Add comprehensive tests

.github/workflows/code-quality-master.yaml

@@ -0,0 +1,22 @@
+# Same as `code-quality-pr.yaml` but triggered on commit to main branch
+# and runs on all files (instead of only the changed ones)
+
+name: Code Quality Main
+
+on:
+  push:
+    branches: [master]
+
+jobs:
+  code-quality:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v3
+
+      - name: Run pre-commits
+        uses: pre-commit/action@v3.0.0

.github/workflows/code-quality-pr.yaml

@@ -0,0 +1,36 @@
+# This workflow finds which files were changed, prints them,
+# and runs `pre-commit` on those files.
+
+# Inspired by the sktime library:
+# https://github.com/alan-turing-institute/sktime/blob/main/.github/workflows/test.yml
+
+name: Code Quality PR
+
+on:
+  pull_request:
+    branches: [master, "release/*", "dev"]
+
+jobs:
+  code-quality:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v3
+
+      - name: Find modified files
+        id: file_changes
+        uses: trilom/file-changes-action@v1.2.4
+        with:
+          output: " "
+
+      - name: List modified files
+        run: echo '${{ steps.file_changes.outputs.files}}'
+
+      - name: Run pre-commits
+        uses: pre-commit/action@v3.0.0
+        with:
+          extra_args: --files ${{ steps.file_changes.outputs.files}}

.github/workflows/tests.yml

@@ -0,0 +1,41 @@
+name: Tests
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master, "release/*", "dev"]
+
+jobs:
+  run_tests_ubuntu:
+    runs-on: ubuntu-latest
+
+    strategy:
+      fail-fast: false
+
+    timeout-minutes: 30
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Set up Python 3.10
+        uses: actions/setup-python@v3
+        with:
+          python-version: "3.10"
+
+      - name: Install packages
+        run: |
+          pip install -e .[dev]
+
+      #----------------------------------------------
+      #              run test suite
+      #----------------------------------------------
+      - name: Run tests
+        run: |
+          pytest -v --doctest-modules --ignore=profiling/ --ignore=run.py --cov=src -s
+
+      - name: Upload coverage reports to Codecov
+        uses: codecov/codecov-action@v4.0.1
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}

pyproject.toml

@@ -28,7 +28,10 @@ dependencies = [
 ]
 
 [project.optional-dependencies]
-dev = ["pre-commit", "pytest", "pytest-cov", ]
+dev = [
+  "pre-commit", "pytest", "pytest-cov", "pytest-subtests", "rootutils"
+]
+profiling = ["psutil"]
 
 [project.urls]
 Homepage = "https://github.com/justin13601/ESGPTTaskQueryingPublic"

src/esgpt_task_querying/config.py

@@ -119,11 +119,9 @@ def build_tree_from_config(cfg: dict[str, Any]) -> Node:
         ...     }
         ... }
         >>> build_tree_from_config(cfg) # doctest: +NORMALIZE_WHITESPACE
-        Node(
-            /window1,
-            constraints={},
-            endpoint_expr=(False, datetime.timedelta(days=1), True, datetime.timedelta(0))
-        )
+        Node(/window1,
+             constraints={},
+             endpoint_expr=(False, datetime.timedelta(days=1), True, datetime.timedelta(0)))
     """
     nodes = {}
     windows = [name for name, _ in cfg["windows"].items()]

src/esgpt_task_querying/predicates.py

@@ -70,7 +70,7 @@ def generate_simple_predicates(predicate_name: str, predicate_info: dict, df: pl
     ┌────────────┬───────────┬────────────┬──────┐
     │ subject_id ┆ timestamp ┆ event_type ┆ is_A │
     │ ---        ┆ ---       ┆ ---        ┆ ---  │
-    │ i64        ┆ i64       ┆ str        ┆ i32  │
+    │ i64        ┆ i64       ┆ str        ┆ i64  │
     ╞════════════╪═══════════╪════════════╪══════╡
     │ 1          ┆ 1         ┆ A          ┆ 1    │
     │ 1          ┆ 1         ┆ B          ┆ 0    │
@@ -142,7 +142,7 @@ def generate_predicate_columns(cfg: dict, data: list | pl.DataFrame) -> pl.DataF
     ┌────────────┬───────────┬──────┬──────┬───┬──────┬───────────┬──────────────────┬────────┐
     │ subject_id ┆ timestamp ┆ is_A ┆ is_B ┆ … ┆ is_D ┆ is_A_or_B ┆ is_A_and_C_and_D ┆ is_any │
     │ ---        ┆ ---       ┆ ---  ┆ ---  ┆   ┆ ---  ┆ ---       ┆ ---              ┆ ---    │
-    │ i64        ┆ i64       ┆ i32  ┆ i32  ┆   ┆ i32  ┆ i32       ┆ i32              ┆ i32    │
+    │ i64        ┆ i64       ┆ i64  ┆ i64  ┆   ┆ i64  ┆ i64       ┆ i64              ┆ i64    │
     ╞════════════╪═══════════╪══════╪══════╪═══╪══════╪═══════════╪══════════════════╪════════╡
     │ 1          ┆ 1         ┆ 1    ┆ 1    ┆ … ┆ 0    ┆ 1         ┆ 0                ┆ 1      │
     │ 1          ┆ 3         ┆ 0    ┆ 0    ┆ … ┆ 0    ┆ 0         ┆ 0                ┆ 1      │

src/esgpt_task_querying/summarize.py

@@ -26,6 +26,7 @@ def summarize_temporal_window(
 
     Examples:
         >>> import polars as pl
+        >>> _ = pl.Config.set_tbl_width_chars(100)
         >>> from datetime import datetime, timedelta
         >>> predicates_df = pl.DataFrame(
         ...     {
@@ -38,7 +39,7 @@ def summarize_temporal_window(
         ...         "is_A": [1, 0, 1],
         ...         "is_B": [0, 1, 0],
         ...     }
-        ... ))
+        ... )
         >>> anchor_to_subtree_root_by_subtree_anchor = pl.DataFrame(
         ...     {
         ...         "subject_id": [1, 1, 1],

tests/test_summarize.py

@@ -313,12 +313,15 @@ def test_summarize_temporal_window(self):
                 got = summarize_temporal_window(**c)
                 self.assertEqual(got, want)
 
+    @unittest.skip("Not yet implemented")
     def test_summarize_event_bound_window(self):
         raise NotImplementedError
 
+    @unittest.skip("Not yet implemented")
     def test_summarize_window(self):
         raise NotImplementedError
 
+    @unittest.skip("Not yet implemented")
     def test_summarize_subtree(self):
         raise NotImplementedError