dantonnoriega

[
{
        "id": "tools",
        "children":
        [{
            "caption": "SublimeREPL",
            "mnemonic": "r",
            "id": "SublimeREPL",
            "children":
            [

dantonnoriega

Set up tmux with a vim REPL on a linux box

1. install https://github.com/tpope/vim-pathogen into ~/.vim/
2. install https://github.com/jpalardy/vim-slime into ~/.vim/bundle
3. copied default vimrc to a user copy: cp /etc/vimrc ~/.vim/vimrc
4. added the following to the end of ~/.vim/vimrc

" vim slime
let g:slime_python_ipython = 1

dantonnoriega

import sublime, sublime_plugin

class MoveForwardToSectionCommand(sublime_plugin.TextCommand):
    def run(self, edit):
        v = self.view
        s = v.sel()

        pattern = "^[ ]*# [#]{4,}|^[ ]*[#]{4,}|^[ ]*#+ [\w]+.+[-]+$|^`{3}"

        # get current point and then look forward

dantonnoriega

import sublime, sublime_plugin

class ExpandSelectionToEofCommand(sublime_plugin.TextCommand):
    def run(self, edit):
        v = self.view
        s = v.sel()
        eof = v.size()

        first_point = v.line(s[0]).a
        region_to_eof = sublime.Region(first_point, eof)

dantonnoriega

dantonnoriega

# a running list of really useful data.table tricks

# TOP 1,2 ... last row by some group id
## source: https://stackoverflow.com/questions/16325641/is-it-possible-to-extract-the-first-2-rows-for-each-date#comment23381259_16325932
## comment by @eddi
id <- c('date', 'userid')
dt[dt[, .I[1:2], by = id]$V1] # first 2 rows by id
dt[dt[, .I[.N], by = id]$V1] # last row by id (.N = length of group, .I = row index)

dantonnoriega

# inspired by https://stats.stackexchange.com/questions/174121/can-a-model-for-non-negative-data-with-clumping-at-zeros-tweedie-glm-zero-infl
# additions by Danton Noriega
library(statmod)
library(tweedie)
library(mgcv)

# generate fake mu (poisson count rates)
set.seed(1789)
x <- seq(1,100, by = .1)
mutrue <- exp(-1+x/25)

dantonnoriega

library(tidyverse)
library(rstan)

## HOW THE SIMULATION LOOP BELOW WORKS -- ignore the shocks for now --------------
# quick example
I = 3 # individuals
M = 5 # "months"
S = 7 # sims
mat <- matrix(NA, I*M, S) # M rows (months) will be filled in at a time for each individual i across all S columns (simulations); records for individual i will populate rows ((i - 1)*M + 1):(i*M)

dantonnoriega

# stan code from https://arxiv.org/pdf/1808.06399.pdf
library("DirichletReg")
Bld <- BloodSamples
Bld <- na.omit(Bld)
Bld$Smp <- DR_data(Bld[, 1:4])

stan_code <- '
data {
  int<lower=1> N;  // total number of observations
  int<lower=2> ncolY; // number of categories

dantonnoriega

# recreate the code from https://arxiv.org/pdf/1808.06399.pdf using greta (https://greta-dev.github.io/greta/)
library("DirichletReg")
Bld <- BloodSamples
Bld <- na.omit(Bld)
Bld$Smp <- DR_data(Bld[, 1:4])

# simplex function. applies simplex to each row of a matrix.
# HUGE speed gains using matrix mat vs for loop!
simplex_mat <- function(x){
  exp_x <- exp(x)