anomalize errors

[duncanwil]

I have tried to run the code from your page https://business-science.github.io/anomalize/ but I get the following problems.

Initially, the first bit of the code that downlaods data from CRAN and then creates the faceted graphs works but when I run it for a second time it tells me

"Error in mutate_impl(.data, dots) : Evaluation error: 'get_index_col' is not an exported object from 'namespace:tibbletime'."

I started again and got this message this time:

"Error: expr must quote a symbol, scalar, or call"

When I run the next bit of code, # Data Manipulation / Anomaly Detection I get this error message even though I have changed nothing in your code:

"Error: index attribute is NULL. Was it removed by a function call?"

When I ran # Anomaly Visualziation, I got this error message:

"Error in eval(lhs, parent, parent) : object 'lubridate_dloads' not found"

My code follows:

Using the anomalize package

https://business-science.github.io/anomalize/

devtools::install_github("business-science/anomalize")

install.packages("anomalize") ... this one did not work for my version of R

library(tidyverse) library(anomalize)

Next, let’s get some data. anomalize ships with a data set called tidyverse_cran_downloads that contains the daily CRAN

download counts for 15 “tidy” packages from 2017-01-01 to 2018-03-01.

tidyverse_cran_downloads %>% ggplot(aes(date, count)) + geom_point(color = "#2c3e50", alpha = 0.25) + facet_wrap(~ package, scale = "free_y", ncol = 2) + theme_minimal() + theme(axis.text.x = element_text(angle = 30, hjust = 1)) + labs(title = "Tidyverse Package Daily Download Counts", subtitle = "Data from CRAN by way of cranlogs package")

Suppose we want to determine which daily download “counts” are anomalous.

It’s as easy as using the three main functions (time_decompose(), a

nomalize(), and time_recompose()) along with a visualization function,

plot_anomalies().

tidyverse_cran_downloads %>%

Data Manipulation / Anomaly Detection

time_decompose(count, method = "stl") %>% anomalize(remainder, method = "iqr") %>% time_recompose() %>%

Anomaly Visualization

plot_anomalies(time_recomposed = TRUE, ncol = 2, alpha_dots = 0.25) + labs(title = "Tidyverse Anomalies", subtitle = "STL + IQR Methods")

If you’re familiar with Twitter’s AnomalyDetection package, you can

implement that method by combining time_decompose(method = "twitter")

with anomalize(method = "gesd"). Additionally, we’ll adjust the

trend = "2 months" to adjust the median spans, which is how Twitter’s

decomposition method works.

Get only lubridate downloads

lubridate_dloads <- tidyverse_cran_downloads %>% filter(package == "lubridate") %>% ungroup()

Anomalize!!

lubridate_dloads %>%

Twitter + GESD

time_decompose(count, method = "twitter", trend = "2 months") %>% anomalize(remainder, method = "gesd") %>% time_recompose() %>%

Anomaly Visualziation

plot_anomalies(time_recomposed = TRUE) + labs(title = "Lubridate Anomalies", subtitle = "Twitter + GESD Methods")

Last, we can compare to STL + IQR methods, which use different

decomposition and anomaly detection approaches.

lubridate_dloads %>%

STL + IQR Anomaly Detection

time_decompose(count, method = "stl", trend = "2 months") %>% anomalize(remainder, method = "iqr") %>% time_recompose() %>%

Anomaly Visualization

plot_anomalies(time_recomposed = TRUE) + labs(title = "Lubridate Anomalies", subtitle = "STL + IQR Methods")

[mdancho84]

Try reinstalling tibbletime. You may need to update it to get some of the functions that anomalize uses.

[leungi]

First off, kudos for this wonderful gift! @mdancho84

Had the same issue as OP and upgrading tibbletime fixed it; safe to close ticket :+1:

[mdancho84]

Awesome!!

[HeinrichMuller]

Hi Matt

I am a newbie to R.

I have tried to run the code from your page https://business-science.github.io/anomalize/ but I just cannot get it to work.

I can install all th packages i need but keep getting an error when i want to view tidyverse_cran_downloads: Error: expr must quote a symbol, scalar, or call

Below are my initial steps:

##################################################

Step 1: Install Anomalize

devtools::install_github("business-science/anomalize",force = TRUE) install.packages("tibbletime")

Step 2: Load Tidyverse and Anomalize

library(tidyverse) library(anomalize) library(tibbletime)

check tidyverse data()

tidyverse_cran_downloads

###############################################

Can you please help me resolve this issue.

Kind regards

Heinrich