Struct arrow_array::RecordBatch

source ·
pub struct RecordBatch { /* private fields */ }
Expand description

A two-dimensional batch of column-oriented data with a defined schema.

A RecordBatch is a two-dimensional dataset of a number of contiguous arrays, each the same length. A record batch has a schema which must match its arrays’ datatypes.

Record batches are a convenient unit of work for various serialization and computation functions, possibly incremental.

Implementations§

source§

impl RecordBatch

source

pub fn try_new( schema: SchemaRef, columns: Vec<ArrayRef>, ) -> Result<Self, ArrowError>

Creates a RecordBatch from a schema and columns.

Expects the following:

  • the vec of columns to not be empty
  • the schema and column data types to have equal lengths and match
  • each array in columns to have the same length

If the conditions are not met, an error is returned.

§Example

let id_array = Int32Array::from(vec![1, 2, 3, 4, 5]);
let schema = Schema::new(vec![
    Field::new("id", DataType::Int32, false)
]);

let batch = RecordBatch::try_new(
    Arc::new(schema),
    vec![Arc::new(id_array)]
).unwrap();
source

pub fn try_new_with_options( schema: SchemaRef, columns: Vec<ArrayRef>, options: &RecordBatchOptions, ) -> Result<Self, ArrowError>

Creates a RecordBatch from a schema and columns, with additional options, such as whether to strictly validate field names.

See RecordBatch::try_new for the expected conditions.

source

pub fn new_empty(schema: SchemaRef) -> Self

Creates a new empty RecordBatch.

source

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

Override the schema of this RecordBatch

Returns an error if schema is not a superset of the current schema as determined by Schema::contains

source

pub fn schema(&self) -> SchemaRef

Returns the Schema of the record batch.

source

pub fn schema_ref(&self) -> &SchemaRef

Returns a reference to the Schema of the record batch.

source

pub fn project(&self, indices: &[usize]) -> Result<RecordBatch, ArrowError>

Projects the schema onto the specified columns

source

pub fn num_columns(&self) -> usize

Returns the number of columns in the record batch.

§Example

let id_array = Int32Array::from(vec![1, 2, 3, 4, 5]);
let schema = Schema::new(vec![
    Field::new("id", DataType::Int32, false)
]);

let batch = RecordBatch::try_new(Arc::new(schema), vec![Arc::new(id_array)]).unwrap();

assert_eq!(batch.num_columns(), 1);
source

pub fn num_rows(&self) -> usize

Returns the number of rows in each column.

§Example

let id_array = Int32Array::from(vec![1, 2, 3, 4, 5]);
let schema = Schema::new(vec![
    Field::new("id", DataType::Int32, false)
]);

let batch = RecordBatch::try_new(Arc::new(schema), vec![Arc::new(id_array)]).unwrap();

assert_eq!(batch.num_rows(), 5);
source

pub fn column(&self, index: usize) -> &ArrayRef

Get a reference to a column’s array by index.

§Panics

Panics if index is outside of 0..num_columns.

source

pub fn column_by_name(&self, name: &str) -> Option<&ArrayRef>

Get a reference to a column’s array by name.

source

pub fn columns(&self) -> &[ArrayRef]

Get a reference to all columns in the record batch.

source

pub fn remove_column(&mut self, index: usize) -> ArrayRef

Remove column by index and return it.

Return the ArrayRef if the column is removed.

§Panics

Panics if `index`` out of bounds.

§Example
use std::sync::Arc;
use arrow_array::{BooleanArray, Int32Array, RecordBatch};
use arrow_schema::{DataType, Field, Schema};
let id_array = Int32Array::from(vec![1, 2, 3, 4, 5]);
let bool_array = BooleanArray::from(vec![true, false, false, true, true]);
let schema = Schema::new(vec![
    Field::new("id", DataType::Int32, false),
    Field::new("bool", DataType::Boolean, false),
]);

let mut batch = RecordBatch::try_new(Arc::new(schema), vec![Arc::new(id_array), Arc::new(bool_array)]).unwrap();

let removed_column = batch.remove_column(0);
assert_eq!(removed_column.as_any().downcast_ref::<Int32Array>().unwrap(), &Int32Array::from(vec![1, 2, 3, 4, 5]));
assert_eq!(batch.num_columns(), 1);
source

pub fn slice(&self, offset: usize, length: usize) -> RecordBatch

Return a new RecordBatch where each column is sliced according to offset and length

§Panics

Panics if offset with length is greater than column length.

source

pub fn try_from_iter<I, F>(value: I) -> Result<Self, ArrowError>
where I: IntoIterator<Item = (F, ArrayRef)>, F: AsRef<str>,

Create a RecordBatch from an iterable list of pairs of the form (field_name, array), with the same requirements on fields and arrays as RecordBatch::try_new. This method is often used to create a single RecordBatch from arrays, e.g. for testing.

The resulting schema is marked as nullable for each column if the array for that column is has any nulls. To explicitly specify nullibility, use RecordBatch::try_from_iter_with_nullable

Example:


let a: ArrayRef = Arc::new(Int32Array::from(vec![1, 2]));
let b: ArrayRef = Arc::new(StringArray::from(vec!["a", "b"]));

let record_batch = RecordBatch::try_from_iter(vec![
  ("a", a),
  ("b", b),
]);
source

pub fn try_from_iter_with_nullable<I, F>(value: I) -> Result<Self, ArrowError>
where I: IntoIterator<Item = (F, ArrayRef, bool)>, F: AsRef<str>,

Create a RecordBatch from an iterable list of tuples of the form (field_name, array, nullable), with the same requirements on fields and arrays as RecordBatch::try_new. This method is often used to create a single RecordBatch from arrays, e.g. for testing.

Example:


let a: ArrayRef = Arc::new(Int32Array::from(vec![1, 2]));
let b: ArrayRef = Arc::new(StringArray::from(vec![Some("a"), Some("b")]));

// Note neither `a` nor `b` has any actual nulls, but we mark
// b an nullable
let record_batch = RecordBatch::try_from_iter_with_nullable(vec![
  ("a", a, false),
  ("b", b, true),
]);
source

pub fn get_array_memory_size(&self) -> usize

Returns the total number of bytes of memory occupied physically by this batch.

Trait Implementations§

source§

impl Clone for RecordBatch

source§

fn clone(&self) -> RecordBatch

Returns a copy of the value. Read more
1.0.0 · source§

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

Performs copy-assignment from source. Read more
source§

impl Debug for RecordBatch

source§

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter. Read more
source§

impl From<&StructArray> for RecordBatch

source§

fn from(struct_array: &StructArray) -> Self

Converts to this type from the input type.
source§

impl From<RecordBatch> for StructArray

source§

fn from(value: RecordBatch) -> Self

Converts to this type from the input type.
source§

impl From<StructArray> for RecordBatch

source§

fn from(value: StructArray) -> Self

Converts to this type from the input type.
source§

impl Index<&str> for RecordBatch

source§

fn index(&self, name: &str) -> &Self::Output

Get a reference to a column’s array by name.

§Panics

Panics if the name is not in the schema.

§

type Output = Arc<dyn Array>

The returned type after indexing.
source§

impl PartialEq for RecordBatch

source§

fn eq(&self, other: &RecordBatch) -> bool

Tests for self and other values to be equal, and is used by ==.
1.0.0 · source§

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.
source§

impl StructuralPartialEq for RecordBatch

Auto Trait Implementations§

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> CloneToUninit for T
where T: Clone,

source§

default unsafe fn clone_to_uninit(&self, dst: *mut T)

🔬This is a nightly-only experimental API. (clone_to_uninit)
Performs copy-assignment from self to dst. Read more
source§

impl<T> From<T> for T

source§

fn from(t: T) -> T

Returns the argument unchanged.

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> ToOwned for T
where T: Clone,

§

type Owned = T

The resulting type after obtaining ownership.
source§

fn to_owned(&self) -> T

Creates owned data from borrowed data, usually by cloning. Read more
source§

fn clone_into(&self, target: &mut T)

Uses borrowed data to replace owned data, usually by cloning. Read more
source§

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

§

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>,

§

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.