Learn: rework binning and linked-views lessons

docs/architecture/11-learning-section.md

@@ -42,7 +42,11 @@ Inside a `:::progression`, each `##` heading is a stage: heading → tab label,
 the following fenced `vega-lite` block → spec. A `:::data` block names datasets once for the
 whole lesson; specs reference them with `{ "data": { "name": … } }` and `injectDatasets`
 merges the rows in at render time — so a shared dataset isn't repeated per stage, and the
-source pane keeps a stage's grammar legible instead of burying it under data.
+source pane keeps a stage's grammar legible instead of burying it under data. Every lesson
+uses the `:::data` form (never per-stage inline rows), targets a misconception rather than
+a chart type, and closes with a "take it further" prose beat that leans on the per-stage
+"Open in Astrolabe" links — the roster and per-lesson briefs live in
+`docs/exploration/lessons-roadmap.md`.
 
 ## The pipeline
 

src/learn/lessons/binning.md

@@ -5,10 +5,18 @@ tagline: How one word turns a noisy bar chart into a distribution — and where
 ---
 
 Counting a continuous field is the most common chart that's _almost_ right. The naive
-version compiles, renders, and quietly lies about your data. Walk the four stages below —
+version compiles, renders, and quietly lies about your data. Walk the stages below — each
-each tab is one small edit — and watch a picket fence become a distribution, then a finished
+tab is one small edit — and watch a picket fence become a distribution, then a finished
 chart.
 
+:::data
+{
+"orders": [
+{"minutes":12},{"minutes":14},{"minutes":15},{"minutes":16},{"minutes":18},{"minutes":19},{"minutes":20},{"minutes":21},{"minutes":22},{"minutes":23},{"minutes":24},{"minutes":25},{"minutes":26},{"minutes":28},{"minutes":30},{"minutes":31},{"minutes":33},{"minutes":35},{"minutes":37},{"minutes":40},{"minutes":43},{"minutes":46},{"minutes":50},{"minutes":55},{"minutes":61},{"minutes":68},{"minutes":77},{"minutes":86}
+]
+}
+:::
+
 :::progression
 
 ## raw counts
@@ -20,12 +28,12 @@ fence, not a distribution. It looks almost right, which is exactly what makes it
 ```vega-lite
 {
   "$schema": "https://vega.github.io/schema/vega-lite/v6.json",
+  "data": { "name": "orders" },
   "mark": "bar",
   "encoding": {
     "x": { "field": "minutes", "type": "quantitative" },
     "y": { "aggregate": "count" }
-  },
+  }
-  "data": { "values": [{"minutes":12},{"minutes":14},{"minutes":15},{"minutes":16},{"minutes":18},{"minutes":19},{"minutes":20},{"minutes":21},{"minutes":22},{"minutes":23},{"minutes":24},{"minutes":25},{"minutes":26},{"minutes":28},{"minutes":30},{"minutes":31},{"minutes":33},{"minutes":35},{"minutes":37},{"minutes":40},{"minutes":43},{"minutes":46},{"minutes":50},{"minutes":55},{"minutes":61},{"minutes":68},{"minutes":77},{"minutes":86}] }
 }
 ```
 
@@ -37,12 +45,12 @@ counts each bucket — a real histogram from a one-word edit.
 ```vega-lite
 {
   "$schema": "https://vega.github.io/schema/vega-lite/v6.json",
+  "data": { "name": "orders" },
   "mark": "bar",
   "encoding": {
     "x": { "field": "minutes", "type": "quantitative", "bin": true },
     "y": { "aggregate": "count" }
-  },
+  }
-  "data": { "values": [{"minutes":12},{"minutes":14},{"minutes":15},{"minutes":16},{"minutes":18},{"minutes":19},{"minutes":20},{"minutes":21},{"minutes":22},{"minutes":23},{"minutes":24},{"minutes":25},{"minutes":26},{"minutes":28},{"minutes":30},{"minutes":31},{"minutes":33},{"minutes":35},{"minutes":37},{"minutes":40},{"minutes":43},{"minutes":46},{"minutes":50},{"minutes":55},{"minutes":61},{"minutes":68},{"minutes":77},{"minutes":86}] }
 }
 ```
 
@@ -54,24 +62,51 @@ Take control of the resolution: `bin: { step: 10 }` forces clean 10-minute bucke
 ```vega-lite
 {
   "$schema": "https://vega.github.io/schema/vega-lite/v6.json",
+  "data": { "name": "orders" },
   "mark": "bar",
   "encoding": {
     "x": { "field": "minutes", "type": "quantitative", "bin": { "step": 10 }, "title": "Delivery time (min)" },
     "y": { "aggregate": "count", "title": "Orders" }
+  }
+}
+```
+
+## + a mean line
+
+The first act of _composition_: the spec becomes a `layer` of two marks sharing the same
+data and x-axis — the bars, and a `rule` at the mean. Each layer keeps its own mark and
+encoding; the shared scale is what makes them one chart. This one jump is most of what
+"layering" means.
+
+```vega-lite
+{
+  "$schema": "https://vega.github.io/schema/vega-lite/v6.json",
+  "data": { "name": "orders" },
+  "layer": [
+    {
+      "mark": "bar",
+      "encoding": {
+        "x": { "field": "minutes", "type": "quantitative", "bin": { "step": 10 }, "title": "Delivery time (min)" },
+        "y": { "aggregate": "count", "title": "Orders" }
+      }
     },
-  "data": { "values": [{"minutes":12},{"minutes":14},{"minutes":15},{"minutes":16},{"minutes":18},{"minutes":19},{"minutes":20},{"minutes":21},{"minutes":22},{"minutes":23},{"minutes":24},{"minutes":25},{"minutes":26},{"minutes":28},{"minutes":30},{"minutes":31},{"minutes":33},{"minutes":35},{"minutes":37},{"minutes":40},{"minutes":43},{"minutes":46},{"minutes":50},{"minutes":55},{"minutes":61},{"minutes":68},{"minutes":77},{"minutes":86}] }
+    {
+      "mark": { "type": "rule", "color": "#d6336c", "size": 2 },
+      "encoding": { "x": { "field": "minutes", "aggregate": "mean" } }
+    }
+  ]
 }
 ```
 
 ## polished
 
-The last 20%: round the bar tops, add a tooltip that reports each bucket's range and count,
+The last 20% is legibility, not structure: round the bar tops, and add a tooltip that
-and _layer_ a mean line over the bars. Composition is where polish lives — one spec, two
+reports each bucket's range and count.
-marks sharing an axis.
 
 ```vega-lite
 {
   "$schema": "https://vega.github.io/schema/vega-lite/v6.json",
+  "data": { "name": "orders" },
   "layer": [
     {
       "mark": { "type": "bar", "cornerRadiusEnd": 2 },
@@ -88,8 +123,7 @@ marks sharing an axis.
       "mark": { "type": "rule", "color": "#d6336c", "size": 2 },
       "encoding": { "x": { "field": "minutes", "aggregate": "mean" } }
     }
-  ],
+  ]
-  "data": { "values": [{"minutes":12},{"minutes":14},{"minutes":15},{"minutes":16},{"minutes":18},{"minutes":19},{"minutes":20},{"minutes":21},{"minutes":22},{"minutes":23},{"minutes":24},{"minutes":25},{"minutes":26},{"minutes":28},{"minutes":30},{"minutes":31},{"minutes":33},{"minutes":35},{"minutes":37},{"minutes":40},{"minutes":43},{"minutes":46},{"minutes":50},{"minutes":55},{"minutes":61},{"minutes":68},{"minutes":77},{"minutes":86}] }
 }
 ```
 
@@ -99,6 +133,9 @@ marks sharing an axis.
 **The sharp edge.** Tempted to wire a slider to the bin width? It won't work. In Vega-Lite,
 `bin.step` and `maxbins` are fixed numbers — no parameter or expression drives them, so a
 bound slider compiles fine and then does nothing. The one binning property you _can_ make
-interactive is `extent`: brush an interval selection to re-bin a chosen range. That's a
+interactive is `extent`: brush an interval selection to re-bin a chosen range.
-lesson of its own.
 :::
+
+Take it further: open the last stage in Astrolabe (the link under the chart) and try a
+`step` of 5 against 20 — watch the story the histogram tells change with the resolution.
+Then swap the rule's `mean` for `median` and see which one your outliers drag.

src/learn/lessons/linked-views.md

@@ -12,8 +12,8 @@ re-aggregate by hand for every window you got curious about.
 
 So we build three views over one interval selection. Brush a span of the run on the top
 chart and the other two recompute over exactly that window — the cumulative gap between the
-arms, and their share split. Five edits, and all three stay in sync through a single
+arms, and their share split. A handful of small edits, and everything stays in sync
-`param`.
+through a single `param`.
 
 :::data
 {
@@ -522,14 +522,165 @@ you'll drag across, because a selection lives on the view whose marks define it.
 }
 ```
 
-## + a linked gap
+## + filter by the brush
 
-Append a second view that reads the selection. `filter: {param: brush}` keeps only the
+Append a second view that reads the selection — `filter: {param: brush}` is the entire
-brushed minutes; then it pivots A and B into columns, re-accumulates each, and plots
+link. Everything downstream of that filter re-runs over only the brushed rows, so this
-A − B. Now dragging the band on the top chart rebases this one — brush the first half-hour
+copy of the cumulative lines rebases to whatever window you drag: brush the first
-and the early gap shows; brush the tail and it flattens. "Is the imbalance localised in
+half-hour and the early race shows; brush the tail and both lines restart from zero
-time?" gets answered by dragging instead of re-querying. With nothing brushed the selection
+there. With nothing brushed the selection is empty, which by default matches _every_
-is empty, which by default means _every_ row, so it opens on the full run.
+row — that's why it opens on the full run.
+
+```vega-lite
+{
+  "$schema": "https://vega.github.io/schema/vega-lite/v6.json",
+  "vconcat": [
+    {
+      "data": {
+        "name": "ev"
+      },
+      "transform": [
+        {
+          "sort": [
+            {
+              "field": "minute"
+            }
+          ],
+          "window": [
+            {
+              "op": "sum",
+              "field": "n",
+              "as": "cum"
+            }
+          ],
+          "groupby": [
+            "arm"
+          ],
+          "frame": [
+            null,
+            0
+          ]
+        }
+      ],
+      "params": [
+        {
+          "name": "brush",
+          "select": {
+            "type": "interval",
+            "encodings": [
+              "x"
+            ]
+          }
+        }
+      ],
+      "mark": "line",
+      "encoding": {
+        "x": {
+          "field": "minute",
+          "type": "temporal",
+          "title": "Time (UTC)",
+          "axis": {
+            "format": "%H:%M"
+          }
+        },
+        "y": {
+          "field": "cum",
+          "type": "quantitative",
+          "title": "Cumulative assignments"
+        },
+        "color": {
+          "field": "arm",
+          "type": "nominal",
+          "scale": {
+            "domain": [
+              "A",
+              "B"
+            ],
+            "range": [
+              "#3a7ca5",
+              "#e0913a"
+            ]
+          },
+          "title": "Branch"
+        }
+      }
+    },
+    {
+      "data": {
+        "name": "ev"
+      },
+      "transform": [
+        {
+          "filter": {
+            "param": "brush"
+          }
+        },
+        {
+          "sort": [
+            {
+              "field": "minute"
+            }
+          ],
+          "window": [
+            {
+              "op": "sum",
+              "field": "n",
+              "as": "cum"
+            }
+          ],
+          "groupby": [
+            "arm"
+          ],
+          "frame": [
+            null,
+            0
+          ]
+        }
+      ],
+      "mark": "line",
+      "encoding": {
+        "x": {
+          "field": "minute",
+          "type": "temporal",
+          "title": "Time (UTC)",
+          "axis": {
+            "format": "%H:%M"
+          }
+        },
+        "y": {
+          "field": "cum",
+          "type": "quantitative",
+          "title": "Rebased in the window"
+        },
+        "color": {
+          "field": "arm",
+          "type": "nominal",
+          "scale": {
+            "domain": [
+              "A",
+              "B"
+            ],
+            "range": [
+              "#3a7ca5",
+              "#e0913a"
+            ]
+          },
+          "legend": null
+        }
+      }
+    }
+  ]
+}
+```
+
+## + the gap math
+
+Two rebased lines still make you subtract by eye. To plot A − B directly, the rows have
+to change _shape_: `pivot` turns the A and B rows into columns of one row per minute,
+two `calculate`s patch the minutes where an arm is missing, and a two-op `window`
+re-accumulates each column before the final subtraction. Four transforms in service of
+one line — reshaping long rows into wide columns is a craft of its own, but the link to
+the brush is unchanged: the same `filter` still heads the pipeline.
 
 ```vega-lite
 {
@@ -1183,3 +1334,7 @@ brush}` inherits Vega-Lite's default `empty: "all"`, so until you drag something
 matches every row — which is why the dashboard opens on the full run. To make it open blank
 instead, set `empty: "none"` on the selection.
 :::
+
+Take it further: open the last stage in Astrolabe (the link under the chart) and try both
+traps for yourself — move the `params` block onto the gap view and feel the dashboard go
+dead, then put it back and set `empty: "none"` to see the blank-until-brushed variant.