update unit test

Author: erdogant

.github/workflows/codeql-analysis.yml

@@ -0,0 +1,71 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+name: "CodeQL"
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    # The branches below must be a subset of the branches above
+    branches: [master]
+  schedule:
+    - cron: '0 7 * * 6'
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-latest
+
+    strategy:
+      fail-fast: false
+      matrix:
+        # Override automatic language detection by changing the below list
+        # Supported options are ['csharp', 'cpp', 'go', 'java', 'javascript', 'python']
+        language: ['python']
+        # Learn more...
+        # https://docs.github.com/en/github/finding-security-vulnerabilities-and-errors-in-your-code/configuring-code-scanning#overriding-automatic-language-detection
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2
+      with:
+        # We must fetch at least the immediate parents so that if this is
+        # a pull request then we can checkout the head.
+        fetch-depth: 2
+
+    # If this run was triggered by a pull request event, then checkout
+    # the head of the pull request instead of the merge commit.
+    - run: git checkout HEAD^2
+      if: ${{ github.event_name == 'pull_request' }}
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v1
+      with:
+        languages: ${{ matrix.language }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file. 
+        # Prefix the list here with "+" to use these queries and those in the config file.
+        # queries: ./path/to/local/query, your-org/your-repo/queries@main
+
+    # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
+    # If this step fails, then you should remove it and run the build manually (see below)
+    - name: Autobuild
+      uses: github/codeql-action/autobuild@v1
+
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 https://git.io/JvXDl
+
+    # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
+    #    and modify them (or add more) to build your code if your project
+    #    uses a compiled language
+
+    #- run: |
+    #   make bootstrap
+    #   make release
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v1

.github/workflows/pytest.yml

@@ -0,0 +1,29 @@
+name: Pytest for clusteval
+on: [push]
+
+jobs:
+  example-1:
+    name: Ex1 (${{ matrix.python-version }}, ${{ matrix.os }})
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: ["ubuntu-latest"]
+        python-version: [3.6, 3.8, 3.9]
+    steps:
+      - uses: actions/checkout@v2
+      - uses: conda-incubator/setup-miniconda@v2
+        with:
+          auto-update-conda: true
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          # install pandas because we have unittests that include pd.DataFrame()
+          pip install -r requirements.txt
+          #pip install pandas
+      - name: Test with pytest
+        run: |
+          pip install pytest
+          pytest
+         

clusteval/__init__.py

@@ -11,7 +11,7 @@
 
 __author__ = 'Erdogan Tasksen'
 __email__ = '[email protected]'
-__version__ = '2.1.2'
+__version__ = '2.1.3'
 
 
 __doc__ = """

clusteval/tests/__init__.py

@@ -2,26 +2,25 @@
 from sklearn.datasets import make_blobs
 import pandas as pd
 import numpy as np
+import unittest
 
 
-# %%
-def test_fit():
-    X, y_true = make_blobs(n_samples=500, centers=6, n_features=10)
-    # ce = clusteval(evaluate='agglomerative', cluster=cluster, metric=metric, linkage=linkage, min_clust=min_clust, max_clust=max_clust, verbose=3)
-    # results = ce.fit(X)
-    # print('Clusters: %s' %(str(np.unique(results['labx']))))
+class TestCLUSTEVAL(unittest.TestCase):
+
+    def test_fit(self):
+        X, y_true = make_blobs(n_samples=500, centers=6, n_features=10)
+        # X, y_true = make_blobs(n_samples=50, centers=[[1, 1], [-1, -1], [1, -1]], cluster_std=0.4,random_state=0)
 
-    # X, y_true = make_blobs(n_samples=50, centers=[[1, 1], [-1, -1], [1, -1]], cluster_std=0.4,random_state=0)
-    # Set all parameters to be evaluated
-    clusters = ['agglomerative', 'kmeans', 'dbscan']
-    evaluates = ['silhouette', 'dbindex', 'derivative']
-    metrics = ['euclidean', 'hamming']
-    linkages = ['ward', 'single', 'complete']
-    min_clusts = [1, 2, 10]
-    max_clusts = [1, 10, 2]
+        # Set all parameters to be evaluated
+        clusters = ['agglomerative', 'kmeans', 'dbscan']
+        evaluates = ['silhouette', 'dbindex', 'derivative']
+        metrics = ['euclidean', 'hamming']
+        linkages = ['ward', 'single', 'complete']
+        min_clusts = [1, 2, 10]
+        max_clusts = [1, 10, 2]
 
-    # Evaluate across all paramters
-    out = parameter_gridtest(X, y_true, clusters, evaluates, metrics, linkages, min_clusts, max_clusts)
+        # Evaluate across all paramters
+        out = parameter_gridtest(X, y_true, clusters, evaluates, metrics, linkages, min_clusts, max_clusts)
 
 # %%
 def parameter_gridtest(X, y_true, clusters, evaluates, metrics, linkages, min_clusts, max_clusts):
@@ -62,15 +61,15 @@ def parameter_gridtest(X, y_true, clusters, evaluates, metrics, linkages, min_cl
                                     print(len(np.unique(results['labx'])))
                                     print(len(np.unique(y_true)))
                                     assert len(np.unique(results['labx']))==len(np.unique(y_true))
-                                    
+
                             except ValueError as err:
                                 assert not 'clusteval' in err.args
                                 status = err.args
                                 print(err.args)
                                 # ce.results=None
-    
+
                             # out.append(ce.results)
-                            count=count+1
+                            count=count + 1
 
     print('Fin! Total number of models evaluated with different paramters: %.0d' %(count))
     return(pd.DataFrame(out))