Share data in the Machine Learning Toolkit

When the Machine Learning Toolkit is deployed on Splunk Enterprise, the Splunk platform sends anonymized usage data to Splunk Inc. ("Splunk") to help improve the MLTK in future releases. For information about how to opt in or out, and how the data is collected, stored, and governed, see Share data in Splunk Enterprise.

What data is collected

The Splunk Machine Learning Toolkit collects the following basic usage information:

Component	Description	Example
algo_name	Name of algorithm used in fit or apply.	{ "algo_name": "StandardScaler" }
apply_time	Time the apply command took.	{ 'apply_time': 0.005 }
app_context	Name of the app from which search is run.	{ "app_context": "Splunk_ML_Toolkit" }
columns	The number of columns being run through fit command.	{ "columns": 10 }
command	fit or apply	{ "command":"apply" }
csv_parse_time	CSV parse time.	{ "csv_parse_time": 0.019296 }
csv_read_time	CSV read time.	{ "csv_read_time": 0.019296 }
csv_render_time	CSV render time.	{ "csv_render_time" : 0.01162 }
example_name	Name of the Showcase example being run.	{ 'example_name': "'Predict Server Power Consumption'" }
experiment_id	ID of the fit and apply run on the Experiments page. All preprocessing steps and final fit have the same ID.	{ "experiment_id": "6c47bca2776d4b6cb82685461d918180" }
fit_time	Amount of time it took to run the fit command.	{ "fit_time": 39.87447 }
full_punct	The punct of the data during fit or apply.	{ "full_punct": [ ...s-s-s[//:::.s-]s"s/-/////.s/."sss"://:/-//@:///-."s"/.s(;sssss)s/.s(,ss)s/...s/."s-ss ] }
handle_time	Time for the handler to handle the data.	{ "handle_time": 0.274072 }
num_fields	Total number of fields.	{ "num_fields": 4 } }
num_fields_fs	Number of fields that have the fs for Field Selector prefix.	{ "num_fields_fs": 9 }
num_fields_PC	Number of fields that have the PC for preprocessed prefix.	{ "num_fields_PC": 70 }
num_fields_prefixed	Total number of preprocessed fields.	{ "num_fields_prefixed": 28 }
num_fields_RS	Number of fields that have the RS for Robust Scaler prefix.	{ "num_fields_RS": 17 }
num_fields_SS	Number of fields that have the SS for Standard Scaler prefix.	{ "num_fields_SS": 30 }
num_fields_tfidf	Number of fields that have used term frequency-inverse document frequency preprocessing.	{ "num_fields_tfidf": 9 }
orig_sourcetype	The original sourcetype of the machine data.	{ "orig_sourcetype" : "access_combined_wcookie" }
params	Optional parameters used in fit step.	{ "params": "{{\"with_std\": \"true\", \"with_mean\": \"true\"}}" }
PID	Process identifer associated with the command.	{ "PID" : 63654 }
pipeline_stage	Each preprocessing step on the Experiments page is assigned a number starting from 0. This helps determine the order of the preprocessing steps and length of the pipeline.	{ "pipeline_stage": 0 }
rows	The number of rows being run through fit command.	{ 'rows': 15627 }
UUID	Universally unique identifier associated with command. This is 128-bit and used to keep each fit/apply unique.	{ "UUID": "7e0828e7-3059-4a43-8419-acc0e81f2f2d" }