@datagrok/eda 1.1.5 → 1.1.7

package/package.json

@@ -1,12 +1,13 @@
 {
   "name": "@datagrok/eda",
   "friendlyName": "EDA",
-  "version": "1.1.5",
+  "version": "1.1.7",
   "description": "Exploratory Data Analysis Tools",
   "dependencies": {
     "@datagrok-libraries/ml": "^6.3.39",
     "@datagrok-libraries/tutorials": "^1.3.6",
     "@datagrok-libraries/utils": "^4.1.4",
+    "@datagrok-libraries/math": "^1.0.3",
     "@keckelt/tsne": "^1.0.2",
     "cash-dom": "^8.1.1",
     "datagrok-api": "^1.16.0",

package/src/package.ts

@@ -14,6 +14,7 @@ import {LINEAR, RBF, POLYNOMIAL, SIGMOID,
   getTrainedModel, getPrediction, showTrainReport, getPackedModel} from './svm';
 
 import {oneWayAnova} from './stat-tools';
+import { getDbscanWorker } from '@datagrok-libraries/math';
 
 export const _package = new DG.Package();
 
@@ -27,9 +28,26 @@ export async function init(): Promise<void> {
   await _initEDAAPI();
 }
 
+//top-menu: ML | Cluster | DBSCAN...
+//name: DBSCAN
+//description: Density-based spatial clustering of applications with noise (DBSCAN)
+//input: dataframe df
+//input: column xCol {type: numerical}
+//input: column yCol {type: numerical}
+//input: double epsilon = 0.02 {caption: Epsilon} [The maximum distance between two samples for them to be considered as in the same neighborhood.]
+//input: int minPts = 4 {caption: Minimum points} [The number of samples (or total weight) in a neighborhood for a point to be considered as a core point.]
+export async function dbScan(df: DG.DataFrame, xCol: DG.Column, yCol: DG.Column, epsilon: number, minPts: number) {
+  const x = xCol.getRawData() as Float32Array;
+  const y = yCol.getRawData() as Float32Array;
+  const res = await getDbscanWorker(x, y, epsilon, minPts);
+  const clusterColName = df.columns.getUnusedName('Cluster');
+  const cluster = DG.Column.fromInt32Array(clusterColName, res);
+  df.columns.add(cluster);
+}
+
 //top-menu: ML | Dimensionality Reduction | PCA...
 //name: PCA
-//description: Principal component analysis (PCA).
+//description: Principal component analysis (PCA)
 //input: dataframe table
 //input: column_list features {type: numerical}
 //input: int components = 2 {caption: Components} [Number of components.]
@@ -46,7 +64,7 @@ export async function PCA(table: DG.DataFrame, features: DG.ColumnList, componen
 
 //top-menu: ML | Dimensionality Reduction | UMAP...
 //name: UMAP
-//description: Uniform Manifold Approximation and Projection (UMAP).
+//description: Uniform Manifold Approximation and Projection (UMAP)
 //input: dataframe table {category: Data}
 //input: column_list features {type: numerical; category: Data}
 //input: int components = 2 {caption: Components; min: 1; max: 20; category: Hyperparameters} [The number of components (dimensions) to project the data to.]
@@ -63,7 +81,7 @@ export async function UMAP(table: DG.DataFrame, features: DG.ColumnList, compone
 
 //top-menu: ML | Dimensionality Reduction | t-SNE...
 //name: t-SNE
-//description: t-distributed stochastic neighbor embedding (t-SNE).
+//description: t-distributed stochastic neighbor embedding (t-SNE)
 //input: dataframe table {category: Data}
 //input: column_list features {type: numerical; category: Data}
 //input: int components = 2 {caption: Components; category: Hyperparameters} [Dimension of the embedded space.]
@@ -79,7 +97,7 @@ export async function tSNE(table: DG.DataFrame, features: DG.ColumnList, compone
 
 //top-menu: ML | Dimensionality Reduction | SPE...
 //name: SPE
-//description: Stochastic proximity embedding (SPE).
+//description: Stochastic proximity embedding (SPE)
 //input: dataframe table {category: Data}
 //input: column_list features {type: numerical; category: Data}
 //input: int dimension = 2 {caption: Dimension; category: Hyperparameters} [Dimension of the embedded space.]
@@ -162,7 +180,7 @@ export async function demoMultivariateAnalysis(): Promise<any>  {
 }
 
 //name: Generate linear separable dataset
-//description: Generates linear separble dataset for testing binary classificators.
+//description: Generates linear separble dataset for testing binary classificators
 //input: string name = 'Data' {caption: name; category: Dataset}
 //input: int samplesCount = 1000 {caption: samples; category: Size}
 //input: int featuresCount = 2 {caption: features; category: Size}
@@ -178,7 +196,7 @@ export async function testDataLinearSeparable(name: string, samplesCount: number
 }
 
 //name: Generate linear non-separable dataset
-//description: Generates linear non-separble dataset for testing binary classificators.
+//description: Generates linear non-separble dataset for testing binary classificators
 //input: string name = 'Data' {caption: name; category: Dataset}
 //input: double sigma = 90  {caption: sigma; category: Hyperparameters} [RBF-kernel paramater]
 //input: int samplesCount = 1000 {caption: samples; category: Size}
@@ -322,7 +340,7 @@ export async function applySigmoidKernelSVM(df: DG.DataFrame, model: any): Promi
 }
 
 //top-menu: ML | Analyze | ANOVA...
-//name: One-way ANOVA
+//name: ANOVA
 //description: One-way analysis of variances (ANOVA) determines whether the examined factor has a significant impact on the studied feature.
 //input: dataframe table
 //input: column factor {type: categorical}