timeout added

.github/workflows/CI.yml

@@ -5,7 +5,7 @@ jobs:
   windows-build-test:
     strategy:
       matrix:
-        pyversion: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        pyversion: ["3.9", "3.10", "3.11", "3.12"]
     runs-on: "windows-latest"
     steps:
       - uses: actions/checkout@v4
@@ -101,7 +101,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        pyversion: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        pyversion: ["3.9", "3.10", "3.11", "3.12"]
     steps:
       - uses: actions/checkout@v4
       - name: Install latests stable Rust

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "perpetual"
-version = "0.5.1"
+version = "0.5.2"
 edition = "2021"
 authors = ["Mutlu Simsek <[email protected]>"]
 homepage = "https://perpetual-ml.com"
@@ -22,7 +22,7 @@ codegen-units = 1
 [dependencies]
 rayon = "1.8"
 thiserror = "1.0.64"
-serde_json = { version = "1.0.127", features = ["float_roundtrip"] }
+serde_json = { version = "1.0.129", features = ["float_roundtrip"] }
 serde = { version = "1.0.209", features = ["derive"] }
 approx = "0.5"
 log = "0.4"

README.md

@@ -61,7 +61,7 @@ pip install perpetual
 To use in a Rust project, add the following to your Cargo.toml file to get the package from [crates.io](https://crates.io/crates/perpetual).
 
 ```toml
-perpetual = "0.5.1"
+perpetual = "0.5.2"
 ```
 
 ## Paper

benches/perpetual_benchmarks.rs

@@ -157,6 +157,7 @@ pub fn tree_benchmarks(c: &mut Criterion) {
                     black_box(0.3),
                     black_box(None),
                     black_box(None),
+                    black_box(None),
                 )
                 .unwrap();
         })
@@ -173,12 +174,13 @@ pub fn tree_benchmarks(c: &mut Criterion) {
                     black_box(0.3),
                     black_box(None),
                     black_box(None),
+                    black_box(None),
                 )
                 .unwrap();
         })
     });
     let mut booster = PerpetualBooster::default();
-    booster.fit(&data, &y, None, None, 0.3, None, None).unwrap();
+    booster.fit(&data, &y, None, None, 0.1, None, None, None).unwrap();
     booster_train.bench_function("Predict Booster", |b| {
         b.iter(|| booster.predict(black_box(&data), false))
     });

examples/cal_housing.rs

@@ -123,7 +123,7 @@ fn main() -> Result<(), Box<dyn Error>> {
         .set_num_threads(Some(*num_threads));
 
     let now = SystemTime::now();
-    model.fit(&matrix_train, &y_train, None, None, *budget, None, None)?;
+    model.fit(&matrix_train, &y_train, None, None, *budget, None, None, None)?;
     println!("now.elapsed: {:?}", now.elapsed().unwrap().as_secs_f32());
 
     let trees = model.get_prediction_trees();

examples/cover_types.rs

@@ -148,7 +148,7 @@ fn main() -> Result<(), Box<dyn Error>> {
             .map(|y| if (*y as i32) == i { 1.0 } else { 0.0 })
             .collect();
 
-        model.fit(&matrix_train, &y_tr, None, None, *budget, None, None)?;
+        model.fit(&matrix_train, &y_tr, None, None, *budget, None, None, None)?;
         println!("Completed fitting model number: {}", i);
 
         let trees = model.get_prediction_trees();

examples/titanic.rs

@@ -51,7 +51,7 @@ fn main() -> Result<(), Box<dyn Error>> {
     // the relevant `set_` methods for any parameters you would like to
     // adjust.
     let mut model = PerpetualBooster::default().set_objective(Objective::LogLoss);
-    model.fit(&matrix, &y, None, None, *budget, None, None)?;
+    model.fit(&matrix, &y, None, None, *budget, None, None, None)?;
 
     println!("Model prediction: {:?} ...", &model.predict(&matrix, true)[0..10]);
 

python-package/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "py-perpetual"
-version = "0.5.1"
+version = "0.5.2"
 edition = "2021"
 authors = ["Mutlu Simsek <[email protected]>"]
 homepage = "https://perpetual-ml.com"
@@ -18,8 +18,8 @@ name = "perpetual"
 crate-type = ["cdylib", "rlib"]
 
 [dependencies]
-pyo3 = { version = "0.22.4", features = ["extension-module"] }
-perpetual_rs = {package="perpetual", version = "0.5.1", path = "../" }
+pyo3 = { version = "0.22.5", features = ["extension-module"] }
+perpetual_rs = {package="perpetual", version = "0.5.2", path = "../" }
 numpy = "0.22.0"
 ndarray = "0.16.1"
 serde_plain = { version = "1.0" }

python-package/examples/openml_mnist.ipynb

@@ -0,0 +1,86 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "from perpetual import PerpetualBooster"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import logging\n",
+    "\n",
+    "logging.basicConfig()\n",
+    "logging.getLogger().setLevel(logging.DEBUG)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train = pd.read_csv(\"../../resources/fashion_train_flat.csv\", index_col=False, header=None).to_numpy().reshape(63000, -1)\n",
+    "X_train.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_train = pd.read_csv(\"../../resources/fashion_train_y.csv\", index_col=False, header=None).to_numpy().flatten()\n",
+    "y_train.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = PerpetualBooster(log_iterations=1)\n",
+    "model.fit(X_train, y_train, budget=1.0, timeout=360)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model.number_of_trees"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "py311",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

python-package/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "maturin"
 
 [project]
 name = "perpetual"
-version = "0.5.1"
+version = "0.5.2"
 description = "A self-generalizing gradient boosting machine which doesn't need hyperparameter optimization"
 license = { file = "LICENSE" }
 keywords = [
@@ -19,11 +19,10 @@ keywords = [
 authors = [{ name = "Mutlu Simsek" }]
 readme = "README.md"
 dependencies = ["numpy", "typing-extensions"]
-requires-python = ">=3.8"
+requires-python = ">=3.9"
 classifiers = [
   "Programming Language :: Rust",
   "Programming Language :: Python :: 3",
-  "Programming Language :: Python :: 3.8",
   "Programming Language :: Python :: 3.9",
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",

python-package/python/perpetual/booster.py

@@ -156,6 +156,7 @@ def fit(
         alpha: Union[float, None] = None,
         reset: Union[bool, None] = None,
         categorical_features: Union[Iterable[int], Iterable[str], str, None] = "auto",
+        timeout: Union[float, None] = None,
     ) -> Self:
         """Fit the gradient booster on a provided dataset.
 
@@ -172,6 +173,7 @@ def fit(
             reset: whether to reset the model or continue training.
             categorical_features: The names or indices for categorical features.
                 `auto` for Polars or Pandas categorical data type.
+            timeout: optional fit timeout in seconds
         """
 
         features_, flat_data, rows, cols, categorical_features_, cat_mapping = (
@@ -244,6 +246,7 @@ def fit(
             alpha=alpha,
             reset=reset,
             categorical_features=categorical_features_,  # type: ignore
+            timeout=timeout,
         )
 
         return self

python-package/src/booster.rs

@@ -140,6 +140,7 @@ impl PerpetualBooster {
         alpha: Option<f32>,
         reset: Option<bool>,
         categorical_features: Option<HashSet<usize>>,
+        timeout: Option<f32>,
     ) -> PyResult<()> {
         let flat_data = flat_data.as_slice()?;
         let data = Matrix::new(flat_data, rows, cols);
@@ -152,10 +153,16 @@ impl PerpetualBooster {
             None => None,
         };
 
-        match self
-            .booster
-            .fit(&data, y, sample_weight_, alpha, budget, reset, categorical_features)
-        {
+        match self.booster.fit(
+            &data,
+            y,
+            sample_weight_,
+            alpha,
+            budget,
+            reset,
+            categorical_features,
+            timeout,
+        ) {
             Ok(m) => Ok(m),
             Err(e) => Err(PyValueError::new_err(e.to_string())),
         }?;