add medoid method for calculation of cluster center

.github/workflows/test_and_deploy.yml

@@ -28,43 +28,43 @@ jobs:
         #python-version: ['3.8', '3.9', '3.10']
         python-version: ['3.10']
 
+    defaults:
+      run:
+        shell: bash -el {0}
     steps:
-      - uses: actions/checkout@v3
-
-      - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
-        with:
-          python-version: ${{ matrix.python-version }}
-
-      # these libraries enable testing on Qt on linux
-      - uses: tlambert03/setup-qt-libs@v1
-
-      # strategy borrowed from vispy for installing opengl libs on windows
-      - name: Install Windows OpenGL
-        if: runner.os == 'Windows'
-        run: |
-          git clone --depth 1 https://github.com/pyvista/gl-ci-helpers.git
-          powershell gl-ci-helpers/appveyor/install_opengl.ps1
-
-      # note: if you need dependencies from conda, considering using
-      # setup-miniconda: https://github.com/conda-incubator/setup-miniconda
-      # and
-      # tox-conda: https://github.com/tox-dev/tox-conda
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          python -m pip install setuptools tox tox-gh-actions
-
-      # this runs the platform-specific tests declared in tox.ini
-      - name: Test with tox
-        uses: GabrielBB/xvfb-action@v1
-        with:
-          run: python -m tox
-        env:
-          PLATFORM: ${{ matrix.platform }}
-
-      - name: Coverage
-        uses: codecov/codecov-action@v2
+    - uses: actions/checkout@v3
+    - name: Set up conda ${{ matrix.python-version }}
+      uses: conda-incubator/setup-miniconda@v2
+      with:
+        mamba-version: "*"
+        activate-environment: napari-tomotwin
+        channel-priority: true
+        python-version: ${{ matrix.python-version }}
+        channels: conda-forge, defaults
+        environment-file: conda_env.yml
+    - run: conda --version
+    - run: conda init bash
+    - run: |
+        which python
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install setuptools setuptools_scm pylint tox tox-gh-actions pytest pytest-coverage twine build
+        pip install .
+    - name: Debug Info
+      run: |
+        which python
+        pip freeze
+    - name: Analysing the code with pylint
+      run: |
+        pylint -E $(git ls-files '*.py')
+    - name: Tests
+      run: |
+        pytest -v --cov=./ --cov-report=xml --cov-config=.coveragerc
+      env:
+        PLATFORM: ${{ matrix.platform }}
+    - name: Upload coverage reports to Codecov
+      uses: codecov/codecov-action@v3
 
   deploy:
     # this will run when you have tagged a commit, starting with "v*"

conda_env.yml

@@ -0,0 +1,14 @@
+name: napari-tomotwin
+channels:
+  - conda-forge
+  - defaults
+dependencies:
+  - python=3.10
+  - napari=0.4.18
+  - pandas
+  - numpy
+  - pyqt
+  - matplotlib
+  - pip:
+    - tqdm
+    - napari-clusters-plotter>=0.7.2

notebooks/test.ipynb

@@ -0,0 +1,43 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Kannst du das lesen?"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [],
+   "metadata": {
+    "collapsed": false
+   }
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

src/napari_tomotwin/_tests/test_make_targets.py

@@ -0,0 +1,129 @@
+import os
+import tempfile
+import unittest
+
+import numpy as np
+import pandas as pd
+from napari_tomotwin.make_targets import _run
+
+from glob import glob
+
+class MyTestCase(unittest.TestCase):
+    def test_make_targets_single_cluster_medoid(self):
+        fake_embedding = {
+            "X": [0, 1, 2],
+            "Y": [0, 1, 2],
+            "Z": [0, 1, 2],
+            "1": [5, 6, 7],
+            "2": [5, 6, 7],
+            "filepath": ["a.mrc","b.mrc","c.mrc"]
+        }
+        cluster = np.array([1,1,1])
+        with tempfile.TemporaryDirectory() as tmpdirname:
+            _run(clusters=cluster,
+                 embeddings=pd.DataFrame(fake_embedding),
+                 average_method_name="Medoid",
+                 output_folder=tmpdirname)
+
+            box_data: pd.DataFrame = pd.read_csv(
+                os.path.join(tmpdirname,"cluster_1_medoid.coords"),
+                delim_whitespace=True,
+                index_col=False,
+                header=None,
+                dtype=float,
+                names=["X","Y","Z"]
+            ).astype(np.int32)  # type: ignore
+            self.assertEqual(box_data.iloc[0, 0], 1)
+            self.assertEqual(box_data.iloc[0, 1], 1)
+            self.assertEqual(box_data.iloc[0, 2], 1)
+
+    def test_make_targets_two_clusters_medoid(self):
+        range(6)
+        fake_embedding = {
+            "X": [0, 1, 2, 8, 9, 10],
+            "Y": [0, 1, 2, 8, 9, 10],
+            "Z": [0, 1, 2, 8, 9, 10],
+            "1": [5, 6, 7, 10, 11, 12],
+            "2": [5, 6, 7, 10, 11, 12],
+        }
+        fake_embedding['filepath'] = [f"{i}.mrc" for i in range(len(fake_embedding["X"]))]
+        cluster = np.array([1,1,1,2,2,2])
+        with tempfile.TemporaryDirectory() as tmpdirname:
+            _run(clusters=cluster,
+                 embeddings=pd.DataFrame(fake_embedding),
+                 average_method_name="Medoid",
+                 output_folder=tmpdirname)
+
+            box_data: pd.DataFrame = pd.read_csv(
+                os.path.join(tmpdirname,"cluster_1_medoid.coords"),
+                delim_whitespace=True,
+                index_col=False,
+                header=None,
+                dtype=float,
+                names=["X","Y","Z"]
+            ).astype(np.int32)  # type: ignore
+            self.assertEqual(box_data.iloc[0, 0], 1)
+            self.assertEqual(box_data.iloc[0, 1], 1)
+            self.assertEqual(box_data.iloc[0, 2], 1)
+
+            box_data: pd.DataFrame = pd.read_csv(
+                os.path.join(tmpdirname, "cluster_2_medoid.coords"),
+                delim_whitespace=True,
+                index_col=False,
+                header=None,
+                dtype=float,
+                names=["X", "Y", "Z"]
+            ).astype(np.int32)  # type: ignore
+            self.assertEqual(box_data.iloc[0, 0], 9)
+            self.assertEqual(box_data.iloc[0, 1], 9)
+            self.assertEqual(box_data.iloc[0, 2], 9)
+
+    def test_make_targets_single_cluster_average(self):
+        fake_embedding = {
+            "X": [0, 1, 2],
+            "Y": [0, 1, 2],
+            "Z": [0, 1, 2],
+            "1": [5, 6, 7],
+            "2": [5, 6, 7],
+            "filepath": ["a.mrc","b.mrc","c.mrc"]
+        }
+        cluster = np.array([1,1,1])
+        with tempfile.TemporaryDirectory() as tmpdirname:
+            _run(clusters=cluster,
+                 embeddings=pd.DataFrame(fake_embedding),
+                 average_method_name="Average",
+                 output_folder=tmpdirname)
+
+            targets_emb: pd.DataFrame = pd.read_pickle(
+                os.path.join(tmpdirname,"cluster_targets.temb"),
+            )
+            self.assertEqual(targets_emb["1"].iloc[0],6)
+            self.assertEqual(targets_emb["2"].iloc[0],6)
+
+    def test_make_targets_single_cluster_no_coords_written(self):
+        fake_embedding = {
+            "X": [0, 1, 2],
+            "Y": [0, 1, 2],
+            "Z": [0, 1, 2],
+            "1": [5, 6, 7],
+            "2": [5, 6, 7],
+            "filepath": ["a.mrc","b.mrc","c.mrc"]
+        }
+        cluster = np.array([1,1,1])
+        with tempfile.TemporaryDirectory() as tmpdirname:
+            _run(clusters=cluster,
+                 embeddings=pd.DataFrame(fake_embedding),
+                 average_method_name="Average",
+                 output_folder=tmpdirname)
+
+            r = glob(os.path.join(tmpdirname,"*.coords"))
+            print(r)
+            self.assertEqual(len(r),0)
+
+
+
+
+
+
+if __name__ == '__main__':
+    unittest.main()