Crate polars

Polars DataFrames in Rust

Read more in the DataFrame and Series modules.

Read and write CSV/ JSON

use polars::prelude::*;
use std::fs::File;

fn example() -> Result<DataFrame> {
    let file = File::open("iris.csv").expect("could not open file");

    CsvReader::new(file)
            .infer_schema(None)
            .has_header(true)
            .finish()
}

For more IO examples see: * the csv module * the json module

Joins

use polars::prelude::*;

// Create first df.
let s0 = Series::new("days", &[0, 1, 2, 3, 4]);
let s1 = Series::new("temp", &[22.1, 19.9, 7., 2., 3.]);
let temp = DataFrame::new(vec![s0, s1]).unwrap();

// Create second df.
let s0 = Series::new("days", &[1, 2]);
let s1 = Series::new("rain", &[0.1, 0.2]);
let rain = DataFrame::new(vec![s0, s1]).unwrap();

// Left join on days column.
let joined = temp.left_join(&rain, "days", "days");
println!("{}", joined.unwrap())

+------+------+------+
| days | temp | rain |
| ---  | ---  | ---  |
| i32  | f64  | f64  |
+======+======+======+
| 0    | 22.1 | null |
+------+------+------+
| 1    | 19.9 | 0.1  |
+------+------+------+
| 2    | 7    | 0.2  |
+------+------+------+
| 3    | 2    | null |
+------+------+------+
| 4    | 3    | null |
+------+------+------+

GroupBys

use polars::prelude::*;
fn groupby_sum(df: &DataFrame) -> Result<DataFrame> {
    df.groupby("column_name")?
    .select("agg_column_name")
    .sum()
}

Arithmetic

use polars::prelude::*;
let s: Series = [1, 2, 3].iter().collect();
let s_squared = &s * &s;

Rust iterators

use polars::prelude::*;

let s: Series = [1, 2, 3].iter().collect();
let s_squared: Series = s.i32()
     .expect("datatype mismatch")
     .into_iter()
     .map(|optional_v| {
         match optional_v {
             Some(v) => Some(v * v),
             None => None, // null value
         }
 }).collect();

Comparisons

use polars::prelude::*;
use itertools::Itertools;
let s = Series::new("dollars", &[1, 2, 3]);
let mask = s.eq(1);
let valid = [true, false, false].iter();
assert!(mask
    .into_iter()
    .map(|opt_bool| opt_bool.unwrap()) // option, because series can be null
    .zip(valid)
    .all(|(a, b)| a == *b))

And more...

Modules

chunked_array	The typed heart of every Series column.
datatypes
error
frame	DataFrame module
prelude
series	Series
testing

Macros

apply_method_all_series
apply_method_arrowprimitive_series
apply_operand_on_chunkedarray_by_iter
exec_concurrent