Fix tests (#9)

Author: flying-sheep

.github/workflows/pytest.yml

@@ -11,38 +11,30 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v3
 
+      - name: Install Poetry
+        run: |
+          pipx install poetry
+
       - name: Setup Python
         id: setup_py
         uses: actions/setup-python@v4
         with:
           python-version: '3.10'
-
-      - name: Install Poetry
-        uses: snok/install-poetry@v1
-        with:
-          virtualenvs-create: true
-          virtualenvs-in-project: true
-
-      - name: Load cached venv
-        id: cached-poetry-dependencies
-        uses: actions/cache@v3
-        with:
-          path: .venv
-          key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('poetry.lock') }}
+          cache: 'poetry'
 
       - name: Poetry install
         run: |
+          poetry lock --check
           poetry install --extras tests --extras docs --extras annlibs
-        if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
 
       - name: Run test suite
         run: |
-          .venv/bin/pytest
+          poetry run pytest -v --color=yes
 
       - name: Run black
         run: |
-          .venv/bin/black --check sklearn_ann
+          poetry run black --check sklearn_ann
 
       - name: Run flake8
         run: |
-          .venv/bin/flake8 sklearn_ann
+          poetry run flake8 sklearn_ann

.gitignore

@@ -1,2 +1,6 @@
+__pycache__/
 docs/_build/
 activate.sh
+
+# IDEs
+.vscode/

docs/conf.py

@@ -19,9 +19,9 @@
 
 # -- Project information -----------------------------------------------------
 
-project = 'sklearn-ann'
-copyright = '2021, Frankie Robertson'
-author = 'Frankie Robertson'
+project = "sklearn-ann"
+copyright = "2021, Frankie Robertson"
+author = "Frankie Robertson"
 
 
 # -- General configuration ---------------------------------------------------
@@ -30,33 +30,33 @@
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
 extensions = [
-    'sphinx.ext.autodoc',
-    'sphinx.ext.autosummary',
-    'numpydoc',
-    'sphinx_issues',
-    'sphinx.ext.viewcode',
+    "sphinx.ext.autodoc",
+    "sphinx.ext.autosummary",
+    "numpydoc",
+    "sphinx_issues",
+    "sphinx.ext.viewcode",
 ]
 
 # Add any paths that contain templates here, relative to this directory.
-templates_path = ['_templates']
+templates_path = ["_templates"]
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
 # This pattern also affects html_static_path and html_extra_path.
-exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
 
 
 # -- Options for HTML output -------------------------------------------------
 
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = 'sphinx_rtd_theme'
+html_theme = "sphinx_rtd_theme"
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+html_static_path = ["_static"]
 html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]
 
 autodoc_mock_imports = ["annoy", "faiss", "pynndescent", "nmslib"]

examples/rnn_dbscan_big.py

@@ -25,7 +25,7 @@ def fetch_mnist():
     return mnist.data / 255, mnist.target
 
 
-memory = Memory('./mnist')
+memory = Memory("./mnist")
 
 X, y = memory.cache(fetch_mnist)()
 
@@ -44,21 +44,22 @@ def run_rnn_dbscan(neighbor_transformer, n_neighbors, **kwargs):
     n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
     n_noise_ = list(labels).count(-1)
 
-    print('Estimated number of clusters: %d' % n_clusters_)
-    print('Estimated number of noise points: %d' % n_noise_)
+    print("Estimated number of clusters: %d" % n_clusters_)
+    print("Estimated number of noise points: %d" % n_noise_)
     print("Homogeneity: %0.3f" % metrics.homogeneity_score(y, labels))
     print("Completeness: %0.3f" % metrics.completeness_score(y, labels))
     print("V-measure: %0.3f" % metrics.v_measure_score(y, labels))
-    print("Adjusted Rand Index: %0.3f"
-          % metrics.adjusted_rand_score(y, labels))
-    print("Adjusted Mutual Information: %0.3f"
-          % metrics.adjusted_mutual_info_score(y, labels))
-    print("Silhouette Coefficient: %0.3f"
-          % metrics.silhouette_score(X, labels))
+    print("Adjusted Rand Index: %0.3f" % metrics.adjusted_rand_score(y, labels))
+    print(
+        "Adjusted Mutual Information: %0.3f"
+        % metrics.adjusted_mutual_info_score(y, labels)
+    )
+    print("Silhouette Coefficient: %0.3f" % metrics.silhouette_score(X, labels))
 
 
 if __name__ == "__main__":
     import code
+
     print("Now you can import your chosen transformer_cls and run:")
     print("run_rnn_dbscan(transformer_cls, n_neighbors, **params)")
     print("e.g.")

examples/rnn_dbscan_simple.py

@@ -22,8 +22,9 @@
 # #############################################################################
 # Generate sample data
 centers = [[1, 1], [-1, -1], [1, -1]]
-X, labels_true = make_blobs(n_samples=750, centers=centers, cluster_std=0.4,
-                            random_state=0)
+X, labels_true = make_blobs(
+    n_samples=750, centers=centers, cluster_std=0.4, random_state=0
+)
 
 X = StandardScaler().fit_transform(X)
 
@@ -38,40 +39,51 @@
 n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
 n_noise_ = list(labels).count(-1)
 
-print('Estimated number of clusters: %d' % n_clusters_)
-print('Estimated number of noise points: %d' % n_noise_)
+print("Estimated number of clusters: %d" % n_clusters_)
+print("Estimated number of noise points: %d" % n_noise_)
 print("Homogeneity: %0.3f" % metrics.homogeneity_score(labels_true, labels))
 print("Completeness: %0.3f" % metrics.completeness_score(labels_true, labels))
 print("V-measure: %0.3f" % metrics.v_measure_score(labels_true, labels))
-print("Adjusted Rand Index: %0.3f"
-      % metrics.adjusted_rand_score(labels_true, labels))
-print("Adjusted Mutual Information: %0.3f"
-      % metrics.adjusted_mutual_info_score(labels_true, labels))
-print("Silhouette Coefficient: %0.3f"
-      % metrics.silhouette_score(X, labels))
+print("Adjusted Rand Index: %0.3f" % metrics.adjusted_rand_score(labels_true, labels))
+print(
+    "Adjusted Mutual Information: %0.3f"
+    % metrics.adjusted_mutual_info_score(labels_true, labels)
+)
+print("Silhouette Coefficient: %0.3f" % metrics.silhouette_score(X, labels))
 
 # #############################################################################
 # Plot result
 import matplotlib.pyplot as plt
 
 # Black removed and is used for noise instead.
 unique_labels = set(labels)
-colors = [plt.cm.Spectral(each)
-          for each in np.linspace(0, 1, len(unique_labels))]
+colors = [plt.cm.Spectral(each) for each in np.linspace(0, 1, len(unique_labels))]
 for k, col in zip(unique_labels, colors):
     if k == -1:
         # Black used for noise.
         col = [0, 0, 0, 1]
 
-    class_member_mask = (labels == k)
+    class_member_mask = labels == k
 
     xy = X[class_member_mask & core_samples_mask]
-    plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),
-             markeredgecolor='k', markersize=14)
+    plt.plot(
+        xy[:, 0],
+        xy[:, 1],
+        "o",
+        markerfacecolor=tuple(col),
+        markeredgecolor="k",
+        markersize=14,
+    )
 
     xy = X[class_member_mask & ~core_samples_mask]
-    plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),
-             markeredgecolor='k', markersize=6)
-
-plt.title('Estimated number of clusters: %d' % n_clusters_)
+    plt.plot(
+        xy[:, 0],
+        xy[:, 1],
+        "o",
+        markerfacecolor=tuple(col),
+        markeredgecolor="k",
+        markersize=6,
+    )
+
+plt.title("Estimated number of clusters: %d" % n_clusters_)
 plt.show()