correlation level for correlated vars? about regional_sdm HOT 6 CLOSED

# run correlation analysis
#correlationtree <- varclus(data.matrix(MoBI_FlowEnvVar_Update[3:173]), similarity="spear")
correlationtree <- varclus(data.matrix(MoBI_FlowEnvVar_Update[c(80:82,105:110,121,174:178)]), similarity="spear")
# plot the data
#pdf("file.pdf",width=24,height=12)
plot(correlationtree, cex=0.6)
abline(h=0.1, col="blue")
abline(h=0.2, col="red")
#dev.off()


# prevent duplicated pairs
var.corelation <- correlationtree$sim*lower.tri(correlationtree$sim)
check.corelation <- which(var.corelation>0.64, arr.ind=TRUE)
graph.cor <- graph.data.frame(check.corelation, directed = FALSE)
groups.cor <- split(unique(as.vector(check.corelation)),         clusters(graph.cor)$membership)
a <- lapply(groups.cor,FUN=function(list.cor){rownames(var.corelation)[list.cor]})
correlated_groups <- do.call("rbind", lapply(a, data.frame))
correlated_groups$group <- rownames(correlated_groups)
correlated_groups$group <- gsub("\\..*","",correlated_groups$group)  #use to join up with the lkupenvvars table
rm(a, var.corelation, check.corelation, groups.cor, graph.cor)

# sqlite loading
db_aqua_lotic <- dbConnect(SQLite(),"MoBI_Aquatic_EnvVars.sqlite")
dbWriteTable(db_aqua_lotic, "envvar_lotic", MoBI_FlowEnvVar_Update)
dbDisconnect(db_aqua_lotic)

# envvar descriptions
envvars <- colnames(MoBI_FlowEnvVar)
ev_desc <- as.data.frame(envvars)
for(i in 1:length(ev_desc$envvars)){
  ev_desc$mean <- mean(get(MoBI_FlowEnvVar)$ev_desc$envvars[i])
  #get(paste('r',i,collapse='',sep=''))$speed
}

ev_desc <- lapply(MoBI_FlowEnvVar[25:262], function(x) rbind( mean = mean(x, na.rm=TRUE) ,
                                         sd = sd(x, na.rm=TRUE) ,
                                         median = median(x, na.rm=TRUE) ,
                                         minimum = min(x, na.rm=TRUE) ,
                                         maximum = max(x, na.rm=TRUE) ,
                                         s.size = length(x) ) )