polars_io::parquet::read

Struct ParquetReader

Source
pub struct ParquetReader<R: Read + Seek> { /* private fields */ }
Available on crate feature parquet only.
Expand description

Read Apache parquet format into a DataFrame.

Implementations§

Source§

impl<R: MmapBytesReader> ParquetReader<R>

Source

pub fn set_low_memory(self, low_memory: bool) -> Self

Try to reduce memory pressure at the expense of performance. If setting this does not reduce memory enough, turn off parallelization.

Source

pub fn read_parallel(self, parallel: ParallelStrategy) -> Self

Read the parquet file in parallel (default). The single threaded reader consumes less memory.

Source

pub fn with_slice(self, slice: Option<(usize, usize)>) -> Self

Source

pub fn with_columns(self, columns: Option<Vec<String>>) -> Self

Columns to select/ project

Source

pub fn with_projection(self, projection: Option<Vec<usize>>) -> Self

Set the reader’s column projection. This counts from 0, meaning that vec![0, 4] would select the 1st and 5th column.

Source

pub fn with_row_index(self, row_index: Option<RowIndex>) -> Self

Add a row index column.

Source

pub fn with_arrow_schema_projection( self, first_schema: &Arc<ArrowSchema>, projected_arrow_schema: Option<&ArrowSchema>, allow_missing_columns: bool, ) -> PolarsResult<Self>

Checks that the file contains all the columns in projected_arrow_schema with the same dtype, and sets the projection indices.

Source

pub fn schema(&mut self) -> PolarsResult<ArrowSchemaRef>

Schema of the file.

Source

pub fn use_statistics(self, toggle: bool) -> Self

Use statistics in the parquet to determine if pages can be skipped from reading.

Source

pub fn num_rows(&mut self) -> PolarsResult<usize>

Number of rows in the parquet file.

Source

pub fn with_hive_partition_columns(self, columns: Option<Vec<Series>>) -> Self

Source

pub fn with_include_file_path( self, include_file_path: Option<(PlSmallStr, Arc<str>)>, ) -> Self

Source

pub fn set_metadata(&mut self, metadata: FileMetadataRef)

Source

pub fn get_metadata(&mut self) -> PolarsResult<&FileMetadataRef>

Source

pub fn with_predicate(self, predicate: Option<Arc<dyn PhysicalIoExpr>>) -> Self

Source§

impl<R: MmapBytesReader + 'static> ParquetReader<R>

Source

pub fn batched(self, chunk_size: usize) -> PolarsResult<BatchedParquetReader>

Trait Implementations§

Source§

impl<R: MmapBytesReader> SerReader<R> for ParquetReader<R>

Source§

fn new(reader: R) -> Self

Create a new ParquetReader from an existing Reader.

Source§

fn set_rechunk(self, rechunk: bool) -> Self

Make sure that all columns are contiguous in memory by aggregating the chunks into a single array.
Source§

fn finish(self) -> PolarsResult<DataFrame>

Take the SerReader and return a parsed DataFrame.

Auto Trait Implementations§

§

impl<R> Freeze for ParquetReader<R>
where R: Freeze,

§

impl<R> !RefUnwindSafe for ParquetReader<R>

§

impl<R> Send for ParquetReader<R>
where R: Send,

§

impl<R> Sync for ParquetReader<R>
where R: Sync,

§

impl<R> Unpin for ParquetReader<R>
where R: Unpin,

§

impl<R> !UnwindSafe for ParquetReader<R>

Blanket Implementations§

Source§

impl<T> Any for T
where T: 'static + ?Sized,

Source§

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more
Source§

impl<T> Borrow<T> for T
where T: ?Sized,

Source§

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more
Source§

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source§

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more
Source§

impl<T> From<T> for T

Source§

fn from(t: T) -> T

Returns the argument unchanged.

§

impl<T> Instrument for T

§

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided [Span], returning an Instrumented wrapper. Read more
§

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more
Source§

impl<T, U> Into<U> for T
where U: From<T>,

Source§

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Source§

impl<T> IntoEither for T

Source§

fn into_either(self, into_left: bool) -> Either<Self, Self>

Converts self into a Left variant of Either<Self, Self> if into_left is true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more
Source§

fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
where F: FnOnce(&Self) -> bool,

Converts self into a Left variant of Either<Self, Self> if into_left(&self) returns true. Converts self into a Right variant of Either<Self, Self> otherwise. Read more
§

impl<T> Pointable for T

§

const ALIGN: usize = _

The alignment of pointer.
§

type Init = T

The type for initializers.
§

unsafe fn init(init: <T as Pointable>::Init) -> usize

Initializes a with the given initializer. Read more
§

unsafe fn deref<'a>(ptr: usize) -> &'a T

Dereferences the given pointer. Read more
§

unsafe fn deref_mut<'a>(ptr: usize) -> &'a mut T

Mutably dereferences the given pointer. Read more
§

unsafe fn drop(ptr: usize)

Drops the object pointed to by the given pointer. Read more
Source§

impl<T> Same for T

Source§

type Output = T

Should always be Self
Source§

impl<T, U> TryFrom<U> for T
where U: Into<T>,

Source§

type Error = Infallible

The type returned in the event of a conversion error.
Source§

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

Performs the conversion.
Source§

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

Source§

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.
Source§

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.
§

impl<V, T> VZip<V> for T
where V: MultiLane<T>,

§

fn vzip(self) -> V

§

impl<T> WithSubscriber for T

§

fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self>
where S: Into<Dispatch>,

Attaches the provided Subscriber to this type, returning a [WithDispatch] wrapper. Read more
§

fn with_current_subscriber(self) -> WithDispatch<Self>

Attaches the current default Subscriber to this type, returning a [WithDispatch] wrapper. Read more
§

impl<T> ErasedDestructor for T
where T: 'static,

§

impl<T> MaybeSendSync for T

§

impl<T> Ungil for T
where T: Send,