1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197
//! # Polars: *<small>DataFrames in Rust</small>* //! //! Polars is a DataFrame library for Rust. It is based on [Apache Arrows](https://arrow.apache.org/) memory model. //! This means that operations on Polars array's *(called `Series` or `ChunkedArray<T>` {if the type `T` is known})* are //! optimally aligned cache friendly operations and SIMD. Sadly, Apache Arrow needs **nightly Rust**, //! which means that Polars cannot run on stable. //! //! Read more in the pages of the [DataFrame](frame/struct.DataFrame.html), [Series](series/enum.Series.html), and //! [ChunkedArray](chunked_array/struct.ChunkedArray.html) data structures. //! //! ## 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 read file"); //! //! CsvReader::new(file) //! .infer_schema(None) //! .has_header(true) //! .finish() //! } //! ``` //! //! For more IO examples see: //! //! * [the csv module](frame/ser/csv/index.html) //! * [the json module](frame/ser/json/index.html) //! * [the IPC module](frame/ser/ipc/index.html) //! * [the parquet module](frame/ser/parquet/index.html) //! //! ## Joins //! //! ``` //! use polars::prelude::*; //! //! fn join() -> Result<DataFrame> { //! // 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])?; //! //! // 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])?; //! //! // Left join on days column. //! temp.left_join(&rain, "days", "days") //! } //! //! println!("{}", join().unwrap()) //! ``` //! //! ```text //! +------+------+------+ //! | 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 | //! +------+------+------+ //! ``` //! //! ## Groupby's | aggregations | pivots //! //! ``` //! 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(); //! ``` //! //! ## Apply custom closures //! //! Besides running custom iterators, custom closures can be applied on the values of [ChunkedArray](chunked_array/struct.ChunkedArray.html) //! by using the [apply](chunked_array/apply/trait.Apply.html) method. This method accepts //! a closure that will be applied on all values of `Option<T>` that are non null. Note that this is the //! **fastest** way to apply a custom closure on `ChunkedArray`'s. //! ``` //! # use polars::prelude::*; //! let s: Series = Series::new("values", [Some(1.0), None, Some(3.0)]); //! // null values are ignored automatically //! let squared = s.f64() //! .unwrap() //! .apply(|value| value.powf(2.0)) //! .into_series(); //! //! assert_eq!(Vec::from(squared.f64().unwrap()), &[Some(1.0), None, Some(9.0)]) //! ``` //! //! ## 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_eq!(Vec::from(mask), &[Some(true), Some(false), Some(false)]); //! ``` //! //! ## Temporal data types //! //! ```rust //! # use polars::prelude::*; //! let dates = &[ //! "2020-08-21", //! "2020-08-21", //! "2020-08-22", //! "2020-08-23", //! "2020-08-22", //! ]; //! // date format //! let fmt = "%Y-%m-%d"; //! // create date series //! let s0 = Date32Chunked::parse_from_str_slice("date", dates, fmt) //! .into_series(); //! ``` //! //! //! ## And more... //! //! * [DataFrame](frame/struct.DataFrame.html) //! * [Series](series/enum.Series.html) //! * [ChunkedArray](chunked_array/struct.ChunkedArray.html) //! - [Operations implemented by Traits](chunked_array/ops/index.html) //! * [Time/ DateTime utilities](doc/time/index.html) //! * [Groupby, aggregations and pivots](frame/group_by/struct.GroupBy.html) //! //! ## Features //! //! Additional cargo features: //! //! * `pretty` (default) //! - pretty printing of DataFrames //! * `temporal (default)` //! - Conversions between Chrono and Polars for temporal data //! * `simd` //! - SIMD operations //! * `paquet_ser` //! - Read Apache Parquet format //! * `random` //! - Generate array's with randomly sampled values #![allow(dead_code)] #![feature(iterator_fold_self)] #[macro_use] pub mod series; #[macro_use] pub(crate) mod utils; pub mod chunked_array; pub mod datatypes; #[cfg(feature = "docs")] pub mod doc; pub mod error; mod fmt; pub mod frame; pub mod prelude; pub mod testing;