How do I smooth out a surface distribution plot?

1 次查看（过去 30 天）
Leon
Leon 2014-10-9
评论： Leon 2014-10-11
Looks like my data has some outliers that should be removed.
Instead of doing that manually, is there a way I can let Matlab do it? Thanks!
In case you need, below is the code to plot the map:
[X, Y] = meshgrid(linspace(min(lon),max(lon),100),linspace(min(lat),max(lat),100));
Z = griddata (lon, lat, V, X, Y);
[C1, h1] = contourf (X, Y, Z, [0:0.1:4], 'LineStyle', 'none' );

请先登录，再回答此问题。

采纳的回答

Bruno Pop-Stefanov
Bruno Pop-Stefanov 2014-10-10
There is no off-the-shelf functionality in MATLAB that allows you to detect outliers in data. Techniques exist but it is still an active field of research.
You'll find a couple of File Exchange submission to remove outliers from data. For example:
http://www.mathworks.com/matlabcentral/fileexchange/37211-remove-outliers
Otherwise, you could maybe try to filter your data with a smoothing filter. Take a look at the filter function:
http://www.mathworks.com/help/matlab/data_analysis/filtering-data.html
This will reduce the magnitude of peaks in your data.

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Descriptive Statistics 的更多信息

标签

产品

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by