tgjc

# List unique values in a DataFrame column
# h/t @makmanalp for the updated syntax!
df['Column Name'].unique()

# Convert Series datatype to numeric (will error if column has non-numeric values)
# h/t @makmanalp
pd.to_numeric(df['Column Name'])

# Convert Series datatype to numeric, changing non-numeric values to NaN
# h/t @makmanalp for the updated syntax!

tgjc

DATA %>% rename_(.dots=setNames(names(.), tolower(gsub("FROM", "TO", names(.)))))

## Taken from: http://stackoverflow.com/questions/30382908/r-dplyr-rename-variables-using-string-functions

tgjc

# Notes: 
# 1. rename staff number field in each spreadsheet to "emp_id"
# 2. When adding new spreadsheets, convert emp_id class to character to allow anti_join() to work
# 3. if time allows, automate cleaning of column names and drop unused from hr-list.csv



library(dplyr)
library(readr)

tgjc

##Split text in the form "surname, firstname" and concantenate 
to (firstname lastname)

##Surname
=LEFT(TEXT,(FIND(",",TEXT)-1))

##First name
=RIGHT(TEXT,LEN(I6) - E6 -1)

##Concantenate

tgjc

# Read data and extract start / finish columns
setwd("/Volumes/emr/Testing/")

raw_file <- read.csv("theo_Epic GANTT 20150605.csv")
raw_start <- raw_file[,"Start"]
raw_finish <- raw_file[,"Finish"]

# Parse date-time and revemove times
raw_start2 <- dmy(raw_start)
new_start <- paste(day(raw_start2), month(raw_start2), year(raw_start2),"/")