adds get_shap_values to README

.gitignore

@@ -173,3 +173,8 @@ store_test.csv
 
 dashboard3.yaml
 test.html
+dashboard1.html
+.gitignore
+hub.html
+db2.html
+hub.zip

README.md

@@ -210,7 +210,12 @@ There are a few tricks to make this less painful:
     number of trees, `L` is the maximum number of leaves in any tree and 
     `D` the maximal depth of any tree. So reducing the number of leaves or average
     depth in the decision tree can really speed up SHAP calculations.
-4. Plotting only a random sample of points. When you have a lots of observations,
+4. Pre-computing shap values. Perhaps you already have calculated the shap values
+    somewhere, or you can calculate them off on a giant cluster somewhere, or
+    your model supports [GPU generated shap values](https://github.com/rapidsai/gputreeshap). 
+    You can simply add these pre-calculated shap values to the explainer 
+    with `explainer.set_shap_values()` and `explainer.set_shap_interaction_values()` methods.
+5. Plotting only a random sample of points. When you have a lots of observations,
     simply rendering the plots may get slow as well. You can pass the `plot_sample`
     parameter to render a (different each time) random sample of observations
     for the various scatter plots in the dashboard. E.g.: 

docs/source/hub.rst

@@ -173,6 +173,14 @@ If you pass ``integrate_dashboard_yamls=True``, then the configuration of the
 dashboards get integrated into a single ``hub.yaml`` file instead of being
 stored in separate files. 
 
+Storing to static html
+======================
+
+You can store the hub front-end and the underlying dashboards to static html with
+e.g. `hub.to_html("hub.html")`. This will also generate individual `.html` files for
+every dashboard e.g. `dashboard1.html`, `dashboard2.html`, etc, etc. 
+
+This might become a bit messy, so instead you can save straight to a zipfile with `hub.to_zip("hub.zip")`.
 
 explainerhub CLI
 ================