ML Platform PipelineExamples Pricing

Sign in Get started free

Loading…

ML Reduce

Dimensionality Reduction

Dashboard

Back to overview

PCA

Principal Components

Incremental PCA

Large datasets

Factor Analysis

Latent variables

Truncated SVD

Sparse data / NLP

t-SNE

Visual 2D/3D maps

UMAP

Fast manifold learning

Isomap

Geodesic distances

Spectral Embedding

Graph-based

Isomap

Load a dataset or pick a sample to get started.

Dataset

Upload a CSV/Excel file or pick a sample dataset to begin.

Target Components

Components2

210

Isomap Parameters

Geometric reduction based on shortest-path (geodesic) distances.

Neighbours

5

2100

Distance Metric

Solver

Pre-Scaling

Standardize features before reduction

Metrics

Reconstruction Error

—

n_neighbors: —

After transform

Components

—

After transform

Samples

—

Rows processed

After transform

Computation Time

—

Seconds

After transform

Visualizations

Component Plot

Component Plot

2D scatter plot of the reduced components. Colour by label to see class separation.

Transformed Data

New Feature Preview

Isomap_1, Isomap_2 will appear after transformation

Dimensionality Reduction — 8 Algorithms for Transformation & DR