PietrH

library(tidyverse)
head(test) %>%
  {.->>intermed_result} %>% #save intermediate result
  print()

PietrH

#parse the date as a string and extract the day, 
#compare it to the string value '1' and '15' and if it's equal to either, respond TRUE else respond FALSE

or((value.toDate('dd MMM yyyy').toString('d'))==toString(1),(value.toDate('dd MMM yyyy').toString('d'))==toString(15))

#to be used as a Facet in OpenRefine

PietrH

library(dplyr)

distinct(DataFrame,Column_To_Filter_On,.keep_all = TRUE) %>%
  view('Dataframe distinct')

PietrH

#Orignial Source: http://www.endmemo.com/program/R/grepl.php

#grepl returns TRUE if a string contains the pattern, otherwise FALSE; if the parameter is a string vector, 
#returns a logical vector (match or not for each element of the vector).

grepl(pattern, x, ignore.case = FALSE, perl = FALSE,
      fixed = FALSE, useBytes = FALSE)
      
#pattern: regular expression, or string for fixed=TRUE
#x: string, the character vector

PietrH

if(value.endsWith(';'),substring(value,0,-1),value)

PietrH

Expression	Description
nodename	Selects all nodes with the name "nodename"
/	Selects from the root node
//	Selects nodes in the document from the current node that match the selection no matter where they are
.	Selects the current node
..	Selects the parent of the current node
@	Selects attributes
[]	Condition on a selection

PietrH

Wildcard	Description
*	matches any element node
@*	matches any attribute node
node()	matches any node

PietrH

import re #regular expressions in Python

def number_from_string(string):
  return re.findall("\d+",string)
  
  
#The function will return a list of all digit sequences in the string

PietrH

Get-ChildItem -Path C:\Demo -Filter *.txt | Rename-Item -NewName {[System.IO.Path]::ChangeExtension($_.Name, ".old")}

PietrH

library(dplyr)

#we want to produce a frequency table of the length (nchar) of a column 'column' of our dataframe 'dataset'

mutate(dataset,nchar=nchar(column)) %>% count(nchar)