mkuhn

library(tidyverse)

set.seed(23)

d <- tibble(x = rnorm(10), y = rnorm(10), a = rep(c("x", "y"),5), b = rep(1:5, 2))

d %>% 
  ggplot(aes(x, y, color = a, size = b)) + geom_point() +
 guides(colour = guide_legend(order = 1), 

mkuhn

Scribble:

B7Z2Y1_HUMAN
ARHG7_HUMAN
ARHG8_HUMAN
KCNA5_HUMAN
VWCE_HUMAN
DNML1_HUMAN
PKP4_HUMAN
NXPE2_HUMAN

mkuhn

library(Rcpp)

`%count<%` <- cppFunction('
size_t count_less(NumericVector x, NumericVector y) {

  const size_t nx = x.size();
  const size_t ny = y.size();

  if (nx > 1 & ny > 1) stop("Only one parameter can be a vector!");

mkuhn

> library(purrr)
> ll <- list(list(a=1:3, b=4), list(a=5:7, b=8))
> ll %>% map(lift_dl(c)) %>% map_call(rbind)
     a1 a2 a3 b
[1,]  1  2  3 4
[2,]  5  6  7 8
> Reduce(rbind, ll)
     a         b
init Integer,3 4
     Integer,3 8

mkuhn

library(purrr)

runtimes <- get_elapsed_time(fit)[,2]

inits <- get_inits(fit)

## traditional conversion to a matrix
# m.init <- do.call(rbind, lapply(inits, function(l) do.call(c, l)))

## using purrr

mkuhn

---
title: "Fitting with uncertainty"
author: "Michael Kuhn"
date: "24 Aug 2015"
output: html_document
---

In this toy example, we assume that we've independently measured values $x$ and $y$ and want to find a linear relationship between them, accounting for measurement uncertainty. Each $x$ and $y$ value is assigned a different uncertainty, and the challenge is to take this information into account. A standard linear model will treat all points equally.

When we treat each measurement as a multivariate normal distribution, we can find a point along the proposed fitted line that is maximizing the probability density function (i.e. that has a maximum likelihood). Thus, given a slope and intercept, we virtually move all measurements to their most likely point along the line, and use the likelihood at this point. 

mkuhn

library(dplyr)

a <- data.frame(foo = 1:10, bar = "bar")
b <- tbl_df(a)

a[,1]
b[,1]

paste0(a[,1], "!")
paste0(b[,1], "!")

mkuhn

library(ggplot2)
library(gtable)

# create example data
set.seed(42)
dataset_names <- c("Human", "Mouse", "Fly", "Worm")
datasets <- data.frame(name = factor(dataset_names, levels=dataset_names), parity = factor(c(0, 0, 1, 0)), v50 = runif(4, max=0.5), y=1:4)
data <- data.frame( dataset1 = rep(datasets$name, 4), dataset2 = rep(datasets$name, each = 4), z = runif(16,min = 0, max = 0.5) )

pal <- c("#dddddd", "#aaaaaa")

mkuhn

// International Chemical Identifier Regex, by lo sauer - lsauer.com
// Morphine InchI:
var x="InChI=1S/C17H19NO3/c1-18-7-6-17-10-3-5-13(20)16(17)21-15-12(19)4-2-9(14(15)17)8-11(10)18/h2-5,10-11,13,16,19-20H,6-8H2,1H3/t10-,11+,13-,16-,17-/m0/s1"

// applying an organic character-subset
// we could check for the length property, but in case of 0 matches 'null' is returned -> hence !!.. \ generally equal to Boolean(..) 
!!x.trim().match(/^((InChI=)?[^J][0-9BCOHNSOPrIFla+\-\(\)\\\/,pqbtmsih]{6,})$/ig)
>true
//generic:
x.trim().match(/^((InChI=)?[^J][0-9a-z+\-\(\)\\\/,]+)$/ig)

mkuhn

library(ggplot2)
library(gridExtra)

mtcars$cyl <- ordered(mtcars$cyl)
p <- ggplot(mtcars, aes(mpg, hp, colour = cyl)) + geom_point()

p1 <- p + theme(legend.position = "none")

p2 <- ggplot(mtcars, aes(x=mpg, group=cyl, colour=cyl))
p2 <- p2 + stat_density(fill = NA, position="dodge")