add some docs

Author: chrishalcrow

doc/how_to/process_by_channel_group.rst

@@ -97,12 +97,13 @@ to any preprocessing function.
     shifted_recordings = spre.phase_shift(split_recording_dict)
     filtered_recording = spre.bandpass_filter(shifted_recording)
     referenced_recording = spre.common_reference(filtered_recording)
+    good_channels_recording = spre.detect_and_remove_bad_channels(filtered_recording)
 
 We can then aggregate the recordings back together using the ``aggregate_channels`` function
 
 .. code-block:: python
 
-    combined_preprocessed_recording = aggregate_channels(referenced_recording)
+    combined_preprocessed_recording = aggregate_channels(good_channels_recording)
 
 Now, when ``combined_preprocessed_recording`` is used in sorting, plotting, or whenever
 calling its :py:func:`~get_traces` method, the data will have been

doc/modules/preprocessing.rst

@@ -247,6 +247,18 @@ interpolated with the :code:`interpolate_bad_channels()` function (channels labe
     # Case 2 : interpolate then
     rec_clean = interpolate_bad_channels(recording=rec, bad_channel_ids=bad_channel_ids)
 
+Once you have tested these functions and decided on your workflow, you can use the `detect_and_*`
+functions to do everything at once. These return a Preprocessor class, so are consistent with
+the "chain" concept for this module. For example:
+
+.. code-block:: python
+
+    # detect and remove bad channels
+    rec_only_good_channels = detect_and_remove_bad_channels(recording=rec)
+
+    # detect and interpolate the bad channels
+    rec_interpolated_channels = detect_and_interpolate_bad_channels(remove_channel_ids=bad_channel_ids)
+
 
 * :py:func:`~spikeinterface.preprocessing.detect_bad_channels()`
 * :py:func:`~spikeinterface.preprocessing.interpolate_bad_channels()`