Building Ensembles with Scikit-Learn and Keras (8.2)

To gain even higher scores with neural networks, several models can be combined. Ensembles are a very common component of high scoring Kaggle models. This video shows how to create an ensemble of Keras neural networks and Scikit-learn models.
Code for This Video:
github.com/jef...
Course Homepage: sites.wustl.ed...
Follow Me/Subscribe:
/ heatonresearch
github.com/jef...
/ jeffheaton
Support Me on Patreon: / jeffheaton

[@russnagel1]

I just found this video. Fairly new to AI/ML but this perturbation technique seems to be a really good technique. I look forward to trying it out. Thank you Jeff, your content is fantastic!

[@JK-ky5of]

Really good job.. but You talked about links in the description but I don't see anything..?

[@HeatonResearch]

Just added it.

[@zackstrater7210]

The code for the perturbation_rank function seems to throw an error (at least when I try it):
for i in range(x.shape[1]):
hold = np.array(x[:, i])
np.random.shuffle(x[:, i])
changing it to:
for i in range(x.shape[1]):
hold = np.array(x[:, i])
np.random.shuffle(x.iloc[:, i].values)
seemed to fix the problem

[@shadyizloo]

hello. can i know how to implement this with a adaboost ensemble?

[@devonk298]

xgboost.......Dr Joy and Dr Death?