mirror of
https://github.com/Magnus167/rustframe.git
synced 2025-08-20 04:00:01 +00:00
Merge 9e6e22fc375181ab6629a4fe109511c768d8ce72 into 7d0978e5fba98538de20d0fdb9d66e6cbf80d3f7
This commit is contained in:
commit
e24eb7796d
11
.github/htmldocs/index.html
vendored
11
.github/htmldocs/index.html
vendored
@ -58,6 +58,14 @@
|
||||
<h2>A lightweight dataframe & math toolkit for Rust</h2>
|
||||
<hr style="border: 1px solid #d4d4d4; margin: 20px 0;">
|
||||
<p>
|
||||
|
||||
🐙 <a href="https://github.com/Magnus167/rustframe">GitHub</a>
|
||||
<br><br>
|
||||
|
||||
📖 <a href="https://magnus167.github.io/rustframe/user-guide">User Guide</a>
|
||||
<br><br>
|
||||
|
||||
|
||||
📚 <a href="https://magnus167.github.io/rustframe/docs">Docs</a> |
|
||||
📊 <a href="https://magnus167.github.io/rustframe/benchmark-report/">Benchmarks</a>
|
||||
|
||||
@ -65,8 +73,7 @@
|
||||
🦀 <a href="https://crates.io/crates/rustframe">Crates.io</a> |
|
||||
🔖 <a href="https://docs.rs/rustframe/latest/rustframe/">docs.rs</a>
|
||||
<br><br>
|
||||
🐙 <a href="https://github.com/Magnus167/rustframe">GitHub</a> |
|
||||
🌐 <a href="https://gitea.nulltech.uk/Magnus167/rustframe">Gitea mirror</a>
|
||||
<!-- 🌐 <a href="https://gitea.nulltech.uk/Magnus167/rustframe">Gitea mirror</a> -->
|
||||
</p>
|
||||
</main>
|
||||
</body>
|
||||
|
21
.github/workflows/docs-and-testcov.yml
vendored
21
.github/workflows/docs-and-testcov.yml
vendored
@ -153,7 +153,6 @@ jobs:
|
||||
|
||||
echo "<meta http-equiv=\"refresh\" content=\"0; url=../docs/index.html\">" > target/doc/rustframe/index.html
|
||||
|
||||
mkdir output
|
||||
cp tarpaulin-report.html target/doc/docs/
|
||||
cp tarpaulin-report.json target/doc/docs/
|
||||
cp tarpaulin-badge.json target/doc/docs/
|
||||
@ -166,16 +165,30 @@ jobs:
|
||||
# copy the benchmark report to the output directory
|
||||
cp -r benchmark-report target/doc/
|
||||
|
||||
mkdir output
|
||||
cp -r target/doc/* output/
|
||||
|
||||
- name: Build user guide
|
||||
run: |
|
||||
cargo binstall mdbook
|
||||
bash ./docs/build.sh
|
||||
|
||||
- name: Copy user guide to output directory
|
||||
run: |
|
||||
mkdir output/user-guide
|
||||
cp -r docs/book/* output/user-guide/
|
||||
|
||||
- name: Add index.html to output directory
|
||||
run: |
|
||||
cp .github/htmldocs/index.html target/doc/index.html
|
||||
cp .github/rustframe_logo.png target/doc/rustframe_logo.png
|
||||
cp .github/htmldocs/index.html output/index.html
|
||||
cp .github/rustframe_logo.png output/rustframe_logo.png
|
||||
|
||||
- name: Upload Pages artifact
|
||||
# if: github.event_name == 'push' || github.event_name == 'workflow_dispatch'
|
||||
uses: actions/upload-pages-artifact@v3
|
||||
with:
|
||||
path: target/doc/
|
||||
# path: target/doc/
|
||||
path: output/
|
||||
|
||||
- name: Deploy to GitHub Pages
|
||||
# if: github.event_name == 'push' || github.event_name == 'workflow_dispatch'
|
||||
|
5
.github/workflows/run-unit-tests.yml
vendored
5
.github/workflows/run-unit-tests.yml
vendored
@ -78,3 +78,8 @@ jobs:
|
||||
uses: codecov/test-results-action@v1
|
||||
with:
|
||||
token: ${{ secrets.CODECOV_TOKEN }}
|
||||
|
||||
- name: Test build user guide
|
||||
run: |
|
||||
cargo binstall mdbook
|
||||
bash ./docs/build.sh
|
||||
|
4
.gitignore
vendored
4
.gitignore
vendored
@ -16,4 +16,6 @@ data/
|
||||
|
||||
tarpaulin-report.*
|
||||
|
||||
.github/htmldocs/rustframe_logo.png
|
||||
.github/htmldocs/rustframe_logo.png
|
||||
|
||||
docs/book/
|
14
README.md
14
README.md
@ -1,11 +1,12 @@
|
||||
# rustframe
|
||||
|
||||
📚 [Docs](https://magnus167.github.io/rustframe/) | 🐙 [GitHub](https://github.com/Magnus167/rustframe) | 🌐 [Gitea mirror](https://gitea.nulltech.uk/Magnus167/rustframe) | 🦀 [Crates.io](https://crates.io/crates/rustframe) | 🔖 [docs.rs](https://docs.rs/rustframe/latest/rustframe/)
|
||||
📚 [Docs](https://magnus167.github.io/rustframe/) | 🐙 [GitHub](https://github.com/Magnus167/rustframe) | 🦀 [Crates.io](https://crates.io/crates/rustframe) | 🔖 [docs.rs](https://docs.rs/rustframe/latest/rustframe/)
|
||||
|
||||
<!-- [](https://github.com/Magnus167/rustframe) -->
|
||||
|
||||
[](https://codecov.io/gh/Magnus167/rustframe)
|
||||
[](https://magnus167.github.io/rustframe/docs/tarpaulin-report.html)
|
||||
[](https://gitea.nulltech.uk/Magnus167/rustframe)
|
||||
|
||||
---
|
||||
|
||||
@ -198,3 +199,14 @@ To run the benchmarks, use:
|
||||
```bash
|
||||
cargo bench --features "bench"
|
||||
```
|
||||
|
||||
## Building the user-guide
|
||||
|
||||
To build the user guide, use:
|
||||
|
||||
```bash
|
||||
cargo binstall mdbook
|
||||
bash docs/build.sh
|
||||
```
|
||||
|
||||
This will generate the user guide in the `docs/book` directory.
|
||||
|
7
docs/book.toml
Normal file
7
docs/book.toml
Normal file
@ -0,0 +1,7 @@
|
||||
[book]
|
||||
title = "Rustframe User Guide"
|
||||
authors = ["Palash Tyagi (https://github.com/Magnus167)"]
|
||||
description = "Guided journey through Rustframe capabilities."
|
||||
|
||||
[build]
|
||||
build-dir = "book"
|
7
docs/build.sh
Executable file
7
docs/build.sh
Executable file
@ -0,0 +1,7 @@
|
||||
#!/usr/bin/env sh
|
||||
# Build and test the Rustframe user guide using mdBook.
|
||||
set -e
|
||||
|
||||
cd docs
|
||||
bash gen.sh "$@"
|
||||
cd ..
|
14
docs/gen.sh
Normal file
14
docs/gen.sh
Normal file
@ -0,0 +1,14 @@
|
||||
#!/usr/bin/env sh
|
||||
|
||||
set -e
|
||||
|
||||
cargo clean
|
||||
|
||||
cargo build --manifest-path ../Cargo.toml
|
||||
|
||||
mdbook test -L ../target/debug/deps "$@"
|
||||
|
||||
mdbook build "$@"
|
||||
|
||||
cargo build
|
||||
# cargo build --release
|
7
docs/src/SUMMARY.md
Normal file
7
docs/src/SUMMARY.md
Normal file
@ -0,0 +1,7 @@
|
||||
# Summary
|
||||
|
||||
- [Introduction](./introduction.md)
|
||||
- [Data Manipulation](./data-manipulation.md)
|
||||
- [Compute Features](./compute.md)
|
||||
- [Machine Learning](./machine-learning.md)
|
||||
- [Utilities](./utilities.md)
|
222
docs/src/compute.md
Normal file
222
docs/src/compute.md
Normal file
@ -0,0 +1,222 @@
|
||||
# Compute Features
|
||||
|
||||
The `compute` module hosts numerical routines for exploratory data analysis.
|
||||
It covers descriptive statistics, correlations, probability distributions and
|
||||
some basic inferential tests.
|
||||
|
||||
## Basic Statistics
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::compute::stats::{mean, mean_horizontal, mean_vertical, stddev, median, population_variance, percentile};
|
||||
use rustframe::matrix::Matrix;
|
||||
|
||||
let m = Matrix::from_vec(vec![1.0, 2.0, 3.0, 4.0], 2, 2);
|
||||
assert_eq!(mean(&m), 2.5);
|
||||
assert_eq!(stddev(&m), 1.118033988749895);
|
||||
assert_eq!(median(&m), 2.5);
|
||||
assert_eq!(population_variance(&m), 1.25);
|
||||
assert_eq!(percentile(&m, 50.0), 3.0);
|
||||
// column averages returned as 1 x n matrix
|
||||
let row_means = mean_horizontal(&m);
|
||||
assert_eq!(row_means.data(), &[2.0, 3.0]);
|
||||
let col_means = mean_vertical(&m);
|
||||
assert_eq!(col_means.data(), & [1.5, 3.5]);
|
||||
```
|
||||
|
||||
### Axis-specific Operations
|
||||
|
||||
Operations can be applied along specific axes (rows or columns):
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::compute::stats::{mean_vertical, mean_horizontal, stddev_vertical, stddev_horizontal};
|
||||
use rustframe::matrix::Matrix;
|
||||
|
||||
// 3x2 matrix
|
||||
let m = Matrix::from_rows_vec(vec![1.0, 2.0, 3.0, 4.0, 5.0, 6.0], 3, 2);
|
||||
|
||||
// Mean along columns (vertical) - returns 1 x cols matrix
|
||||
let col_means = mean_vertical(&m);
|
||||
assert_eq!(col_means.shape(), (1, 2));
|
||||
assert_eq!(col_means.data(), &[3.0, 4.0]); // [(1+3+5)/3, (2+4+6)/3]
|
||||
|
||||
// Mean along rows (horizontal) - returns rows x 1 matrix
|
||||
let row_means = mean_horizontal(&m);
|
||||
assert_eq!(row_means.shape(), (3, 1));
|
||||
assert_eq!(row_means.data(), &[1.5, 3.5, 5.5]); // [(1+2)/2, (3+4)/2, (5+6)/2]
|
||||
|
||||
// Standard deviation along columns
|
||||
let col_stddev = stddev_vertical(&m);
|
||||
assert_eq!(col_stddev.shape(), (1, 2));
|
||||
|
||||
// Standard deviation along rows
|
||||
let row_stddev = stddev_horizontal(&m);
|
||||
assert_eq!(row_stddev.shape(), (3, 1));
|
||||
```
|
||||
|
||||
## Correlation
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::compute::stats::{pearson, covariance};
|
||||
use rustframe::matrix::Matrix;
|
||||
|
||||
let x = Matrix::from_vec(vec![1.0, 2.0, 3.0, 4.0], 2, 2);
|
||||
let y = Matrix::from_vec(vec![2.0, 4.0, 6.0, 8.0], 2, 2);
|
||||
let corr = pearson(&x, &y);
|
||||
let cov = covariance(&x, &y);
|
||||
assert!((corr - 1.0).abs() < 1e-8);
|
||||
assert!((cov - 2.5).abs() < 1e-8);
|
||||
```
|
||||
|
||||
## Covariance
|
||||
|
||||
### `covariance`
|
||||
|
||||
Computes the population covariance between two equally sized matrices by flattening
|
||||
their values.
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::compute::stats::covariance;
|
||||
use rustframe::matrix::Matrix;
|
||||
|
||||
let x = Matrix::from_vec(vec![1.0, 2.0, 3.0, 4.0], 2, 2);
|
||||
let y = Matrix::from_vec(vec![2.0, 4.0, 6.0, 8.0], 2, 2);
|
||||
let cov = covariance(&x, &y);
|
||||
assert!((cov - 2.5).abs() < 1e-8);
|
||||
```
|
||||
|
||||
### `covariance_vertical`
|
||||
|
||||
Evaluates covariance between columns (i.e. across rows) and returns a matrix of
|
||||
column pair covariances.
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::compute::stats::covariance_vertical;
|
||||
use rustframe::matrix::Matrix;
|
||||
|
||||
let m = Matrix::from_rows_vec(vec![1.0, 2.0, 3.0, 4.0], 2, 2);
|
||||
let cov = covariance_vertical(&m);
|
||||
assert_eq!(cov.shape(), (2, 2));
|
||||
assert!(cov.data().iter().all(|&v| (v - 1.0).abs() < 1e-8));
|
||||
```
|
||||
|
||||
### `covariance_horizontal`
|
||||
|
||||
Computes covariance between rows (i.e. across columns) returning a matrix that
|
||||
describes how each pair of rows varies together.
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::compute::stats::covariance_horizontal;
|
||||
use rustframe::matrix::Matrix;
|
||||
|
||||
let m = Matrix::from_rows_vec(vec![1.0, 2.0, 3.0, 4.0], 2, 2);
|
||||
let cov = covariance_horizontal(&m);
|
||||
assert_eq!(cov.shape(), (2, 2));
|
||||
assert!(cov.data().iter().all(|&v| (v - 0.25).abs() < 1e-8));
|
||||
```
|
||||
|
||||
### `covariance_matrix`
|
||||
|
||||
Builds a covariance matrix either between columns (`Axis::Col`) or rows
|
||||
(`Axis::Row`). Each entry represents how two series co-vary.
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::compute::stats::covariance_matrix;
|
||||
use rustframe::matrix::{Axis, Matrix};
|
||||
|
||||
let data = Matrix::from_rows_vec(vec![1.0, 2.0, 3.0, 4.0], 2, 2);
|
||||
|
||||
// Covariance between columns
|
||||
let cov_cols = covariance_matrix(&data, Axis::Col);
|
||||
assert!((cov_cols.get(0, 0) - 2.0).abs() < 1e-8);
|
||||
|
||||
// Covariance between rows
|
||||
let cov_rows = covariance_matrix(&data, Axis::Row);
|
||||
assert!((cov_rows.get(0, 1) + 0.5).abs() < 1e-8);
|
||||
```
|
||||
|
||||
## Distributions
|
||||
|
||||
Probability distribution helpers are available for common PDFs and CDFs.
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::compute::stats::distributions::normal_pdf;
|
||||
use rustframe::matrix::Matrix;
|
||||
|
||||
let x = Matrix::from_vec(vec![0.0, 1.0], 1, 2);
|
||||
let pdf = normal_pdf(x, 0.0, 1.0);
|
||||
assert_eq!(pdf.data().len(), 2);
|
||||
```
|
||||
|
||||
### Additional Distributions
|
||||
|
||||
Rustframe provides several other probability distributions:
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::compute::stats::distributions::{normal_cdf, binomial_pmf, binomial_cdf, poisson_pmf};
|
||||
use rustframe::matrix::Matrix;
|
||||
|
||||
// Normal distribution CDF
|
||||
let x = Matrix::from_vec(vec![0.0, 1.0], 1, 2);
|
||||
let cdf = normal_cdf(x, 0.0, 1.0);
|
||||
assert_eq!(cdf.data().len(), 2);
|
||||
|
||||
// Binomial distribution PMF
|
||||
// Probability of k successes in n trials with probability p
|
||||
let k = Matrix::from_vec(vec![0_u64, 1, 2, 3], 1, 4);
|
||||
let pmf = binomial_pmf(3, k.clone(), 0.5);
|
||||
assert_eq!(pmf.data().len(), 4);
|
||||
|
||||
// Binomial distribution CDF
|
||||
let cdf = binomial_cdf(3, k, 0.5);
|
||||
assert_eq!(cdf.data().len(), 4);
|
||||
|
||||
// Poisson distribution PMF
|
||||
// Probability of k events with rate parameter lambda
|
||||
let k = Matrix::from_vec(vec![0_u64, 1, 2], 1, 3);
|
||||
let pmf = poisson_pmf(2.0, k);
|
||||
assert_eq!(pmf.data().len(), 3);
|
||||
```
|
||||
|
||||
### Inferential Statistics
|
||||
|
||||
Rustframe provides several inferential statistical tests:
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::matrix::Matrix;
|
||||
use rustframe::compute::stats::inferential::{t_test, chi2_test, anova};
|
||||
|
||||
// Two-sample t-test
|
||||
let sample1 = Matrix::from_vec(vec![1.0, 2.0, 3.0, 4.0, 5.0], 1, 5);
|
||||
let sample2 = Matrix::from_vec(vec![6.0, 7.0, 8.0, 9.0, 10.0], 1, 5);
|
||||
let (t_statistic, p_value) = t_test(&sample1, &sample2);
|
||||
assert!((t_statistic + 5.0).abs() < 1e-5);
|
||||
assert!(p_value > 0.0 && p_value < 1.0);
|
||||
|
||||
// Chi-square test of independence
|
||||
let observed = Matrix::from_vec(vec![12.0, 5.0, 8.0, 10.0], 2, 2);
|
||||
let (chi2_statistic, p_value) = chi2_test(&observed);
|
||||
assert!(chi2_statistic > 0.0);
|
||||
assert!(p_value > 0.0 && p_value < 1.0);
|
||||
|
||||
// One-way ANOVA
|
||||
let group1 = Matrix::from_vec(vec![1.0, 2.0, 3.0], 1, 3);
|
||||
let group2 = Matrix::from_vec(vec![2.0, 3.0, 4.0], 1, 3);
|
||||
let group3 = Matrix::from_vec(vec![3.0, 4.0, 5.0], 1, 3);
|
||||
let groups = vec![&group1, &group2, &group3];
|
||||
let (f_statistic, p_value) = anova(groups);
|
||||
assert!(f_statistic > 0.0);
|
||||
assert!(p_value > 0.0 && p_value < 1.0);
|
||||
```
|
||||
|
||||
With the basics covered, explore predictive models in the
|
||||
[machine learning](./machine-learning.md) chapter.
|
157
docs/src/data-manipulation.md
Normal file
157
docs/src/data-manipulation.md
Normal file
@ -0,0 +1,157 @@
|
||||
# Data Manipulation
|
||||
|
||||
Rustframe's `Frame` type couples tabular data with
|
||||
column labels and a typed row index. Frames expose a familiar API for loading
|
||||
data, selecting rows or columns and performing aggregations.
|
||||
|
||||
## Creating a Frame
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::frame::{Frame, RowIndex};
|
||||
use rustframe::matrix::Matrix;
|
||||
|
||||
let data = Matrix::from_cols(vec![vec![1.0, 2.0], vec![3.0, 4.0]]);
|
||||
let frame = Frame::new(data, vec!["A", "B"], None);
|
||||
assert_eq!(frame["A"], vec![1.0, 2.0]);
|
||||
```
|
||||
|
||||
## Indexing Rows
|
||||
|
||||
Row labels can be integers, dates or a default range. Retrieving a row returns a
|
||||
view that lets you inspect values by column name or position.
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
# extern crate chrono;
|
||||
use chrono::NaiveDate;
|
||||
use rustframe::frame::{Frame, RowIndex};
|
||||
use rustframe::matrix::Matrix;
|
||||
|
||||
let d = |y, m, d| NaiveDate::from_ymd_opt(y, m, d).unwrap();
|
||||
let data = Matrix::from_cols(vec![vec![1.0, 2.0], vec![3.0, 4.0]]);
|
||||
let index = RowIndex::Date(vec![d(2024, 1, 1), d(2024, 1, 2)]);
|
||||
let mut frame = Frame::new(data, vec!["A", "B"], Some(index));
|
||||
assert_eq!(frame.get_row_date(d(2024, 1, 2))["B"], 4.0);
|
||||
|
||||
// mutate by row key
|
||||
frame.get_row_date_mut(d(2024, 1, 1)).set_by_index(0, 9.0);
|
||||
assert_eq!(frame.get_row_date(d(2024, 1, 1))["A"], 9.0);
|
||||
```
|
||||
|
||||
## Column operations
|
||||
|
||||
Columns can be inserted, renamed, removed or reordered in place.
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::frame::{Frame, RowIndex};
|
||||
use rustframe::matrix::Matrix;
|
||||
|
||||
let data = Matrix::from_cols(vec![vec![1, 2], vec![3, 4]]);
|
||||
let mut frame = Frame::new(data, vec!["X", "Y"], Some(RowIndex::Range(0..2)));
|
||||
|
||||
frame.add_column("Z", vec![5, 6]);
|
||||
frame.rename("Y", "W");
|
||||
let removed = frame.delete_column("X");
|
||||
assert_eq!(removed, vec![1, 2]);
|
||||
frame.sort_columns();
|
||||
assert_eq!(frame.columns(), &["W", "Z"]);
|
||||
```
|
||||
|
||||
## Aggregations
|
||||
|
||||
Any numeric aggregation available on `Matrix` is forwarded to `Frame`.
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::frame::Frame;
|
||||
use rustframe::matrix::{Matrix, SeriesOps};
|
||||
|
||||
let frame = Frame::new(Matrix::from_cols(vec![vec![1.0, 2.0], vec![3.0, 4.0]]), vec!["A", "B"], None);
|
||||
assert_eq!(frame.sum_vertical(), vec![3.0, 7.0]);
|
||||
assert_eq!(frame.sum_horizontal(), vec![4.0, 6.0]);
|
||||
```
|
||||
|
||||
## Matrix Operations
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::matrix::Matrix;
|
||||
|
||||
let data1 = Matrix::from_vec(vec![1.0, 2.0, 3.0, 4.0], 2, 2);
|
||||
let data2 = Matrix::from_vec(vec![5.0, 6.0, 7.0, 8.0], 2, 2);
|
||||
|
||||
let sum = data1.clone() + data2.clone();
|
||||
assert_eq!(sum.data(), vec![6.0, 8.0, 10.0, 12.0]);
|
||||
|
||||
let product = data1.clone() * data2.clone();
|
||||
assert_eq!(product.data(), vec![5.0, 12.0, 21.0, 32.0]);
|
||||
|
||||
let scalar_product = data1.clone() * 2.0;
|
||||
assert_eq!(scalar_product.data(), vec![2.0, 4.0, 6.0, 8.0]);
|
||||
|
||||
let equals = data1 == data1.clone();
|
||||
assert_eq!(equals, true);
|
||||
```
|
||||
|
||||
### Advanced Matrix Operations
|
||||
|
||||
Matrices support a variety of advanced operations:
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::matrix::{Matrix, SeriesOps};
|
||||
|
||||
// Matrix multiplication (dot product)
|
||||
let a = Matrix::from_vec(vec![1.0, 2.0, 3.0, 4.0], 2, 2);
|
||||
let b = Matrix::from_vec(vec![5.0, 6.0, 7.0, 8.0], 2, 2);
|
||||
let product = a.matrix_mul(&b);
|
||||
assert_eq!(product.data(), vec![23.0, 34.0, 31.0, 46.0]);
|
||||
|
||||
// Transpose
|
||||
let m = Matrix::from_vec(vec![1.0, 2.0, 3.0, 4.0], 2, 2);
|
||||
let transposed = m.transpose();
|
||||
assert_eq!(transposed.data(), vec![1.0, 3.0, 2.0, 4.0]);
|
||||
|
||||
// Map function over all elements
|
||||
let m = Matrix::from_vec(vec![1.0, 2.0, 3.0, 4.0], 2, 2);
|
||||
let squared = m.map(|x| x * x);
|
||||
assert_eq!(squared.data(), vec![1.0, 4.0, 9.0, 16.0]);
|
||||
|
||||
// Zip two matrices with a function
|
||||
let a = Matrix::from_vec(vec![1.0, 2.0, 3.0, 4.0], 2, 2);
|
||||
let b = Matrix::from_vec(vec![5.0, 6.0, 7.0, 8.0], 2, 2);
|
||||
let zipped = a.zip(&b, |x, y| x + y);
|
||||
assert_eq!(zipped.data(), vec![6.0, 8.0, 10.0, 12.0]);
|
||||
```
|
||||
|
||||
### Matrix Reductions
|
||||
|
||||
Matrices support various reduction operations:
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::matrix::{Matrix, SeriesOps};
|
||||
|
||||
let m = Matrix::from_rows_vec(vec![1.0, 2.0, 3.0, 4.0, 5.0, 6.0], 3, 2);
|
||||
|
||||
// Sum along columns (vertical)
|
||||
let col_sums = m.sum_vertical();
|
||||
assert_eq!(col_sums, vec![9.0, 12.0]); // [1+3+5, 2+4+6]
|
||||
|
||||
// Sum along rows (horizontal)
|
||||
let row_sums = m.sum_horizontal();
|
||||
assert_eq!(row_sums, vec![3.0, 7.0, 11.0]); // [1+2, 3+4, 5+6]
|
||||
|
||||
// Cumulative sum along columns
|
||||
let col_cumsum = m.cumsum_vertical();
|
||||
assert_eq!(col_cumsum.data(), vec![1.0, 4.0, 9.0, 2.0, 6.0, 12.0]);
|
||||
|
||||
// Cumulative sum along rows
|
||||
let row_cumsum = m.cumsum_horizontal();
|
||||
assert_eq!(row_cumsum.data(), vec![1.0, 3.0, 5.0, 3.0, 7.0, 11.0]);
|
||||
```
|
||||
|
||||
With the basics covered, continue to the [compute features](./compute.md)
|
||||
chapter for statistics and analytics.
|
40
docs/src/introduction.md
Normal file
40
docs/src/introduction.md
Normal file
@ -0,0 +1,40 @@
|
||||
# Introduction
|
||||
|
||||
📚 [Docs](https://magnus167.github.io/rustframe/) | 🐙 [GitHub](https://github.com/Magnus167/rustframe) | 🦀 [Crates.io](https://crates.io/crates/rustframe) | 🔖 [docs.rs](https://docs.rs/rustframe/latest/rustframe/)
|
||||
|
||||
Welcome to the **Rustframe User Guide**. Rustframe is a lightweight dataframe
|
||||
and math toolkit for Rust written in 100% safe Rust. It focuses on keeping the
|
||||
API approachable while offering handy features for small analytical or
|
||||
educational projects.
|
||||
|
||||
Rustframe bundles:
|
||||
|
||||
- column‑labelled frames built on a fast column‑major matrix
|
||||
- familiar element‑wise math and aggregation routines
|
||||
- a growing `compute` module for statistics and machine learning
|
||||
- utilities for dates and random numbers
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::{frame::Frame, matrix::{Matrix, SeriesOps}};
|
||||
|
||||
let data = Matrix::from_cols(vec![vec![1.0, 2.0], vec![3.0, 4.0]]);
|
||||
let frame = Frame::new(data, vec!["A", "B"], None);
|
||||
|
||||
// Perform column wise aggregation
|
||||
assert_eq!(frame.sum_vertical(), vec![3.0, 7.0]);
|
||||
```
|
||||
|
||||
## Resources
|
||||
|
||||
- [GitHub repository](https://github.com/Magnus167/rustframe)
|
||||
- [Crates.io](https://crates.io/crates/rustframe) & [API docs](https://docs.rs/rustframe)
|
||||
- [Code coverage](https://codecov.io/gh/Magnus167/rustframe)
|
||||
|
||||
This guide walks through the main building blocks of the library. Each chapter
|
||||
contains runnable snippets so you can follow along:
|
||||
|
||||
1. [Data manipulation](./data-manipulation.md) for loading and transforming data
|
||||
2. [Compute features](./compute.md) for statistics and analytics
|
||||
3. [Machine learning](./machine-learning.md) for predictive models
|
||||
4. [Utilities](./utilities.md) for supporting helpers and upcoming modules
|
146
docs/src/machine-learning.md
Normal file
146
docs/src/machine-learning.md
Normal file
@ -0,0 +1,146 @@
|
||||
# Machine Learning
|
||||
|
||||
The `compute::models` module bundles several learning algorithms that operate on
|
||||
`Matrix` structures. These examples highlight the basic training and prediction
|
||||
APIs. For more end‑to‑end walkthroughs see the examples directory in the
|
||||
repository.
|
||||
|
||||
Currently implemented models include:
|
||||
|
||||
- Linear and logistic regression
|
||||
- K‑means clustering
|
||||
- Principal component analysis (PCA)
|
||||
- Gaussian Naive Bayes
|
||||
- Dense neural networks
|
||||
|
||||
## Linear Regression
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::compute::models::linreg::LinReg;
|
||||
use rustframe::matrix::Matrix;
|
||||
|
||||
let x = Matrix::from_vec(vec![1.0, 2.0, 3.0, 4.0], 4, 1);
|
||||
let y = Matrix::from_vec(vec![2.0, 3.0, 4.0, 5.0], 4, 1);
|
||||
let mut model = LinReg::new(1);
|
||||
model.fit(&x, &y, 0.01, 100);
|
||||
let preds = model.predict(&x);
|
||||
assert_eq!(preds.rows(), 4);
|
||||
```
|
||||
|
||||
## K-means Walkthrough
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::compute::models::k_means::KMeans;
|
||||
use rustframe::matrix::Matrix;
|
||||
|
||||
let data = Matrix::from_vec(vec![1.0, 1.0, 5.0, 5.0], 2, 2);
|
||||
let (model, _labels) = KMeans::fit(&data, 2, 10, 1e-4);
|
||||
let new_point = Matrix::from_vec(vec![0.0, 0.0], 1, 2);
|
||||
let cluster = model.predict(&new_point)[0];
|
||||
```
|
||||
|
||||
For helper functions and upcoming modules, visit the
|
||||
[utilities](./utilities.md) section.
|
||||
|
||||
## Logistic Regression
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::compute::models::logreg::LogReg;
|
||||
use rustframe::matrix::Matrix;
|
||||
|
||||
let x = Matrix::from_vec(vec![1.0, 2.0, 3.0, 4.0], 4, 1);
|
||||
let y = Matrix::from_vec(vec![0.0, 0.0, 1.0, 1.0], 4, 1);
|
||||
let mut model = LogReg::new(1);
|
||||
model.fit(&x, &y, 0.1, 200);
|
||||
let preds = model.predict_proba(&x);
|
||||
assert_eq!(preds.rows(), 4);
|
||||
```
|
||||
|
||||
## Principal Component Analysis
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::compute::models::pca::PCA;
|
||||
use rustframe::matrix::Matrix;
|
||||
|
||||
let data = Matrix::from_vec(vec![1.0, 2.0, 3.0, 4.0], 2, 2);
|
||||
let pca = PCA::fit(&data, 1, 0);
|
||||
let transformed = pca.transform(&data);
|
||||
assert_eq!(transformed.cols(), 1);
|
||||
```
|
||||
|
||||
### Gaussian Naive Bayes
|
||||
|
||||
Gaussian Naive Bayes classifier for continuous features:
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::compute::models::gaussian_nb::GaussianNB;
|
||||
use rustframe::matrix::Matrix;
|
||||
|
||||
// Training data with 2 features
|
||||
let x = Matrix::from_rows_vec(vec![
|
||||
1.0, 2.0,
|
||||
2.0, 3.0,
|
||||
3.0, 4.0,
|
||||
4.0, 5.0
|
||||
], 4, 2);
|
||||
|
||||
// Class labels (0 or 1)
|
||||
let y = Matrix::from_vec(vec![0.0, 0.0, 1.0, 1.0], 4, 1);
|
||||
|
||||
// Train the model
|
||||
let mut model = GaussianNB::new(1e-9, true);
|
||||
model.fit(&x, &y);
|
||||
|
||||
// Make predictions
|
||||
let predictions = model.predict(&x);
|
||||
assert_eq!(predictions.rows(), 4);
|
||||
```
|
||||
|
||||
### Dense Neural Networks
|
||||
|
||||
Simple fully connected neural network:
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::compute::models::dense_nn::{DenseNN, DenseNNConfig, ActivationKind, InitializerKind, LossKind};
|
||||
use rustframe::matrix::Matrix;
|
||||
|
||||
// Training data with 2 features
|
||||
let x = Matrix::from_rows_vec(vec![
|
||||
0.0, 0.0,
|
||||
0.0, 1.0,
|
||||
1.0, 0.0,
|
||||
1.0, 1.0
|
||||
], 4, 2);
|
||||
|
||||
// XOR target outputs
|
||||
let y = Matrix::from_vec(vec![0.0, 1.0, 1.0, 0.0], 4, 1);
|
||||
|
||||
// Create a neural network with 2 hidden layers
|
||||
let config = DenseNNConfig {
|
||||
input_size: 2,
|
||||
hidden_layers: vec![4, 4],
|
||||
output_size: 1,
|
||||
activations: vec![ActivationKind::Sigmoid, ActivationKind::Sigmoid, ActivationKind::Sigmoid],
|
||||
initializer: InitializerKind::Uniform(0.5),
|
||||
loss: LossKind::MSE,
|
||||
learning_rate: 0.1,
|
||||
epochs: 1000,
|
||||
};
|
||||
let mut model = DenseNN::new(config);
|
||||
|
||||
// Train the model
|
||||
model.train(&x, &y);
|
||||
|
||||
// Make predictions
|
||||
let predictions = model.predict(&x);
|
||||
assert_eq!(predictions.rows(), 4);
|
||||
```
|
||||
|
||||
For helper functions and upcoming modules, visit the
|
||||
[utilities](./utilities.md) section.
|
63
docs/src/utilities.md
Normal file
63
docs/src/utilities.md
Normal file
@ -0,0 +1,63 @@
|
||||
# Utilities
|
||||
|
||||
Utilities provide handy helpers around the core library. Existing tools
|
||||
include:
|
||||
|
||||
- Date utilities for generating calendar sequences and business‑day sets
|
||||
- Random number generators for simulations and testing
|
||||
|
||||
## Date Helpers
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::utils::dateutils::{BDatesList, BDateFreq, DatesList, DateFreq};
|
||||
|
||||
// Calendar sequence
|
||||
let list = DatesList::new("2024-01-01".into(), "2024-01-03".into(), DateFreq::Daily);
|
||||
assert_eq!(list.count().unwrap(), 3);
|
||||
|
||||
// Business days starting from 2024‑01‑02
|
||||
let bdates = BDatesList::from_n_periods("2024-01-02".into(), BDateFreq::Daily, 3).unwrap();
|
||||
assert_eq!(bdates.list().unwrap().len(), 3);
|
||||
```
|
||||
|
||||
## Random Numbers
|
||||
|
||||
The `random` module offers deterministic and cryptographically secure RNGs.
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::random::{Prng, Rng};
|
||||
|
||||
let mut rng = Prng::new(42);
|
||||
let v1 = rng.next_u64();
|
||||
let v2 = rng.next_u64();
|
||||
assert_ne!(v1, v2);
|
||||
```
|
||||
|
||||
## Stats Functions
|
||||
|
||||
```rust
|
||||
# extern crate rustframe;
|
||||
use rustframe::matrix::Matrix;
|
||||
use rustframe::compute::stats::descriptive::{mean, median, stddev};
|
||||
|
||||
let data = Matrix::from_vec(vec![1.0, 2.0, 3.0, 4.0, 5.0], 1, 5);
|
||||
|
||||
let mean_value = mean(&data);
|
||||
assert_eq!(mean_value, 3.0);
|
||||
|
||||
let median_value = median(&data);
|
||||
assert_eq!(median_value, 3.0);
|
||||
|
||||
let std_value = stddev(&data);
|
||||
assert_eq!(std_value, 2.0_f64.sqrt());
|
||||
```
|
||||
|
||||
Upcoming utilities will cover:
|
||||
|
||||
- Data import/export helpers
|
||||
- Visualization adapters
|
||||
- Streaming data interfaces
|
||||
|
||||
Contributions to these sections are welcome!
|
Loading…
x
Reference in New Issue
Block a user