Struct LazyCsvReader

pub struct LazyCsvReader { /* private fields */ }

Available on crate feature csv only.

Implementations

impl LazyCsvReader

pub fn new_paths(paths: Arc<[PathBuf]>) -> Self

pub fn new_with_sources(sources: ScanSources) -> Self

pub fn new(path: impl AsRef<Path>) -> Self

pub fn with_skip_rows_after_header(self, offset: usize) -> Self

Skip this number of rows after the header location.

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

Add a row index column.

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

Try to stop parsing when n rows are parsed. During multithreaded parsing the upper bound n cannot be guaranteed.

pub fn with_infer_schema_length(self, num_rows: Option<usize>) -> Self

Set the number of rows to use when inferring the csv schema. the default is 100 rows. Setting to None will do a full table scan, very slow.

pub fn with_ignore_errors(self, ignore: bool) -> Self

Continue with next batch when a ParserError is encountered.

pub fn with_schema(self, schema: Option<SchemaRef>) -> Self

Set the CSV file’s schema

pub fn with_skip_rows(self, skip_rows: usize) -> Self

Skip the first n rows during parsing. The header will be parsed at row n. Note that by row we mean valid CSV, encoding and comments are respected.

pub fn with_skip_lines(self, skip_lines: usize) -> Self

Skip the first n lines during parsing. The header will be parsed at line n. We don’t respect CSV escaping when skipping lines.

pub fn with_dtype_overwrite(self, schema: Option<SchemaRef>) -> Self

Overwrite the schema with the dtypes in this given Schema. The given schema may be a subset of the total schema.

pub fn with_has_header(self, has_header: bool) -> Self

Set whether the CSV file has headers

pub fn with_chunk_size(self, chunk_size: usize) -> Self

Sets the chunk size used by the parser. This influences performance. This can be used as a way to reduce memory usage during the parsing at the cost of performance.

pub fn with_separator(self, separator: u8) -> Self

Set the CSV file’s column separator as a byte character

pub fn with_comment_prefix(self, comment_prefix: Option<PlSmallStr>) -> Self

Set the comment prefix for this instance. Lines starting with this prefix will be ignored.

pub fn with_quote_char(self, quote_char: Option<u8>) -> Self

Set the char used as quote char. The default is b'"'. If set to None quoting is disabled.

pub fn with_eol_char(self, eol_char: u8) -> Self

Set the char used as end of line. The default is b'\n'.

pub fn with_null_values(self, null_values: Option<NullValues>) -> Self

Set values that will be interpreted as missing/ null.

pub fn with_missing_is_null(self, missing_is_null: bool) -> Self

Treat missing fields as null.

pub fn with_cache(self, cache: bool) -> Self

Cache the DataFrame after reading.

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

Reduce memory usage at the expense of performance

pub fn with_encoding(self, encoding: CsvEncoding) -> Self

Set CsvEncoding

pub fn with_try_parse_dates(self, try_parse_dates: bool) -> Self

Available on crate feature temporal only.

Automatically try to parse dates/datetimes and time. If parsing fails, columns remain of dtype DataType::String.

pub fn with_raise_if_empty(self, raise_if_empty: bool) -> Self

Raise an error if CSV is empty (otherwise return an empty frame)

pub fn with_truncate_ragged_lines(self, truncate_ragged_lines: bool) -> Self

Truncate lines that are longer than the schema.

pub fn with_decimal_comma(self, decimal_comma: bool) -> Self

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

Expand path given via globbing rules.

pub fn with_cloud_options(self, cloud_options: Option<CloudOptions>) -> Self

pub fn with_schema_modify<F>(self, f: F) -> PolarsResult<Self>

where F: Fn(Schema) -> PolarsResult<Schema>,

Modify a schema before we run the lazy scanning.

Important! Run this function latest in the builder!

pub fn with_include_file_paths( self, include_file_paths: Option<PlSmallStr>, ) -> Self

Trait Implementations

impl Clone for LazyCsvReader

fn clone(&self) -> LazyCsvReader

Returns a copy of the value.

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

Performs copy-assignment from source.

impl LazyFileListReader for LazyCsvReader

fn finish(self) -> PolarsResult<LazyFrame>

Get the final LazyFrame.

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

Rechunk the memory to contiguous chunks when parsing is done.

fn n_rows(&self) -> Option<usize>

Try to stop parsing when n rows are parsed. During multithreaded parsing the upper bound n cannot be guaranteed.

fn row_index(&self) -> Option<&RowIndex>

Return the row index settings.

fn cloud_options(&self) -> Option<&CloudOptions>

CloudOptions used to list files.

fn finish_no_glob(self) -> PolarsResult<LazyFrame>

Get the final LazyFrame. This method assumes, that path is not a glob.

fn glob(&self) -> bool

fn sources(&self) -> &ScanSources

Get the sources for this reader.

fn with_sources(self, sources: ScanSources) -> Self

Set sources of the scanned files.

fn with_n_rows(self, n_rows: impl Into<Option<usize>>) -> Self

Configure the row limit.

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

Configure the row index.

fn rechunk(&self) -> bool

Rechunk the memory to contiguous chunks when parsing is done.

fn concat_impl(&self, lfs: Vec<LazyFrame>) -> PolarsResult<LazyFrame>

Recommended concatenation of LazyFrames from many input files.

fn with_paths(self, paths: Arc<[PathBuf]>) -> Self

Set paths of the scanned files.