@datagrok/eda 1.5.0 → 1.5.1

package/package.json

@@ -1,12 +1,12 @@
 {
   "name": "@datagrok/eda",
   "friendlyName": "EDA",
-  "version": "1.5.0",
+  "version": "1.5.1",
   "description": "Exploratory Data Analysis Tools",
   "dependencies": {
     "@datagrok-libraries/math": "^1.2.6",
     "@datagrok-libraries/ml": "^6.10.10",
-    "@datagrok-libraries/statistics": "^1.12.0",
+    "@datagrok-libraries/statistics": "^1.12.1",
     "@datagrok-libraries/tutorials": "^1.7.4",
     "@datagrok-libraries/utils": "^4.7.0",
     "@keckelt/tsne": "^1.0.2",

package/src/pls/pls-constants.ts

@@ -46,6 +46,7 @@ export enum TITLE {
   BROWSE = 'Browse',
   ANALYSIS = 'Features Analysis',
   QUADRATIC = 'Quadratic',
+  BIAS = 'bias',
 }
 
 /** Tooltips */
@@ -102,6 +103,10 @@ export const X_COORD = 200;
 export const Y_COORD = 200;
 export const DELAY = 2000;
 
+export const MAX_ROWS_IN_PREDICTION_TOOLTIP = 20;
+
+export const NUMS_AFTER_COMMA = 3;
+
 /** Curves colors */
 export enum COLOR {
   AXIS = '#838383',

package/src/pls/pls-tools.ts

@@ -4,9 +4,10 @@ import * as grok from 'datagrok-api/grok';
 import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 
-import {PLS_ANALYSIS, ERROR_MSG, TITLE, HINT, LINK, COMPONENTS, INT, TIMEOUT,
+import {PLS_ANALYSIS, ERROR_MSG, TITLE, HINT, LINK, COMPONENTS,
   RESULT_NAMES, WASM_OUTPUT_IDX, RADIUS, LINE_WIDTH, COLOR, X_COORD, Y_COORD,
-  DEMO_INTRO_MD, DEMO_RESULTS_MD, DEMO_RESULTS} from './pls-constants';
+  DEMO_INTRO_MD, DEMO_RESULTS_MD, DEMO_RESULTS, NUMS_AFTER_COMMA,
+  MAX_ROWS_IN_PREDICTION_TOOLTIP} from './pls-constants';
 import {checkWasmDimensionReducerInputs, checkColumnType, checkMissingVals, describeElements} from '../utils';
 import {_partialLeastSquareRegressionInWebWorker} from '../../wasm/EDAAPI';
 import {carsDataframe} from '../data-generators';
@@ -54,6 +55,19 @@ function setStyle(valid: boolean, element: HTMLElement, tooltip: string, errorMs
   }
 };
 
+function getModelFormulaTerms(loadingsRegrCoefsTable: DG.DataFrame, bias: number): Map<string, number> {
+  const featureNames = loadingsRegrCoefsTable.col(TITLE.FEATURE)!.toList() as string[];
+  const regrCoefs = loadingsRegrCoefsTable.col(TITLE.REGR_COEFS)!.getRawData();
+
+  const terms = new Map([[TITLE.BIAS as string, bias]]);
+
+  featureNames.forEach((name, idx) => {
+    terms.set(name, regrCoefs[idx]);
+  });
+
+  return terms;
+}
+
 /** Return lines */
 export function getLines(names: string[]): DG.FormulaLine[] {
   const lines: DG.FormulaLine[] = [];
@@ -115,7 +129,7 @@ export async function getPlsAnalysis(input: PlsInput): Promise<PlsOutput> {
 
 /** Return debiased predction by PLS regression */
 function debiasedPrediction(features: DG.ColumnList, params: DG.Column,
-  target: DG.Column, biasedPrediction: DG.Column): DG.Column {
+  target: DG.Column, biasedPrediction: DG.Column): {debiased: DG.Column, bias: number} {
   const samples = target.length;
   const dim = features.length;
   const rawParams = params.getRawData();
@@ -131,7 +145,7 @@ function debiasedPrediction(features: DG.ColumnList, params: DG.Column,
   for (let i = 0; i < samples; ++i)
     debiased[i] = bias + biased[i];
 
-  return DG.Column.fromFloat32Array('Debiased', debiased, samples);
+  return {debiased: DG.Column.fromFloat32Array('Debiased', debiased, samples), bias: bias};
 }
 
 /** Return an input for the quadratic PLS regression */
@@ -223,7 +237,8 @@ async function performMVA(input: PlsInput, analysisType: PLS_ANALYSIS): Promise<
 
   // 1. Predicted vs Reference scatter plot
   // Debias prediction (since PLS center data)
-  const pred = debiasedPrediction(features, result.regressionCoefficients, input.predict, result.prediction);
+  const debiased = debiasedPrediction(features, result.regressionCoefficients, input.predict, result.prediction);
+  const pred = debiased.debiased;
   pred.name = cols.getUnusedName(`${input.predict.name} ${RESULT_NAMES.SUFFIX}`);
   cols.add(pred);
   const predictVsReferScatter = view.addViewer(DG.Viewer.scatterPlot(sourceTable, {
@@ -250,6 +265,9 @@ async function performMVA(input: PlsInput, analysisType: PLS_ANALYSIS): Promise<
     help: LINK.COEFFS,
     showValueSelector: false,
     showStackSelector: false,
+    description: `bias = ${debiased.bias.toFixed(NUMS_AFTER_COMMA)}`,
+    descriptionVisibilityMode: 'Always',
+    descriptionPosition: 'Bottom',
   }));
 
   // 3. Loadings Scatter Plot
@@ -348,6 +366,10 @@ async function performMVA(input: PlsInput, analysisType: PLS_ANALYSIS): Promise<
       ['left', 'left', 'right', 'right', 'left'],
     );
   }
+
+  // Add formula tooltip to the prediction column
+  const modelFormulaTerms = getModelFormulaTerms(loadingsRegrCoefsTable, debiased.bias);
+  setPredictionTooltip(view, pred, modelFormulaTerms);
 } // performMVA
 
 /** Run multivariate analysis (PLS) */
@@ -559,3 +581,79 @@ export async function runDemoMVA(): Promise<void> {
 
   await runMVA(PLS_ANALYSIS.DEMO);
 }
+
+function setPredictionTooltip(view: DG.TableView, predCol: DG.Column, modelTerms: Map<string, number>): void {
+  view.grid.onCellTooltip((cell, x, y) => {
+    if (cell.isColHeader) {
+      const cellCol = cell.tableColumn;
+
+      if (cellCol == null)
+        return false;
+
+      if (cellCol.name === predCol.name) {
+        ui.tooltip.show(getPredictionTooltip(modelTerms, predCol), x, y);
+        return true;
+      }
+    }
+    return false;
+  });
+}
+
+function getPredictionTooltip(modelTerms: Map<string, number>, predCol: DG.Column): HTMLElement {
+  let idx = 0;
+  const bias = modelTerms.get(TITLE.BIAS) ?? 0;
+  const elements: HTMLElement[] = [];
+  if (Math.abs(bias) > 0) {
+    const biasEl = ui.divText(`${bias}`);
+    biasEl.style.marginTop = '2px';
+    biasEl.style.marginLeft = '4px';
+    elements.push(biasEl);
+    ++idx;
+  }
+
+  const sortedTerms = [...modelTerms.entries()]
+    .filter(([key]) => key !== TITLE.BIAS)
+    .sort((a, b) => Math.abs(b[1]) - Math.abs(a[1]));
+
+  const maxFeatureRows = MAX_ROWS_IN_PREDICTION_TOOLTIP - elements.length;
+  const hasOverflow = sortedTerms.length > maxFeatureRows;
+  const visibleTerms = hasOverflow ? sortedTerms.slice(0, maxFeatureRows - 1) : sortedTerms;
+
+  for (const [key, value] of visibleTerms) {
+    const signEl = ui.divText(idx > 0 ? '+ ' : '');
+    signEl.style.marginRight = '4px';
+    signEl.style.marginLeft = '4px';
+
+    const featureEl = ui.divText(`${key}`);
+    featureEl.style.fontWeight = 'bold';
+
+    const valueEl = ui.divText(` * ${value > 0 ? value : `(${value})`}`);
+    valueEl.style.marginLeft = '4px';
+
+    const rowEl = ui.divH([signEl, featureEl, valueEl]);
+    rowEl.style.marginTop = '4px';
+    elements.push(rowEl);
+
+    ++idx;
+  }
+
+  if (hasOverflow) {
+    const hidden = sortedTerms.length - visibleTerms.length;
+    const ellipsisEl = ui.divText(`(${hidden} more term${hidden > 1 ? 's' : ''})`);
+    ellipsisEl.style.marginTop = '4px';
+    ellipsisEl.style.marginLeft = '4px';
+    ellipsisEl.style.fontStyle = 'italic';
+    elements.push(ellipsisEl);
+  }
+
+  const headerEl = ui.divText('Formula:');
+
+  const leftEl = ui.divText(`${predCol.name} = `);
+  leftEl.style.fontWeight = 'bold';
+  leftEl.style.marginTop = '4px';
+
+  const elementsContainer = ui.divV(elements);
+  elementsContainer.style.marginTop = '4px';
+
+  return ui.divV([headerEl, leftEl, elementsContainer]);
+}

package/src/probabilistic-scoring/prob-scoring.ts

@@ -540,13 +540,13 @@ export class Pmpo {
     const rows = rootsCol.querySelectorAll('div.d4-flex-row.ui-div.statistics-mpo-row');
 
     rows.forEach((row, idx) => {
-      const children = row.children;
-      if (children.length < 2) // expecting descriptor name, weight & profile
+      const editor = row.querySelector('.statistics-mpo-line-editor') as HTMLElement;
+      if (!editor)
         return;
 
-      const profileRoot = children[2] as HTMLElement;
-      profileRoot.style.width = '100%';
-      this.desirabilityProfileRoots.set(names[idx], profileRoot);
+      editor.style.width = '100%';
+      editor.style.height = '100%';
+      this.desirabilityProfileRoots.set(names[idx], editor);
     });
   } // updateDesirabilityProfileData