hauselin

hauselin

library(dplyr)
library(broom)
library(modelsummary)


clean_colnames <- function(df) {
    new <- tolower(gsub(" ", "_", names(df)))
    new <- gsub(".", "_", new, fixed = TRUE)
    new <- gsub("(", "", new, fixed = TRUE)
    new <- gsub(")", "", new, fixed = TRUE)

hauselin

alias gh="open \`git remote -v | grep git@github.com | grep fetch | head -1 | cut -f2 | cut -d' ' -f1 | sed -e's/:/\//' -e 's/git@/http:\/\//'\`"

hauselin

# see also seWithin function in hausekeep package
# https://hauselin.github.io/hausekeep/reference/seWithin.html
summarySE2 <- function (data = NULL, measurevar, groupvars = NULL, na.rm = TRUE, conf.interval = 0.95) {
    library(data.table)
    data <- data.table(data)
    
    length2 <- function(x, na.rm = FALSE) {
        if (na.rm) 
            sum(!is.na(x))
        else length(x)

hauselin

df_long = pd.DataFrame(
  {"student": ["Andy", "Bernie", "Cindy", "Deb", "Andy", "Bernie", "Cindy", "Deb", "Andy", "Bernie", "Cindy", "Deb"],
   "school":  ["Z", "Y", "Z", "Y", "Z", "Y", "Z", "Y", "Z", "Y", "Z", "Y"],
   "class":   ["english", "english", "english", "english", "math", "math", "math", "math", "physics", "physics", "physics", "physics"],
   "grade":   [10, 100, 1000, 10000, 20, 200, 2000, 20000, 30, 300, 3000, 30000]
  }
)

df_long
>    student school    class  grade

hauselin

def simulate(simulations=1000, n=500, quantile=0.80):
    
    correlations = np.zeros(simulations)

    for i in range(simulations):
        
        data = {"personality": np.random.randn(
            n), "attract": np.random.randn(n)}
        df = pd.DataFrame(data)
        

hauselin

Using Git

Global Settings

• Related Setup: https://gist.github.com/hofmannsven/6814278
• Related Pro Tips: https://ochronus.com/git-tips-from-the-trenches/
• Interactive Beginners Tutorial: http://try.github.io/
• Git Cheatsheet by GitHub: https://services.github.com/on-demand/downloads/github-git-cheat-sheet/

hauselin

Atom Settings

hauselin

summarySE2 <- function (data = NULL, measurevar, groupvars = NULL, na.rm = TRUE, conf.interval = 0.95) {
    library(data.table)
    data <- data.table(data)
    
    length2 <- function(x, na.rm = FALSE) {
        if (na.rm) 
            sum(!is.na(x))
        else length(x)
    }
    

hauselin

#function to read raw data from Qualtrics
cleanQualtrics <- function(csvFile, rowAsHeader, skipRows) {
    #this function assumes that you have named your
    #Qualtrics questions properly when setting up the survey;
    #if questions are properly named, then the first row 
    #will be most informative and suitable for use as column names
    #read.csv sets header = T by default; stringsAsFactor set to FALSE to ensure strings aren't converted to factors
    QualtricsRaw <- read.csv(csvFile, header = F, stringsAsFactors = F)
    #row 1 contains the strings that we'd like to use as column names; select row 1 and turn them into characters
    colNames <- as.character(QualtricsRaw[rowAsHeader,])