evalsuite-python 0.1.0b1__tar.gz → 0.1.1__tar.gz

{evalsuite_python-0.1.0b1 → evalsuite_python-0.1.1}/CHANGELOG.md

@@ -6,6 +6,27 @@ All notable changes to this project are documented here. The format follows
 
 ## [Unreleased]
 
+## [0.1.1] - 2026-10-08
+
+### Changed
+- Credits: Manoj Kumar C S and Nikhil D Bharadwaj listed as authors and maintainers (README and package metadata).
+
+## [0.1.0] - 2026-10-08
+
+First stable release. Everything from the 0.1.0 roadmap: classification and regression metrics, result
+system, input validation, metric registry, model comparison with confidence intervals and paired tests,
+plots, HTML/CSV/LaTeX/Markdown reports, classification report, command-line tool and benchmarks.
+
+### Changed
+- Development status: Production/Stable.
+- README (PyPI description) now includes the benchmark table against scikit-learn.
+
+## [0.1.0b2]
+
+### Changed
+- `es.plot.calibration`: the legend now sits below the axes by default so it no longer covers the
+  curves; new `legend_loc` argument (`"below"` or any matplotlib location).
+
 ## [0.1.0b1]
 
 Feature-complete for 0.1.0.

{evalsuite_python-0.1.0b1 → evalsuite_python-0.1.1}/PKG-INFO

@@ -1,18 +1,18 @@
 Metadata-Version: 2.5
 Name: evalsuite-python
-Version: 0.1.0b1
+Version: 0.1.1
 Summary: A unified Python framework for machine-learning, clinical, statistical, segmentation, object-detection, uncertainty, and model evaluation.
 Project-URL: Homepage, https://evalsuite-nine.vercel.app
 Project-URL: Documentation, https://evalsuite-nine.vercel.app/docs
 Project-URL: Source, https://github.com/mkcs28/evalsuite-python
 Project-URL: Issues, https://github.com/mkcs28/evalsuite-python/issues
 Project-URL: Changelog, https://github.com/mkcs28/evalsuite-python/blob/main/CHANGELOG.md
-Author: Manoj Kumar C S
-Maintainer: Manoj Kumar C S
+Author: Manoj Kumar C S, Nikhil D Bharadwaj
+Maintainer: Manoj Kumar C S, Nikhil D Bharadwaj
 License-Expression: MIT
 License-File: LICENSE
 Keywords: classification,evaluation,machine learning,metrics,regression,reproducibility,statistics
-Classifier: Development Status :: 4 - Beta
+Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
 Classifier: Operating System :: OS Independent
@@ -62,7 +62,7 @@ Description-Content-Type: text/markdown
 EvalSuite brings classification and regression metrics (with clinical, statistical, segmentation and
 object-detection evaluation on the roadmap) into one consistent, validated, documented framework.
 
-> **Status: beta (0.1.0b1).** Feature-complete for 0.1.0; the stable release follows once this beta is verified.
+> **Status: stable (0.1.1).** Every item on the 0.1.0 roadmap is implemented and verified.
 
 ## Installation
 
@@ -185,8 +185,25 @@ Input files can be CSV, TSV, Parquet or JSON. Output format follows `--format` o
 
 ## Performance
 
-`evaluate()` validates inputs once and computes the confusion matrix once for all metrics: about 10× faster
-than the equivalent separate scikit-learn calls, with identical results. See [BENCHMARKS.md](BENCHMARKS.md).
+Benchmarked against scikit-learn on the same data (fastest of 5 runs; Python 3.12, NumPy 2.5,
+scikit-learn 1.9, Linux x86_64). Every result agrees with scikit-learn to floating-point rounding
+(largest difference 1.1e-16).
+
+| Case | n | EvalSuite (ms) | scikit-learn (ms) | Speed-up | Peak memory EvalSuite / sklearn (MiB) |
+| --- | ---: | ---: | ---: | ---: | ---: |
+| 8 binary label metrics via `evaluate()` | 1,000 | 0.38 | 11.70 | **31.2×** | 0.04 / 0.05 |
+| 8 binary label metrics via `evaluate()` | 100,000 | 10.9 | 116.9 | **10.7×** | 3.2 / 3.1 |
+| 8 binary label metrics via `evaluate()` | 1,000,000 | 108.8 | 1043.6 | **9.6×** | 31.5 / 30.5 |
+| macro F1, 10 classes | 1,000,000 | 88.4 | 139.3 | **1.58×** | 30.5 / 21.8 |
+| ROC AUC, binary | 1,000,000 | 247.4 | 352.5 | **1.42×** | 91.6 / 76.3 |
+| MAE, MSE, RMSE, R² via `evaluate()` | 1,000 | 0.12 | 0.90 | **7.2×** | 0.03 / 0.02 |
+| MAE, MSE, RMSE, R² via `evaluate()` | 1,000,000 | 29.3 | 20.1 | 0.69× | 22.9 / 15.3 |
+
+`evaluate()` validates inputs once and builds the confusion matrix once for all metrics, which is where the
+speed-up comes from. Large regression arrays are slower because EvalSuite checks every value for NaN,
+infinity, shape and dtype before computing. Reproduce on your machine with `evalsuite benchmark`; full
+table and notes in
+[BENCHMARKS.md](https://github.com/mkcs28/evalsuite-python/blob/main/BENCHMARKS.md).
 
 ## Metrics in this release
 
@@ -225,6 +242,10 @@ ruff check . && ruff format --check . && mypy
 - Website and documentation: https://evalsuite-nine.vercel.app
 - Website source: https://github.com/mkcs28/evalsuite
 
+## Credits
+
+Authors and maintainers: **Manoj Kumar C S** and **Nikhil D Bharadwaj**.
+
 ## License
 
 MIT. See [LICENSE](LICENSE).

{evalsuite_python-0.1.0b1 → evalsuite_python-0.1.1}/README.md

@@ -10,7 +10,7 @@
 EvalSuite brings classification and regression metrics (with clinical, statistical, segmentation and
 object-detection evaluation on the roadmap) into one consistent, validated, documented framework.
 
-> **Status: beta (0.1.0b1).** Feature-complete for 0.1.0; the stable release follows once this beta is verified.
+> **Status: stable (0.1.1).** Every item on the 0.1.0 roadmap is implemented and verified.
 
 ## Installation
 
@@ -133,8 +133,25 @@ Input files can be CSV, TSV, Parquet or JSON. Output format follows `--format` o
 
 ## Performance
 
-`evaluate()` validates inputs once and computes the confusion matrix once for all metrics: about 10× faster
-than the equivalent separate scikit-learn calls, with identical results. See [BENCHMARKS.md](BENCHMARKS.md).
+Benchmarked against scikit-learn on the same data (fastest of 5 runs; Python 3.12, NumPy 2.5,
+scikit-learn 1.9, Linux x86_64). Every result agrees with scikit-learn to floating-point rounding
+(largest difference 1.1e-16).
+
+| Case | n | EvalSuite (ms) | scikit-learn (ms) | Speed-up | Peak memory EvalSuite / sklearn (MiB) |
+| --- | ---: | ---: | ---: | ---: | ---: |
+| 8 binary label metrics via `evaluate()` | 1,000 | 0.38 | 11.70 | **31.2×** | 0.04 / 0.05 |
+| 8 binary label metrics via `evaluate()` | 100,000 | 10.9 | 116.9 | **10.7×** | 3.2 / 3.1 |
+| 8 binary label metrics via `evaluate()` | 1,000,000 | 108.8 | 1043.6 | **9.6×** | 31.5 / 30.5 |
+| macro F1, 10 classes | 1,000,000 | 88.4 | 139.3 | **1.58×** | 30.5 / 21.8 |
+| ROC AUC, binary | 1,000,000 | 247.4 | 352.5 | **1.42×** | 91.6 / 76.3 |
+| MAE, MSE, RMSE, R² via `evaluate()` | 1,000 | 0.12 | 0.90 | **7.2×** | 0.03 / 0.02 |
+| MAE, MSE, RMSE, R² via `evaluate()` | 1,000,000 | 29.3 | 20.1 | 0.69× | 22.9 / 15.3 |
+
+`evaluate()` validates inputs once and builds the confusion matrix once for all metrics, which is where the
+speed-up comes from. Large regression arrays are slower because EvalSuite checks every value for NaN,
+infinity, shape and dtype before computing. Reproduce on your machine with `evalsuite benchmark`; full
+table and notes in
+[BENCHMARKS.md](https://github.com/mkcs28/evalsuite-python/blob/main/BENCHMARKS.md).
 
 ## Metrics in this release
 
@@ -173,6 +190,10 @@ ruff check . && ruff format --check . && mypy
 - Website and documentation: https://evalsuite-nine.vercel.app
 - Website source: https://github.com/mkcs28/evalsuite
 
+## Credits
+
+Authors and maintainers: **Manoj Kumar C S** and **Nikhil D Bharadwaj**.
+
 ## License
 
 MIT. See [LICENSE](LICENSE).

{evalsuite_python-0.1.0b1 → evalsuite_python-0.1.1}/pyproject.toml

@@ -10,11 +10,11 @@ readme = "README.md"
 license = "MIT"
 license-files = ["LICENSE"]
 requires-python = ">=3.9"
-authors = [{ name = "Manoj Kumar C S" }]
-maintainers = [{ name = "Manoj Kumar C S" }]
+authors = [{ name = "Manoj Kumar C S" }, { name = "Nikhil D Bharadwaj" }]
+maintainers = [{ name = "Manoj Kumar C S" }, { name = "Nikhil D Bharadwaj" }]
 keywords = ["evaluation", "metrics", "machine learning", "statistics", "classification", "regression", "reproducibility"]
 classifiers = [
-  "Development Status :: 4 - Beta",
+  "Development Status :: 5 - Production/Stable",
   "Intended Audience :: Science/Research",
   "Intended Audience :: Developers",
   "Operating System :: OS Independent",

{evalsuite_python-0.1.0b1 → evalsuite_python-0.1.1}/src/evalsuite/plot.py

@@ -190,9 +190,13 @@ def calibration(
     strategy: str = "uniform",
     pos_label: Any = None,
     sample_weight: Optional[ArrayLike] = None,
+    legend_loc: str = "below",
 ) -> Axes:
     """Reliability diagram: observed frequency against mean predicted probability per bin, with ECE and Brier
-    score in the legend; the diagonal is perfect calibration."""
+    score in the legend; the diagonal is perfect calibration.
+
+    ``legend_loc="below"`` (default) puts the legend under the axes so it never covers the curves; any
+    matplotlib location (e.g. ``"upper left"``) places it inside instead."""
     from .classification.metrics import brier_score, calibration_curve, expected_calibration_error
 
     ax = _axes(ax)
@@ -218,7 +222,10 @@ def calibration(
         ylim=(-0.01, 1.01),
     )
     ax.set_aspect("equal")
-    ax.legend(loc="upper left", frameon=False)
+    if legend_loc == "below":
+        ax.legend(loc="upper center", bbox_to_anchor=(0.5, -0.14), frameon=False, fontsize="small")
+    else:
+        ax.legend(loc=legend_loc, frameon=False)  # type: ignore[call-overload]
     return ax
 
 

{evalsuite_python-0.1.0b1 → evalsuite_python-0.1.1}/src/evalsuite/version.py

@@ -1,3 +1,3 @@
 """Package version (single source of truth, read by the build backend)."""
 
-__version__ = "0.1.0b1"
+__version__ = "0.1.1"

{evalsuite_python-0.1.0b1 → evalsuite_python-0.1.1}/tests/output/test_plot.py

@@ -121,3 +121,13 @@ def test_matplotlib_is_optional(monkeypatch) -> None:
     monkeypatch.setattr(builtins, "__import__", fake)
     with pytest.raises(es.OptionalDependencyError, match=r"evalsuite-python\[plot\]"):
         es.plot.roc([0, 1], [0.2, 0.8])
+
+
+def test_calibration_legend_below_by_default_and_configurable():
+    y = np.array([0, 1, 0, 1, 1, 0, 1, 0])
+    p = np.array([0.1, 0.8, 0.3, 0.7, 0.9, 0.2, 0.6, 0.4])
+    ax = es.plot.calibration(y, p)
+    anchor = ax.get_legend().get_bbox_to_anchor().transformed(ax.transAxes.inverted())
+    assert anchor.y0 < 0  # outside, under the axes
+    ax2 = es.plot.calibration(y, p, legend_loc="upper left")
+    assert ax2.get_legend()._loc == 2