Hi I am not sure how the "Sliding window" method work. Let's assume I have a dataset of number of logins by hour. a) A window of 24hours to predict the next 24h? b) A window of 24h to predict the next 1h? Thank you ... View more

Hi I have a table with 2 columns: "_time" and "isOutlier". I want to remove all the fields with the value = 1 from the column "isOutlier". Is there any command? Thank you ... View more

Hi I am working on a forecasting problem. I want to use DBSCAN to detect outliers and then apply Kalman filter to make forecasts. But I do not know how to remove or transform the samples inside a cluster. How can I connect these 2 "algorithms" #THIS IS TO APPLY DBSCAN | inputlookup fortigate_QC_May2019_logins.csv | fit StandardScaler "logins" with_mean=false with_std=true | fit DBSCAN eps=0.2 "SS_logins" #THIS IS TO FORECAST WITH KALMAN FILTER | predict "logins" as prediction algorithm=LLP5 holdback=288 future_timespan=324 upper95=upper95 lower95=lower95 | `forecastviz(324, 288, "logins", 95)` | where prediction!="" AND 'logins' != "" | `regressionstatistics("logins", prediction)` Thank you ... View more

Hi I want to see the python code of the Kalman filter. But I cannot find it in the algos folder. I can see ARIMA, ACF, PACF but not Kalman. Where is it? ... View more

Hello I want to count the number of logins by hour and then try to predict them. I have tested 2 codes but I do not know why there is a difference in results. This code gives me 741 results: |index=fortigate |bucket _time span=1h |stats count by _time This code gives me 744 results: |index=fortigate |timechart span=1h count(status) as logins Thank you. ... View more

Hi I used SPL to get the number of logins by the hour for 1 month. The goal is to later import them into python using pandas. But I am having problems understanding the "_time" column. This is what I see in Splunk's SPL search result: But when I export it into .csv, I see: _time Logins 2019-05-01T00:00:00.000-0400 3735 2019-05-01T01:00:00.000-0400 4665 2019-05-01T02:00:00.000-0400 5860 2019-05-01T03:00:00.000-0400 5184 2019-05-01T04:00:00.000-0400 5324 2019-05-01T05:00:00.000-0400 5523 2019-05-01T06:00:00.000-0400 8863 2019-05-01T07:00:00.000-0400 12493 And when I use "outpulookup" to create the .csv, I see: _time logins _span 1556683200 3735 3600 1556686800 4665 3600 1556690400 5860 3600 1556694000 5184 3600 1556697600 5324 3600 1556701200 5523 3600 1556704800 8863 3600 1556708400 12493 3600 The SPL to get the search results are: index=fortigate status=logon |timechart span=1h count(status) as logins Thank you ... View more

Hi, I need a book/webpage of MLTK with examples. From use-case definition to programming alerts. Can anyone recommend one? Thank you. ... View more

Hi I am new to Splunk and MLTK. Is it possible to use MLPClassifier in an MLTK Experiment? The algorithm is not available in the dropdown list. But if I write SPL, will the results be reliable? Thanks ... View more

Hi I am using MLTK for anomaly detection. So I am benchmarking algorithms. I was wondering if it is possible to optimize the hyperparameters using techniques like: random search, grid search, bayesian optimization, etc. I am not sure if it could be possible to apply it with real-time data. Has anyone done it before? Thank you ... View more