Fork of Nikolai's "Improve Model QC" branch

.github/workflows/python-package.yml

@@ -32,7 +32,7 @@ jobs:
       run: |
         uv run --frozen pytest
 
-    - name: Lint with black
+    - name: Lint with ruff
       run: |
-        uv run --frozen black --check src/
-        uv run --frozen black --check tests/
+        uv run --frozen ruff format --check src/
+        uv run --frozen ruff format --check tests/

jupyter/fidelity-plot.ipynb

@@ -20,12 +20,38 @@
    "outputs": [],
    "source": [
     "# Make up some fake fidelity data.\n",
-    "fidelity_data = pl.DataFrame([\n",
-    "    {\"column-1\":\"total_score\",\"column-2\":\"sports_flg\",\"tvd\":0.001757401,\"model\":\"LPM\",\"index\":0},\n",
-    "    {\"column-1\":\"terrace_flg\",\"column-2\":\"darts_flg\",\"tvd\":0.0018333333,\"model\":\"LPM\",\"index\":1},\n",
-    "    {\"column-1\":\"total_score\",\"column-2\":\"live_flg\",\"tvd\":0.0020490196,\"model\":\"LPM\",\"index\":2},\n",
-    "    {\"column-1\":\"total_score\",\"column-2\":\"closed\",\"tvd\":0.056201461,\"model\":\"LPM\",\"index\":35}\n",
-    "])"
+    "fidelity_data = pl.DataFrame(\n",
+    "    [\n",
+    "        {\n",
+    "            \"column-1\": \"total_score\",\n",
+    "            \"column-2\": \"sports_flg\",\n",
+    "            \"tvd\": 0.001757401,\n",
+    "            \"model\": \"LPM\",\n",
+    "            \"index\": 0,\n",
+    "        },\n",
+    "        {\n",
+    "            \"column-1\": \"terrace_flg\",\n",
+    "            \"column-2\": \"darts_flg\",\n",
+    "            \"tvd\": 0.0018333333,\n",
+    "            \"model\": \"LPM\",\n",
+    "            \"index\": 1,\n",
+    "        },\n",
+    "        {\n",
+    "            \"column-1\": \"total_score\",\n",
+    "            \"column-2\": \"live_flg\",\n",
+    "            \"tvd\": 0.0020490196,\n",
+    "            \"model\": \"LPM\",\n",
+    "            \"index\": 2,\n",
+    "        },\n",
+    "        {\n",
+    "            \"column-1\": \"total_score\",\n",
+    "            \"column-2\": \"closed\",\n",
+    "            \"tvd\": 0.056201461,\n",
+    "            \"model\": \"LPM\",\n",
+    "            \"index\": 35,\n",
+    "        },\n",
+    "    ]\n",
+    ")"
    ]
   },
   {
@@ -39,24 +65,25 @@
       "text/html": [
        "\n",
        "<style>\n",
-       "  #altair-viz-7b641f7c0e5b41afbc0db1e112806a48.vega-embed {\n",
+       "  #altair-viz-ccc2885fcee74291bbc48cce44ffaecd.vega-embed {\n",
        "    width: 100%;\n",
        "    display: flex;\n",
        "  }\n",
        "\n",
-       "  #altair-viz-7b641f7c0e5b41afbc0db1e112806a48.vega-embed details,\n",
-       "  #altair-viz-7b641f7c0e5b41afbc0db1e112806a48.vega-embed details summary {\n",
+       "  #altair-viz-ccc2885fcee74291bbc48cce44ffaecd.vega-embed details,\n",
+       "  #altair-viz-ccc2885fcee74291bbc48cce44ffaecd.vega-embed details summary {\n",
        "    position: relative;\n",
        "  }\n",
        "</style>\n",
-       "<div id=\"altair-viz-7b641f7c0e5b41afbc0db1e112806a48\"></div>\n",
+       "<div id=\"altair-viz-ccc2885fcee74291bbc48cce44ffaecd\"></div>\n",
        "<script type=\"text/javascript\">\n",
        "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
        "  (function(spec, embedOpt){\n",
        "    let outputDiv = document.currentScript.previousElementSibling;\n",
-       "    if (outputDiv.id !== \"altair-viz-7b641f7c0e5b41afbc0db1e112806a48\") {\n",
-       "      outputDiv = document.getElementById(\"altair-viz-7b641f7c0e5b41afbc0db1e112806a48\");\n",
+       "    if (outputDiv.id !== \"altair-viz-ccc2885fcee74291bbc48cce44ffaecd\") {\n",
+       "      outputDiv = document.getElementById(\"altair-viz-ccc2885fcee74291bbc48cce44ffaecd\");\n",
        "    }\n",
+       "\n",
        "    const paths = {\n",
        "      \"vega\": \"https://cdn.jsdelivr.net/npm/vega@5?noext\",\n",
        "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm/vega-lib?noext\",\n",
@@ -93,15 +120,16 @@
        "\n",
        "    if(typeof define === \"function\" && define.amd) {\n",
        "      requirejs.config({paths});\n",
-       "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
+       "      let deps = [\"vega-embed\"];\n",
+       "      require(deps, displayChart, err => showError(`Error loading script: ${err.message}`));\n",
        "    } else {\n",
        "      maybeLoadScript(\"vega\", \"5\")\n",
        "        .then(() => maybeLoadScript(\"vega-lite\", \"5.20.1\"))\n",
        "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
        "        .catch(showError)\n",
        "        .then(() => displayChart(vegaEmbed));\n",
        "    }\n",
-       "  })({\"config\": {\"view\": {\"continuousWidth\": 300, \"continuousHeight\": 300}}, \"layer\": [{\"mark\": {\"type\": \"line\", \"strokeDash\": [5, 5]}, \"encoding\": {\"color\": {\"field\": \"model\", \"type\": \"nominal\"}, \"x\": {\"axis\": null, \"field\": \"index\", \"type\": \"ordinal\"}, \"y\": {\"field\": \"tvd\", \"title\": \"Total variation distance\", \"type\": \"quantitative\"}}}, {\"mark\": {\"type\": \"point\"}, \"encoding\": {\"color\": {\"field\": \"model\", \"type\": \"nominal\"}, \"tooltip\": [{\"field\": \"column-1\", \"title\": \"Column 1\", \"type\": \"nominal\"}, {\"field\": \"column-2\", \"title\": \"Column 2\", \"type\": \"nominal\"}], \"x\": {\"axis\": {\"labels\": false}, \"field\": \"index\", \"title\": \"Pairs of columns (ordered from best fit to worst)\", \"type\": \"ordinal\"}, \"y\": {\"field\": \"tvd\", \"type\": \"quantitative\"}}}], \"data\": {\"name\": \"data-7397a78c2d03a088ce5ee99bbed1e8bb\"}, \"height\": 400, \"width\": 400, \"$schema\": \"https://vega.github.io/schema/vega-lite/v5.20.1.json\", \"datasets\": {\"data-7397a78c2d03a088ce5ee99bbed1e8bb\": [{\"column-1\": \"total_score\", \"column-2\": \"sports_flg\", \"tvd\": 0.001757401, \"model\": \"LPM\", \"index\": 0}, {\"column-1\": \"terrace_flg\", \"column-2\": \"darts_flg\", \"tvd\": 0.0018333333, \"model\": \"LPM\", \"index\": 1}, {\"column-1\": \"total_score\", \"column-2\": \"live_flg\", \"tvd\": 0.0020490196, \"model\": \"LPM\", \"index\": 2}, {\"column-1\": \"total_score\", \"column-2\": \"closed\", \"tvd\": 0.056201461, \"model\": \"LPM\", \"index\": 35}]}}, {\"mode\": \"vega-lite\"});\n",
+       "  })({\"$schema\": \"https://vega.github.io/schema/vega/v5.json\", \"data\": [{\"name\": \"source_0\", \"values\": [{\"column-1\": \"total_score\", \"column-2\": \"sports_flg\", \"tvd\": 0.001757401, \"model\": \"LPM\", \"index\": 0}, {\"column-1\": \"terrace_flg\", \"column-2\": \"darts_flg\", \"tvd\": 0.0018333333, \"model\": \"LPM\", \"index\": 1}, {\"column-1\": \"total_score\", \"column-2\": \"live_flg\", \"tvd\": 0.0020490196, \"model\": \"LPM\", \"index\": 2}, {\"column-1\": \"total_score\", \"column-2\": \"closed\", \"tvd\": 0.056201461, \"model\": \"LPM\", \"index\": 35}]}, {\"name\": \"data_0\", \"values\": [{\"column-1\": \"total_score\", \"column-2\": \"sports_flg\", \"index\": 0, \"model\": \"LPM\", \"tvd\": 0.001757401}, {\"column-1\": \"terrace_flg\", \"column-2\": \"darts_flg\", \"index\": 1, \"model\": \"LPM\", \"tvd\": 0.0018333333}, {\"column-1\": \"total_score\", \"column-2\": \"live_flg\", \"index\": 2, \"model\": \"LPM\", \"tvd\": 0.0020490196}, {\"column-1\": \"total_score\", \"column-2\": \"closed\", \"index\": 35, \"model\": \"LPM\", \"tvd\": 0.056201461}]}, {\"name\": \"source_0_x_domain_index_0\", \"values\": [{\"index\": 0}, {\"index\": 1}, {\"index\": 2}, {\"index\": 35}]}, {\"name\": \"data_0_x_domain_index_1\", \"values\": [{\"index\": 0}, {\"index\": 1}, {\"index\": 2}, {\"index\": 35}]}, {\"name\": \"source_0_color_domain_model_0\", \"values\": [{\"model\": \"LPM\"}]}, {\"name\": \"data_0_color_domain_model_1\", \"values\": [{\"model\": \"LPM\"}]}], \"marks\": [{\"type\": \"group\", \"name\": \"layer_0_pathgroup\", \"from\": {\"facet\": {\"data\": \"source_0\", \"name\": \"faceted_path_layer_0_main\", \"groupby\": [\"model\"]}}, \"encode\": {\"update\": {\"width\": {\"field\": {\"signal\": null, \"datum\": null, \"group\": \"width\", \"parent\": null}}, \"height\": {\"field\": {\"signal\": null, \"datum\": null, \"group\": \"height\", \"parent\": null}}}}, \"marks\": [{\"type\": \"line\", \"name\": \"layer_0_marks\", \"from\": {\"data\": \"faceted_path_layer_0_main\"}, \"sort\": {\"field\": \"x\"}, \"encode\": {\"update\": {\"y\": {\"field\": \"tvd\", \"scale\": \"y\"}, \"stroke\": {\"field\": \"model\", \"scale\": \"color\"}, \"strokeDash\": {\"value\": [5, 5]}, \"x\": {\"field\": \"index\", \"scale\": \"x\"}, \"defined\": {\"signal\": \"isValid(datum[\\\"tvd\\\"]) && isFinite(+datum[\\\"tvd\\\"])\"}}}, \"style\": [\"line\"]}]}, {\"type\": \"symbol\", \"name\": \"layer_1_marks\", \"from\": {\"data\": \"data_0\"}, \"encode\": {\"update\": {\"fill\": {\"value\": \"transparent\"}, \"tooltip\": {\"signal\": \"{\\\"Column 1\\\": isValid(datum[\\\"column-1\\\"]) ? datum[\\\"column-1\\\"] : \\\"\\\"+datum[\\\"column-1\\\"], \\\"Column 2\\\": isValid(datum[\\\"column-2\\\"]) ? datum[\\\"column-2\\\"] : \\\"\\\"+datum[\\\"column-2\\\"]}\"}, \"stroke\": {\"field\": \"model\", \"scale\": \"color\"}, \"x\": {\"field\": \"index\", \"scale\": \"x\"}, \"y\": {\"field\": \"tvd\", \"scale\": \"y\"}, \"opacity\": {\"value\": 0.7}}}, \"style\": [\"point\"]}], \"scales\": [{\"name\": \"x\", \"type\": \"point\", \"domain\": {\"fields\": [{\"data\": \"source_0_x_domain_index_0\", \"field\": \"index\"}, {\"data\": \"data_0_x_domain_index_1\", \"field\": \"index\"}], \"sort\": true}, \"range\": [0, {\"signal\": \"width\"}], \"padding\": 0.5}, {\"name\": \"y\", \"type\": \"linear\", \"domain\": {\"fields\": [{\"data\": \"source_0\", \"field\": \"tvd\"}, {\"data\": \"data_0\", \"field\": \"tvd\"}]}, \"range\": [{\"signal\": \"height\"}, 0], \"nice\": true, \"zero\": true}, {\"name\": \"color\", \"type\": \"ordinal\", \"domain\": {\"fields\": [{\"data\": \"source_0_color_domain_model_0\", \"field\": \"model\"}, {\"data\": \"data_0_color_domain_model_1\", \"field\": \"model\"}], \"sort\": true}, \"range\": \"category\"}], \"axes\": [{\"scale\": \"y\", \"zindex\": 0, \"minExtent\": 0, \"labels\": false, \"grid\": true, \"ticks\": false, \"maxExtent\": 0, \"aria\": false, \"gridScale\": \"x\", \"tickCount\": {\"signal\": \"ceil(height/40)\"}, \"orient\": \"left\", \"domain\": false}, {\"scale\": \"x\", \"orient\": \"bottom\", \"title\": \"Pairs of columns (ordered from best fit to worst)\", \"zindex\": 0, \"labelAngle\": 270, \"labelBaseline\": \"middle\", \"grid\": false, \"labels\": false, \"labelAlign\": \"right\"}, {\"scale\": \"y\", \"zindex\": 0, \"title\": \"Total variation distance\", \"orient\": \"left\", \"grid\": false, \"labelOverlap\": true, \"tickCount\": {\"signal\": \"ceil(height/40)\"}}], \"style\": \"cell\", \"legends\": [{\"stroke\": \"color\", \"symbolType\": \"circle\", \"title\": \"model\", \"encode\": {\"symbols\": {\"update\": {\"fill\": {\"value\": \"transparent\"}, \"opacity\": {\"value\": 0.7}}}}}], \"width\": 400, \"background\": \"white\", \"padding\": 5, \"height\": 400}, {\"mode\": \"vega\"});\n",
        "</script>"
       ],
       "text/plain": [
@@ -120,9 +148,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "LPM Plot (Python 3.12)",
    "language": "python",
-   "name": "python3"
+   "name": "lpm-plot"
   },
   "language_info": {
    "codemirror_mode": {
@@ -134,7 +162,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.3"
+   "version": "3.12.11"
   }
  },
  "nbformat": 4,