Re: 2.8.1 : EVT_NODE_RECONNECTED, EVT_NODE_SEGMENTED on the client side

[VeenaMithare]

Hi Anton,

There are a few thoughts on this : 

1. I found this issue after I upgraded from 2.7.6 to 2.8.1 ( No timeout
values etc has been changed in our application ). So for the same scenario
and the same application configuration 
a. in 2.7.6 , the client receives a evt_node_segmented
b. in 2.8.1 , the client receives a evt_node_reconnected.

2. it logs the event of client state updated
from DISCONNECTED to RECONNECTED because the node succeeded to join the
topology back within some time, the node was not segmented from the
topology

>From the logs I posted, it looks like client tries to reconnect using a new
client id 
>>[tcp-client-disco-msg-worker-#4%client-null-igniteclient-SINGLE%] INFO
org.apache.ignite.spi.discovery.tcp.TcpDiscoverySpi [] - Client node
disconnected from cluster, will try to reconnect with new id

3. The logs also say 
>>Client node was
reconnected after it was already considered failed by the server topology
(this could happen after all servers restarted or due to a long network
outage between the client and servers). All continuous queries and remote
event listeners created by this client will be unsubscribed, consider
listening to EVT_CLIENT_NODE_RECONNECTED event to restore them.

If a client node reconnects after it was considered failed by server,
shouldnt it receive a EVT_NODE_SEGMENTED ?

regards,
Veena.



--
Sent from: http://apache-ignite-users.70518.x6.nabble.com/

Re: 2.8.1 - Loading Plugin Provider - Conflicting documentation

[VeenaMithare]

Okay. If I set pluginconfiguration using setPluginConfiguration, how do I get
it in the plugins ?

getPluginConfigurations is deprecated in 2.8.1.





--
Sent from: http://apache-ignite-users.70518.x6.nabble.com/

Ignite ML random forest questions

[Thilo-Alexander Ginkel]

Hello everyone,

I am currently experimenting with Ignite machine learning (random
forest regression / classifier) and have come up with a couple of
questions that I can't seem to answer using docs or sample code. I am
rather new to ML as well as Ignite, so I hope that answers aren't too
obvious. ;-)

Is my assumption correct that the label is the coordinate that is
supposed to be learned (possibly depending on all other features) and
later predicted by the model?

At the moment, I am training my model from a local cache
(CacheMode.LOCAL) that I populate through a CacheStoreAdapter from
ElasticSearch as I can fit all data into RAM of a single node.
Training seems to be single-threaded, though. Is there a way to
parallelize the training across available cores while still limiting
the operation to a single JVM process?

After training a model I'd like to figure out the importance of the
different features. Is there a way to obtain the feature importance
from the model?

Thanks,
Thilo