Could someone who comes from R language and SAS programming help me? I need to execute the code below programmatically in SAS. The code below was developed in R Spark on databricks. The goal is to run SAS through PROC, but as is little known in SAS Transfers. If anyone can help me with any suggestions.
6
for(i in 1:nrow(distinct_cluster)){
grupo=distinct_cluster[[i]]
dados<-dados_cluster
dados<-dados%>%filter(grupos==grupo)
variaveis_clusters <- dados %>%
filter(DATIPRNOTFSC<'2019-01-01', DATIPRNOTFSC>='2018-01-01')%>%
group_by(DESATICLI, Calculation)%>%
summarize(qtde=n())%>%
sdf_pivot(DESATICLI ~ Calculation, fun.aggregate = list(qtde = "sum"))
stats <- variaveis_clusters %>% select(-DESATICLI) %>% summarise_all(funs(avg, min, max)) %>% collect()
cols <- variaveis_clusters%>% select(-DESATICLI) %>% colnames()
avgs <- stats %>% select(ends_with("avg")) %>% unlist
mins <- stats %>% select(ends_with("min")) %>% unlist
maxs <- stats %>% select(ends_with("max")) %>% unlist
exprs <- glue("(`{cols}` - {avgs}) / ({maxs} - {mins})") %>%
setNames(cols) %>%
lapply(parse_quosure)
variaveis_escaladas<-variaveis_clusters %>% mutate(!!! exprs)
variaveis_clusters_tratado <- na.replace(variaveis_escaladas,0)
variaveis_clusters_tratado <- sdf_copy_to(sc, variaveis_clusters_tratado,
name = "variaveis_clusters_tratado", overwrite = TRUE)
set.seed(364221)
cluster <- ml_kmeans(variaveis_clusters_tratado, DESATICLI ~ ., k = 6)
clusters <- ml_predict(cluster, variaveis_clusters_tratado)
clusters <- clusters%>%mutate(grupos = case_when(
prediction==0 ~ "A",
prediction==1 ~ "B",
prediction==2 ~ "C",
prediction==3 ~ "D",
prediction==4 ~ "E",
prediction==5 ~ "F"))
if(i==1){
saida<-clusters%>%select(DESATICLI,grupos)%>%mutate(grupos_1=grupo)
}else{
saida<-sdf_bind_rows(saida,clusters%>%select(DESATICLI,grupos)%>%mutate(grupos_1=grupo))
}
}
