Merge pull request #129 from lucasimi/develop

Develop

Author: lucasimi

.github/workflows/bench.yml

@@ -0,0 +1,24 @@
+name: bench
+
+on: 
+  push:
+    branches:
+      - develop
+      - main      
+
+jobs:
+  test-job:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out repository code
+        uses: actions/checkout@v2
+      - name: Install Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10' 
+      - 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.yml

@@ -21,7 +21,7 @@ jobs:
           python -m pip install -e .[dev]
       - name: Run tests and code coverage
         run: | 
-          coverage run --source=src -m unittest discover -s tests
+          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@v3

.gitignore

@@ -1,13 +1,22 @@
 **/__pycache__
 **/*.pyc
+**/*.pyo
 **/*.csv
 **/*.egg-info
 **/.ipynb_checkpoints
 **/*.log
 **/docs/build
 **/*.ipynb
 
+**/*.c
+**/*.cpp
+**/*.so
+**/*.pyd
+**/*.dll
+**/*.dylib
+
 .coverage
 .vscode
 .idea
-dist
+dist/
+build/

app/requirements.txt

@@ -2,4 +2,4 @@ streamlit==1.34.0
 numpy>=1.25.2
 scikit-learn>=1.5.0
 pandas>=2.1.0
-tda-mapper==0.6.0
+tda-mapper==0.7.0

app/streamlit_app.py

@@ -19,6 +19,7 @@
 from tdamapper.cover import CubicalCover, BallCover, TrivialCover
 from tdamapper.clustering import TrivialClustering, FailSafeClustering
 from tdamapper.plot import MapperLayoutInteractive
+from tdamapper.utils.metrics import minkowski
 
 
 MAX_NODES = 1000
@@ -182,7 +183,7 @@ def set_mapper_fig(self, dim, seed, color_feat, agg, cmap, title):
 
 
 def lp_metric(p):
-    return lambda x, y: np.linalg.norm(x - y, ord=p)
+    return minkowski(p)
 
 
 def fix_data(data):
@@ -634,11 +635,11 @@ def mapper_draw_section(color_feat):
     seed = _mapper_seed()
     cmap = _mapper_cmap()
     agg, agg_name = _mapper_aggregation()
-    mapper_plot = st.session_state[S_RESULTS].mapper_plot
+    mapper_graph = st.session_state[S_RESULTS].mapper_graph
     update_button = st.button(
         '🖌️ Draw',
         use_container_width=True,
-        disabled=mapper_plot is None)
+        disabled=mapper_graph is None)
     mapper_fig_outdated = st.session_state[S_RESULTS].mapper_fig_outdated
     auto_rendering = st.session_state[S_RESULTS].auto_rendering
     title = f'{agg_name} of {color_feat}'

docs/source/tdamapper.rst

@@ -33,6 +33,22 @@ tdamapper.clustering
    :undoc-members:
    :show-inheritance:
 
+tdamapper.utils.metrics
+-----------------------
+
+.. automodule:: tdamapper.utils.metrics
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+tdamapper.utils.vptree
+-----------------------
+
+.. automodule:: tdamapper.utils.vptree
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
 tdamapper.plot
 --------------
 

pyproject.toml

@@ -1,10 +1,10 @@
 [build-system]
-requires = ["setuptools>=42", "wheel"]
+requires = ["setuptools>=42", "wheel", "Cython"]
 build-backend = "setuptools.build_meta"
 
 [project]
 name = "tda-mapper"
-version = "0.6.0"
+version = "0.7.0"
 description = "A simple and efficient Python implementation of Mapper algorithm for Topological Data Analysis"
 readme = "README.md"
 authors = [{ name = "Luca Simi", email = "lucasimi90@gmail.com" }]

setup.py

@@ -0,0 +1,11 @@
+from setuptools import setup
+from setuptools.extension import Extension
+from Cython.Build import cythonize
+
+
+setup(
+    ext_modules=cythonize([
+        Extension(
+            "tdamapper.utils._metrics",
+            ["src/tdamapper/utils/_metrics.pyx"])
+    ]))

src/tdamapper/cover.py

@@ -75,21 +75,50 @@ class BallCover(ProximityCover):
     Cover algorithm based on `ball proximity function` implemented as
     :class:`tdamapper.proximity.BallProximity`.
 
-    :param radius: The radius of the open balls, must be positive.
+    :param radius: The radius of the open balls. Must be a positive value.
     :type radius: float
-    :param metric: The (pseudo-)metric function that defines the distance
-        between points, must be symmetric, positive, and satisfy the
-        triangle-inequality, i.e.
-        :math:`metric(x, z) \leq metric(x, y) + metric(y, z)` for every x, y, z
-        in the dataset.
-    :type metric: Callable
-    :param flat: A flag that indicates whether to use a flat or a hierarchical
-        vantage point tree, defaults to False.
-    :type flat: bool, optional
+    :param metric: The metric used to define the distance between points.
+        Accepts any value compatible with `tdamapper.utils.metrics.get_metric`.
+        Defaults to 'euclidean'.
+    :type metric: str or callable
+    :param metric_params: Additional parameters for the metric function, to be
+        passed to `tdamapper.utils.metrics.get_metric`. Defaults to None.
+    :type metric_params: dict, optional
+    :param kind: Specifies whether to use a flat or a hierarchical vantage
+        point tree. Acceptable values are 'flat' or 'hierarchical'. Defaults
+        to 'flat'.
+    :type kind: str
+    :param leaf_capacity: The maximum number of points in a leaf node of the
+        vantage point tree. Must be a positive value. Defaults to 1.
+    :type leaf_capacity: int
+    :param leaf_radius: The radius of the leaf nodes. If not specified, it
+        defaults to the value of `radius`. Must be a positive value. Defaults
+        to None.
+    :type leaf_radius: float, optional
+    :param pivoting: The method used for pivoting in the vantage point tree.
+        Acceptable values are None, 'random', or 'furthest'. Defaults to None.
+    :type pivoting: str or callable, optional
     """
 
-    def __init__(self, radius, metric, flat=True):
-        prox = BallProximity(radius=radius, metric=metric, flat=flat)
+    def __init__(
+        self,
+        radius,
+        metric='euclidean',
+        metric_params=None,
+        kind='flat',
+        leaf_capacity=1,
+        leaf_radius=None,
+        pivoting=None,
+    ):
+        prox = BallProximity(
+            radius=radius,
+            metric=metric,
+            metric_params=metric_params,
+            kind=kind,
+            leaf_capacity=leaf_capacity,
+            leaf_radius=leaf_radius,
+            pivoting=pivoting,
+        )
         super().__init__(proximity=prox)
 
 
@@ -101,19 +130,48 @@ class KNNCover(ProximityCover):
     :param neighbors: The number of neighbors to use for the KNN Proximity
         function, must be positive and less than the length of the dataset.
     :type neighbors: int
-    :param metric: The (pseudo-)metric function that defines the distance
-        between points, must be symmetric, positive, and satisfy the
-        triangle-inequality, i.e.
-        :math:`metric(x, z) \leq metric(x, y) + metric(y, z)` for every x, y, z
-        in the dataset.
-    :type metric: Callable
-    :param flat: A flag that indicates whether to use a flat or a hierarchical
-        vantage point tree, defaults to False.
-    :type flat: bool, optional
+    :param metric: The metric used to define the distance between points.
+        Accepts any value compatible with `tdamapper.utils.metrics.get_metric`.
+        Defaults to 'euclidean'.
+    :type metric: str or callable
+    :param metric_params: Additional parameters for the metric function, to be
+        passed to `tdamapper.utils.metrics.get_metric`. Defaults to None.
+    :type metric_params: dict, optional
+    :param kind: Specifies whether to use a flat or a hierarchical vantage
+        point tree. Acceptable values are 'flat' or 'hierarchical'. Defaults
+        to 'flat'.
+    :type kind: str
+    :param leaf_capacity: The maximum number of points in a leaf node of the
+        vantage point tree. If not specified, it defaults to the value of
+        `neighbors`. Must be a positive value. Defaults to None.
+    :type leaf_capacity: int, optional
+    :param leaf_radius: The radius of the leaf nodes. Must be a positive value.
+        Defaults to 0.0.
+    :type leaf_radius: float
+    :param pivoting: The method used for pivoting in the vantage point tree.
+        Acceptable values are None, 'random', or 'furthest'. Defaults to None.
+    :type pivoting: str or callable, optional
     """
 
-    def __init__(self, neighbors, metric, flat=True):
-        prox = KNNProximity(neighbors=neighbors, metric=metric, flat=flat)
+    def __init__(
+        self,
+        neighbors,
+        metric='euclidean',
+        metric_params=None,
+        kind='flat',
+        leaf_capacity=None,
+        leaf_radius=0.0,
+        pivoting=None,
+    ):
+        prox = KNNProximity(
+            neighbors=neighbors,
+            metric=metric,
+            metric_params=metric_params,
+            kind=kind,
+            leaf_capacity=leaf_capacity,
+            leaf_radius=leaf_radius,
+            pivoting=pivoting,
+        )
         super().__init__(proximity=prox)
 
 
@@ -122,22 +180,52 @@ class CubicalCover(ProximityCover):
     Cover algorithm based on the `cubical proximity function` implemented as
     :class:`tdamapper.proximity.CubicalProximity`.
 
-    :param n_intervals: The number of intervals to use for each dimension, must
-        be positive and less than or equal to the length of the dataset.
+    :param n_intervals: The number of intervals to use for each dimension.
+        Must be positive and less than or equal to the length of the dataset.
     :type n_intervals: int
     :param overlap_frac: The fraction of overlap between adjacent intervals on
         each dimension, must be in the range (0.0, 1.0).
     :type overlap_frac: float
-    :param flat: A flag that indicates whether to use a flat or a hierarchical
-        vantage point tree, defaults to False.
-    :type flat: bool, optional
+    :param metric: The metric used to define the distance between points.
+        Accepts any value compatible with `tdamapper.utils.metrics.get_metric`.
+        Defaults to 'euclidean'.
+    :type metric: str or callable
+    :param metric_params: Additional parameters for the metric function, to be
+        passed to `tdamapper.utils.metrics.get_metric`. Defaults to None.
+    :type metric_params: dict, optional
+    :param kind: Specifies whether to use a flat or a hierarchical vantage
+        point tree. Acceptable values are 'flat' or 'hierarchical'. Defaults
+        to 'flat'.
+    :type kind: str
+    :param leaf_capacity: The maximum number of points in a leaf node of the
+        vantage point tree. Must be a positive value. Defaults to 1.
+    :type leaf_capacity: int
+    :param leaf_radius: The radius of the leaf nodes. If not specified, it
+        defaults to the value of `radius`. Must be a positive value. Defaults
+        to None.
+    :type leaf_radius: float, optional
+    :param pivoting: The method used for pivoting in the vantage point tree.
+        Acceptable values are None, 'random', or 'furthest'. Defaults to None.
+    :type pivoting: str or callable, optional
     """
 
-    def __init__(self, n_intervals, overlap_frac, flat=True):
+    def __init__(
+        self,
+        n_intervals,
+        overlap_frac,
+        kind='flat',
+        leaf_capacity=1,
+        leaf_radius=None,
+        pivoting=None,
+    ):
         prox = CubicalProximity(
             n_intervals=n_intervals, 
             overlap_frac=overlap_frac,
-            flat=flat)
+            kind=kind,
+            leaf_capacity=leaf_capacity,
+            leaf_radius=leaf_radius,
+            pivoting=pivoting,
+        )
         super().__init__(proximity=prox)