Add github actions for tests and pre-commit

.github/workflows/pre-commit-check.yml

@@ -0,0 +1,28 @@
+
+name: Pre-commit
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.11", "3.12"]
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v3
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install pre-commit
+      run: pip install pre-commit
+    - name: Run pre-commit
+      run: pre-commit run --all-files

.github/workflows/python-package.yml

@@ -0,0 +1,43 @@
+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python
+
+name: Python package
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.11", "3.12"]
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v3
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install packagge
+      run: |
+        python -m pip install --upgrade pip pytest pytest-cov
+        python -m pip install -e .
+
+    - name: Create tasks needed for testing
+      run: |
+          python scripts/tasks_retrival/gene2gene_task_creation.py --allow-downloads True
+          python scripts/tasks_retrival/Genecorpus_tasks_creation.py --allow-downloads True
+          python scripts/tasks_retrival/HLA_task_creation.py --allow-downloads True
+          python scripts/tasks_retrival/HPA_tasks_creation.py --allow-downloads True
+          python scripts/tasks_retrival/humantfs_task_creation.py --allow-downloads True
+          python scripts/tasks_retrival/Reactome_tasks_creation.py --use-local-files False
+
+    - name: Test with pytest
+      run: |
+         python -m pytest -v --durations=40 --cov=gene_benchmark--cov-fail-under=70 gene_benchmark

.pre-commit-config.yaml

@@ -1,35 +1,3 @@
-###################################
-# GETTING STARTED WITH PRE-COMMIT #
-###################################
-# To start using this pre-commit file instapp pre-commit:
-#   pip install pre-commit
-# Install hooks:
-#   pre-commit install
-# Note:  Multiple changes to the same file by a hook will block git commits.
-#    Therefore hooks should be added one at a time.
-# Apply to all files without commiting:
-#   pre-commit run --all-files
-# For more info, see https://pre-commit.com/
-
-##########
-# UPDATE #
-##########
-# Update this file (will change version numbers of tools, which could lead to
-# simultaneous changes that require manual resolution):
-#   pre-commit autoupdate
-
-#############
-# CUSTOMIZE #
-#############
-# To customize per-hook behavior you can use:
-#  1) the `args` option to pass cli args to the tool
-#  2) per-tool config files such as mypy.ini, .pylintrc etc in repo root
-#  3) the shared config file pyproject.toml in repo root
-
-#############
-# UNINSTALL #
-#############
-# pre-commit uninstall
 repos:
   # default hooks provided by the pre-commit project
   - repo: https://github.com/pre-commit/pre-commit-hooks
@@ -48,14 +16,20 @@ repos:
       - id: end-of-file-fixer
       - id: trailing-whitespace
       - id: mixed-line-ending
-
+  # mypy: type checking - caution this can be hard to satisfy also slow
+  # - repo: https://github.com/pre-commit/mirrors-mypy
+  #   rev: v0.910-1
+  #   hooks:
+  #       - id: mypy
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.4.4
+    rev: v0.4.9
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]
         types_or: [ python, pyi, jupyter ]
-    # Run the formatter.
-      - id: ruff-format
-        types_or: [ python, pyi, jupyter ]
+  # black: automatic pep8 compliance code formatting
+  - repo: https://github.com/psf/black
+    rev: 24.4.2
+    hooks:
+      - id: black

gene_benchmark/tests/test_encoder.py

@@ -236,11 +236,9 @@ def test_sentenceTransformerEncoder_series(self):
         encoder = SentenceTransformerEncoder(mpnet_name)
         txt1 = "It was originally taken from a Latin text written by a Roman Scholar, Sceptic and Philosopher\
             by the name of Marcus Tullius Cicero, who influenced the Latin language greatly."
-        txt2 = (
-            "The filler text we know today has been altered over the years (in fact Lorem isn't actually a\
+        txt2 = "The filler text we know today has been altered over the years (in fact Lorem isn't actually a\
             Latin word. It is suggested that the reason that the text starts with Lorem is because there was a\
                 page break spanning the word"
-        )
         txt3 = "Do-lorem. If you a re looking for a translation of the text, it's meaningless. The original text\
             talks about the pain and love involved in the pursuit of pleasure or something like that."
         txt4 = "The reason we use Lorem Ipsum is simple. If we used real text, it would possibly distract from\
@@ -255,11 +253,9 @@ def test_sentenceTransformerEncoder_series_with_none(self):
         encoder = SentenceTransformerEncoder(mpnet_name)
         txt1 = "It was originally taken from a Latin text written by a Roman Scholar, Sceptic and Philosopher\
             by the name of Marcus Tullius Cicero, who influenced the Latin language greatly."
-        txt2 = (
-            "The filler text we know today has been altered over the years (in fact Lorem isn't actually a\
+        txt2 = "The filler text we know today has been altered over the years (in fact Lorem isn't actually a\
             Latin word. It is suggested that the reason that the text starts with Lorem is because there was a\
                 page break spanning the word"
-        )
         txt3 = "Do-lorem. If you a re looking for a translation of the text, it's meaningless. The original text\
             talks about the pain and love involved in the pursuit of pleasure or something like that."
         txt4 = "The reason we use Lorem Ipsum is simple. If we used real text, it would possibly distract from\
@@ -277,11 +273,9 @@ def test_entenceTransformerEncoder_df(self):
         encoder = SentenceTransformerEncoder(mpnet_name)
         txt1 = "It was originally taken from a Latin text written by a Roman Scholar, Sceptic and Philosopher\
             by the name of Marcus Tullius Cicero, who influenced the Latin language greatly."
-        txt2 = (
-            "The filler text we know today has been altered over the years (in fact Lorem isn't actually a\
+        txt2 = "The filler text we know today has been altered over the years (in fact Lorem isn't actually a\
             Latin word. It is suggested that the reason that the text starts with Lorem is because there was a\
                 page break spanning the word"
-        )
         txt3 = "Do-lorem. If you a re looking for a translation of the text, it's meaningless. The original text\
             talks about the pain and love involved in the pursuit of pleasure or something like that."
         txt4 = "The reason we use Lorem Ipsum is simple. If we used real text, it would possibly distract from\
@@ -300,11 +294,9 @@ def test_sentenceTransformerEncoder_pdseries(self):
         encoder = SentenceTransformerEncoder(mpnet_name)
         txt1 = "It was originally taken from a Latin text written by a Roman Scholar, Sceptic and Philosopher\
             by the name of Marcus Tullius Cicero, who influenced the Latin language greatly."
-        txt2 = (
-            "The filler text we know today has been altered over the years (in fact Lorem isn't actually a\
+        txt2 = "The filler text we know today has been altered over the years (in fact Lorem isn't actually a\
             Latin word. It is suggested that the reason that the text starts with Lorem is because there was a\
                 page break spanning the word"
-        )
         txt3 = "Do-lorem. If you a re looking for a translation of the text, it's meaningless. The original text\
             talks about the pain and love involved in the pursuit of pleasure or something like that."
         txt4 = "The reason we use Lorem Ipsum is simple. If we used real text, it would possibly distract from\

gene_benchmark/tests/test_tasks.py

@@ -329,7 +329,7 @@ def test_list_subtests(self):
     def test_get_task_names(self):
         tasks_folder = _get_tasks_folder()
         names = list(get_tasks_definition_names(tasks_folder))
-        assert len(names) >= 81
+        assert len(names) >= 70
         assert "RNA cancer distribution" in names
         assert "bivalent vs non-methylated" in names
 

pyproject.toml

@@ -24,6 +24,7 @@ dependencies = [
 "mygene",
 "sentence_transformers",
 "scikit-learn",
+"click",
 ]
 
 [project.optional-dependencies]

scripts/tasks_retrival/HPA_tasks_creation.py

@@ -93,7 +93,7 @@ def save_task_to_dir(main_task_directory, task_name, entities, outcomes):
     "--columns-to-use-yaml",
     type=click.STRING,
     help="A path to a yaml file containing the column names to be used as tasks",
-    default="scripts/hpa_column_names_for_tasks.yaml",
+    default="scripts/tasks_retrival/hpa_column_names_for_tasks.yaml",
 )
 @click.option(
     "--main-task-directory",
@@ -110,9 +110,7 @@ def save_task_to_dir(main_task_directory, task_name, entities, outcomes):
     default=False,
 )
 @click.option(
-    "--input-file",
-    type=click.STRING,
-    help="The path to the data file",
+    "--input-file", type=click.STRING, help="The path to the data file", default=None
 )
 def main(columns_to_use_yaml, main_task_directory, allow_downloads, input_file):
     if allow_downloads: