GoPCA

PRINCIPAL COMPONENT ANALYSIS
LEARN AND ANALYSE

Learn PCA. Analyse real data. Export publication-ready results.
Desktop app and command-line tool.
LOCAL PROCESSING • FREE BINARIES • SOURCE AVAILABLE

━━━ THREE TOOLS ━━━

GoPCA DESKTOP

GoPCA Desktop

DESKTOP APPLICATION
Interactive visualizations. Export publication-ready figures.

  • ◉ Beautiful visualizations
  • ◉ Multiple PCA algorithms (SVD, NIPALS, Kernel, SSA)
  • ◉ Analysis of linear, non-linear and time-series data
  • ◉ 6 guided tutorials with real datasets
  • ◉ Dark and light themes

pca CLI

# Quick analysis
$ pca analyze data.csv
$ pca validate spectra.csv
$ pca transform model.json

                    

COMMAND-LINE TOOL
Automation-ready tool. CSV input format. JSON output format.

  • ◉ Batch processing capabilities
  • ◉ Pipeline integration
  • ◉ Cross-platform support

GoCSV DESKTOP

GoCSV Desktop

CSV EDITOR
Prepare data for PCA analysis. Handle missing values.

  • ◉ Spreadsheet-like editing
  • ◉ Data quality validation
  • ◉ Missing value handling
  • ◉ Export PCA-ready CSV

━━━ QUICK START ━━━

01

DOWNLOAD

macOS, Windows, and Linux binaries available.

→ Download latest version
02

LOAD DATA

Import CSV files with numerical data.

Use GoCSV Desktop for easy import and editing
03

RUN ANALYSIS

Configure components and algorithm. View results instantly.

Execute PCA computation in GoPCA Desktop or pca CLI

━━━ LEARN AND ANALYSE ━━━

⚫ LEARN BY DOING

Six real datasets. Six guided tutorials. From Iris flowers to EEG brain signals — each dataset teaches a specific skill: reading scores and loadings, choosing preprocessing, handling spectroscopic data, unrolling nonlinear structure, analysing time series, and monitoring dynamic processes.

🔴 YOUR DATA, YOUR ANALYSIS

The same application you use to learn is the one you use professionally. No tutorial mode. No feature limits. Load your own CSV, run the analysis, export your results. GoPCA is ready when you are.

⚫ REAL CHALLENGES

The datasets were chosen because they expose real problems: scale imbalance, outlier domination, multiplicative scatter in spectra, curved manifolds, temporal dynamics, and process monitoring. Not toy examples — real data with real lessons.

🔴 BUILT-IN PROGRESSION

Iris → Wine → Corn → Swiss Roll → Eye State → CSTR. Each tutorial builds on the last. By the end you will have used every major feature of GoPCA and encountered every major challenge that real datasets present.

━━━ WHY GoPCA? ━━━

⚫ LOCAL PROCESSING

All computations run on your machine. No external dependencies.

🔴 SOURCE AVAILABLE

Full source code publicly viewable. Free binary redistribution. No proprietary black box.

⚫ ACCURATE ALGORITHMS

SVD, NIPALS, Kernel, and SSA algorithms. Validated against scikit-learn.

🔴 PRIVACY FOCUSED

No telemetry. No analytics. No data collection.

━━━ DOCUMENTATION ━━━