junos
/
rapids
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Ignore NA values for dropping zero variance columns

pull/95/head
JulioV 2020-04-13 16:59:33 -04:00
parent 010114c1aa
commit cdd10578b3
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/models/clean_metrics_for_model.R
View File

@ -27,7 +27,7 @@ if(nrow(clean_metrics))
clean_metrics <- clean_metrics %>% select_if(~ sum(is.na(.)) / length(.) <= cols_nan_threshold )
if(drop_zero_variance_columns)
clean_metrics <- clean_metrics %>% select_if(grepl("pid|local_date",names(.)) | sapply(., n_distinct) > 1)
clean_metrics <- clean_metrics %>% select_if(grepl("pid|local_date",names(.)) | sapply(., n_distinct, na.rm = T) > 1)
# drop rows with a percentage of NA values above rows_nan_threshold
clean_metrics <- clean_metrics %>%