Improved CI, updated info. Minor fixes to tests

Author: lucasimi

.flake8

@@ -0,0 +1,5 @@
+[flake8]
+max-line-length = 88
+extend-ignore = E203, W503
+exclude = 
+    docs

.github/workflows/test-bench.yml

@@ -3,22 +3,38 @@ name: test-bench
 on: 
   push:
     branches:
-      - develop
-      - main      
+      - main
+  pull_request:
+    branches:
+      - main 
 
 jobs:
   test-bench-job:
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
     steps:
       - name: Check out repository code
         uses: actions/checkout@v4
+
+      - name: Cache pip
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('pyproject.toml') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-
+
       - name: Install Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10' 
+          python-version: ${{ matrix.python-version }}
+
       - name: Install dependencies
         run: | 
           python -m pip install -e .[dev]
+
       - name: Run benchmarks
         run: | 
           python -m unittest discover -s tests -p 'test_bench_*.py'

.github/workflows/test-unit.yml

@@ -2,27 +2,44 @@ name: test-unit
 
 on: 
   push:
-    branches:
-      - develop
-      - main      
+    branches: 
+      - '**'
+  pull_request:
+    branches: 
+      - '**'
 
 jobs:
   test-unit-job:
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
     steps:
       - name: Check out repository code
         uses: actions/checkout@v4
+
+      - name: Cache pip
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('pyproject.toml') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-
+
       - name: Install Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10' 
+          python-version: ${{ matrix.python-version }}
+      
       - name: Install dependencies
         run: | 
           python -m pip install -e .[dev]
+
       - name: Run tests and code coverage
         run: | 
           coverage run --source=src -m unittest discover -s tests -p 'test_unit_*.py'
           coverage report -m
+
       - name: Upload coverage reports to Codecov
         uses: codecov/codecov-action@v4
         env:

CONTRIBUTING.md

@@ -112,7 +112,11 @@ removed whenever required by a new jump in major version.
 
 We follow [PEP 8](https://peps.python.org/pep-0008/) for Python code style.
 You can run a linter to check your code. The dev dependencies of **tda-mapper**
-include `black` and `isort` to help you manage that.
+include `flake8`, `black` and `isort` to help you manage code style.
+
+```bash
+flake8
+```
 
 ```bash
 black .

benchmarks/benchmark.py

@@ -74,14 +74,14 @@ def run_gm(X, n, p):
         cover=gm.CubicalCover(n_intervals=n, overlap_frac=p),
         clusterer=TrivialEstimator(),
     )
-    mapper_graph = pipe.fit_transform(X)
+    pipe.fit_transform(X)
     t1 = time.time()
     return t1 - t0
 
 
 def run_tm(X, n, p):
     t0 = time.time()
-    mapper_graph = tm.core.MapperAlgorithm(
+    tm.core.MapperAlgorithm(
         cover=tm.cover.CubicalCover(
             n_intervals=n,
             overlap_frac=p,
@@ -99,7 +99,7 @@ def run_tm(X, n, p):
 def run_km(X, n, p):
     t0 = time.time()
     mapper = km.KeplerMapper(verbose=0)
-    graph = mapper.map(
+    mapper.map(
         lens=X,
         X=X,
         cover=km.Cover(n_cubes=n, perc_overlap=p),

docs/source/notebooks/digits.py

@@ -44,7 +44,6 @@
 from sklearn.datasets import load_digits
 from sklearn.decomposition import PCA
 
-from tdamapper.clustering import FailSafeClustering
 from tdamapper.cover import CubicalCover
 from tdamapper.learn import MapperAlgorithm
 from tdamapper.plot import MapperPlot

pyproject.toml

@@ -40,9 +40,9 @@ dev = [
     "coverage[toml]",
     "pandas",
     "scikit-learn<1.6.0",
-    "flake8",
     "black[jupyter]",
-    "isort"
+    "isort",
+    "flake8",
 ]
 
 [project.urls]
@@ -80,4 +80,3 @@ include_trailing_comma = true
 force_grid_wrap = 0
 combine_as_imports = true
 skip = ["venv", ".venv", "build", "dist"]
-

tests/test_bench_cover.py

@@ -38,17 +38,16 @@ def cover(self, vpt, X, r):
 
     def run_bench(self, X, r, dist, vp, **kwargs):
         XX = np.array([[i] + [xi for xi in x] for i, x in enumerate(X)])
-        d = lambda x, y: dist(x[1:], y[1:])
         t0 = time.time()
-        vpt = vp(XX, metric=d, **kwargs)
+        vpt = vp(XX, metric=lambda x, y: dist(x[1:], y[1:]), **kwargs)
         list(self.cover(vpt, XX, r))
         t1 = time.time()
         self.logger.info(f"time: {t1 - t0}")
 
     def test_cover_random(self):
         for r in [1.0, 10.0, 100.0]:
             for n in [100, 1000, 10000]:
-                self.logger.info(f"============ Cover Bench Random ==========")
+                self.logger.info("============ Cover Bench Random ==========")
                 self.logger.info(f"[n: {n}, r: {r}]")
                 X = dataset(num=n)
                 self.logger.info(">>>>>>> HVPT >>>>>>")
@@ -66,7 +65,7 @@ def test_cover_digits(self):
         X, _ = load_digits(return_X_y=True)
         # X = PCA(n_components=3).fit_transform(X)
         for r in [1.0, 10.0, 100.0]:
-            self.logger.info(f"======= Cover Bench Digits =======")
+            self.logger.info("======= Cover Bench Digits =======")
             self.logger.info(f"[r: {r}]")
             self.logger.info(">>>>>>> HVPT >>>>>>")
             self.run_bench(X, r, dist, HVPT, leaf_radius=r, pivoting="random")

tests/test_bench_vptree.py

@@ -77,14 +77,14 @@ def _test_ball_search_naive(self, data, name):
         d(np.array([0.0]), np.array([0.0]))  # jit-compile numba
         t0 = time()
         for val in data:
-            neigh = [x for x in data if d(val, x) <= self.eps]
+            [x for x in data if d(val, x) <= self.eps]
         t1 = time()
         self.logger.info(f"{name}: {t1 - t0}")
 
     def _test_ball_search(self, data, name, vpt):
         t0 = time()
         for val in data:
-            neigh = vpt.ball_search(val, self.eps)
+            vpt.ball_search(val, self.eps)
         t1 = time()
         self.logger.info(f"{name}: {t1 - t0}")
 
@@ -94,13 +94,13 @@ def _test_knn_search_naive(self, data, name):
         t0 = time()
         for val in data:
             data.sort(key=lambda x: d(x, val))
-            neigh = [x for x in data[: self.k]]
+            [x for x in data[: self.k]]
         t1 = time()
         self.logger.info(f"{name}: {t1 - t0}")
 
     def _test_knn_search(self, data, name, vpt):
         t0 = time()
         for val in data:
-            neigh = vpt.knn_search(val, self.k)
+            vpt.knn_search(val, self.k)
         t1 = time()
         self.logger.info(f"{name}: {t1 - t0}")

tests/test_unit_learn.py

@@ -2,15 +2,11 @@
 
 import networkx as nx
 import numpy as np
-from sklearn.cluster import DBSCAN
 from sklearn.utils.estimator_checks import check_estimator
 
 from tdamapper.core import TrivialClustering, TrivialCover
 from tdamapper.cover import BallCover
-from tdamapper.learn import (
-    MapperAlgorithm,
-    MapperClustering,
-)
+from tdamapper.learn import MapperAlgorithm, MapperClustering
 
 
 def euclidean(x, y):