Struct polars::prelude::LazyCsvReader

pub struct LazyCsvReader<'a> { /* private fields */ }

Implementations

impl<'a> LazyCsvReader<'a>

pub fn new(path: String) -> LazyCsvReader<'a>

pub fn with_skip_rows_after_header(self, offset: usize) -> LazyCsvReader<'a>

Skip this number of rows after the header location.

pub fn with_row_count(self, row_count: Option<RowCount>) -> LazyCsvReader<'a>

Add a row_count column.

pub fn with_n_rows(self, num_rows: Option<usize>) -> LazyCsvReader<'a>

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>
) -> LazyCsvReader<'a>

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_parser_errors(self, ignore: bool) -> LazyCsvReader<'a>

Continue with next batch when a ParserError is encountered.

pub fn with_schema(self, schema: Arc<Schema>) -> LazyCsvReader<'a>

Set the CSV file’s schema

pub fn with_skip_rows(self, skip_rows: usize) -> LazyCsvReader<'a>

Skip the first n rows during parsing. The header will be parsed at row n.

pub fn with_dtype_overwrite(
    self,
    schema: Option<&'a Schema>
) -> LazyCsvReader<'a>

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

pub fn has_header(self, has_header: bool) -> LazyCsvReader<'a>

Set whether the CSV file has headers

pub fn with_delimiter(self, delimiter: u8) -> LazyCsvReader<'a>

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

pub fn with_comment_char(self, comment_char: Option<u8>) -> LazyCsvReader<'a>

Set the comment character. Lines starting with this character will be ignored.

pub fn with_quote_char(self, quote: Option<u8>) -> LazyCsvReader<'a>

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

pub fn with_end_of_line_char(self, eol_char: u8) -> LazyCsvReader<'a>

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

pub fn with_null_values(
    self,
    null_values: Option<NullValues>
) -> LazyCsvReader<'a>

Set values that will be interpreted as missing/ null.

pub fn with_cache(self, cache: bool) -> LazyCsvReader<'a>

Cache the DataFrame after reading.

pub fn low_memory(self, toggle: bool) -> LazyCsvReader<'a>

Reduce memory usage in expensive of performance

pub fn with_rechunk(self, toggle: bool) -> LazyCsvReader<'a>

Rechunk the memory to contiguous chunks when parsing is done.

pub fn with_encoding(self, enc: CsvEncoding) -> LazyCsvReader<'a>

Set CsvEncoding

pub fn with_parse_dates(self, toggle: bool) -> LazyCsvReader<'a>

Automatically try to parse dates/ datetimes and time. If parsing fails, columns remain of dtype [DataType::Utf8].

pub fn with_schema_modify<F>(
    self,
    f: F
) -> Result<LazyCsvReader<'a>, PolarsError> where
    F: Fn(Schema) -> Result<Schema, PolarsError>, 

Modify a schema before we run the lazy scanning.

Important! Run this function latest in the builder!

pub fn finish_impl(self) -> Result<LazyFrame, PolarsError>

pub fn finish(self) -> Result<LazyFrame, PolarsError>

Trait Implementations

impl<'a> Clone for LazyCsvReader<'a>

fn clone(&self) -> LazyCsvReader<'a>

Returns a copy of the value.

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

Performs copy-assignment from source.