Module peroxide::structure::dataframe

Pandas-like dataframe & series.

Series

1. Declare Series

• To declare series, you should have Vec<T> where T is one of following types.

Primitive type	DType
usize	USIZE
u8	U8
u16	U16
u32	U32
u64	U64
isize	ISIZE
i8	I8
i16	I16
i32	I32
i64	I64
f32	F32
f64	F64
bool	Bool
char	Char
String	Str

• If you prepare Vec<T>, then Series::new(Vec<T>)

2. Methods for Series

• TypedVector<T> trait for Series

  pub trait TypedVector<T> {
      fn new(v: Vec<T>) -> Self;
      fn to_vec(&self) -> Vec<T>;
      fn as_slice(&self) -> &[T];
      fn as_slice_mut(&mut self) -> &mut [T];
      fn at_raw(&self, i: usize) -> T;
      fn push(&mut self, elem: T);
  }

• Series methods

  impl Series {
      pub fn at(&self, i: usize) -> Scalar;
      pub fn len(&self) -> usize;
      pub fn to_type(&self, dtype: DType) -> Series;
      pub fn as_type(&mut self, dtype: DType);
  }

  • at is simple getter for Series. It returns Scalar.
  • as_type is a method for mutable type casting.
    • All types can be changed to Str.
    • All integer & float types can be exchanged.
    • Bool, Char can be changed to Str or U8 only.
    • U8 can be changed to all types.

3. Example

extern crate peroxide;
use peroxide::fuga::*;

fn main() {
    let a = Series::new(vec![1, 2, 3, 4]);
    let b = Series::new(vec!['a', 'b', 'c', 'd']);
    let mut c = Series::new(vec![true, false, false, true]);

    a.print();       // print for Series
    b.dtype.print(); // print for dtype of Series (=Char)
    c.as_type(U8);   // Bool => U8 
     
    assert_eq!(c.dtype, U8);
}

DataFrame

1. Declare DataFrame

• To declare dataframe, use constructor.
  • DataFrame::new(Vec<Series>)

extern crate peroxide;
use peroxide::fuga::*;

fn main() {
    // 1-1. Empty DataFrame
    let mut df = DataFrame::new(vec![]);

    // 1-2. Push Series
    df.push("a", Series::new(vec![1, 2, 3, 4]));
    df.push("b", Series::new(vec![0.1, 0.2, 0.3, 0.4]));
    df.push("c", Series::new(vec!['a', 'b', 'c', 'd']));

    // 1-3. Print
    df.print();

    // 2-1. Construct Series first
    let a = Series::new(vec![1, 2, 3, 4]);
    let b = Series::new(vec![0.1, 0.2, 0.3, 0.4]);
    let c = Series::new(vec!['a', 'b', 'c', 'd']);

    // 2-2. Declare DataFrame with exist Series
    let mut dg = DataFrame::new(vec![a, b, c]);

    // 2-3. Print or Set header
    dg.print();                         // But header: 0 1 2
    dg.set_header(vec!["a", "b", "c"]); // Change header
}

2. Methods for DataFrame

• DataFrame method

  impl DataFrame {
      pub fn new(v: Vec<Series>) -> Self;
      pub fn header(&self) -> &Vec<String>;
      pub fn header_mut(&mut self) -> &mut Vec<String>;
      pub fn set_header(&mut self, new_header: Vec<&str>);
      pub fn push(&mut self, name: &str, series: Series);
      pub fn drop(&mut self, col_header: &str);
      pub fn row(&self, i: usize) -> DataFrame;
      pub fn spread(&self) -> String;
      pub fn as_types(&mut self, dtypes: Vec<DType>);
  }

  • push(&mut self, name: &str, series: Series): push head & Series pair
  • drop(&mut self, col_header: &str): drop specific column by header
  • row(&self, i: usize) -> DataFrame : Extract $i$-th row as new DataFrame

• WithCSV trait

  pub trait WithCSV: Sized {
      fn write_csv(&self, file_path: &str) -> Result<(), Box<dyn Error>>;
      fn read_csv(file_path: &str, delimiter: char) -> Result<Self, Box<dyn Error>>;
  }

  // Example for CSV
  #[macro_use]
  extern crate peroxide;
  use peroxide::fuga::*;
  
  fn main() -> Result<(), Box<dyn Error>> {
      // Write CSV
      let mut df = DataFrame::new(vec![]);
      df.push("a", Series::new(vec!['x', 'y', 'z']));
      df.push("b", Series::new(vec![0, 1, 2]));
      df.push("c", Series::new(c!(0.1, 0.2, 0.3)));
      df.write_csv("example_data/doc_csv.csv")?;
  
      // Read CSV
      let mut dg = DataFrame::read_csv("example_data/doc_csv.csv", ',')?;
      dg.as_types(vec![Char, I32, F64]);
  
      assert_eq!(df, dg);
  
      Ok(())
  }

• WithNetCDF trait

  pub trait WithNetCDF: Sized {
      fn write_nc(&self, file_path: &str) -> Result<(), Box<dyn Error>>;
      fn read_nc(file_path: &str) -> Result<Self, Box<dyn Error>>;
      fn read_nc_by_header(file_path: &str, header: Vec<&str>) -> Result<Self, Box<dyn Error>>;
  }

  • nc feature should be required
  • libnetcdf dependency should be required
  • Char, Bool are saved as U8 type. Thus, for reading Char or Bool type nc file, explicit type casting is required.

  #[macro_use]
  extern crate peroxide;
  use peroxide::fuga::*;
  
  fn main() -> Result<(), Box<dyn Error>> {
      // Write netcdf
      let mut df = DataFrame::new(vec![]);
      df.push("a", Series::new(vec!['x', 'y', 'z']));
      df.push("b", Series::new(vec![0, 1, 2]));
      df.push("c", Series::new(c!(0.1, 0.2, 0.3)));
      df.write_nc("example_data/doc_nc.nc")?;
  
      // Read netcdf
      let mut dg = DataFrame::read_nc("example_data/doc_nc.nc")?;
      dg[0].as_type(Char); // Char, Bool are only read/written as U8 type
  
      assert_eq!(df, dg);
  
      Ok(())
  }

Structs

DataFrame	Generic DataFrame structure
Scalar	Generic Scalar
Series	Generic Series

Enums

DType	Data Type enum
DTypeArray	Vector with DType
DTypeValue	Scalar with DType

Traits

TypedScalar
TypedVector
WithCSV	To handle CSV file format