Enum DslPlan

pub enum DslPlan {
    PythonScan {
        options: PythonOptions,
    },
    Filter {
        input: Arc<DslPlan>,
        predicate: Expr,
    },
    Cache {
        input: Arc<DslPlan>,
        id: usize,
    },
    Scan {
        sources: ScanSources,
        file_info: Option<FileInfo>,
        file_options: FileScanOptions,
        scan_type: FileScan,
        cached_ir: Arc<Mutex<Option<IR>>>,
    },
    DataFrameScan {
        df: Arc<DataFrame>,
        schema: Arc<Schema<DataType>>,
    },
    Select {
        expr: Vec<Expr>,
        input: Arc<DslPlan>,
        options: ProjectionOptions,
    },
    GroupBy {
        input: Arc<DslPlan>,
        keys: Vec<Expr>,
        aggs: Vec<Expr>,
        maintain_order: bool,
        options: Arc<GroupbyOptions>,
        apply: Option<(Arc<dyn DataFrameUdf>, Arc<Schema<DataType>>)>,
    },
    Join {
        input_left: Arc<DslPlan>,
        input_right: Arc<DslPlan>,
        left_on: Vec<Expr>,
        right_on: Vec<Expr>,
        predicates: Vec<Expr>,
        options: Arc<JoinOptions>,
    },
    HStack {
        input: Arc<DslPlan>,
        exprs: Vec<Expr>,
        options: ProjectionOptions,
    },
    Distinct {
        input: Arc<DslPlan>,
        options: DistinctOptionsDSL,
    },
    Sort {
        input: Arc<DslPlan>,
        by_column: Vec<Expr>,
        slice: Option<(i64, usize)>,
        sort_options: SortMultipleOptions,
    },
    Slice {
        input: Arc<DslPlan>,
        offset: i64,
        len: u64,
    },
    MapFunction {
        input: Arc<DslPlan>,
        function: DslFunction,
    },
    Union {
        inputs: Vec<DslPlan>,
        args: UnionArgs,
    },
    HConcat {
        inputs: Vec<DslPlan>,
        options: HConcatOptions,
    },
    ExtContext {
        input: Arc<DslPlan>,
        contexts: Vec<DslPlan>,
    },
    Sink {
        input: Arc<DslPlan>,
        payload: SinkType,
    },
    IR {
        dsl: Arc<DslPlan>,
        version: u32,
        node: Option<Node>,
    },
}

Variants

PythonScan

Available on crate feature python only.

Fields

options: PythonOptions

Filter

Filter on a boolean mask

Fields

input: Arc<DslPlan>

predicate: Expr

Cache

Cache the input at this point in the LP

Fields

input: Arc<DslPlan>

id: usize

Scan

Fields

sources: ScanSources

file_info: Option<FileInfo>

Materialized at IR except for AnonymousScan.

file_options: FileScanOptions

scan_type: FileScan

cached_ir: Arc<Mutex<Option<IR>>>

Local use cases often repeatedly collect the same LazyFrame (e.g. in interactive notebook use-cases), so we cache the IR conversion here, as the path expansion can be quite slow (especially for cloud paths).

DataFrameScan

In memory DataFrame

Fields

df: Arc<DataFrame>

schema: Arc<Schema<DataType>>

Select

Polars’ select operation, this can mean projection, but also full data access.

Fields

expr: Vec<Expr>

input: Arc<DslPlan>

options: ProjectionOptions

GroupBy

Groupby aggregation

Fields

input: Arc<DslPlan>

keys: Vec<Expr>

aggs: Vec<Expr>

maintain_order: bool

options: Arc<GroupbyOptions>

apply: Option<(Arc<dyn DataFrameUdf>, Arc<Schema<DataType>>)>

Join

Join operation

Fields

input_left: Arc<DslPlan>

input_right: Arc<DslPlan>

left_on: Vec<Expr>

right_on: Vec<Expr>

predicates: Vec<Expr>

options: Arc<JoinOptions>

HStack

Adding columns to the table without a Join

Fields

input: Arc<DslPlan>

exprs: Vec<Expr>

options: ProjectionOptions

Distinct

Remove duplicates from the table

Fields

input: Arc<DslPlan>

options: DistinctOptionsDSL

Sort

Sort the table

Fields

input: Arc<DslPlan>

by_column: Vec<Expr>

slice: Option<(i64, usize)>

sort_options: SortMultipleOptions

Slice

Slice the table

Fields

input: Arc<DslPlan>

offset: i64

len: u64

MapFunction

A (User Defined) Function

Fields

input: Arc<DslPlan>

function: DslFunction

Union

Vertical concatenation

Fields

inputs: Vec<DslPlan>

args: UnionArgs

HConcat

Horizontal concatenation of multiple plans

Fields

inputs: Vec<DslPlan>

options: HConcatOptions

ExtContext

This allows expressions to access other tables

Fields

input: Arc<DslPlan>

contexts: Vec<DslPlan>

Sink

Fields

input: Arc<DslPlan>

payload: SinkType

IR

Fields

dsl: Arc<DslPlan>

version: u32

node: Option<Node>

Implementations

impl DslPlan

pub fn compute_schema(&self) -> Result<Arc<Schema<DataType>>, PolarsError>

Compute the schema. This requires conversion to [IR] and type-resolving.

impl DslPlan

pub fn describe(&self) -> Result<String, PolarsError>

pub fn describe_tree_format(&self) -> Result<String, PolarsError>

pub fn display(&self) -> Result<impl Display, PolarsError>

pub fn to_alp(self) -> Result<IRPlan, PolarsError>

Trait Implementations

impl Clone for DslPlan

fn clone(&self) -> DslPlan

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Default for DslPlan

fn default() -> DslPlan

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for DslPlan

fn deserialize<__D>( __deserializer: __D, ) -> Result<DslPlan, <__D as Deserializer<'de>>::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl From<DslPlan> for LazyFrame

fn from(plan: DslPlan) -> Self

Converts to this type from the input type.

impl<'a> IntoIterator for &'a DslPlan

type Item = &'a DslPlan

The type of the elements being iterated over.

type IntoIter = DslPlanIter<'a>

Which kind of iterator are we turning this into?

fn into_iter(self) -> <&'a DslPlan as IntoIterator>::IntoIter

Creates an iterator from a value.

impl Serialize for DslPlan

fn serialize<__S>( &self, __serializer: __S, ) -> Result<<__S as Serializer>::Ok, <__S as Serializer>::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.