How to visual graph on High Dimensional Data.

On Wed, Mar 1, 2017 at 6:07 AM nitin.solanki@synerzip.com wrote:

Hello,

I’m across a data set where there are 160 features and 2 classes. I want to plot a graph on it. I tried with 2 features using x and y axis respectively and draw Scatter plot. How can I use all features and plot a graph using them. Any help will be appreciated.

Nitin

This e-mail, including any attached files, may contain confidential and privileged information for the sole use of the intended recipient. Any review, use, distribution, or disclosure by others is strictly prohibited. If you are not the intended recipient (or authorized to receive information for the intended recipient), please contact the sender by reply e-mail and delete all copies of this message.

–

You received this message because you are subscribed to the Google Groups “Bokeh Discussion - Public” group.

To unsubscribe from this group and stop receiving emails from it, send an email to bokeh+unsubscribe@continuum.io.

To post to this group, send email to bokeh@continuum.io.

To view this discussion on the web visit https://groups.google.com/a/continuum.io/d/msgid/bokeh/463631a1-61f0-4a03-80b8-55d34735ab09%40continuum.io.

For more options, visit https://groups.google.com/a/continuum.io/d/optout.

On Fri, Mar 3, 2017 at 12:24 PM, Dennis O’Brien dennis@dennisobrien.net wrote:

Hi Nitin,

I think your question is less of a charting question and more of a data manipulation problem. Visualizing 160 dimensions is tough for us mere mortals, so people often rely on dimensionality reduction techniques. The gist is to represent your data in the two or three dimensions that include the most variance and visualize just that. For a good primer on several of the most common techniques, including principal component analysis and singular value decomposition, check out the scikit-learn documentation. The examples use matplotlib, but you could just as well use Bokeh for visualization.

http://scikit-learn.org/stable/modules/decomposition.html#decompositions

I often rely on the pairgrid from seaborn to visualize how each pair of features are related. You would probably want to reduce the number of features you want to compare, maybe by removing features that are correlated to others, or contain little information.

http://seaborn.pydata.org/examples/pair_grid_with_kde.html

Getting seaborn to plot to Bokeh instead of matplotlib would be really nifty, especially if you could make it interactive.

Hope this helps.

cheers,

Dennis

On Wed, Mar 1, 2017 at 6:07 AM nitin.solanki@synerzip.com wrote:

Hello,

I’m across a data set where there are 160 features and 2 classes. I want to plot a graph on it. I tried with 2 features using x and y axis respectively and draw Scatter plot. How can I use all features and plot a graph using them. Any help will be appreciated.

Nitin

This e-mail, including any attached files, may contain confidential and privileged information for the sole use of the intended recipient. Any review, use, distribution, or disclosure by others is strictly prohibited. If you are not the intended recipient (or authorized to receive information for the intended recipient), please contact the sender by reply e-mail and delete all copies of this message.

–

You received this message because you are subscribed to the Google Groups “Bokeh Discussion - Public” group.

To unsubscribe from this group and stop receiving emails from it, send an email to bokeh+unsubscribe@continuum.io.

To post to this group, send email to bokeh@continuum.io.

To view this discussion on the web visit https://groups.google.com/a/continuum.io/d/msgid/bokeh/463631a1-61f0-4a03-80b8-55d34735ab09%40continuum.io.

For more options, visit https://groups.google.com/a/continuum.io/d/optout.

–

You received this message because you are subscribed to the Google Groups “Bokeh Discussion - Public” group.

To unsubscribe from this group and stop receiving emails from it, send an email to bokeh+unsubscribe@continuum.io.

To post to this group, send email to bokeh@continuum.io.

To view this discussion on the web visit https://groups.google.com/a/continuum.io/d/msgid/bokeh/CAPUwX3NnaH620BpU2Tgv3bDGVUW5MpTEoF2PDxsR%3DOg8zqBGCA%40mail.gmail.com.

For more options, visit https://groups.google.com/a/continuum.io/d/optout.