Merge pull request #37 from VIDA-NYU/setup-test-ci

Setup CI infrastructure for automated tests

Author: aecio

.github/workflows/build.yml

@@ -0,0 +1,30 @@
+name: Tests
+
+on: [push, pull_request]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.8", "3.9", "3.10", "3.11"]
+
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install pytest jupyter
+
+      - name: Install the bdikit package
+        run: |
+          pip install -e .
+
+      - name: Test with pytest
+        run: |
+          pytest

Makefile

@@ -0,0 +1,6 @@
+all: test
+
+PHONY: test
+
+test:
+	python3 -m pytest

requirements.txt

@@ -8,3 +8,5 @@ scikit-learn
 tabulate
 flair
 requests
+scipy<1.13
+matplotlib<3.9

tests/__init__.py

@@ -0,0 +1,39 @@
+import unittest
+import pandas as pd
+from bdikit.mapping_algorithms.column_mapping.algorithms import (
+    SimFloodAlgorithm,
+    JaccardDistanceAlgorithm,
+    DistributionBasedAlgorithm,
+    ComaAlgorithm,
+    CupidAlgorithm,
+)
+
+
+class ColumnMappingTest(unittest.TestCase):
+    def test_basic_column_mapping_algorithms(self):
+        for ColumnMatcher in [
+            SimFloodAlgorithm,
+            JaccardDistanceAlgorithm,
+            DistributionBasedAlgorithm,
+            ComaAlgorithm,
+            CupidAlgorithm,
+        ]:
+            # given
+            table1 = pd.DataFrame(
+                {"column_1": ["a1", "b1", "c1"], "col_2": ["a2", "b2", "c2"]}
+            )
+            table2 = pd.DataFrame(
+                {"column_1a": ["a1", "b1", "c1"], "col2": ["a2", "b2", "c2"]}
+            )
+            column_matcher = ColumnMatcher(dataset=table1, global_table=table2)
+
+            # when
+            mapping = column_matcher.map()
+
+            # then
+            print(mapping)
+            self.assertEqual(
+                {"column_1": "column_1a", "col_2": "col2"},
+                mapping,
+                msg=f"{ColumnMatcher.__name__} failed to map columns",
+            )