Last active
May 1, 2016 06:04
-
-
Save Gedevan-Aleksizde/f3505d462c218889bfc2dc739c3cb4d5 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(dplyr) | |
library(tidyr) | |
library(ggplot2) | |
library(rstan) | |
library(loo) | |
# working directory | |
work.dir <- "HOGEHOGE/20160406_RFM" | |
df <- read.csv(paste(work.dir, "rfm.csv",sep="/"), stringsAsFactors = F) | |
colnames(df)[1] <- "ID" | |
df.spending <- read.csv(paste(work.dir, "spending_mat.csv", sep="/"), stringsAsFactors = F) | |
spending.num <- read.csv(paste(work.dir, "spending_freq.csv", sep="/"), stringsAsFactors = F, header=F) | |
colnames(spending.num) <- c("ID","num") | |
# make TEST datasets | |
#sample.ID <- sample(df$ID, size=100, replace = F) | |
#df.test <- df[df$ID %in% sample.ID,] | |
#df.spending.test <- df.spending[df.spending$CustomerID %in% sample.ID, ] | |
#spending.num.test <- spending.num[spending.num$ID %in% sample.ID,] | |
rstan_options(auto_write = TRUE) | |
options(mc.cores = parallel::detectCores()) | |
model <- stan_model(paste(work.dir, "rfm_hierarchical.stan", sep="/")) | |
# annualy discount = 15 % | |
RFM.res <- sampling(model, data=list(N=nrow(df), | |
Time=df$Time, | |
time=df$time, | |
x=df$Freq, | |
K=ncol(df.spending), | |
NSpend=spending.num$num, | |
Spend=df.spending, | |
delta=.0027), | |
init=list(chain1=list(tau=rowMeans(df[,c('time','Time')])), | |
chain2=list(tau=rowMeans(df[,c('time','Time')])), | |
chain3=list(tau=rowMeans(df[,c('time','Time')])), | |
chain4=list(tau=rowMeans(df[,c('time','Time')])) | |
), | |
alogorithm="HMC", | |
warmup=15000, iter=17000, chain=4) | |
save(df.res, RFM.res, file=paste(work.dir, "result.RData", sep="/")) | |
traceplot(RFM.res, 'theta0') | |
traceplot(RFM.res, 'Gamma0') | |
print(RFM.res, 'theta0') | |
print(RFM.res, 'Gamma0') | |
print(RFM.res,'pzeta') | |
print(RFM.res, pars='CLV') | |
print(RFM.res, pars='tau') | |
res.descript <- function(stan.result, df){ | |
for( col in c("lambda", "mu", "eta", "CLV", "zeta" ,"tau")){ | |
df[,col] <- apply(rstan::extract(stan.result, col)[[col]], 2, mean) | |
} | |
df$tau_well <- with(df, (time <= tau ) ); | |
df$tau_well[df$zeta < 1] <- with(df[df$zeta < 1,], tau_well && (tau <= Time)) | |
return(dplyr::select(df, ID, lambda, mu, eta, CLV, zeta, tau, time, Time, Recency, Freq, Monetary, tau_well)) | |
} | |
df.res <- res.descript(RFM.res, df) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment