tomhopper

find . -name '.filename' -print -exec rm -r {} \;

# . = in current directory
# -name = file name to find
# -print = print the result's full file name to standard output
# -exec = execute the following command
# {} = fill in with the result of standard output
# \; = semicolon to terminate the -exec command, and the escape
#      character so that the terminal doesn't treat the semicolon as a 
#      return character (used for stringing together multiple commands).

tomhopper

# The xkcd font used by the package xkcd (which provides a theme for ggplot2)
# is missing many characters and some characters don't seem to display correctly.
# An alternate xkcd-style font is Humor Sans, available free from 
# \url{http://antiyawn.com/uploads/humorsans.html}
# The code below forces the use of Humor Sans instead of xkcd.
# The xkcd and ggplot2 packages are available from CRAN.

library(ggplot2)
library(xkcd)

tomhopper

# Create 2 replicates of 5 "words" generated from random characters,
# each "word" 5 - 15 characters long, with word length following a 
# poisson distribution.
rep(replicate(5, paste(sample(letters, round(rpois(5000, lambda = 3)+5, 0), replace = FALSE), collapse = "")), 2)

# Sample output:
# [1] "rfexnwyjst" "vwtadhjnly" "ztfgvldo"   "tmerol"     "mcqhosap"   "rfexnwyjst" "vwtadhjnly" "ztfgvldo"   "tmerol"    
#[10] "mcqhosap" 

tomhopper

## For original file showing use of .env to add functions invisibly, see 
## \link{http://gettinggeneticsdone.blogspot.com/2013/06/customize-rprofile.html}

## Load packages
#library(BiocInstaller)

## Don't show those silly significanct stars
#options(show.signif.stars=FALSE)

## Do you want to automatically convert strings to factor variables in a data.frame?

tomhopper

#' @title Sorting data frames factor levels for ggplot2
#' @description Sorting a factor variable by a numeric variable.
#'    In one case, each factor level is matched to one numeric value.
#'    In the other case, each factor level is repeated across a second
#'    grouping factor variable, and we want to sort only the 
library(dplyr)
library(tidyr)
library(ggplot2)

# Sort a factor by variable by a numeric variable

tomhopper

# Response to a post at Storytelling with Data:
# \url{http://www.storytellingwithdata.com/blog/orytellingwithdata.com/2015/07/align-against-common-baseline.html}
# Demonstrates
#  * Cleveland-style dot plots (improvement over pie and bar charts)
#  * Sorting categorical data by a numerical variable with more than one grouping variable
#  * Highlighting differences between groups graphically

library(ggplot2)
library(scales)

tomhopper

library(dplyr)

# create a dummy dataframe with 100,000 groups and 1,000,000 rows
# and partition by group_id
df <- data.frame(group_id=sample(1:1e5, 1e6, replace=T),
                 val=sample(1:100, 1e6, replace=T)) %>%
      group_by(group_id)

# filter rows with a value of 1 naively
system.time(df %>% filter(val == 1))

tomhopper

# from Conrad Hacket
# Median hourly earnings
# \url{https://twitter.com/conradhackett/status/748884076493475840}
# makeover: convert from two groups of side-by-side vertical bar charts to a more readable dot plot
# Demonstrates:
#   Use of in ggplot2
#   Creating dot plots 
#   Combining color and shape in a single legend
#   Sorting a dataframe so that categorical data in one column is ordered by a second numerical column
# Note: resulting graph displays best at about 450 pixels x 150 pixels

tomhopper

# Based on a post at \url{http://www.walkingrandomly.com/?p=5254}
library(dplyr)
library(ggplot2)
library(minpack.lm)

# The data to fit
my_df <- data_frame(x = c(0,15,45,75,105,135,165,195,225,255,285,315),
                    y = c(0,0,0,4.5,19.7,39.5,59.2,77.1,93.6,98.7,100,100))

# EDA to see the trend

tomhopper

##' Modifies 'data' by adding new values supplied in newDataFileName
##'
##' newDataFileName is expected to have columns 
##' c(lookupVariable,lookupValue,newVariable,newValue,source)
##' 
##' Within the column 'newVariable', replace values that
##' match 'lookupValue' within column 'lookupVariable' with the value
##' newValue'.  If 'lookupVariable' is NA, then replace *all* elements
##' of 'newVariable' with the value 'newValue'.
##'