Add column2Vec test workflow

.github/workflows/py_test.yml

@@ -48,10 +48,10 @@ jobs:
         run: |
           black --check $(git ls-files '*.py')
 
-  python-tests:
+  similarity-tests:
     env:
-      TEST_FILES: test/test_types.py test/test_metadata.py test/test_comparator.py test/test_column2VecCache.py
-    name: Run Python Tests
+      TEST_FILES: test/test_types.py test/test_metadata.py test/test_comparator.py
+    name: Run Similarity Tests
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
@@ -69,7 +69,7 @@ jobs:
           pip install coverage pytest
 
       - name: Run tests
-        run: coverage run --source='similarity,column2Vec' -m pytest $TEST_FILES
+        run: coverage run --source='similarity' -m pytest $TEST_FILES
 
       - name: Show coverage
         run: coverage report -m --omit=".*.ipynb"
@@ -90,6 +90,52 @@ jobs:
       - uses: actions/upload-artifact@v4
         if: github.event_name == 'pull_request'
         with:
-          name: coverage
+          name: Similarity coverage
+          path: coverage.xml
+          retention-days: 1
+
+  column2vec-tests:
+    env:
+      TEST_FILES: test/test_column2VecCache.py test/test_column2Vec.py
+    name: Run Column2Vec Tests
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+          cache: 'pip'
+
+      - name: Install dependencies
+        run: |
+          pip install -r requirements.txt
+          pip install coverage pytest pytest-xdist
+
+      - name: Run tests
+        run: coverage run --source='column2Vec' -m pytest -n auto $TEST_FILES
+
+      - name: Show coverage
+        run: coverage report -m --omit=".*.ipynb"
+
+      - name: Create coverage file
+        if: github.event_name == 'pull_request'
+        run: coverage xml
+
+      - name: Get Cover
+        if: github.event_name == 'pull_request'
+        uses: orgoro/[email protected]
+        with:
+          coverageFile: coverage.xml
+          token: ${{ secrets.GITHUB_TOKEN }}
+          thresholdAll: 0.7
+          thresholdNew: 0.9
+
+      - uses: actions/upload-artifact@v4
+        if: github.event_name == 'pull_request'
+        with:
+          name: Column2Vec coverage
           path: coverage.xml
           retention-days: 1

constants.py

@@ -51,7 +51,12 @@ class TrainedModel:
     """
 
     configure()
-    __model = SentenceTransformer("paraphrase-multilingual-mpnet-base-v2")
+    __model = SentenceTransformer(
+        "paraphrase-multilingual-mpnet-base-v2",
+        tokenizer_kwargs={
+            "clean_up_tokenization_spaces": True,
+        },
+    )
 
     def set_module(self, model: SentenceTransformer):
         """

test/test_column2Vec.py

@@ -18,7 +18,7 @@
 # MODEL = 'all-mpnet-base-v2'  # bert-base-nli-mean-tokens
 MODEL = 'bert-base-nli-mean-tokens'  #
 THIS_DIR = os.path.dirname(os.path.abspath(__file__))
-
+TRANSFORMER = SentenceTransformer(MODEL)
 
 def vectors_are_same(vec1, vec2):
     for i, j in zip(vec1, vec2):
@@ -33,7 +33,7 @@ def get_vectors(function, data):
     count = 1
     for key in data:
         # print("Processing column: " + key + " " + str(round((count / len(data)) * 100, 2)) + "%")
-        result[key] = function(data[key], SentenceTransformer(MODEL), key)
+        result[key] = function(data[key], TRANSFORMER, key)
         count += 1
     end = time.time()
     print(f"ELAPSED TIME :{end - start}")
@@ -60,7 +60,7 @@ def get_data(files):
 class TestSimilarityOfVectors(unittest.TestCase):
     @classmethod
     def setUpClass(cls):
-        cls.model = SentenceTransformer(MODEL)
+        cls.model = TRANSFORMER
         file_m2 = os.path.join(THIS_DIR, os.pardir, 'data/netflix_titles.csv')
         # make an array of all the files
         files = [file_m2]
@@ -76,7 +76,7 @@ def setUpClass(cls):
             stop += 1
 
     def test_column2vec_as_sentence(self):
-        model = SentenceTransformer(MODEL)
+        model = TRANSFORMER
         self.assertTrue(
             vectors_are_same(column2vec_as_sentence(self.first, model, "a"),
                              column2vec_as_sentence(self.first, self.model, "b")))
@@ -87,7 +87,7 @@ def test_column2vec_as_sentence(self):
                              column2vec_as_sentence(self.third, self.model, "f")))
 
     def test_column2vec_as_sentence_clean(self):
-        model = SentenceTransformer(MODEL)
+        model = TRANSFORMER
         self.assertTrue(vectors_are_same(column2vec_as_sentence_clean(self.first, model, "g"),
                                          column2vec_as_sentence_clean(self.first, self.model, "h")))
         self.assertTrue(vectors_are_same(column2vec_as_sentence_clean(self.second, model, "i"),
@@ -96,7 +96,7 @@ def test_column2vec_as_sentence_clean(self):
                                          column2vec_as_sentence_clean(self.third, self.model, "l")))
 
     def test_column2vec_as_sentence_clean_uniq(self):
-        model = SentenceTransformer(MODEL)
+        model = TRANSFORMER
         self.assertTrue(vectors_are_same(column2vec_as_sentence_clean_uniq(self.first, model, "m"),
                                          column2vec_as_sentence_clean_uniq(self.first, self.model, "n")))
         self.assertTrue(vectors_are_same(column2vec_as_sentence_clean_uniq(self.second, model, "o"),
@@ -105,14 +105,14 @@ def test_column2vec_as_sentence_clean_uniq(self):
                                          column2vec_as_sentence_clean_uniq(self.third, self.model, "r")))
 
     def test_column2vec_avg(self):
-        model = SentenceTransformer(MODEL)
+        model = TRANSFORMER
         self.assertTrue(vectors_are_same(column2vec_avg(self.first, model, "v"),
                                          column2vec_avg(self.first, self.model, "s")))
         # self.assertTrue(vectors_are_same(column2vec_avg(self.second, model), column2vec_avg(self.second, self.model)))
         # self.assertTrue(vectors_are_same(column2vec_avg(self.third, model), column2vec_avg(self.third, self.model)))
 
     def test_column2vec_weighted_avg(self):
-        model = SentenceTransformer(MODEL)
+        model = TRANSFORMER
         self.assertTrue(vectors_are_same(column2vec_weighted_avg(self.first, model, "u"),
                                          column2vec_weighted_avg(self.first, self.model, "w")))
         # self.assertTrue(vectors_are_same(column2vec_weighted_avg(self.second, model),
@@ -121,12 +121,12 @@ def test_column2vec_weighted_avg(self):
         # column2vec_weighted_avg(self.third, self.model)))
 
     def test_column2vec_sum(self):
-        model = SentenceTransformer(MODEL)
+        model = TRANSFORMER
         self.assertTrue(vectors_are_same(column2vec_sum(self.first, model, "x"),
                                          column2vec_sum(self.first, self.model, "y")))
 
     def test_column2vec_weighted_sum(self):
-        model = SentenceTransformer(MODEL)
+        model = TRANSFORMER
         self.assertTrue(vectors_are_same(column2vec_weighted_sum(self.first, model, "z"),
                                          column2vec_weighted_sum(self.first, self.model, "ab")))