anomaly-detection | 易学教程

Disconnect points to plot overlay in Vega-lite / Vega

阅读更多关于 Disconnect points to plot overlay in Vega-lite / Vega

问题 An example in vega-editor here I don’t want dateTime 5 & dateTime 7 to be connected since they are not consecutive. Idea is to plot on overlay based on some condition and connect only when the count is >=5. Has anyone tried this already? 回答1: You can replace your filter statement: {"filter": "datum.count >= 5"} With a calculate statement that sets filtered values to null: {"as": "count", "calculate": "if(datum.count >= 5, datum.count, null)"} The result is here 来源： https://stackoverflow.com

How to monitor messages rate in kafka topics?

阅读更多关于 How to monitor messages rate in kafka topics?

问题 How can I get alerted when there is a message rate in some topic higher or lower than usual? 回答1: Kafka emits tons of metrics that allow to monitor its usage and health. This includes metrics for incoming message rate, see the Monitoring section in the docs. Your use case is typically achieved with a tool that handles metrics and is able to fire alerts based on user defined queries. For example, Prometheus handles that very well. You need to set it up so metrics from Kafka are forwarded to

Error in mutate_impl(.data, dots) : Evaluation error: Only year, quarter, month, week, and day periods are allowed for an index of class Date

阅读更多关于 Error in mutate_impl(.data, dots) : Evaluation error: Only year, quarter, month, week, and day periods are allowed for an index of class Date

问题 I am using Anomalize package to detect the Anomalies, but I am getting the mentioned error even though I have defined the Date as index : Sample Code : x <- as.data.frame(data %>% group_by(date,acc_id) %>% summarise(count = as.numeric(n_distinct(d_id))) %>% ungroup()) x$acc_id <- as.character(x$acc_id) x <- x %>% tibbletime::as_tbl_time(index = date) x %>% time_decompose(count, method = "twitter", trend = "2 months") %>% anomalize(remainder, method = "gesd") %>% time_recompose() %>% plot

Reconstruction MSE calculation using h2o.anomaly function from H2O R package

阅读更多关于 Reconstruction MSE calculation using h2o.anomaly function from H2O R package

问题 I was trying to perform Autoencoder for anomaly detection. I used H2O R package to generate reconstruction MSE for a sample data using h2o.anomaly function. However, I have also tried to manually calculate it by myself according the the MSE formula from the documentation link below: http://docs.h2o.ai/h2o/latest-stable/h2o-docs/performance-and-prediction.html#mse-mean-squared-error The training data consisting of three features and 5 rows that I used to build the model is as below: head(train

Anomaly detection with PCA in Spark

阅读更多关于 Anomaly detection with PCA in Spark

I read the following article Anomaly detection with Principal Component Analysis (PCA) In the article is written following: • PCA algorithm basically transforms data readings from an existing coordinate system into a new coordinate system. • The closer data readings are to the center of the new coordinate system, the closer these readings are to an optimum value. • The anomaly score is calculated using the Mahalanobis distance between a reading and the mean of all readings, which is the center of the transformed coordinate system. Can anyone describe me more in detail about anomaly detection