Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[SPARK-48227][PYTHON][DOC] Document the requirement of seed in protos #46518

Closed
wants to merge 1 commit into from
Closed

[SPARK-48227][PYTHON][DOC] Document the requirement of seed in protos #46518

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions connector/connect/common/src/main/protobuf/spark/connect/relations.proto
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -467,7 +467,9 @@ message Sample {
// (Optional) Whether to sample with replacement.
optional bool with_replacement = 4;

// (Optional) The random seed.
// (Required) The random seed.
// This filed is required to avoid generate mutable dataframes (see SPARK-48184 for details),
// however, still keep it 'optional' here for backward compatibility.
optional int64 seed = 5;
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ya, this looks like inevitable.


// (Required) Explicitly sort the underlying plan to make the ordering deterministic or cache it.
Expand Down Expand Up @@ -687,7 +689,9 @@ message StatSampleBy {
// If a stratum is not specified, we treat its fraction as zero.
repeated Fraction fractions = 3;

// (Optional) The random seed.
// (Required) The random seed.
// This filed is required to avoid generate mutable dataframes (see SPARK-48184 for details),
// however, still keep it 'optional' here for backward compatibility.
optional int64 seed = 5;

message Fraction {
Expand Down
10 changes: 4 additions & 6 deletions python/pyspark/sql/connect/plan.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -717,7 +717,7 @@ def __init__(
lower_bound: float,
upper_bound: float,
with_replacement: bool,
seed: Optional[int],
seed: int,
deterministic_order: bool = False,
) -> None:
super().__init__(child)
Expand All @@ -734,8 +734,7 @@ def plan(self, session: "SparkConnectClient") -> proto.Relation:
plan.sample.lower_bound = self.lower_bound
plan.sample.upper_bound = self.upper_bound
plan.sample.with_replacement = self.with_replacement
if self.seed is not None:
plan.sample.seed = self.seed
plan.sample.seed = self.seed
plan.sample.deterministic_order = self.deterministic_order
return plan

Expand Down Expand Up @@ -1526,7 +1525,7 @@ def __init__(
child: Optional["LogicalPlan"],
col: Column,
fractions: Sequence[Tuple[Column, float]],
seed: Optional[int],
seed: int,
) -> None:
super().__init__(child)

Expand Down Expand Up @@ -1554,8 +1553,7 @@ def plan(self, session: "SparkConnectClient") -> proto.Relation:
fraction.stratum.CopyFrom(k.to_plan(session).literal)
fraction.fraction = float(v)
plan.sample_by.fractions.append(fraction)
if self._seed is not None:
plan.sample_by.seed = self._seed
plan.sample_by.seed = self._seed
return plan


Expand Down
10 changes: 8 additions & 2 deletions python/pyspark/sql/connect/proto/relations_pb2.pyi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1865,7 +1865,10 @@ class Sample(google.protobuf.message.Message):
with_replacement: builtins.bool
"""(Optional) Whether to sample with replacement."""
seed: builtins.int
"""(Optional) The random seed."""
"""(Required) The random seed.
This filed is required to avoid generate mutable dataframes (see SPARK-48184 for details),
however, still keep it 'optional' here for backward compatibility.
"""
deterministic_order: builtins.bool
"""(Required) Explicitly sort the underlying plan to make the ordering deterministic or cache it.
This flag is true when invoking `dataframe.randomSplit` to randomly splits DataFrame with the
Expand Down Expand Up @@ -2545,7 +2548,10 @@ class StatSampleBy(google.protobuf.message.Message):
If a stratum is not specified, we treat its fraction as zero.
"""
seed: builtins.int
"""(Optional) The random seed."""
"""(Required) The random seed.
This filed is required to avoid generate mutable dataframes (see SPARK-48184 for details),
however, still keep it 'optional' here for backward compatibility.
"""
def __init__(
self,
*,
Expand Down