logo

NuMojo is a library for numerical computing in Mojo 🔥 similar to NumPy, SciPy in Python.

Explore the docs» | Changelog» | Check out our Discord»

中文·简» | 中文·繁» | 日本語»

Table of Contents

1. About The Project
2. Goals
3. Usage
4. How to install
5. Contributing
6. Warnings
7. License
8. Acknowledgements
9. Contributors

NuMojo aims to encompass the extensive numerics capabilities found in Python packages such as NumPy, SciPy, and Scikit-learn.

=======

What NuMojo is

We seek to harness the full potential of Mojo, including vectorization, parallelization, and GPU acceleration (when available). Currently, NuMojo extends most (if not all) standard library math functions to support array inputs.

Our vision for NuMojo is to serve as an essential building block for other Mojo packages needing fast math operations, without the additional weight of a machine learning back-propagation system.

What NuMojo is not

NuMojo is not a machine learning library and will never include back-propagation as part of the base library.

Our primary objective is to develop a fast, comprehensive numerics library in Mojo. Below are some features and long-term goals. Some have already been implemented, either fully or partially.

Core data types:

• Native n-dimensional array (numojo.NDArray).
• Native 2-dimensional array, i.e., matrix (numojo.Matrix).
• Native n-dimensional complex array (numojo.ComplexNDArray)
• Native fixed-dimension array (to be implemented when trait parameterization is available).

Routines and objects:

• Array creation routines (numojo.creation)
• Array manipulation routines (numojo.manipulation)
• Input and output (numojo.io)
• Linear algebra (numojo.linalg)
• Logic functions (numojo.logic)
• Mathematical functions (numojo.math)
• Exponents and logarithms (numojo.exponents)
• Extrema finding (numojo.extrema)
• Rounding (numojo.rounding)
• Trigonometric functions (numojo.trig)
• Random sampling (numojo.random)
• Sorting and searching (numojo.sorting, numojo.searching)
• Statistics (numojo.statistics)
• etc...

Please find all the available functions and objects here.

For a detailed roadmap, please refer to the docs/roadmap.md file.

An example of n-dimensional array (NDArray type) goes as follows.

import numojo as nm
from numojo.prelude import *
fn main() raises:
 # Generate two 1000x1000 matrices with random float64 values
 var A = nm.random.randn(Shape(1000, 1000))
 var B = nm.random.randn(Shape(1000, 1000))
 # Generate a 3x2 matrix from string representation
 var X = nm.fromstring[f32]("[[1.1, -0.32, 1], [0.1, -3, 2.124]]")
 # Print array
 print(A)
 # Array multiplication
 var C = A @ B
 # Array inversion
 var I = nm.inv(A)
 # Array slicing
 var A_slice = A[1:3, 4:19]
 # Get scalar from array
 var A_item = A[item(291, 141)]
 var A_item_2 = A.item(291, 141)

An example of matrix (Matrix type) goes as follows.

from numojo import Matrix
from numojo.prelude import *
fn main() raises:
 # Generate two 1000x1000 matrices with random float64 values
 var A = Matrix.rand(shape=(1000, 1000))
 var B = Matrix.rand(shape=(1000, 1000))
 # Generate 1000x1 matrix (column vector) with random float64 values
 var C = Matrix.rand(shape=(1000, 1))
 # Generate a 4x3 matrix from string representation
 var F = Matrix.fromstring[i8](
 "[[12,11,10],[9,8,7],[6,5,4],[3,2,1]]", shape=(4, 3)
 )
 # Matrix slicing
 var A_slice = A[1:3, 4:19]
 var B_slice = B[255, 103:241:2]
 # Get scalar from matrix
 var A_item = A[291, 141]
 # Flip the column vector
 print(C[::-1, :])
 # Sort and argsort along axis
 print(nm.sort(A, axis=1))
 print(nm.argsort(A, axis=0))
 # Sum the matrix
 print(nm.sum(B))
 print(nm.sum(B, axis=1))
 # Matrix multiplication
 print(A @ B)
 # Matrix inversion
 print(A.inv())
 # Solve linear algebra
 print(nm.solve(A, B))
 # Least square
 print(nm.lstsq(A, C))

An example of ComplexNDArray is as follows,

import numojo as nm
from numojo.prelude import *
fn main() raises:
 # Create a complexscalar 5 + 5j
 var complexscalar = ComplexSIMD[f32](re=5, im=5) 
 # Create complex array filled with (5 + 5j)
 var A = nm.full[f32](Shape(1000, 1000), fill_value=complexscalar)
 # Create complex array filled with (1 + 1j)
 var B = nm.ones[f32](Shape(1000, 1000))
 # Print array
 print(A)
 # Array slicing
 var A_slice = A[1:3, 4:19]
 # Array multiplication
 var C = A * B
 # Get scalar from array
 var A_item = A[item(291, 141)]
 # Set an element of the array
 A[item(291, 141)] = complexscalar

There are three approach to install and use the Numojo package.

You can add the package numojo of a specific version in the dependencies section of your toml file.

[dependencies]
numojo = "=0.7.0"

Then, you can run pixi install to install the package.

The following table shows the version of numojo and the corresponding version of mojo that is required.

This approach involves building a standalone package file mojopkg.

1. Clone the repository.
2. Build the package using pixi run package.
3. Move the numojo.mojopkg into the directory containing the your code.

This approach does not require building a package file. Instead, when you compile your code, you can include the path of NuMojo repository with the following command:

mojo run -I "../NuMojo" example.mojo

This is more flexible as you are able to edit the NuMojo source files when testing your code.

In order to allow VSCode LSP to resolve the imported numojo package, you can:

1. Go to preference page of VSCode.
2. Go to Mojo › Lsp: Include Dirs
3. Click add item and write the path where the Numojo repository is located, e.g. /Users/Name/Programs/NuMojo.
4. Restart the Mojo LSP server.

Now VSCode can show function hints for the Numojo package!

Any contributions you make are greatly appreciated. For more details and guidelines on contributions, please check here

This library is still very much a work in progress and may change at any time.

Distributed under the Apache 2.0 License with LLVM Exceptions. See LICENSE and the LLVM License for more information.

This project includes code from Mojo Standard Library, licensed under the Apache License v2.0 with LLVM Exceptions (see the LLVM License). MAX and Mojo usage and distribution are licensed under the MAX & Mojo Community License.

Built in native Mojo which was created by Modular.