@datagrok/eda 1.1.25 → 1.1.28

package/package.json

@@ -1,94 +1,94 @@
 {
-  "name": "@datagrok/eda",
-  "friendlyName": "EDA",
-  "version": "1.1.25",
-  "description": "Exploratory Data Analysis Tools",
-  "dependencies": {
-    "@datagrok-libraries/math": "^1.1.8",
-    "@datagrok-libraries/ml": "^6.6.8",
-    "@datagrok-libraries/tutorials": "^1.3.6",
-    "@datagrok-libraries/utils": "^4.1.44",
-    "@keckelt/tsne": "^1.0.2",
-    "@webgpu/types": "^0.1.40",
-    "cash-dom": "^8.1.1",
-    "datagrok-api": "^1.16.0",
-    "dayjs": "^1.11.9",
-    "jstat": "^1.9.6",
-    "source-map-loader": "^4.0.1",
-    "umap-js": "^1.3.3",
-    "worker-loader": "latest"
-  },
-  "author": {
-    "name": "Viktor Makarichev",
-    "email": "vmakarichev@datagrok.ai"
-  },
-  "devDependencies": {
-    "@typescript-eslint/eslint-plugin": "^5.32.0",
-    "@typescript-eslint/parser": "^5.32.0",
-    "eslint": "^8.21.0",
-    "eslint-config-google": "^0.14.0",
-    "ts-loader": "latest",
-    "typescript": "latest",
-    "webpack": "latest",
-    "webpack-cli": "latest",
-    "css-loader": "latest",
-    "style-loader": "latest"
-  },
-  "scripts": {
-    "link-all": "npm link datagrok-api @datagrok-libraries/utils @datagrok-libraries/tutorials",
-    "debug-eda": "webpack && grok publish",
-    "release-eda": "webpack && grok publish --release",
-    "build-eda": "webpack",
-    "build": "webpack",
-    "debug-eda-dev": "webpack && grok publish dev",
-    "release-eda-dev": "webpack && grok publish dev --release",
-    "debug-eda-local": "webpack && grok publish local",
-    "release-eda-local": "webpack && grok publish local --release",
-    "build-all": "npm --prefix ./../../js-api run build && npm --prefix ./../../libraries/utils run build && npm --prefix ./../../libraries/tutorials run build && npm run build"
-  },
-  "canEdit": [
-    "Developers"
-  ],
-  "canView": [
-    "All users"
-  ],
-  "repository": {
-    "type": "git",
-    "url": "https://github.com/datagrok-ai/public.git",
-    "directory": "packages/EDA"
-  },
-  "category": "Machine Learning",
-  "sources": [
-    "wasm/EDA.js"
-  ],
-  "meta": {
-    "menu": {
-      "ML": {
-        "Tools": {
-          "Impute Missing Values...": null,
-          "Random Data...": null
-        },
-        "Cluster": {
-          "Cluster...": null,
-          "DBSCAN...": null
-        },
-        "Notebooks": {
-          "Browse Notebooks": null,
-          "Open in Notebook": null,
-          "New Notebook": null
-        },
-        "Models": {
-          "Browse Models": null,
-          "Train Model...": null,
-          "Apply Model...": null
-        },
-        "Analyse": {
-          "PCA...": null,
-          "ANOVA...": null,
-          "Multivariate Analysis...": null
-        },
-        "Reduce Dimensionality": null
-      }
+    "name": "@datagrok/eda",
+    "friendlyName": "EDA",
+    "version": "1.1.28",
+    "description": "Exploratory Data Analysis Tools",
+    "dependencies": {
+        "@datagrok-libraries/math": "^1.1.10",
+        "@datagrok-libraries/ml": "^6.6.13",
+        "@datagrok-libraries/tutorials": "^1.3.6",
+        "@datagrok-libraries/utils": "^4.1.44",
+        "@keckelt/tsne": "^1.0.2",
+        "@webgpu/types": "^0.1.40",
+        "cash-dom": "^8.1.1",
+        "datagrok-api": "^1.20.0",
+        "dayjs": "^1.11.9",
+        "jstat": "^1.9.6",
+        "source-map-loader": "^4.0.1",
+        "umap-js": "^1.3.3",
+        "worker-loader": "latest"
+    },
+    "author": {
+        "name": "Viktor Makarichev",
+        "email": "vmakarichev@datagrok.ai"
+    },
+    "devDependencies": {
+        "@typescript-eslint/eslint-plugin": "^5.32.0",
+        "@typescript-eslint/parser": "^5.32.0",
+        "eslint": "^8.21.0",
+        "eslint-config-google": "^0.14.0",
+        "ts-loader": "latest",
+        "typescript": "latest",
+        "webpack": "latest",
+        "webpack-cli": "latest",
+        "css-loader": "latest",
+        "style-loader": "latest"
+    },
+    "scripts": {
+        "link-all": "npm link datagrok-api @datagrok-libraries/utils @datagrok-libraries/tutorials",
+        "debug-eda": "webpack && grok publish",
+        "release-eda": "webpack && grok publish --release",
+        "build-eda": "webpack",
+        "build": "webpack",
+        "debug-eda-dev": "webpack && grok publish dev",
+        "release-eda-dev": "webpack && grok publish dev --release",
+        "debug-eda-local": "webpack && grok publish local",
+        "release-eda-local": "webpack && grok publish local --release",
+        "build-all": "npm --prefix ./../../js-api run build && npm --prefix ./../../libraries/utils run build && npm --prefix ./../../libraries/tutorials run build && npm run build"
+    },
+    "canEdit": [
+        "Developers"
+    ],
+    "canView": [
+        "All users"
+    ],
+    "repository": {
+        "type": "git",
+        "url": "https://github.com/datagrok-ai/public.git",
+        "directory": "packages/EDA"
+    },
+    "category": "Machine Learning",
+    "sources": [
+        "wasm/EDA.js"
+    ],
+    "meta": {
+        "menu": {
+            "ML": {
+                "Tools": {
+                    "Impute Missing Values...": null,
+                    "Random Data...": null
+                },
+                "Cluster": {
+                    "Cluster...": null,
+                    "DBSCAN...": null
+                },
+                "Notebooks": {
+                    "Browse Notebooks": null,
+                    "Open in Notebook": null,
+                    "New Notebook": null
+                },
+                "Models": {
+                    "Browse Models": null,
+                    "Train Model...": null,
+                    "Apply Model...": null
+                },
+                "Analyse": {
+                    "PCA...": null,
+                    "ANOVA...": null,
+                    "Multivariate Analysis...": null
+                },
+                "Reduce Dimensionality": null
+            }
+        }
     }
-  }
-}
+}

package/scripts/command.txt

@@ -1 +1 @@
-em++ -O3 ../wasm/pcaExport.cpp ../wasm/PCA/PCA.cpp ../wasm/plsExport.cpp ../wasm/PLS/PLS.cpp ../wasm/svmApi.cpp -o ../wasm/EDA.js -s TOTAL_MEMORY=268435456 -s WASM=1 -s ALLOW_MEMORY_GROWTH=1 -s MODULARIZE=1 -s EXPORT_NAME="exportEDA" -s EXPORTED_FUNCTIONS=["_principalComponentAnalysis","_error","_partialLeastSquareRegression","_generateDataset","_normalizeDataset","_trainLSSVM","_predictByLSSVM","_trainAndAnalyzeLSSVM","_malloc","_free"] -s EXPORTED_RUNTIME_METHODS=["cwrap","ccall"] -sENVIRONMENT=web,worker
+em++ -O3 ../wasm/pcaExport.cpp ../wasm/PCA/PCA.cpp ../wasm/plsExport.cpp ../wasm/PLS/PLS.cpp ../wasm/svmApi.cpp ../wasm/regression-api.cpp -o ../wasm/EDA.js -s TOTAL_MEMORY=268435456 -s WASM=1 -s ALLOW_MEMORY_GROWTH=1 -s MODULARIZE=1 -s EXPORT_NAME="exportEDA" -s EXPORTED_FUNCTIONS=["_principalComponentAnalysis","_error","_partialLeastSquareRegression","_generateDataset","_normalizeDataset","_trainLSSVM","_predictByLSSVM","_trainAndAnalyzeLSSVM","_fitLinearRegressionParamsWithDataNormalizing","_fitLinearRegressionParams","_malloc","_free"] -s EXPORTED_RUNTIME_METHODS=["cwrap","ccall"] -sENVIRONMENT=web,worker

package/scripts/func.json

@@ -1 +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"}}, "yLoadings": {"type": "newFloatColumn", "numOfRows": {"ref": "componentsCount", "value": "data"}}}, "output": {"type": "objects", "source": "['prediction', 'regressionCoefficients', 'tScores', 'uScores', 'xLoadings', 'yLoadings']"}, "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]"}}}
+{"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"}}, "yLoadings": {"type": "newFloatColumn", "numOfRows": {"ref": "componentsCount", "value": "data"}}}, "output": {"type": "objects", "source": "['prediction', 'regressionCoefficients', 'tScores', 'uScores', 'xLoadings', 'yLoadings']"}, "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]"}}, "regression-api.cpp": {"fitLinearRegressionParamsWithDataNormalizing": {"arguments": {"features": {"type": "floatColumns"}, "featureAvgs": {"type": "floatColumn"}, "featureStdDevs": {"type": "floatColumn"}, "targets": {"type": "floatColumn"}, "targetsAvg": {"type": "num"}, "targetsStdDev": {"type": "num"}, "paramsCount": {"type": "num"}, "params": {"type": "newFloatColumn", "numOfRows": {"ref": "paramsCount", "value": "data"}}}, "output": {"type": "column", "source": "params"}, "annotation": ["//name: fitLinearRegressionParamsWithDataNormalizing", "//input: column_list features", "//input: column featureAvgs", "//input: column featureStdDevs", "//input: column targets", "//input: double targetsAvg", "//input: double targetsStdDev", "//input: int paramsCount", "//output: column params"], "prototype": "fitLinearRegressionParamsWithDataNormalizing(features, featureAvgs, featureStdDevs, targets, targetsAvg, targetsStdDev, paramsCount)", "prototypeForWebWorker": "fitLinearRegressionParamsWithDataNormalizingInWebWorker(features, featureAvgs, featureStdDevs, targets, targetsAvg, targetsStdDev, paramsCount)", "callArgs": "[features, featureAvgs, featureStdDevs, targets, targetsAvg, targetsStdDev, paramsCount]"}, "fitLinearRegressionParams": {"arguments": {"features": {"type": "floatColumns"}, "targets": {"type": "floatColumn"}, "paramsCount": {"type": "num"}, "params": {"type": "newFloatColumn", "numOfRows": {"ref": "paramsCount", "value": "data"}}}, "output": {"type": "column", "source": "params"}, "annotation": ["//name: fitLinearRegressionParams", "//input: column_list features", "//input: column targets", "//input: int paramsCount", "//output: column params"], "prototype": "fitLinearRegressionParams(features, targets, paramsCount)", "prototypeForWebWorker": "fitLinearRegressionParamsInWebWorker(features, targets, paramsCount)", "callArgs": "[features, targets, paramsCount]"}}}

package/scripts/module.json

@@ -1,7 +1,7 @@
 {
     "name": "EDA",    
     "folder": "../wasm",
-    "source": ["pcaExport.cpp", "PCA/PCA.cpp", "plsExport.cpp", "PLS/PLS.cpp", "svmApi.cpp"],    
+    "source": ["pcaExport.cpp", "PCA/PCA.cpp", "plsExport.cpp", "PLS/PLS.cpp", "svmApi.cpp", "regression-api.cpp"],    
     "optimizationMode": "-O3",    
     "packageFile": "../src/package.ts",
     "packageJsonFile": "../package.json",    

package/src/missing-values-imputation/ui.ts

@@ -2,51 +2,51 @@ import * as grok from 'datagrok-api/grok';
 import * as ui from 'datagrok-api/ui';
 import * as DG from 'datagrok-api/dg';
 
-import { TITLE, KNN_IMPUTER, ERROR_MSG, HINT } from './ui-constants';
-import { SUPPORTED_COLUMN_TYPES, METRIC_TYPE, DISTANCE_TYPE, MetricInfo, DEFAULT, MIN_NEIGHBORS, 
-  impute, getMissingValsIndices, areThereFails, imputeFailed } from "./knn-imputer";
+import {TITLE, KNN_IMPUTER, ERROR_MSG, HINT} from './ui-constants';
+import {SUPPORTED_COLUMN_TYPES, METRIC_TYPE, DISTANCE_TYPE, MetricInfo, DEFAULT, MIN_NEIGHBORS,
+  impute, getMissingValsIndices, areThereFails, imputeFailed} from './knn-imputer';
 
 /** Setting of the feature metric inputs */
 type FeatureInputSettings = {
   defaultWeight: number,
   defaultMetric: METRIC_TYPE,
-  availableMetrics: METRIC_TYPE[], 
+  availableMetrics: METRIC_TYPE[],
 };
 
 /** Return default setting of the feature metric inputs */
 function getFeatureInputSettings(type: DG.COLUMN_TYPE): FeatureInputSettings {
   switch (type) {
-    case DG.COLUMN_TYPE.STRING:
-    case DG.COLUMN_TYPE.DATE_TIME:
-      return {
-        defaultWeight: DEFAULT.WEIGHT,
-        defaultMetric: METRIC_TYPE.ONE_HOT,
-        availableMetrics: [METRIC_TYPE.ONE_HOT]
-      };
-
-    case DG.COLUMN_TYPE.INT:
-    case DG.COLUMN_TYPE.FLOAT:
-    case DG.COLUMN_TYPE.QNUM:
-      return {
-        defaultWeight: DEFAULT.WEIGHT,
-        defaultMetric: METRIC_TYPE.DIFFERENCE,
-        availableMetrics: [METRIC_TYPE.DIFFERENCE, METRIC_TYPE.ONE_HOT]
-      };
-
-    default:
-      throw new Error(ERROR_MSG.UNSUPPORTED_COLUMN_TYPE);
+  case DG.COLUMN_TYPE.STRING:
+  case DG.COLUMN_TYPE.DATE_TIME:
+    return {
+      defaultWeight: DEFAULT.WEIGHT,
+      defaultMetric: METRIC_TYPE.ONE_HOT,
+      availableMetrics: [METRIC_TYPE.ONE_HOT],
+    };
+
+  case DG.COLUMN_TYPE.INT:
+  case DG.COLUMN_TYPE.FLOAT:
+  case DG.COLUMN_TYPE.QNUM:
+    return {
+      defaultWeight: DEFAULT.WEIGHT,
+      defaultMetric: METRIC_TYPE.DIFFERENCE,
+      availableMetrics: [METRIC_TYPE.DIFFERENCE, METRIC_TYPE.ONE_HOT],
+    };
+
+  default:
+    throw new Error(ERROR_MSG.UNSUPPORTED_COLUMN_TYPE);
   }
 }
 
 /** Run the KNN missing values imputer */
-export function runKNNImputer(): void {
+export async function runKNNImputer(df?: DG.DataFrame): Promise<void> {
   /** current dataframe */
-  let df: DG.DataFrame | null = grok.shell.t;
+  df ??= grok.shell.t;
 
   if (df === null) {
     grok.shell.warning(ERROR_MSG.NO_DATAFRAME);
     return;
-  }    
+  }
 
   /** columns with missing values */
   const colsWithMissingVals = [] as DG.Column[];
@@ -84,53 +84,54 @@ export function runKNNImputer(): void {
 
   // In-place components
   let inPlace = DEFAULT.IN_PLACE > 0;
-  const inPlaceInput = ui.boolInput(TITLE.IN_PLACE, inPlace, () => { inPlace = inPlaceInput.value ?? false;});
+  const inPlaceInput = ui.input.bool(TITLE.IN_PLACE, {value: inPlace,
+    onValueChanged: () => {inPlace = inPlaceInput.value ?? false;}});
   inPlaceInput.setTooltip(HINT.IN_PLACE);
 
   // Keep empty feature
   let keepEmpty = DEFAULT.KEEP_EMPTY > 0;
-  const keepEmptyInput = ui.boolInput(TITLE.KEEP_EMPTY, keepEmpty, () => { keepEmpty = keepEmptyInput.value ?? false });
+  const keepEmptyInput = ui.input.bool(TITLE.KEEP_EMPTY, {value: keepEmpty,
+    onValueChanged: () => {keepEmpty = keepEmptyInput.value ?? false;}});
   keepEmptyInput.setTooltip(HINT.KEEP_EMPTY);
 
   // Neighbors components
   let neighbors = DEFAULT.NEIGHBORS;
-  const neighborsInput = ui.intInput(TITLE.NEIGHBORS, neighbors, () => {
+  const neighborsInput = ui.input.int(TITLE.NEIGHBORS, {value: neighbors, onValueChanged: () => {
     const val = neighborsInput.value;
     if (val === null)
       neighborsInput.value = neighbors;
-    else if (val >= MIN_NEIGHBORS) 
+    else if (val >= MIN_NEIGHBORS)
       neighbors = val;
     else
       neighborsInput.value = neighbors;
-  });
+  }});
   neighborsInput.setTooltip(HINT.NEIGHBORS);
 
   // Distance components
   let distType = DISTANCE_TYPE.EUCLIDEAN;
-  const distTypeInput = ui.choiceInput(TITLE.DISTANCE, distType, [DISTANCE_TYPE.EUCLIDEAN, DISTANCE_TYPE.MANHATTAN], 
-    () => distType = distTypeInput.value ?? DISTANCE_TYPE.EUCLIDEAN);
+  const distTypeInput: DG.ChoiceInput<DISTANCE_TYPE> = ui.input.choice(TITLE.DISTANCE, {value: distType,
+    items: [DISTANCE_TYPE.EUCLIDEAN, DISTANCE_TYPE.MANHATTAN], onValueChanged: () => distType = distTypeInput.value ?? DISTANCE_TYPE.EUCLIDEAN}) as DG.ChoiceInput<DISTANCE_TYPE>;
   distTypeInput.setTooltip(HINT.DISTANCE);
 
   // Target columns components (cols with missing values to be imputed)
   let targetColNames = colsWithMissingVals.map((col) => col.name);
-  const targetColInput = ui.columnsInput(TITLE.COLUMNS, df, () => {
-    targetColNames = targetColInput.value.map((col) => col.name);    
+  const targetColInput = ui.input.columns(TITLE.COLUMNS, {table: df, onValueChanged: () => {
+    targetColNames = targetColInput.value.map((col) => col.name);
     checkApplicability();
-  }, {available: availableTargetColsNames, checked: availableTargetColsNames});
+  }, available: availableTargetColsNames, checked: availableTargetColsNames});
   targetColInput.setTooltip(HINT.TARGET);
 
   // Feature columns components
   let selectedFeatureColNames = availableFeatureColsNames as string[];
-  const featuresInput = ui.columnsInput(TITLE.FEATURES, df, () => {    
+  const featuresInput = ui.input.columns(TITLE.FEATURES, {table: df, onValueChanged: () => {
     selectedFeatureColNames = featuresInput.value.map((col) => col.name);
 
     if (selectedFeatureColNames.length > 0) {
       checkApplicability();
-      metricInfoInputs.forEach((div, name) => div.hidden = !selectedFeatureColNames.includes(name));      
-    }
-    else
+      metricInfoInputs.forEach((div, name) => div.hidden = !selectedFeatureColNames.includes(name));
+    } else
       hideWidgets();
-  }, {available: availableFeatureColsNames, checked: availableFeatureColsNames});
+  }, available: availableFeatureColsNames, checked: availableFeatureColsNames});
   featuresInput.setTooltip(HINT.FEATURES);
 
   /** Hide widgets (use if run is not applicable) */
@@ -155,14 +156,15 @@ export function runKNNImputer(): void {
 
   /** Check applicability of the imputation */
   const checkApplicability = () => {
-    showWidgets();    
-    
+    showWidgets();
+
     if (selectedFeatureColNames.length === 1) {
       targetColNames.forEach((name) => {
         if (selectedFeatureColNames[0] === name) {
           hideWidgets();
           grok.shell.warning(`${ERROR_MSG.ONE_FEATURE_SELECTED} the column '${name}'`);
-      }});
+        }
+      });
     }
   };
 
@@ -173,25 +175,26 @@ export function runKNNImputer(): void {
   metricsDiv.style.overflow = 'auto';
 
   // Create metrics UI
-  availableFeatureColsNames.forEach((name) => {    
+  availableFeatureColsNames.forEach((name) => {
     // initialization
     const type = df!.col(name)!.type as DG.COLUMN_TYPE;
     const settings = getFeatureInputSettings(type);
     featuresMetrics.set(name, {weight: settings.defaultWeight, type: settings.defaultMetric});
 
     // distance input
-    const distTypeInput = ui.choiceInput(name, settings.defaultMetric, settings.availableMetrics, () => {
-      const distInfo = featuresMetrics.get(name) ?? {weight: settings.defaultWeight, type: settings.defaultMetric};
-      distInfo.type = distTypeInput.value ?? settings.defaultMetric;
-      featuresMetrics.set(name, distInfo);
-    });
+    const distTypeInput = ui.input.choice(name, {value: settings.defaultMetric,
+      items: settings.availableMetrics, onValueChanged: () => {
+        const distInfo = featuresMetrics.get(name) ?? {weight: settings.defaultWeight, type: settings.defaultMetric};
+        distInfo.type = distTypeInput.value ?? settings.defaultMetric;
+        featuresMetrics.set(name, distInfo);
+      }});
     distTypeInput.root.style.width = '50%';
     distTypeInput.setTooltip(HINT.METRIC);
     distTypeInput.root.hidden = true; // this input will be used further
 
     // The following should provide a slider (see th bug https://reddata.atlassian.net/browse/GROK-14431)
     // @ts-ignore
-    const prop = DG.Property.fromOptions({ "name": name, "inputType": "Float", min: 0, max: 10, "showSlider": true, "step": 1});
+    const prop = DG.Property.fromOptions({'name': name, 'inputType': 'Float', 'min': 0, 'max': 10, 'showSlider': true, 'step': 1});
     const weightInput = ui.input.forProperty(prop);
     weightInput.value = settings.defaultWeight;
     weightInput.onChanged(() => {
@@ -200,7 +203,7 @@ export function runKNNImputer(): void {
       featuresMetrics.set(name, distInfo);
     });
     weightInput.setTooltip(HINT.WEIGHT);
-    
+
     const div = ui.divH([distTypeInput.root, weightInput.root]);
     metricInfoInputs.set(name, div);
     metricsDiv.append(div);
@@ -214,11 +217,27 @@ export function runKNNImputer(): void {
   keepEmptyInput.root.hidden = !areThereFails(targetColNames, selectedFeatureColNames, misValsInds);
 
   // Icon showing/hiding metrics UI
-  const settingsIcon = ui.icons.settings(() => { metricsDiv.hidden = !metricsDiv.hidden;}, HINT.METRIC_SETTINGS);
+  const settingsIcon = ui.icons.settings(() => {metricsDiv.hidden = !metricsDiv.hidden;}, HINT.METRIC_SETTINGS);
 
   const distDiv = ui.divH([distTypeInput.root, settingsIcon]);
 
-  dlg.addButton(TITLE.RUN, () => {
+  let resolve: (value: void | PromiseLike<void>) => void;
+  let reject: (reason?: any) => void;
+  let okClicked = false;
+  const promise = new Promise<void>((res, rej) => {
+    resolve = res;
+    reject = rej;
+  });
+  dlg.add(targetColInput)
+    .add(featuresInput)
+    .add(distDiv)
+    .add(metricsDiv)
+    .add(neighborsInput)
+    .add(inPlaceInput)
+    .add(keepEmptyInput)
+    .show()
+    .onOK(() => {
+      okClicked = true;
       dlg.close();
       availableFeatureColsNames.filter((name) => !selectedFeatureColNames.includes(name)).forEach((name) => featuresMetrics.delete(name));
 
@@ -227,20 +246,15 @@ export function runKNNImputer(): void {
 
         if (!keepEmpty)
           imputeFailed(df!, failedToImpute);
-      }
-      catch (err) {
+        resolve();
+      } catch (err) {
         if (err instanceof Error)
           grok.shell.error(`${ERROR_MSG.KNN_FAILS}: ${err.message}`);
         else
           grok.shell.error(`${ERROR_MSG.KNN_FAILS}: ${ERROR_MSG.CORE_ISSUE}`);
-      }      
-    })
-    .add(targetColInput)
-    .add(featuresInput)    
-    .add(distDiv)
-    .add(metricsDiv)
-    .add(neighborsInput)
-    .add(inPlaceInput)
-    .add(keepEmptyInput)
-    .show();
+        reject(err);
+      }
+    }).onClose.subscribe(() => !okClicked && reject());
+
+    return promise;
 } // runKNNImputer