Struct polars::prelude::ParquetReader

pub struct ParquetReader<R> where
    R: Read + Seek, { /* private fields */ }

Read Apache parquet format into a DataFrame.

Implementations

impl<R> ParquetReader<R> where
    R: MmapBytesReader, 

pub fn _finish_with_scan_ops(
    self,
    predicate: Option<Arc<dyn PhysicalIoExpr + 'static>>,
    aggregate: Option<&[ScanAggregation]>,
    projection: Option<&[usize]>
) -> Result<DataFrame, PolarsError>

pub fn set_low_memory(self, low_memory: bool) -> ParquetReader<R>

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

pub fn read_parallel(self, parallel: ParallelStrategy) -> ParquetReader<R>

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

pub fn with_n_rows(self, num_rows: Option<usize>) -> ParquetReader<R>

Stop parsing when n rows are parsed. By settings this parameter the csv will be parsed sequentially.

pub fn with_columns(
    self,
    columns: Option<Vec<String, Global>>
) -> ParquetReader<R>

Columns to select/ project

pub fn with_projection(
    self,
    projection: Option<Vec<usize, Global>>
) -> ParquetReader<R>

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

pub fn with_row_count(self, row_count: Option<RowCount>) -> ParquetReader<R>

Add a row_count column.

pub fn schema(self) -> Result<Schema, PolarsError>

Trait Implementations

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

fn new(reader: R) -> ParquetReader<R>

Create a new ParquetReader from an existing Reader.

fn set_rechunk(self, rechunk: bool) -> ParquetReader<R>

Rechunk to a single chunk after Reading file.

fn finish(self) -> Result<DataFrame, PolarsError>

Take the SerReader and return a parsed DataFrame.