File Exchange > Data Analysis >    Principal Component Analysis

Author:
OriginLab Technical Support
Date Added:
9/7/2016
Last Update:
4/25/2022
Downloads (90 Days):
5112
Total Ratings:
74
File Size:
344 KB
Average Rating:
File Name:
PCAC.opx
File Version:
1.50
Minimum Versions:
License:
Free
Summary:

An enhanced version of Principal Component Analysis tool.

Screen Shot and Video:
Description:

PURPOSE
This tool is an enhanced version of the built-in Principal Component Analysis tool available in OriginPro.
This version offers the following additional features:

  • Group support in Score Plot and Biplot.
  • Confidence ellipse in Score Plot and Biplot.
  • 3D plot support for Loading PlotScore Plot and Biplot.
  • Outlier detection in Score Plot and Biplot.

INSTALLATION
Download the file PCAC.opx, and then drag-and-drop onto the Origin workspace. An icon will appear in the Apps Gallery window.
NOTE: This tool requires OriginPro.

OPERATION

  1. Click the Principal Component Analysis icon in the Apps Gallery window to open the dialog.
  2. In the Input tab, choose data in the worksheet for Input Data, where each column represents a variable.
    You can also choose a column for Observations, which can be used for labels in Score Plot and Biplot.
    Group can be used to divide observations in Score Plot and Biplot.
  3. In the Settings tab, Analyze option determines whether to standardize columns (Correlation Matrix) or not. 
    Number of Components to Extract is used to control output of loadings, scores and their plots. 
    Standardize Scores option will standardize scores of each component to set the variance to be equal to 1.
  4. In Quantities to Compute tab, check options to control which results to output in Report Data sheet.
  5. In Plots tab, specify whether to create Scree PlotLoading PlotScore Plot and Biplot.
    All except Scree Plot support 2D and 3D. The last two also support confidence ellipse and labeling of outliers.
  6. Click OK button. A report sheet, a report data sheet and a plot data sheet will be created.
    If Show Confidence Ellipse option is checked in Plots tab, a Matrix book will also be created.

Sample OPJU File
This App provides a sample OPJU file.  Right click on the Principal Component Analysis icon in the Apps Gallery window, and choose Show Samples Folder from the short-cut menu. A folder will open. Drag-and-drop the project file PCASample.opju from the folder onto Origin.
Note: If you wish to save the OPJU after changing, it is recommended that you save to a different folder location (e.g. User Files Folder).

NOTES
If a row in Input Data contains one or more missing values, the entire row will be excluded in the analysis.

Updates:

v1.5 12/5/2019 Standardized loading signs and added a sample project file.
v1.4 8/23/2019 Updated to make it compatible with Origin 2020.
v1.3 3/20/2019 Updated function for 2D Confidence Ellipse.
v1.2 2/27/2019 Fixed biplot bug in Origin 2019.
v1.1 12/3/2018 Fixed Standardize Scores bug.

Reviews and Comments:
03/03/2023LPP1987good

02/22/2023OriginLabHi winstonpcg,

Thank you for your suggestion. We will consider adding an App to support Sparse Principal Components Analysis.

Thanks,
OriginLab Technical Service

02/22/2023winstonpcgGood afternoon,

Does the PCA tool have the possibility to make a Sparse PCA?

01/17/2023yimingcHi szabo.lili,

The data of the biplot should be in the sheet "Score Data1" and "PCA Plot Data1". Also, in the biplot graph, you can right click on the symbols or the vectors and select "Go to bookname...." to locate the data.

Yiming

01/17/2023szabo.liliI have done the PCA, but would like to make a separate biplot. Is it possible to create a standalone biplot outside the program (I want to extract some data)?

12/26/202215737342116No

11/17/2022OriginLabHi Jingjing999,
Please refers to 3D Confidence Ellipsoid APP’s “Algorithm” section for details.

Thanks,
OriginLab Technical Service

11/17/2022Jingjing999What's the formula used in this PCA tool to calculate the confidence ellipse?

11/17/2022PXP1

11/04/2022weiareyoungAWW, I find the amazing correlation matrix and the eigenvectors in the score data ( the exported new sheet). Now I give a 100% rate :)

12345678