[MRG] DOC cleaning up what's new for 0.19 (scikit-learn#9252)

* DOC cleaning up what's new for 0.19

* More cleaning up

* More cleaning up

* Deprecations

* Clean up merge

* Update

* TODOs to prose and minor changes

* Changed models and minor fixes

* sort

* Merge in 0.18.2 docs

* Missing entry from 0.18 logs

* Optimistically add some features to highlights

* Forgotten user directive

* Fix alignment

* Cleaning up for Andy's comments

* Mention beta_loss=0 speedup

* Update

* Clean up new what's new entries

* DOC Add changes missed from what's new

And other minor things.

This took lots of effort which I would have not committed where I not home sick...

Author: jnothman

doc/modules/classes.rst

@@ -724,8 +724,6 @@ Kernels:
    linear_model.PassiveAggressiveClassifier
    linear_model.PassiveAggressiveRegressor
    linear_model.Perceptron
-   linear_model.RandomizedLasso
-   linear_model.RandomizedLogisticRegression
    linear_model.RANSACRegressor
    linear_model.Ridge
    linear_model.RidgeClassifier
@@ -1392,6 +1390,18 @@ Recently deprecated
 ===================
 
 
+To be removed in 0.21
+---------------------
+
+.. autosummary::
+   :toctree: generated/
+   :template: deprecated_class.rst
+
+   linear_model.RandomizedLasso
+   linear_model.RandomizedLogisticRegression
+   neighbors.LSHForest
+
+
 To be removed in 0.20
 ---------------------
 

doc/modules/pipeline.rst

@@ -124,6 +124,8 @@ i.e. if the last estimator is a classifier, the :class:`Pipeline` can be used
 as a classifier. If the last estimator is a transformer, again, so is the
 pipeline.
 
+.. _pipeline_cache:
+
 Caching transformers: avoid repeated computation
 -------------------------------------------------