@datagrok/eda 1.0.3

package/scripts/exportForTSConstants.py

@@ -0,0 +1,93 @@
+""" exportConstants.py
+Constants for C/C++-to-wasm export script.
+"""
+
+# export settings constants
+NAME = 'name'
+FOLDER = 'folder'
+RUNTIME_SYSTEM = 'runtimeSystemFile'
+RUNTIME_SYSTEM_FOR_WEBWORKER= 'runtimeSystemForWebWorker'
+PACKAGE_FILE = 'packageFile'
+OPTIMIZATION_MODE = 'optimizationMode'
+TOTAL_MEMORY = 'totalMemory'
+PACKAGE_JSON_FILE = 'packageJsonFile'
+WORKERS_FOLDER = 'workers'
+
+# constants for function specification
+ARGUMENTS = 'arguments'
+OUTPUT = 'output'
+ANNOTATION = 'annotation'
+PROTOTYPE = 'prototype'
+CALL_ARGS = 'callArgs'
+WW_PROTOTYPE = 'prototypeForWebWorker'
+TYPE = 'type'
+COLUMN = 'Column'
+COLUMNS = 'Columns'
+NUM = 'num'
+DATA = 'data'
+NEW = 'new'
+NUM_OF_ROWS = 'numOfRows'
+NUM_OF_COLUMNS = 'numOfColumns'
+REF = 'ref'
+VALUE = 'value'
+SOURCE = 'source'
+TABLE_FROM_COLUMNS = 'tableFromColumns'
+OBJECTS = 'objects'
+
+AUTOMATIC_GENERATION_LINE = '// The following code is generated automatically.'
+
+# constants for processing code that is generated by Emscripten
+EM_LIB_EXTENSION = '.js'
+WW_FILE_SUFFIX = 'ForWebWorker'
+NUM_OF_LINE_TO_MODIFY = 1
+KEY_WORD_TO_ADD = 'export '
+LINE_TO_REPLACE = 'fetch(wasmBinaryFile,{credentials:"same-origin"})' 
+
+# constants for generating JS-code
+CALL_WASM = 'callWasm'
+WORKER_SUFFIX = 'Worker'
+IN_WEBWORKER_SUFFIX = 'InWebWorker'
+WORKER_EXTENSION = '.js'
+CPP_WRAPPER_FUNCTION = 'cppWrapper'
+GET_CPP_INPUT = 'getCppInput'
+GET_RESULT = 'getResult'
+WW_SPACE = ' ' * 2
+WW_SUBSPACE = ' ' * 4
+WW_SUBSUBSPACE = ' ' * 6
+SPACE = ' ' * 2
+SUBSPACE = ' ' * 4
+SUBSUBSPACE = ' ' * 6
+SUBSUBSUBSPACE = ' ' * 8
+API_SUFFIX = 'API'
+SERVICE_PREFFIX = '_'
+ANY_TYPE = 'any'
+OUTPUT_VARIABLE = '_output'
+PROMISE_VARIABLE = '_promise'
+RESULT_VARIBLABLE = '_result'
+ERROR_VARIABLE = '_error'
+
+# file operating constants
+READ_MODE = 'r'
+WRITE_MODE = 'w'
+APPEND_MODE = 'a'
+
+# annotation constants
+ANNOT_INPUT = '//input:'
+ANNOT_OUTPUT = '//output:'
+ANNOT_NAME = '//name:'
+ANNOT_NEW = 'new'
+ANNOT_DATAFRAME = 'dataframe'
+ANNOT_COLUMN = 'column'
+ANNOT_COLUMN_LIST = 'column_list'
+ANNOT_DOT = '.'
+ANNOT_OBJECTS = 'objects'
+
+# auxiliry maps 
+sizesMap = {'rowCount': 'numOfRows', 'columnCount': 'numOfColumns', 'data': 'data'}
+typesMap = {'int': 'number', 'double': 'number', 'column': 'DG.Column', 
+            'column_list': 'DG.ColumnList', 'dataframe': 'DG.DataFrame'}
+
+# Emscripten constants
+EM_MACROS = 'EMSCRIPTEN_KEEPALIVE'
+
+PJSN_SOURCES = 'sources'

package/scripts/func.json

@@ -0,0 +1 @@
+{"pcaExport.cpp": {"principalComponentAnalysis": {"arguments": {"columns": {"type": "floatColumns"}, "componentsCount": {"type": "num"}, "centerNum": {"type": "num"}, "scaleNum": {"type": "num"}, "components": {"type": "newFloatColumns", "numOfRows": {"ref": "columns", "value": "numOfRows"}, "numOfColumns": {"ref": "componentsCount", "value": "data"}}}, "output": {"type": "tableFromColumns", "source": "components"}, "annotation": ["//name: principalComponentAnalysis", "//input: dataframe table", "//input: column_list columns", "//input: int componentsCount", "//input: int centerNum", "//input: int scaleNum", "//output: dataframe result "], "prototype": "principalComponentAnalysis(table, columns, componentsCount, centerNum, scaleNum)", "prototypeForWebWorker": "principalComponentAnalysisInWebWorker(table, columns, componentsCount, centerNum, scaleNum)", "callArgs": "[columns, componentsCount, centerNum, scaleNum]"}, "error": {"arguments": {"col1": {"type": "floatColumn"}, "col2": {"type": "floatColumn"}}, "output": {"type": "double", "source": "_callResult"}, "annotation": ["//name: error", "//input: dataframe df", "//input: column col1", "//input: column col2", "//output: double mad "], "prototype": "error(df, col1, col2)", "prototypeForWebWorker": "errorInWebWorker(df, col1, col2)", "callArgs": "[col1, col2]"}}, "PCA/PCA.cpp": {}, "plsExport.cpp": {"partialLeastSquareRegression": {"arguments": {"features": {"type": "floatColumns"}, "predict": {"type": "floatColumn"}, "componentsCount": {"type": "num"}, "prediction": {"type": "newFloatColumn", "numOfRows": {"ref": "predict", "value": "numOfRows"}}, "regressionCoefficients": {"type": "newFloatColumn", "numOfRows": {"ref": "features", "value": "numOfColumns"}}, "tScores": {"type": "newFloatColumns", "numOfRows": {"ref": "predict", "value": "numOfRows"}, "numOfColumns": {"ref": "componentsCount", "value": "data"}}, "uScores": {"type": "newFloatColumns", "numOfRows": {"ref": "predict", "value": "numOfRows"}, "numOfColumns": {"ref": "componentsCount", "value": "data"}}, "xLoadings": {"type": "newFloatColumns", "numOfRows": {"ref": "features", "value": "numOfColumns"}, "numOfColumns": {"ref": "componentsCount", "value": "data"}}}, "output": {"type": "objects", "source": "['prediction', 'regressionCoefficients', 'tScores', 'uScores', 'xLoadings']"}, "annotation": ["//name: partialLeastSquareRegression", "//input: dataframe table", "//input: column_list features", "//input: column predict", "//input: int componentsCount"], "prototype": "partialLeastSquareRegression(table, features, predict, componentsCount)", "prototypeForWebWorker": "partialLeastSquareRegressionInWebWorker(table, features, predict, componentsCount)", "callArgs": "[features, predict, componentsCount]"}}, "PLS/PLS.cpp": {}, "svmApi.cpp": {"generateDataset": {"arguments": {"kernel": {"type": "num"}, "kernelParams": {"type": "floatColumn"}, "samplesCount": {"type": "num"}, "featuresCount": {"type": "num"}, "min": {"type": "num"}, "max": {"type": "num"}, "violatorsPercentage": {"type": "num"}, "dataset": {"type": "newFloatColumns", "numOfRows": {"ref": "samplesCount", "value": "data"}, "numOfColumns": {"ref": "featuresCount", "value": "data"}}, "labels": {"type": "newFloatColumn", "numOfRows": {"ref": "samplesCount", "value": "data"}}}, "output": {"type": "objects", "source": "['dataset', 'labels']"}, "annotation": ["//name: generateDataset", "//input: int kernel", "//input: column kernelParams", "//input: int samplesCount", "//input: int featuresCount", "//input: double min", "//input: double max", "//input: double violatorsPercentage"], "prototype": "generateDataset(kernel, kernelParams, samplesCount, featuresCount, min, max, violatorsPercentage)", "prototypeForWebWorker": "generateDatasetInWebWorker(kernel, kernelParams, samplesCount, featuresCount, min, max, violatorsPercentage)", "callArgs": "[kernel, kernelParams, samplesCount, featuresCount, min, max, violatorsPercentage]"}, "normalizeDataset": {"arguments": {"data": {"type": "floatColumns"}, "normalizedData": {"type": "newFloatColumns", "numOfRows": {"ref": "data", "value": "numOfColumns"}, "numOfColumns": {"ref": "data", "value": "numOfRows"}}, "means": {"type": "newFloatColumn", "numOfRows": {"ref": "data", "value": "numOfColumns"}}, "stdDevs": {"type": "newFloatColumn", "numOfRows": {"ref": "data", "value": "numOfColumns"}}}, "output": {"type": "objects", "source": "['normalizedData', 'means', 'stdDevs']"}, "annotation": ["//name: normalizeDataset", "//input: column_list data"], "prototype": "normalizeDataset(data)", "prototypeForWebWorker": "normalizeDatasetInWebWorker(data)", "callArgs": "[data]"}, "trainLSSVM": {"arguments": {"gamma": {"type": "num"}, "kernel": {"type": "num"}, "kernelParams": {"type": "floatColumn"}, "modelParamsCount": {"type": "num"}, "precomputedWeightsCount": {"type": "num"}, "dataset": {"type": "floatColumns"}, "labels": {"type": "floatColumn"}, "normalizedData": {"type": "newFloatColumns", "numOfRows": {"ref": "dataset", "value": "numOfColumns"}, "numOfColumns": {"ref": "dataset", "value": "numOfRows"}}, "means": {"type": "newFloatColumn", "numOfRows": {"ref": "dataset", "value": "numOfColumns"}}, "stdDevs": {"type": "newFloatColumn", "numOfRows": {"ref": "dataset", "value": "numOfColumns"}}, "modelParams": {"type": "newFloatColumn", "numOfRows": {"ref": "modelParamsCount", "value": "data"}}, "precomputedWeights": {"type": "newFloatColumn", "numOfRows": {"ref": "precomputedWeightsCount", "value": "data"}}}, "output": {"type": "objects", "source": "['normalizedData', 'means', 'stdDevs', 'modelParams', 'precomputedWeights']"}, "annotation": ["//name: trainLSSVM", "//input: double gamma", "//input: int kernel", "//input: column kernelParams", "//input: int modelParamsCount", "//input: int precomputedWeightsCount", "//input: column_list dataset", "//input: column labels"], "prototype": "trainLSSVM(gamma, kernel, kernelParams, modelParamsCount, precomputedWeightsCount, dataset, labels)", "prototypeForWebWorker": "trainLSSVMInWebWorker(gamma, kernel, kernelParams, modelParamsCount, precomputedWeightsCount, dataset, labels)", "callArgs": "[gamma, kernel, kernelParams, modelParamsCount, precomputedWeightsCount, dataset, labels]"}, "predictByLSSVM": {"arguments": {"kernel": {"type": "num"}, "kernelParams": {"type": "floatColumn"}, "normalizedData": {"type": "floatColumns"}, "labels": {"type": "floatColumn"}, "means": {"type": "floatColumn"}, "stdDevs": {"type": "floatColumn"}, "modelParams": {"type": "floatColumn"}, "precomputedWeights": {"type": "floatColumn"}, "targetData": {"type": "floatColumns"}, "prediction": {"type": "newFloatColumn", "numOfRows": {"ref": "targetData", "value": "numOfRows"}}}, "output": {"type": "column", "source": "prediction"}, "annotation": ["//name: predictByLSSVM", "//input: int kernel", "//input: column kernelParams", "//input: column_list normalizedData", "//input: column labels", "//input: column means", "//input: column stdDevs", "//input: column modelParams", "//input: column precomputedWeights", "//input: column_list targetData", "//output: column prediction"], "prototype": "predictByLSSVM(kernel, kernelParams, normalizedData, labels, means, stdDevs, modelParams, precomputedWeights, targetData)", "prototypeForWebWorker": "predictByLSSVMInWebWorker(kernel, kernelParams, normalizedData, labels, means, stdDevs, modelParams, precomputedWeights, targetData)", "callArgs": "[kernel, kernelParams, normalizedData, labels, means, stdDevs, modelParams, precomputedWeights, targetData]"}, "trainAndAnalyzeLSSVM": {"arguments": {"gamma": {"type": "num"}, "kernel": {"type": "num"}, "kernelParams": {"type": "floatColumn"}, "modelParamsCount": {"type": "num"}, "precomputedWeightsCount": {"type": "num"}, "confusionMatrixElementsCount": {"type": "num"}, "dataset": {"type": "floatColumns"}, "labels": {"type": "floatColumn"}, "normalizedData": {"type": "newFloatColumns", "numOfRows": {"ref": "dataset", "value": "numOfColumns"}, "numOfColumns": {"ref": "dataset", "value": "numOfRows"}}, "means": {"type": "newFloatColumn", "numOfRows": {"ref": "dataset", "value": "numOfColumns"}}, "stdDevs": {"type": "newFloatColumn", "numOfRows": {"ref": "dataset", "value": "numOfColumns"}}, "modelParams": {"type": "newFloatColumn", "numOfRows": {"ref": "modelParamsCount", "value": "data"}}, "precomputedWeights": {"type": "newFloatColumn", "numOfRows": {"ref": "precomputedWeightsCount", "value": "data"}}, "predictedLabels": {"type": "newFloatColumn", "numOfRows": {"ref": "dataset", "value": "numOfRows"}}, "correctness": {"type": "newFloatColumn", "numOfRows": {"ref": "dataset", "value": "numOfRows"}}, "consfusionMatrix": {"type": "newIntColumn", "numOfRows": {"ref": "confusionMatrixElementsCount", "value": "data"}}}, "output": {"type": "objects", "source": "['normalizedData', 'means', 'stdDevs', 'modelParams', 'precomputedWeights', 'predictedLabels', 'correctness', 'consfusionMatrix']"}, "annotation": ["//name: trainAndAnalyzeLSSVM", "//input: double gamma", "//input: int kernel", "//input: column kernelParams", "//input: int modelParamsCount", "//input: int precomputedWeightsCount", "//input: int confusionMatrixElementsCount", "//input: column_list dataset", "//input: column labels"], "prototype": "trainAndAnalyzeLSSVM(gamma, kernel, kernelParams, modelParamsCount, precomputedWeightsCount, confusionMatrixElementsCount, dataset, labels)", "prototypeForWebWorker": "trainAndAnalyzeLSSVMInWebWorker(gamma, kernel, kernelParams, modelParamsCount, precomputedWeightsCount, confusionMatrixElementsCount, dataset, labels)", "callArgs": "[gamma, kernel, kernelParams, modelParamsCount, precomputedWeightsCount, confusionMatrixElementsCount, dataset, labels]"}}}

package/scripts/module.json

@@ -0,0 +1,11 @@
+{
+    "name": "EDA",    
+    "folder": "../wasm",
+    "source": ["pcaExport.cpp", "PCA/PCA.cpp", "plsExport.cpp", "PLS/PLS.cpp", "svmApi.cpp"],    
+    "optimizationMode": "-O3",    
+    "packageFile": "../src/package.ts",
+    "packageJsonFile": "../package.json",    
+    "runtimeSystemFile": "../wasm/callWasm.js",
+    "runtimeSystemForWebWorker": "../wasm/callWasmForWebWorker.js",
+    "totalMemory": "268435456"
+}

package/src/EDAtools.ts

@@ -0,0 +1,46 @@
+// Exploratory data analysis (EDA) tools
+
+import * as grok from 'datagrok-api/grok';
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+
+import {_principalComponentAnalysisInWebWorker,
+  _partialLeastSquareRegressionInWebWorker} from '../wasm/EDAAPI';
+
+import {checkComponenets, checkGeneratorSVMinputs} from './utils';
+
+// Principal components analysis (PCA)
+export async function computePCA(table: DG.DataFrame, features: DG.ColumnList, components: number,
+  center: boolean, scale: boolean): Promise<DG.DataFrame> 
+{
+  checkComponenets(features, components);
+
+  const centerNum = center ? 1 : 0;
+  const scaleNum = scale ? 1 : 0;
+
+  let _output: any;
+  let _promise = _principalComponentAnalysisInWebWorker(table, features, components, centerNum, scaleNum);
+
+  await _promise.then(
+    _result => { _output = _result; },
+    _error => {  throw new Error (`Error: ${_error}`); }
+  );
+
+  return _output;  
+} 
+
+// Partial least square regression (PLS)
+export async function computePLS(table: DG.DataFrame, features: DG.ColumnList, predict: DG.Column, components: number): Promise<any> 
+{
+  checkComponenets(features, components);
+
+  let _output: any;
+  let _promise = _partialLeastSquareRegressionInWebWorker(table, features, predict, components);
+
+  await _promise.then(
+    _result => { _output = _result; },    
+    _error => {  throw new Error (`Error: ${_error}`); }
+  );
+
+  return _output;
+} 

package/src/EDAui.ts

@@ -0,0 +1,118 @@
+// Custom UI for Exploratory data analysis (EDA) tools
+
+import * as grok from 'datagrok-api/grok';
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+
+// Rename PCA columns
+export function renamePCAcolumns(pcaTable: DG.DataFrame): DG.DataFrame {  
+  for (const col of pcaTable.columns.toList()) 
+    col.name = '_PCA' + col.name;
+
+  return pcaTable;
+}
+
+// Predicted vs Reference scatter plot
+export function predictedVersusReferenceScatterPlot(reference: DG.Column, prediction: DG.Column): DG.Viewer {  
+  prediction.name = reference.name + '(predicted)';
+ 
+  let dfReferencePrediction = DG.DataFrame.fromColumns([reference, prediction]);
+  dfReferencePrediction.name = 'Reference vs. Predicted';
+   
+  return DG.Viewer.scatterPlot(dfReferencePrediction, 
+    { title: dfReferencePrediction.name,
+      x: reference.name,
+      y: prediction.name,
+      showRegressionLine: true,
+      markerType: 'circle'
+     });  
+}
+
+// Regression Coefficients Bar Chart
+export function regressionCoefficientsBarChart(features: DG.ColumnList, regressionCoeffs: DG.Column): DG.Viewer {    regressionCoeffs.name = 'regression coefficient';
+ 
+  let namesOfPredictors = [];
+  for (const col of features)
+    namesOfPredictors.push(col.name); 
+  
+  let predictorNamesColumn = DG.Column.fromStrings('feature', namesOfPredictors);  
+ 
+  let dfRegrCoefs = DG.DataFrame.fromColumns([predictorNamesColumn, regressionCoeffs]);
+  dfRegrCoefs.name = 'Regression Coefficients';
+
+  return DG.Viewer.barChart(dfRegrCoefs, 
+    {title: dfRegrCoefs.name, split: 'feature', 
+     value: 'regression coefficient', valueAggrType: 'avg'}); 
+}
+
+// Scores Scatter Plot
+export function scoresScatterPlot(xScores: Array<DG.Column>, yScores: Array<DG.Column>): DG.Viewer {
+  
+  let scoresColumns = [];
+
+  for (let i = 0; i < xScores.length; i++) {
+    xScores[i].name = `x.score.t${i+1}`;
+    scoresColumns.push(xScores[i]);
+  } 
+  
+  for (let i = 0; i < yScores.length; i++) {
+    yScores[i].name = `y.score.u${i+1}`;
+    scoresColumns.push(yScores[i]);
+  }  
+ 
+  let scores = DG.DataFrame.fromColumns(scoresColumns);
+  scores.name = 'Scores';
+  //grok.shell.addTableView(scores);
+ 
+  return DG.Viewer.scatterPlot(scores, 
+    { title: scores.name,
+      x: xScores[0].name,
+      y: yScores[0].name,      
+      markerType: 'circle'
+     });
+}
+
+// Loading Scatter Plot
+export function loadingScatterPlot(features: DG.ColumnList, xLoadings: Array<DG.Column>): DG.Viewer {
+  let loadingCols = [];
+ 
+  let loadingLabels = [];
+  for (let col of features)
+    loadingLabels.push(col.name);
+ 
+  loadingCols.push(DG.Column.fromStrings('labels', loadingLabels)); 
+  
+  for (let i = 0; i < xLoadings.length; i++) {
+    xLoadings[i].name = `x.loading.p${i+1}`;
+    loadingCols.push(xLoadings[i]);
+  }
+ 
+  let dfLoadings = DG.DataFrame.fromColumns(loadingCols);
+  dfLoadings.name = 'Loadings';
+   
+  return DG.Viewer.scatterPlot(dfLoadings, 
+    { title: dfLoadings.name,
+      x: xLoadings[0].name,
+      y: xLoadings[xLoadings.length - 1].name,      
+      markerType: 'circle',
+      labels: 'labels'
+     });
+}
+
+// Add PLS visualization
+export function addPLSvisualization(table: DG.DataFrame, features: DG.ColumnList, predict: DG.Column, plsOutput: any): void {
+
+  let view = grok.shell.getTableView(table.name);
+ 
+  // 1. Predicted vs Reference scatter plot
+  view.addViewer(predictedVersusReferenceScatterPlot(predict, plsOutput[0]));
+  
+  // 2. Regression Coefficients Bar Chart
+  view.addViewer(regressionCoefficientsBarChart(features, plsOutput[1])); 
+ 
+  // 3. Scores Scatter Plot
+  view.addViewer(scoresScatterPlot(plsOutput[2], plsOutput[3]));
+ 
+  // 4. Loading Scatter Plot
+  view.addViewer(loadingScatterPlot(features, plsOutput[4]));  
+}

package/src/dataGenerators.ts

@@ -0,0 +1,74 @@
+// Test data generation tools
+
+/* Do not change these import lines to match external modules in webpack configuration */
+import * as grok from 'datagrok-api/grok';
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+
+import {checkGeneratorSVMinputs} from './utils';
+import {_generateDatasetInWebWorker} from '../wasm/EDAAPI';
+
+const SVM_GEN_FEATURES_INDEX = 0;
+const SVM_GEN_LABELS_INDEX = 1;
+const SVM_FEATURE_NAME = 'Feature #';
+const SVM_LABEL_NAME = 'Label';
+
+// Returns the dataframe "cars"
+export function carsDataframe(): DG.DataFrame {
+  return DG.DataFrame.fromColumns(
+    [
+      DG.Column.fromStrings('model', ['alfaromeo', 'audi', 'bmw', 'chevrolet', 'dodge1', 'dodge2', 'honda1', 'honda2', 'isuzu', 'jaguar', 'mazda', 'mercedes', 'mercury', 'mitsubishi', 'nissan1', 'nissan2', 'peugot', 'plymouth', 'porsche', 'saab', 'subaru', 'toyota1', 'toyota2', 'toyota3', 'toyota4', 'volkswagen1', 'volkswagen2', 'volvo1', 'volvo2', 'volvo3']),
+      DG.Column.fromInt32Array('diesel', new Int32Array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 1])),
+      DG.Column.fromInt32Array('turbo', new Int32Array([0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1])),
+      DG.Column.fromInt32Array('two.doors', new Int32Array([1, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0])),
+      DG.Column.fromInt32Array('hatchback', new Int32Array([1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0])),      
+      DG.Column.fromFloat32Array('wheel.base', new Float32Array([94.5, 105.80000305175781, 101.19999694824219, 94.5, 93.69999694824219, 93.69999694824219, 93.69999694824219, 96.5, 94.30000305175781, 113, 93.0999984741211, 115.5999984741211, 102.69999694824219, 93.69999694824219, 94.5, 94.5, 93.69999694824219, 114.19999694824219, 89.5, 99.0999984741211, 97.19999694824219, 95.69999694824219, 95.69999694824219, 98.4000015258789, 102.4000015258789, 97.30000305175781, 100.4000015258789, 104.30000305175781, 109.0999984741211, 109.0999984741211])),
+      DG.Column.fromFloat32Array('length', new Float32Array([171.1999969482422, 192.6999969482422, 176.8000030517578, 158.8000030517578, 157.3000030517578, 157.3000030517578, 150, 175.39999389648438, 170.6999969482422, 199.60000610351562, 166.8000030517578, 202.60000610351562, 178.39999389648438, 157.3000030517578, 170.1999969482422, 165.3000030517578, 157.3000030517578, 198.89999389648438, 168.89999389648438, 186.60000610351562, 172, 158.6999969482422, 166.3000030517578, 176.1999969482422, 175.60000610351562, 171.6999969482422, 180.1999969482422, 188.8000030517578, 188.8000030517578, 188.8000030517578])),
+      DG.Column.fromFloat32Array('width', new Float32Array([65.5, 71.4000015258789, 64.80000305175781, 63.599998474121094, 63.79999923706055, 63.79999923706055, 64, 65.19999694824219, 61.79999923706055, 69.5999984741211, 64.19999694824219, 71.69999694824219, 68, 64.4000015258789, 63.79999923706055, 63.79999923706055, 63.79999923706055, 68.4000015258789, 65, 66.5, 65.4000015258789, 63.599998474121094, 64.4000015258789, 65.5999984741211, 66.5, 65.5, 66.9000015258789, 67.19999694824219, 68.80000305175781, 68.9000015258789])),
+      DG.Column.fromFloat32Array('height', new Float32Array([52.400001525878906, 55.70000076293945, 54.29999923706055, 52, 50.79999923706055, 50.599998474121094, 52.599998474121094, 54.099998474121094, 53.5, 52.79999923706055, 54.099998474121094, 56.29999923706055, 54.79999923706055, 50.79999923706055, 53.5, 54.5, 50.599998474121094, 58.70000076293945, 51.599998474121094, 56.099998474121094, 52.5, 54.5, 53, 52, 54.900001525878906, 55.70000076293945, 55.099998474121094, 56.20000076293945, 55.5, 55.5])),
+      DG.Column.fromInt32Array('curb.weight', new Int32Array([2823, 2844, 2395, 1909, 2128, 1967, 1956, 2304, 2337, 4066, 1950, 3770, 2910, 1918, 2024, 1951, 1967, 3430, 2800, 2695, 2190, 1985, 2275, 2551, 2480, 2261, 2661, 2912, 3049, 3217])),
+      DG.Column.fromInt32Array('eng.size', new Int32Array([152, 136, 108, 90, 98, 90, 92, 110, 111, 258, 91, 183, 140, 92, 97, 97, 90, 152, 194, 121, 108, 92, 110, 146, 110, 97, 136, 141, 141, 145])),
+      DG.Column.fromInt32Array('horsepower', new Int32Array([154, 110, 101, 70, 102, 68, 76, 86, 78, 176, 68, 123, 175, 68, 69, 69, 68, 95, 207, 110, 82, 62, 56, 116, 73, 52, 110, 114, 160, 106])),
+      DG.Column.fromInt32Array('peak.rpm', new Int32Array([5000, 5500, 5800, 5400, 5500, 5500, 6000, 5800, 4800, 4750, 5000, 4350, 5000, 5500, 5200, 5200, 5500, 4150, 5900, 5250, 4400, 4800, 4500, 4800, 4500, 4800, 5500, 5400, 5300, 4800])),
+      DG.Column.fromInt32Array('symbol', new Int32Array([1, 1, 2, 0, 1, 1, 1, 0, 0, 0, 1, -1, 1, 2, 1, 1, 1, 0, 3, 2, 0, 1, 0, 2, -1, 2, 0, -2, -1, -1])),
+      DG.Column.fromInt32Array('city.mpg', new Int32Array([19, 19, 23, 38, 24, 31, 30, 27, 24, 15, 31, 22, 19, 37, 31, 31, 31, 25, 17, 21, 28, 35, 34, 24, 30, 37, 19, 23, 19, 26])),
+      DG.Column.fromInt32Array('highway.mpg', new Int32Array([26, 25, 29, 43, 30, 38, 34, 33, 29, 19, 38, 25, 24, 41, 37, 37, 38, 25, 25, 28, 33, 39, 36, 30, 33, 46, 24, 28, 25, 27])),
+      DG.Column.fromInt32Array('price', new Int32Array([16500, 17710, 16430, 6575, 7957, 6229, 7129, 8845, 6785, 35550, 7395, 31600, 16503, 5389, 7349, 7299, 6229, 13860, 37028, 12170, 7775, 5348, 7898, 9989, 10698, 7775, 13295, 12940, 19045, 22470])),
+    ]);
+} // carsDataframe
+
+// Generate dataset for testing binary classifiers
+export async function testDataForBinaryClassification(kernel: number, kernelParams: Array<number>, 
+  name: string, samplesCount: number, featuresCount: number, min: number, 
+  max: number, violatorsPercentage: number): Promise<DG.DataFrame> {
+
+  // check inputs
+  checkGeneratorSVMinputs(samplesCount, featuresCount, min, max, violatorsPercentage);
+  
+  // kernel params column
+  const kernelParamsCol = DG.Column.fromList('double', 'kernelParams', kernelParams);
+  
+  // CALL WASM-COMPUTATIONS  
+  let _output: any;
+  let _promise = _generateDatasetInWebWorker(kernel, kernelParamsCol, 
+    samplesCount, featuresCount, min, max, violatorsPercentage);
+
+  await _promise.then(
+    _result => { _output = _result; },
+    _error => {  throw new Error (`Error: ${_error}`); }
+  );
+  
+  // Rename labels column
+  _output[SVM_GEN_LABELS_INDEX].name = SVM_LABEL_NAME;
+  
+  // Rename feature columns
+  for (const col of _output[SVM_GEN_FEATURES_INDEX])
+    col.name = SVM_FEATURE_NAME + col.name;
+
+  // Create dataframe
+  const df = DG.DataFrame.fromColumns(_output[SVM_GEN_FEATURES_INDEX]);
+  df.name = name;  
+  df.columns.add(_output[SVM_GEN_LABELS_INDEX]);
+
+  return df;
+} // testDataForMachineLearning

package/src/demos.ts

@@ -0,0 +1,38 @@
+/* Do not change these import lines to match external modules in webpack configuration */
+import * as grok from 'datagrok-api/grok';
+import * as ui from 'datagrok-api/ui';
+import * as DG from 'datagrok-api/dg';
+
+import {computePLS} from './EDAtools';
+import {addPLSvisualization} from './EDAui';
+
+// Demo multivariate analysis (PLS)
+export async function demoPLS(rowCount: number, colCount: number, componentsCount: number): Promise<void> {
+  // check inputs
+  if ((rowCount <= 0) || (colCount <= 0) || (componentsCount <= 0) || (componentsCount > colCount)) {
+    const bal = new DG.Balloon;
+    bal.error('Incorrect inputs.');
+    return;
+  }
+
+  // further, custom interface is provided
+  
+  const PREDICT = 'Reference';
+  
+  const bigDemoTable = grok.data.testData('random walk', rowCount, colCount);   
+  bigDemoTable.name = `${rowCount} x ${colCount}`;
+  
+  for (const col of bigDemoTable.columns)
+    col.name = 'Feature ' + col.name;
+  bigDemoTable.columns.byIndex(0).name = PREDICT;
+  
+  grok.shell.addTableView(bigDemoTable);
+  let predict = bigDemoTable.columns.byName(PREDICT);
+  let features = bigDemoTable.columns.remove(PREDICT);      
+  
+  const plsResults = await computePLS(bigDemoTable, features, predict, componentsCount);
+  
+  addPLSvisualization(bigDemoTable, features, predict, plsResults);
+  
+  bigDemoTable.columns.add(predict);
+}

package/src/package-test.ts

@@ -0,0 +1,12 @@
+import * as DG from "datagrok-api/dg";
+import {runTests, tests} from '@datagrok-libraries/utils/src/test';
+
+export let _package = new DG.Package();
+export {tests};
+
+//name: test
+//output: dataframe result
+export async function test(): Promise<DG.DataFrame> {
+  let data = await runTests();
+  return DG.DataFrame.fromObjects(data)!;
+}