padpadpadpad

# difference in Phil McNulty rating and public votes
# https://www.bbc.co.uk/sport/football/44595146

library(tibble)
library(ggplot2)
library(tidyr)
library(dplyr)


player <- c('Jordan Pickford', 'Kieran Trippier', 'Harry Maguire', 'John Stones', 'Kyle Walker', 'Jordan Henderson', 'Ashley Young', 'Ruben Loftus-Cheek', 'Raheem Sterling', 'Jesse Lingard', 'Harry Kane')

padpadpadpad

# load packages
library(multidplyr)
library(dplyr)
library(tidyr)
library(purrr)
library(furrr)
library(tibble)
library(tictoc)

# I want to know which gene a bunch of SNPs is in. This will show us how to give different inputs to a function and also parallelising. Hopefully.

padpadpadpad

# code problem
# want to feed into a function to filter values of a dataframe based on values from a master dataframe
# inspiration - rates of false positives for snps (mutations) in a gene are influenced by the threshold for proportion of expression in a population. For example, if 0.01 of the population has it, its less likely to be a SNP than if you're at 0.9. Where to set this threshold is unknown.
# However, if you have the list of actual snps (from sequencing individual clones), you can look at different thresholds of variables to check which values give the least false positives and find the most true snps

# load packages
library(ggplot2)
library(dplyr)
library(tidyr)
library(tibble)

padpadpadpad

# load / install packages
library(dplyr)
library(tibble)
# devtools::install_github('padpadpadpad/TeamPhytoplankton')

# make dummy data
temp = (5:30) + 273.15
rate = TeamPhytoplankton::boltzmann(15, 1, temp, Tc = 15, log = 'N')
d <- tibble(rate, temp)

padpadpadpad

# load ggplot2
library(ggplot2)

# make data frame
d <- tibble(x = rep(c('a', 'b', 'c'), each = 10),
y = rnorm(30, mean = 10, sd = 1),
group = rep(1:10, times = 3))

# create jitter position with seeding
pos <- position_jitter(width = 0.1, height = 0, seed = 42)

padpadpadpad

---
title: "Non-linear bootstrapping approach 2.0"
author: "Daniel Padfield"
date: "15/03/2018"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

padpadpadpad

# example
# putting the SNP pos in the correct gene by its start and end position

# load packages
library(tibble)
library(dplyr)
library(tidyr)
library(purrr)

# dataframe of SNP positions and proportions

padpadpadpad

# cheeky late night bootstrapped mean

# load packages
library(broom)
library(tidyr)
library(purrr)
library(modelr)
library(dplyr)

# load dataset

padpadpadpad

# smatr bootstrap example

# load packages
library(smatr)
library(dplyr)
library(purrr)
library(tidyr)
library(ggplot2)

# load data

padpadpadpad

# example of trying to subset a matrix ####

# So I am trying to do Mantel tests that require distance matrices
# However I do not care about every pairwise distance in the matrix. instead I want to make some of the values of the distance NA to remove them
# Struggling to work out how to subset a matrix

# load packages
library(tibble)
library(dplyr)