Corrections to Stacked Ensemble docs - metalearner support is in latest version & spelling errors

In [FAQ|http://docs.h2o.ai/h2o/latest-stable/h2o-docs/data-science/stacked-ensembles.html#faq] on Question 3 (How do I improve the performance of an ensemble?), sentence is obsolete:

{quote}Once fully customized metalearner support is added, you can try out different hyperparamters for the metalearner algorithm as well.{quote}

metalearner support [was added on 3.18.0.1|https://0xdata.atlassian.net/browse/PUBDEV-5086]

Consider replacing with:

{quote}Additionally, the customer parameters could be passed to metalearner_params (e.g., a GBM with ntrees=1000, max_depth=10, etc.) {quote}

Additionally, spelling errors:

found spelling error in [http://docs.h2o.ai/h2o/latest-stable/h2o-docs/data-science/stacked-ensembles.html#introduction|http://docs.h2o.ai/h2o/latest-stable/h2o-docs/data-science/stacked-ensembles.html#introduction], should be Ensemble:

{quote}H2O’s Stacked Ensemble method is supervised ensemble machine learning algorithm that finds the optimal combination of a collection of prediction algorithms using a process called stacking. Like all supervised models in H2O, Stacked {color:#6554c0}Enemseble{color} supports regression, binary classification and multiclass classification.{quote}

Spelling error in [http://docs.h2o.ai/h2o/latest-stable/h2o-docs/data-science/stacked-ensembles.html#training-base-models-for-the-ensemble|http://docs.h2o.ai/h2o/latest-stable/h2o-docs/data-science/stacked-ensembles.html#training-base-models-for-the-ensemble], should be together:

{quote}Before training a stacked ensemble, you will need to train and cross-validate a set of “base models” which will make up the ensemble. In order to stack these models {color:#6554c0}toegther{color}, a few things are required:{quote}

h2oai / h2o-3

Corrections to Stacked Ensemble docs - metalearner support is in latest version & spelling errors #8434