Adding pytests

.github/workflows/test.yaml

@@ -0,0 +1,41 @@
+name: test
+
+on: [push,pull_request]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.12"]
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          submodules: true
+
+      - name: Clear conda cache
+        run: conda clean --all -y
+
+      - name: Conda setup
+        uses: conda-incubator/setup-miniconda@v4
+        with:
+          activate-environment: tdbsumstat
+          environment-file: base_environment.yml
+          auto-update-conda: true
+          auto-activate-base: false
+          python-version: ${{ matrix.python-version }}
+          miniforge-version: latest
+
+      - name:  Install project
+        shell: bash -el {0}
+        run: |
+          make dependencies
+          make install
+
+      - name: Run test
+        shell: bash -el {0}
+        run: |
+          make test-unit

.gitignore

@@ -3,3 +3,4 @@ dist/*
 work/
 results/
 .nextflow*
+.coverage

Makefile

@@ -17,6 +17,12 @@ clean:
 	find . -type d -name '__pycache__' -exec rm -rf {} +
 	rm -rf dist build
 
+test-all:
+	pytest --cov=tdbsumstat --cov-report=term-missing
+
+test-unit:
+	pytest tests/unit
+
 dependencies:
 	poetry install --no-root
 

tdbsumstat/utils/harmonize_ingest.py

@@ -34,7 +34,6 @@ def __init__(self, mapping_file: str, uri: str, type_sumstat: str, pvar_file: st
         self.mac = mac
         self.maf = maf
         self.permuted = permuted
-        print(self.permuted)
 
     def create_mapping(self):
         df = pd.read_csv(self.mapping_file, header=None, names=["key", "value"])

tests/unit/core/conftest.py

@@ -0,0 +1,39 @@
+import pytest
+import pandas as pd
+from tdbsumstat.utils.harmonize_ingest import Harmonize
+
+@pytest.fixture
+def create_df_sumstat():
+    ensg00 = pd.read_csv('tests/data/dummy_out_ENSG0000010001.tsv.gz', sep = '\t')
+    return ensg00
+
+@pytest.fixture
+def create_harmonized_obj(tmp_path):
+    obj = Harmonize(
+        mapping_file= 'tests/data/mapping_file_test.csv',
+        uri = str(tmp_path / "test_tiledb_array"),
+        type_sumstat = "qtl",
+        pvar_file = str(tmp_path / "temp_pvar.pvar"),
+        type_trait = 'quant',
+        permuted = False,
+        mac = 10,
+        maf = 0.001,
+            )
+    return obj
+
+@pytest.fixture
+def create_pvar(tmp_path):
+    # Added list brackets to ensure pandas creates rows correctly
+    pvar = pd.DataFrame({
+        "CHROM": ["1"], 
+        "POS": ["1234"], 
+        "SNPID": ["1:1234:A:G"], 
+        "REF": ["A"],
+        "ALT": ["G"]
+    })
+
+    # CRITICAL: index=False prevents pandas from writing a row-number column
+    pvar_path = f"{tmp_path}/temp_pvar.pvar"
+    pvar.to_csv(pvar_path, sep='\t', index=False)
+
+    return pvar_path

tests/unit/core/test_ingestion.py

@@ -0,0 +1,40 @@
+import os 
+import polars as pl
+from tdbsumstat.utils.harmonize_ingest import Harmonize
+
+def test_create_mapping(create_harmonized_obj):
+    # 1. Execute the method
+    create_harmonized_obj.create_mapping()
+    # 2. Check the attribute on the object
+    assert create_harmonized_obj.mapping_types == {
+        "Chr": "CHR",
+        "Gene": "GENE",
+        "cell.type": "CELL",
+        "pos": "POS",
+        "a0": "A1",
+        "a1": "A2",
+        "p": "P",
+        "N": "N",
+        "beta": "BETA",
+        "se": "SE",
+    }
+
+def test_create_tiledb(create_harmonized_obj, tmp_path):
+    create_harmonized_obj.create_tiledb()
+    # 2. Check the attribute on the object
+    assert os.path.exists(f'{tmp_path}/test_tiledb_array')
+
+def test_align_alleles(create_harmonized_obj, create_pvar):
+    create_harmonized_obj.chunk_pl = pl.DataFrame({
+        "CHR": 1,
+        "POS": 1234,
+        "SNPID": "1:1234:A:G",
+        "BETA": -0.1, 
+        "SE": 0.01,
+        "EAF": 0.3
+    })
+    create_harmonized_obj.align_alleles()
+    result_df = create_harmonized_obj.chunk_pl
+    assert result_df.select("BETA").item() == 0.1
+    assert result_df.select("EAF").item() == 0.7
+