + _MAPPARTITIONS._serialized_end = 11994 + _GROUPMAP._serialized_start = 11997 + _GROUPMAP._serialized_end = 12632 + _COGROUPMAP._serialized_start = 12635 + _COGROUPMAP._serialized_end = 13161 + _APPLYINPANDASWITHSTATE._serialized_start = 13164 + _APPLYINPANDASWITHSTATE._serialized_end = 13521 + _COMMONINLINEUSERDEFINEDTABLEFUNCTION._serialized_start = 13524 + _COMMONINLINEUSERDEFINEDTABLEFUNCTION._serialized_end = 13768 + _PYTHONUDTF._serialized_start = 13771 + _PYTHONUDTF._serialized_end = 13948 + _COLLECTMETRICS._serialized_start = 13951 + _COLLECTMETRICS._serialized_end = 14087 + _PARSE._serialized_start = 14090 + _PARSE._serialized_end = 14478 _PARSE_OPTIONSENTRY._serialized_start = 4291 _PARSE_OPTIONSENTRY._serialized_end = 4349 - _PARSE_PARSEFORMAT._serialized_start = 14195 - _PARSE_PARSEFORMAT._serialized_end = 14283 - _ASOFJOIN._serialized_start = 14297 - _ASOFJOIN._serialized_end = 14772 + _PARSE_PARSEFORMAT._serialized_start = 14379 + _PARSE_PARSEFORMAT._serialized_end = 14467 + _ASOFJOIN._serialized_start = 14481 + _ASOFJOIN._serialized_end = 14956 # @@protoc_insertion_point(module_scope) diff --git a/python/pyspark/sql/connect/proto/relations_pb2.pyi b/python/pyspark/sql/connect/proto/relations_pb2.pyi index 5bca4f21b2ea0..f8b7a2ad1cd94 100644 --- a/python/pyspark/sql/connect/proto/relations_pb2.pyi +++ b/python/pyspark/sql/connect/proto/relations_pb2.pyi @@ -1380,6 +1380,7 @@ class Aggregate(google.protobuf.message.Message): GROUP_TYPE_ROLLUP: Aggregate._GroupType.ValueType # 2 GROUP_TYPE_CUBE: Aggregate._GroupType.ValueType # 3 GROUP_TYPE_PIVOT: Aggregate._GroupType.ValueType # 4 + GROUP_TYPE_GROUPING_SETS: Aggregate._GroupType.ValueType # 5 class GroupType(_GroupType, metaclass=_GroupTypeEnumTypeWrapper): ... GROUP_TYPE_UNSPECIFIED: Aggregate.GroupType.ValueType # 0 @@ -1387,6 +1388,7 @@ class Aggregate(google.protobuf.message.Message): GROUP_TYPE_ROLLUP: Aggregate.GroupType.ValueType # 2 GROUP_TYPE_CUBE: Aggregate.GroupType.ValueType # 3 GROUP_TYPE_PIVOT: Aggregate.GroupType.ValueType # 4 + GROUP_TYPE_GROUPING_SETS: Aggregate.GroupType.ValueType # 5 class Pivot(google.protobuf.message.Message): DESCRIPTOR: google.protobuf.descriptor.Descriptor @@ -1423,11 +1425,35 @@ class Aggregate(google.protobuf.message.Message): self, field_name: typing_extensions.Literal["col", b"col", "values", b"values"] ) -> None: ... + class GroupingSets(google.protobuf.message.Message): + DESCRIPTOR: google.protobuf.descriptor.Descriptor + + GROUPING_SET_FIELD_NUMBER: builtins.int + @property + def grouping_set( + self, + ) -> google.protobuf.internal.containers.RepeatedCompositeFieldContainer[ + pyspark.sql.connect.proto.expressions_pb2.Expression + ]: + """(Required) Individual grouping set""" + def __init__( + self, + *, + grouping_set: collections.abc.Iterable[ + pyspark.sql.connect.proto.expressions_pb2.Expression + ] + | None = ..., + ) -> None: ... + def ClearField( + self, field_name: typing_extensions.Literal["grouping_set", b"grouping_set"] + ) -> None: ... + INPUT_FIELD_NUMBER: builtins.int GROUP_TYPE_FIELD_NUMBER: builtins.int GROUPING_EXPRESSIONS_FIELD_NUMBER: builtins.int AGGREGATE_EXPRESSIONS_FIELD_NUMBER: builtins.int PIVOT_FIELD_NUMBER: builtins.int + GROUPING_SETS_FIELD_NUMBER: builtins.int @property def input(self) -> global___Relation: """(Required) Input relation for a RelationalGroupedDataset.""" @@ -1450,6 +1476,13 @@ class Aggregate(google.protobuf.message.Message): @property def pivot(self) -> global___Aggregate.Pivot: """(Optional) Pivots a column of the current `DataFrame` and performs the specified aggregation.""" + @property + def grouping_sets( + self, + ) -> google.protobuf.internal.containers.RepeatedCompositeFieldContainer[ + global___Aggregate.GroupingSets + ]: + """(Optional) List of values that will be translated to columns in the output DataFrame.""" def __init__( self, *, @@ -1464,6 +1497,7 @@ class Aggregate(google.protobuf.message.Message): ] | None = ..., pivot: global___Aggregate.Pivot | None = ..., + grouping_sets: collections.abc.Iterable[global___Aggregate.GroupingSets] | None = ..., ) -> None: ... def HasField( self, field_name: typing_extensions.Literal["input", b"input", "pivot", b"pivot"] @@ -1477,6 +1511,8 @@ class Aggregate(google.protobuf.message.Message): b"group_type", "grouping_expressions", b"grouping_expressions", + "grouping_sets", + b"grouping_sets", "input", b"input", "pivot", diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py index 383a5566ded5f..82087adc82f5a 100644 --- a/python/pyspark/sql/dataframe.py +++ b/python/pyspark/sql/dataframe.py @@ -4204,7 +4204,6 @@ def cube(self, *cols: "ColumnOrName") -> "GroupedData": # type: ignore[misc] return GroupedData(jgd, self) - # TODO(SPARK-46048): Add it to Python Spark Connect client. def groupingSets( self, groupingSets: Sequence[Sequence["ColumnOrName"]], *cols: "ColumnOrName" ) -> "GroupedData":