Kentaro Matsuura MatsuuraKentaro

## model1.stan
data {
  int D;
  int N;
  matrix[N,D] X;
  vector[N] Y;
}

parameters {
  vector[D] b;
  real<lower=0> sigma;

## model.stan
data {
  int I;
  int J;
  matrix[I,J] Y;
  real<lower=0> U;
}

parameters {
  matrix<lower=-5, upper=5>[I,J] mu;
  real<lower=0> s_mu;

## model.stan
data {
  int Q;
  int N;
  vector[Q] D;
  int Solved[Q, N];
  vector[N] D_max;
  real D_range;
}

parameters {

## calc-scale_best-example.R
library(ggjoy)
library(dplyr)
library(purrr)

# yutani data ------------------------------------------------------------
set.seed(10)
l <- rerun(26, rnorm(1000, mean = runif(1), sd = sqrt(runif(1))))
names(l) <- LETTERS
l[[2]] <- c(rnorm(500, mean = -1, sd = 0.3), rnorm(500, mean = 1, sd = 0.3))
d <- as.data.frame(l) %>% tidyr::gather(id, value)

## dynoload.js
var fileref=document.createElement('script')
fileref.setAttribute("type","text/javascript")
fileref.setAttribute("src", "https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML")
document.getElementsByTagName("head")[0].appendChild(fileref)

## data.csv

          
            Time
            Date
            Y

            
              0
              2012-03-01
              28140

            
              1
              2012-03-08
              28850

            
              2
              2012-03-15
              34230

            
              3
              2012-03-22
              29260

            
              4
              2012-03-29
              29200

            
              5
              2012-04-05
              33940

            
              7
              2012-04-19
              24800

            
              8
              2012-04-26
              26060

            
              9
              2012-05-03
              26490

## DP.csv

          
            Age10
            N
            Y

            
              1
              1
              0

            
              2
              5
              2

            
              3
              28
              25

            
              4
              34
              27

            
              5
              27
              19

            
              6
              59
              28

            
              7
              177
              76

            
              8
              234
              95

            
              9
              52
              27

## model1.stan
functions {
  // calculating the convolutions
  vector convolution(vector x, vector y_rev) {
    int T = num_elements(x);
    vector[T-1] res;
    for (t in 2:T) {
      res[t-1] = dot_product(x[1:(t-1)], y_rev[(T-t+2):T]);
    }
    return res;
  }

## calculate-WAIC.R
library(cmdstanr)

waic <- function(log_likelihood) {
  training_error <- - mean(log(colMeans(exp(log_likelihood))))
  functional_variance_div_N <- mean(colMeans(log_likelihood^2) - colMeans(log_likelihood)^2)
  waic <- training_error + functional_variance_div_N
  return(waic)
}

model1_Si <- cmdstan_model('model1-addG-Simpson.stan')

## iterfuns.hpp
#include <ostream>

static int iteration_index = 1;

inline void add_iter(std::ostream* pstream__) {
  iteration_index += 1;
}

inline int get_iter(std::ostream* pstream__) {
  return iteration_index;
	data {
	int D;
	int N;
	matrix[N,D] X;
	vector[N] Y;
	}

	parameters {
	vector[D] b;
	real<lower=0> sigma;
	data {
	int I;
	int J;
	matrix[I,J] Y;
	real<lower=0> U;
	}

	parameters {
	matrix<lower=-5, upper=5>[I,J] mu;
	real<lower=0> s_mu;
	data {
	int Q;
	int N;
	vector[Q] D;
	int Solved[Q, N];
	vector[N] D_max;
	real D_range;
	}

	parameters {
	library(ggjoy)
	library(dplyr)
	library(purrr)

	# yutani data ------------------------------------------------------------
	set.seed(10)
	l <- rerun(26, rnorm(1000, mean = runif(1), sd = sqrt(runif(1))))
	names(l) <- LETTERS
	l[[2]] <- c(rnorm(500, mean = -1, sd = 0.3), rnorm(500, mean = 1, sd = 0.3))
	d <- as.data.frame(l) %>% tidyr::gather(id, value)
	var fileref=document.createElement('script')
	fileref.setAttribute("type","text/javascript")
	fileref.setAttribute("src", "https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML")
	document.getElementsByTagName("head")[0].appendChild(fileref)
Time	Date	Y
0	2012-03-01	28140
1	2012-03-08	28850
2	2012-03-15	34230
3	2012-03-22	29260
4	2012-03-29	29200
5	2012-04-05	33940
7	2012-04-19	24800
8	2012-04-26	26060
9	2012-05-03	26490
	functions {
	// calculating the convolutions
	vector convolution(vector x, vector y_rev) {
	int T = num_elements(x);
	vector[T-1] res;
	for (t in 2:T) {
	res[t-1] = dot_product(x[1:(t-1)], y_rev[(T-t+2):T]);
	}
	return res;
	}
	library(cmdstanr)

	waic <- function(log_likelihood) {
	training_error <- - mean(log(colMeans(exp(log_likelihood))))
	functional_variance_div_N <- mean(colMeans(log_likelihood^2) - colMeans(log_likelihood)^2)
	waic <- training_error + functional_variance_div_N
	return(waic)
	}

	model1_Si <- cmdstan_model('model1-addG-Simpson.stan')
	#include <ostream>

	static int iteration_index = 1;

	inline void add_iter(std::ostream* pstream__) {
	iteration_index += 1;
	}

	inline int get_iter(std::ostream* pstream__) {
	return iteration_index;