[[ml-limitations]]
== Machine Learning Limitations

[float]
=== Misleading High Missing Field Counts
//See x-pack-elasticsearch/#684

One of the counts associated with a {ml} job is +missingFieldCount+,
which indicates the number of records that are missing a configured field.
This information is most useful when your job analyzes CSV data.  In this case,
missing fields indicate data is not being analyzed and you might receive poor results.

If your job analyzes JSON data, the +missingFieldCount+ might be misleading.
Missing fields might be expected due to the structure of the data and therefore do
not generate poor results.


//When you refer to a file script in a watch, the watch itself is not updated
//if you change the script on the filesystem.

//Currently, the only way to reload a file script in a watch is to delete
//the watch and recreate it.

//=== The _data Endpoint Requires Data to be in JSON Format

//See x-pack-elasticsearch/#777

//=== tBD

//See x-pack-elasticsearch/#601
//When you use aggregations, you must ensure +size+ is configured correctly.
//Otherwise, not all data will be analyzed.