Deleted:Is there a python package that can replicate this model?
0
0
Entering edit mode
6 weeks ago
Mike ▴ 10

Hi all, I hope this question belongs here since I'm analyzing biological data, if not I'll remove it.

I'm trying to convert a short R data analysis script to python and can't find the right modules/packages to do so. This is the script in R:

for(var in vars){
  model<-lm(eval(parse(text=dep))~treatment,data = param)
  org.lsm<-lsmeans(model,"treatment")
  org.lsm <- confint(org.lsm, side = “=”, level = 0.95, type = "lsmean")  
  final = data.frame()
  treatments = unique(param$treatment)
  for (treat in treatments){
    results<-list()
    ind = paste0(treat)
    results[[ind]]$A <-  var
    results[[ind]]$B <-  param
    results[[ind]]$C <- treat
    results[[ind]]$N <- dim(param[param$treatment == treat,])[1]
    results[[ind]]$LS <- org.lsm$lsmean[org.lsm$treatment==treat]
    results[[ind]]$SE <- org.lsm$SE[org.lsm$Treatment==treat]
    results[[ind]]$df <- org.lsm$df[org.lsm$Treatment==treat]
    t=org.lsm$lsmean[org.lsm$treatment==treat]-0
    t=t/org.lsm$SE[org.lsm$treatment==treat]
    results[[ind]]$PVAL=round(2*pt(-abs(t),df=org.lsm$df[org.lsm$treatment==treat]),5)
    if (is.na(results[[ind]]$PVAL)){stop("Message")}
    results<-do.call("rbind.data.frame",results)
    final <- rbind(final,results)
  }
  }

Basically I'm trying to understand just how to make the initial model in python- not rewrite the whole script. I found statsmodels but can't seem to configure it so much as in the R script. (the lsmeans, confint, SE and more)

Any help with this will be highly appreciated!

python R data analysis statsmodels • 136 views
ADD COMMENT
This thread is not open. No new answers may be added
Traffic: 1053 users visited in the last hour
Help About
FAQ
Access RSS
API
Stats

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.

Powered by the version 2.3.6