Query ML Endpoint with R and Curl

[BogdanV]

I am trying to get a prediction by querying the ML Endpoint on Azure Databricks with R. 
I'm not sure what is the format of the expected data. Is there any other problem with this code?

 

Thanks!!!

[Kaniz_Fatma]

Hi @BogdanV, Please paste the code stack here.

[BogdanV · Accepted solution]

Hi Kaniz, 

I was able to find the solution. You should post this in the examples when you click "Query Endpoint"
You only have code for Browser, Curl, Python, SQL. You should add a tab for R
Here is the solution:

library(httr)
url <- "https://adb-********.azuredatabricks.net/serving-endpoints/********/invocations"
db_token="dap*******"
headers <- add_headers('Authorization'==paste('Bearer', db_token, sep=' '),
"Content-Type" = "application/json")

data='{"dataframe_split": {"columns": ["***columnName1String***", "***ColumnName2Integer****"], "data": [["val11", val12], ["val21", val22], ["val31", val32]]}}'
response= POST(url,headers,body=data)
results <- content(response, "parsed")

[Kaniz_Fatma]

Hi @BogdanV, 

Thank you so much for sharing your solution! We greatly appreciate your input. I'm glad to hear that you were able to find a solution that works for you.

If you have any more questions or need further assistance, please don't hesitate to reach out. We're here to help!