| library(ggplot2) | |
| library(dplyr) | |
| so <- read.csv(file = "2016 Stack Overflow Survey Responses.csv") %>% tbl_df() | |
| # What is the difference in salaries betewen people who report workring remotely | |
| # and people who don't? | |
| # (Full-time remote + Part-time remote) vs (Rarely work remotely and Never) | |
| so_salary_remote <- so %>% select(salary_midpoint, remote) |
| # Parallelize R | |
| # Source: http://blog.yhat.com/posts/running-r-in-parallel.html | |
| library(plyr) | |
| library(doMC) | |
| # set number of cores (mine has two cores) | |
| doMC::registerDoMC(cores = 2) # number of cores you have access to | |
| # Process data |
| # Load package | |
| library(openxlsx) # Write data to Excel sheets | |
| # Remind what is in data | |
| head(iris) | |
| head(mtcars) | |
| # Create workbook (i.e. file) to put data in | |
| fileName <- "iris-mtcars.xlsx" | |
| excel <- createWorkbook(fileName) |
| # Title: | |
| # Show dangers of relative abundance | |
| # Import graphics library | |
| library(ggplot2) | |
| # Create dummy data | |
| a <- c(2, 3, 4, 15, 3) | |
| b <- c(2, 3, 4, 30, 3) | |
| sample <- 1:5 |
| # Question: https://stats.stackexchange.com/q/59343/132399 | |
| # Source: https://stats.stackexchange.com/a/59348/132399 | |
| matrix(c(5, 3, 2, 17), nrow = 2, byrow = TRUE) | |
| # [,1] [,2] | |
| # [1,] 5 3 | |
| # [2,] 2 17 | |
| # Matthews correlation coefficient directly from Wikipedia formula | |
| (5*17-3*2) / sqrt((5+3)*(5+2)*(17+3)*(17+2)) |
| # Demonstrate unintuitiveness of entropy to describe diversity | |
| # Resources used: | |
| # - Code influenced by https://stackoverflow.com/a/27255815 | |
| # - Problem from http://www.biodiverseperspectives.com/2013/03/25/an-intuitive-approach-to-describing-diversity/ | |
| # Load libraries | |
| library(entropy) | |
| # Make two communities, each with equally abundant species | |
| eightspecies <- rep(letters[1:8], 5) |
| # Quick script to calculate Gini index and show that it is counterintuitive to | |
| # how we should think about diversity | |
| # Calculate Gini-Simpson quadratic index | |
| # gini = 1 - \sum_{i = 1}^R p_i^2 | |
| gini <- function(x) { | |
| temp <- x / sum(x) | |
| 1 - sum(temp * temp) | |
| } |
| # --- | |
| # title: Export QIIME2 OTU table to compatible file for phyloseq | |
| # description: | | |
| # Three main steps to get to compatible file to import to phyloseq | |
| # | |
| # Outline: | |
| # 1. Export OTU table | |
| # 2. Export taxonomy table | |
| # 3. Export phylogenetic tree | |
| # --- |
| #!/usr/bin/env bash | |
| # Purpose: Find largest directories and files in your home directory | |
| # Note: Tested on macOS | |
| # To Run: | |
| # $ bash find_largest_files.sh | |
| # Output: | |
| # - top_100_largest.txt | |
| # - Output to the terminal total space used in home directory | |
| # To explore results: |
List of running topics that may be of interest.