@qe-libs/rena-wasm 0.1.7 → 0.1.8

package/README.md

@@ -91,6 +91,26 @@ const model = ena.fit(rows, { codes, units, conversations, window: 4, weightMode
 
 ---
 
+## Modeling a Subset of Units
+
+`unitsUsed` (= R's `units.used`) lists the units to model, as unit keys (the
+unit column values joined with `__`, as in `model.unitLabels`). Every row
+stays in the data: rows of other units still count as context in the modeled
+units' windows, but those units get no network and never reach sphere
+normalization, centering or rotation. Omit it to model every unit.
+
+```js
+// Students' connections to what teachers said are kept; teachers aren't units.
+const model = ena.fit(rows, { codes, units: ['Role', 'Name'], conversations,
+                              window: 4, unitsUsed: studentKeys });
+```
+
+`unitsUsed` works in `fit()`, `accumulate()`, `tuneWindowSize()` and `pria()`.
+This differs from dropping the other units' rows, which also removes them from
+everyone's windows.
+
+---
+
 ## Reduced-Code Search (PRIA)
 
 `pria()` finds the largest set of codes (up to `removeNum`, never leaving

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qe-libs/rena-wasm",
-  "version": "0.1.7",
+  "version": "0.1.8",
   "description": "JavaScript/WebAssembly ENA pipeline — thin orchestration layer over @qe-libs/libqe-wasm",
   "main": "src/index.js",
   "type": "module",

package/src/data.js

@@ -24,6 +24,10 @@ export function rowKey(row, cols) {
  * @param {string[]} codes      - Code column names
  * @param {string[]} unitCols   - Column(s) that identify a unit (e.g. ['UserName', 'Condition'])
  * @param {string[]} convoCols  - Column(s) that identify a conversation (e.g. ['Condition', 'GroupName'])
+ * @param {string[]|null} [unitsUsed=null] - Unit keys (rowKey format) to model
+ *   (= R's `units.used`). Rows of other units stay in their conversations, so
+ *   they still count as context in the included units' windows, but they get
+ *   no unit (unitOf = -1) and so produce no network. null = every unit.
  *
  * @returns {{
  *   codeMatrix:  Float64Array,            // n_rows × n_codes, row-major
@@ -31,14 +35,14 @@ export function rowKey(row, cols) {
  *   nCodes:      number,
  *   nUnits:      number,
  *   unitLabels:  string[],                // unit key for each unit index
- *   unitOf:      Int32Array,              // unit index for each row
+ *   unitOf:      Int32Array,              // unit index for each row (-1 = not a modeled unit)
  *   convoOf:     Int32Array,              // conversation index for each row
  *   convoGroups: Map<number, number[]>,   // convoIdx → [rowIdx, ...]
  *   metaData:    Object[],               // one metadata object per unit (first-row representative)
  *   metaCols:    string[],               // names of metadata columns
  * }}
  */
-export function parseData(rows, codes, unitCols, convoCols) {
+export function parseData(rows, codes, unitCols, convoCols, unitsUsed = null) {
     const nRows  = rows.length;
     const nCodes = codes.length;
 
@@ -58,6 +62,8 @@ export function parseData(rows, codes, unitCols, convoCols) {
     // Per-unit metadata rows — populated on first occurrence of each unit.
     const metaData = [];
 
+    const used = unitsUsed ? new Set(unitsUsed.map(String)) : null;
+
     for (let i = 0; i < nRows; i++) {
         const row = rows[i];
 
@@ -68,7 +74,9 @@ export function parseData(rows, codes, unitCols, convoCols) {
 
         // Unit index
         const uKey = rowKey(row, unitCols);
-        if (!unitIndex.has(uKey)) {
+        if (used && !used.has(uKey)) {
+            unitOf[i] = -1;
+        } else if (!unitIndex.has(uKey)) {
             const uIdx = unitIndex.size;
             unitIndex.set(uKey, uIdx);
             // First row for this unit → representative metadata
@@ -76,7 +84,7 @@ export function parseData(rows, codes, unitCols, convoCols) {
             for (const col of metaCols) meta[col] = row[col];
             metaData[uIdx] = meta;
         }
-        unitOf[i] = unitIndex.get(uKey);
+        if (unitOf[i] !== -1) unitOf[i] = unitIndex.get(uKey);
 
         // Conversation index
         const cKey = rowKey(row, convoCols);
@@ -90,6 +98,9 @@ export function parseData(rows, codes, unitCols, convoCols) {
 
     const unitLabels = Array.from(unitIndex.keys());
     const nUnits     = unitLabels.length;
+    if (used && nUnits === 0) {
+        throw new Error('opts.unitsUsed matched no units in the data');
+    }
 
     return { codeMatrix, nRows, nCodes, nUnits, unitLabels, unitOf, convoOf, convoGroups,
              metaData, metaCols };

package/src/index.js

@@ -407,6 +407,8 @@ export default async function loadENA() {
          * @param {number[]} [opts.groupB]         - Unit indices for means rotation group B
          * @param {object}   [opts.gParams]        - Pre-built GMR parameters for 'generalized' rotation
          * @param {number}   [opts.dims=2]         - Number of dimensions to return
+         * @param {string[]} [opts.unitsUsed]      - Unit keys to model (= R's units.used);
+         *                                           other units' rows remain as context
          *
          * @returns {ENAModel}
          */
@@ -426,6 +428,7 @@ export default async function loadENA() {
                 dims                 = 2,
                 codeMask,
                 weightModel,
+                unitsUsed,
             } = opts;
 
             if (!codes?.length)         throw new Error('opts.codes is required');
@@ -442,7 +445,7 @@ export default async function loadENA() {
 
             const { codeMatrix, nRows, nCodes, nUnits, unitLabels,
                     unitOf, convoGroups, metaData } =
-                parseData(rows, codes, units, conversations);
+                parseData(rows, codes, units, conversations, unitsUsed);
 
             // Every model accumulates through the tensor path; a plain moving
             // window is expressed as defaultTensor(window).
@@ -486,11 +489,12 @@ export default async function loadENA() {
                 tensor:  tensorDef,
                 codeMask,
                 weightModel,
+                unitsUsed,
             } = opts;
 
             const { codeMatrix, nRows, nCodes, nUnits, unitLabels,
                     unitOf, convoGroups, metaData } =
-                parseData(rows, codes, units, conversations);
+                parseData(rows, codes, units, conversations, unitsUsed);
 
             const { networks, rowConnectionCounts } = accumulateTensor(
                 qe, rows, codeMatrix, nRows, nCodes, nUnits,
@@ -509,7 +513,7 @@ export default async function loadENA() {
                 // (= R's ENAAccumulation$`_function.call`).
                 _call: { rows, codes, units, conversations,
                          window: windowSize, binary, ordered, tensor: tensorDef,
-                         weightModel },
+                         weightModel, unitsUsed },
             };
         },
 
@@ -547,12 +551,12 @@ export default async function loadENA() {
                 'maxSize must be greater than minSize to compare windows.'
             );
 
-            const { rows, codes, units, conversations, binary, ordered, weightModel } = call;
+            const { rows, codes, units, conversations, binary, ordered, weightModel, unitsUsed } = call;
 
             // Parse once; only the window size changes between iterations.
             const { codeMatrix, nRows, nCodes, nUnits, unitLabels,
                     unitOf, convoGroups, metaData } =
-                parseData(rows, codes, units, conversations);
+                parseData(rows, codes, units, conversations, unitsUsed);
             const nConnections = ordered ? nCodes * nCodes : qe.choose_two(nCodes);
 
             // 1. Rebuild + fit at each window, collecting unit points.
@@ -590,7 +594,7 @@ export default async function loadENA() {
             // 4. Rebuild the accumulation at the selected window size.
             return api.accumulate(rows, {
                 codes, units, conversations, window: bestWindow, binary, ordered,
-                weightModel,
+                weightModel, unitsUsed,
             });
         },
 
@@ -722,7 +726,8 @@ export default async function loadENA() {
          * @param {Object[]} rows
          * @param {object}   opts  - fit() options (codes, units, conversations,
          *                           window, binary, ordered, tensor, weightModel,
-         *                           codeMask, rotation, groupA, groupB, gParams)
+         *                           codeMask, rotation, groupA, groupB, gParams,
+         *                           unitsUsed)
          *                           plus removeNum (default 3) and threshold
          *                           (default 0.95). `dims` is ignored: scoring
          *                           uses dims 1:2 and the variance uses all dims.
@@ -735,7 +740,7 @@ export default async function loadENA() {
                 window: windowSize = 4, binary = true, ordered = false,
                 tensor: tensorDef, weightModel, codeMask,
                 rotation = 'svd', gParams, groupA, groupB,
-                removeNum = 3, threshold = 0.95,
+                removeNum = 3, threshold = 0.95, unitsUsed,
             } = opts;
             if (!codes?.length)         throw new Error('opts.codes is required');
             if (!units?.length)         throw new Error('opts.units is required');
@@ -749,7 +754,7 @@ export default async function loadENA() {
             // Accumulate once, exactly as fit() would for these options.
             const { codeMatrix, nRows, nCodes, nUnits, unitLabels,
                     unitOf, convoGroups, metaData } =
-                parseData(rows, codes, units, conversations);
+                parseData(rows, codes, units, conversations, unitsUsed);
             const { networks: raw } = accumulateTensor(
                 qe, rows, codeMatrix, nRows, nCodes, nUnits,
                 unitOf, convoGroups, tensorDef ?? defaultTensor(windowSize),

package/src/tensor.js

@@ -197,10 +197,13 @@ export function accumulateTensor(qe, rows, codeMatrix, nRows, nCodes, nUnits,
             ? buildContextLookupWithTimes(rows, rowIndices, factors, factorLevels, timesCol)
             : buildContextLookup(rows, rowIndices, factors, factorLevels);
 
-        // Group response rows by unit (within this conversation)
+        // Group response rows by unit (within this conversation). Rows with
+        // no unit (unitOf = -1, excluded via unitsUsed) are never responses,
+        // but stay in convoCodes as context for the other units' windows.
         const unitConvoRows = new Map();
         for (let r = 0; r < nConvo; r++) {
             const unit = unitOf[rowIndices[r]];
+            if (unit < 0) continue;
             if (!unitConvoRows.has(unit)) unitConvoRows.set(unit, []);
             unitConvoRows.get(unit).push(r);  // local (conversation-relative) index
         }