Add cohorts snapshot tests with syrupy (#379)

* Add cohorts snapshot tests with syrupy

* Fix.

* fix again

* Rework CI

* [revery]

* improve

* fix mypy?

* Revert "[revery]"

This reverts commit 7664e5e.

* Try again

* fix mypy

Author: dcherian

.github/workflows/ci-additional.yaml

@@ -128,7 +128,8 @@ jobs:
 
       - name: Run mypy
         run: |
-          python -m mypy --install-types --non-interactive --cobertura-xml-report mypy_report
+          mkdir .mypy_cache
+          python -m mypy --install-types --non-interactive --cache-dir=.mypy_cache/ --cobertura-xml-report mypy_report
 
       - name: Upload mypy coverage to Codecov
         uses: codecov/[email protected]

.github/workflows/ci.yaml

@@ -16,7 +16,7 @@ concurrency:
 
 jobs:
   test:
-    name: Test (${{ matrix.python-version }}, ${{ matrix.os }})
+    name: Test (${{matrix.env}}, ${{ matrix.python-version }}, ${{ matrix.os }})
     runs-on: ${{ matrix.os }}
     defaults:
       run:
@@ -25,10 +25,18 @@ jobs:
       fail-fast: false
       matrix:
         os: ["ubuntu-latest"]
+        env: ["environment"]
         python-version: ["3.9", "3.12"]
         include:
           - os: "windows-latest"
+            env: "environment"
             python-version: "3.12"
+          - os: "ubuntu-latest"
+            env: "no-dask" # "no-xarray", "no-numba"
+            python-version: "3.12"
+          - os: "ubuntu-latest"
+            env: "minimal-requirements"
+            python-version: "3.9"
     steps:
       - uses: actions/checkout@v4
         with:
@@ -39,7 +47,7 @@ jobs:
       - name: Set up conda environment
         uses: mamba-org/setup-micromamba@v1
         with:
-          environment-file: ci/environment.yml
+          environment-file: ci/${{ matrix.env }}.yml
           environment-name: flox-tests
           init-shell: bash
           cache-environment: true
@@ -81,48 +89,6 @@ jobs:
           path: .hypothesis/
           key: cache-hypothesis-${{ runner.os }}-${{ matrix.python-version }}-${{ github.run_id }}
 
-  optional-deps:
-    name: ${{ matrix.env }}
-    runs-on: "ubuntu-latest"
-    defaults:
-      run:
-        shell: bash -l {0}
-    strategy:
-      fail-fast: false
-      matrix:
-        python-version: ["3.12"]
-        env: ["no-dask"] # "no-xarray", "no-numba"
-        include:
-          - env: "minimal-requirements"
-            python-version: "3.9"
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0 # Fetch all history for all branches and tags.
-      - name: Set up conda environment
-        uses: mamba-org/setup-micromamba@v1
-        with:
-          environment-file: ci/${{ matrix.env }}.yml
-          environment-name: flox-tests
-          init-shell: bash
-          cache-environment: true
-          create-args: |
-            python=${{ matrix.python-version }}
-      - name: Install flox
-        run: |
-          python -m pip install --no-deps -e .
-      - name: Run tests
-        run: |
-          python -m pytest -n auto --cov=./ --cov-report=xml
-      - name: Upload code coverage to Codecov
-        uses: codecov/[email protected]
-        with:
-          file: ./coverage.xml
-          flags: unittests
-          env_vars: RUNNER_OS
-          name: codecov-umbrella
-          fail_ci_if_error: false
-
   xarray-groupby:
     name: xarray-groupby
     runs-on: ubuntu-latest

asv_bench/__init__.py

@@ -18,6 +18,7 @@ dependencies:
   - pytest-cov
   - pytest-pretty
   - pytest-xdist
+  - syrupy
   - xarray
   - pre-commit
   - numpy_groupies>=0.9.19

ci/environment.yml

@@ -9,6 +9,7 @@ dependencies:
   - pytest-cov
   - pytest-pretty
   - pytest-xdist
+  - syrupy
   - numpy==1.22
   - scipy==1.9.0
   - numpy_groupies==0.9.19

ci/minimal-requirements.yml

@@ -13,6 +13,7 @@ dependencies:
   - pytest-cov
   - pytest-pretty
   - pytest-xdist
+  - syrupy
   - xarray
   - numpydoc
   - pre-commit

ci/no-dask.yml

@@ -18,6 +18,7 @@ dependencies:
   - pytest-cov
   - pytest-pretty
   - pytest-xdist
+  - syrupy
   - xarray
   - pre-commit
   - numpy_groupies>=0.9.19

ci/no-numba.yml

@@ -3,6 +3,7 @@ channels:
   - conda-forge
 dependencies:
   - codecov
+  - syrupy
   - pandas
   - numpy>=1.22
   - scipy
@@ -11,6 +12,7 @@ dependencies:
   - pytest-cov
   - pytest-pretty
   - pytest-xdist
+  - syrupy
   - dask-core
   - numpydoc
   - pre-commit

ci/no-xarray.yml

@@ -11,6 +11,7 @@ dependencies:
   # - scipy
   - pytest-pretty
   - pytest-xdist
+  - syrupy
   - pip
   # for cftime
   - cython>=0.29.20

ci/upstream-dev-env.yml

@@ -394,7 +394,9 @@ def find_group_cohorts(
         chunks_per_label = chunks_per_label[present_labels_mask]
 
     label_chunks = {
-        present_labels[idx]: bitmask.indices[slice(bitmask.indptr[idx], bitmask.indptr[idx + 1])]
+        present_labels[idx].item(): bitmask.indices[
+            slice(bitmask.indptr[idx], bitmask.indptr[idx + 1])
+        ]
         for idx in range(bitmask.shape[LABEL_AXIS])
     }
 
@@ -485,7 +487,7 @@ def invert(x) -> tuple[np.ndarray, ...]:
 
     # Iterate over labels, beginning with those with most chunks
     logger.debug("find_group_cohorts: merging cohorts")
-    order = np.argsort(containment.sum(axis=LABEL_AXIS))[::-1]
+    order = np.argsort(containment.sum(axis=LABEL_AXIS), kind="stable")[::-1]
     merged_cohorts = {}
     merged_keys = set()
     # TODO: we can optimize this to loop over chunk_cohorts instead
@@ -495,11 +497,11 @@ def invert(x) -> tuple[np.ndarray, ...]:
             slice(containment.indptr[rowidx], containment.indptr[rowidx + 1])
         ]
         cohort_ = present_labels[cohidx]
-        cohort = [elem for elem in cohort_ if elem not in merged_keys]
+        cohort = [elem.item() for elem in cohort_ if elem not in merged_keys]
         if not cohort:
             continue
         merged_keys.update(cohort)
-        allchunks = (label_chunks[member] for member in cohort)
+        allchunks = (label_chunks[member].tolist() for member in cohort)
         chunk = tuple(set(itertools.chain(*allchunks)))
         merged_cohorts[chunk] = cohort