Update tutorial for new VariantData format

.github/workflows/docs.yml

@@ -29,32 +29,22 @@ jobs:
 
       - uses: actions/setup-python@v5
         with:
-          python-version: "3.10"
+          python-version: "3.11"
+          cache: "pip"
 
-      - uses: actions/cache@v4
-        id: venv-cache
-        with:
-          path: venv
-          key: docs-venv-v6-${{ hashFiles('requirements/CI-docs/requirements.txt') }}
-
-      - name: Create venv and install deps (one by one to avoid conflict errors)
-        if: steps.venv-cache.outputs.cache-hit != 'true'
+      - name: Install deps (one by one to avoid conflict errors)
         run: |
-          python -m venv venv
-          . venv/bin/activate
           pip install --upgrade pip wheel
-          pip install -r requirements/CI-docs/requirements.txt          
-
+          pip install -r requirements/CI-docs/requirements.txt
+          sudo apt-get install -y tabix
 
       - name: Build C module
         if: env.MAKE_TARGET
         run: |
-          . venv/bin/activate
           make $MAKE_TARGET
 
       - name: Build Docs
         run: |
-          . venv/bin/activate
           cd docs && make dist
 
       - name: Trigger docs site rebuild

docs/.gitignore

@@ -1,4 +1,7 @@
 notebook-simulation.trees
 notebook-simulation.samples
 notebook-simulation-source.trees
+notebook-simulation.vc*
+notebook-simulation-AA.npy
 P_dom_chr24_phased.samples
+sparrows.vcz

docs/_config.yml

@@ -41,7 +41,7 @@ sphinx:
     config:
       html_theme: sphinx_book_theme
       html_theme_options:
-        pygment_dark_style: monokai
+        pygments_dark_style: monokai
       pygments_style: monokai
       myst_enable_extensions:
       - colon_fence

docs/_static/example_data.vcz/.zattrs

@@ -0,0 +1,6 @@
+{
+    "contigs": [
+        "0"
+    ],
+    "source": "sgkit-0.9.0"
+}

docs/_static/example_data.vcz/.zgroup

@@ -0,0 +1,3 @@
+{
+    "zarr_format": 2
+}

docs/_static/example_data.vcz/.zmetadata

@@ -0,0 +1,243 @@
+{
+    "metadata": {
+        ".zattrs": {
+            "contigs": [
+                "0"
+            ],
+            "source": "sgkit-0.9.0"
+        },
+        ".zgroup": {
+            "zarr_format": 2
+        },
+        "call_genotype/.zarray": {
+            "chunks": [
+                8,
+                3,
+                2
+            ],
+            "compressor": {
+                "blocksize": 0,
+                "clevel": 5,
+                "cname": "lz4",
+                "id": "blosc",
+                "shuffle": 1
+            },
+            "dtype": "|i1",
+            "fill_value": null,
+            "filters": null,
+            "order": "C",
+            "shape": [
+                8,
+                3,
+                2
+            ],
+            "zarr_format": 2
+        },
+        "call_genotype/.zattrs": {
+            "_ARRAY_DIMENSIONS": [
+                "variants",
+                "samples",
+                "ploidy"
+            ],
+            "comment": "Call genotype. Encoded as allele values (0 for the reference, 1 for\nthe first allele, 2 for the second allele), -1 to indicate a\nmissing value, or -2 to indicate a non allele in mixed ploidy datasets.",
+            "mixed_ploidy": false
+        },
+        "call_genotype_mask/.zarray": {
+            "chunks": [
+                8,
+                3,
+                2
+            ],
+            "compressor": {
+                "blocksize": 0,
+                "clevel": 5,
+                "cname": "lz4",
+                "id": "blosc",
+                "shuffle": 1
+            },
+            "dtype": "|i1",
+            "fill_value": null,
+            "filters": null,
+            "order": "C",
+            "shape": [
+                8,
+                3,
+                2
+            ],
+            "zarr_format": 2
+        },
+        "call_genotype_mask/.zattrs": {
+            "_ARRAY_DIMENSIONS": [
+                "variants",
+                "samples",
+                "ploidy"
+            ],
+            "comment": "A flag for each call indicating which values are missing.",
+            "dtype": "bool"
+        },
+        "call_genotype_phased/.zarray": {
+            "chunks": [
+                8,
+                3
+            ],
+            "compressor": {
+                "blocksize": 0,
+                "clevel": 5,
+                "cname": "lz4",
+                "id": "blosc",
+                "shuffle": 1
+            },
+            "dtype": "|i1",
+            "fill_value": null,
+            "filters": null,
+            "order": "C",
+            "shape": [
+                8,
+                3
+            ],
+            "zarr_format": 2
+        },
+        "call_genotype_phased/.zattrs": {
+            "_ARRAY_DIMENSIONS": [
+                "variants",
+                "samples"
+            ],
+            "comment": "A flag for each call indicating if it is phased or not. If omitted\nall calls are unphased.",
+            "dtype": "bool"
+        },
+        "contig_id/.zarray": {
+            "chunks": [
+                1
+            ],
+            "compressor": {
+                "blocksize": 0,
+                "clevel": 5,
+                "cname": "lz4",
+                "id": "blosc",
+                "shuffle": 1
+            },
+            "dtype": "<U1",
+            "fill_value": null,
+            "filters": null,
+            "order": "C",
+            "shape": [
+                1
+            ],
+            "zarr_format": 2
+        },
+        "contig_id/.zattrs": {
+            "_ARRAY_DIMENSIONS": [
+                "contigs"
+            ],
+            "comment": "Contig identifiers."
+        },
+        "sample_id/.zarray": {
+            "chunks": [
+                3
+            ],
+            "compressor": {
+                "blocksize": 0,
+                "clevel": 5,
+                "cname": "lz4",
+                "id": "blosc",
+                "shuffle": 1
+            },
+            "dtype": "<U2",
+            "fill_value": null,
+            "filters": null,
+            "order": "C",
+            "shape": [
+                3
+            ],
+            "zarr_format": 2
+        },
+        "sample_id/.zattrs": {
+            "_ARRAY_DIMENSIONS": [
+                "samples"
+            ],
+            "comment": "The unique identifier of the sample."
+        },
+        "variant_allele/.zarray": {
+            "chunks": [
+                8,
+                2
+            ],
+            "compressor": {
+                "blocksize": 0,
+                "clevel": 5,
+                "cname": "lz4",
+                "id": "blosc",
+                "shuffle": 1
+            },
+            "dtype": "|S1",
+            "fill_value": null,
+            "filters": null,
+            "order": "C",
+            "shape": [
+                8,
+                2
+            ],
+            "zarr_format": 2
+        },
+        "variant_allele/.zattrs": {
+            "_ARRAY_DIMENSIONS": [
+                "variants",
+                "alleles"
+            ],
+            "comment": "The possible alleles for the variant."
+        },
+        "variant_contig/.zarray": {
+            "chunks": [
+                8
+            ],
+            "compressor": {
+                "blocksize": 0,
+                "clevel": 5,
+                "cname": "lz4",
+                "id": "blosc",
+                "shuffle": 1
+            },
+            "dtype": "<i8",
+            "fill_value": null,
+            "filters": null,
+            "order": "C",
+            "shape": [
+                8
+            ],
+            "zarr_format": 2
+        },
+        "variant_contig/.zattrs": {
+            "_ARRAY_DIMENSIONS": [
+                "variants"
+            ],
+            "comment": "Index corresponding to contig name for each variant. In some less common\nscenarios, this may also be equivalent to the contig names if the data\ngenerating process used contig names that were also integers."
+        },
+        "variant_position/.zarray": {
+            "chunks": [
+                8
+            ],
+            "compressor": {
+                "blocksize": 0,
+                "clevel": 5,
+                "cname": "lz4",
+                "id": "blosc",
+                "shuffle": 1
+            },
+            "dtype": "<i8",
+            "fill_value": null,
+            "filters": null,
+            "order": "C",
+            "shape": [
+                8
+            ],
+            "zarr_format": 2
+        },
+        "variant_position/.zattrs": {
+            "_ARRAY_DIMENSIONS": [
+                "variants"
+            ],
+            "comment": "The reference position of the variant."
+        }
+    },
+    "zarr_consolidated_format": 1
+}

docs/_static/example_data.vcz/call_genotype/.zarray

@@ -0,0 +1,24 @@
+{
+    "chunks": [
+        8,
+        3,
+        2
+    ],
+    "compressor": {
+        "blocksize": 0,
+        "clevel": 5,
+        "cname": "lz4",
+        "id": "blosc",
+        "shuffle": 1
+    },
+    "dtype": "|i1",
+    "fill_value": null,
+    "filters": null,
+    "order": "C",
+    "shape": [
+        8,
+        3,
+        2
+    ],
+    "zarr_format": 2
+}

docs/_static/example_data.vcz/call_genotype/.zattrs

@@ -0,0 +1,9 @@
+{
+    "_ARRAY_DIMENSIONS": [
+        "variants",
+        "samples",
+        "ploidy"
+    ],
+    "comment": "Call genotype. Encoded as allele values (0 for the reference, 1 for\nthe first allele, 2 for the second allele), -1 to indicate a\nmissing value, or -2 to indicate a non allele in mixed ploidy datasets.",
+    "mixed_ploidy": false
+}

docs/_static/example_data.vcz/call_genotype_mask/.zarray

@@ -0,0 +1,24 @@
+{
+    "chunks": [
+        8,
+        3,
+        2
+    ],
+    "compressor": {
+        "blocksize": 0,
+        "clevel": 5,
+        "cname": "lz4",
+        "id": "blosc",
+        "shuffle": 1
+    },
+    "dtype": "|i1",
+    "fill_value": null,
+    "filters": null,
+    "order": "C",
+    "shape": [
+        8,
+        3,
+        2
+    ],
+    "zarr_format": 2
+}

docs/_static/example_data.vcz/call_genotype_mask/.zattrs

@@ -0,0 +1,9 @@
+{
+    "_ARRAY_DIMENSIONS": [
+        "variants",
+        "samples",
+        "ploidy"
+    ],
+    "comment": "A flag for each call indicating which values are missing.",
+    "dtype": "bool"
+}