Hello @Paddy_chu,

Here's an updated version of the R code:

%r

library(sparklyr)

library(SparkR)

sc <- spark_connect(method = "databricks")

matched_rdf <- psm_tbl %>% select(c(code_treat, code_control)) %>% data.frame()

# Write the R dataframe to Spark

matched_spark <- copy_to(sc, matched_rdf, overwrite = TRUE)

# Register the Spark DataFrame as a temporary view to query it using SQL

spark.sql("CREATE OR REPLACE TEMP VIEW matched_view AS SELECT * FROM matched_spark")