Last active
August 26, 2016 03:40
-
-
Save jmcurran/36734b7d62d4995e0b16ee4b2b7b4075 to your computer and use it in GitHub Desktop.
Script for converting imperial height measurements (of humans) into millimetres
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| raw | clean | ft | in | mm | |
|---|---|---|---|---|---|
| "5 | 5'0 | 5 | 0 | 1524 | |
| 5' | 5'0 | 5 | 0 | 1524 | |
| 5'5 | 5'5 | 5 | 5 | 1651 | |
| 5'7 1/2 | 5'7 1/2 | 5 | 7.5 | 1714.5 | |
| 5'7 | 5'7 | 5 | 7 | 1701.8 | |
| 5'8.5 | 5'8.5 | 5 | 8.5 | 1739.9 | |
| 5'612 | 5'6 1/2 | 5 | 6.5 | 1689.1 | |
| 6'0 1/2 | 6'0 1/2 | 6 | 0.5 | 1841.5 | |
| 5'4 1/2 ? | 5'4 1/2 ? | 5 | 4.5 | 1638.3 | |
| 5'6.25 | 5'6.25 | 5 | 6.25 | 1682.75 | |
| 4'0 | 4'0 | 4 | 0 | 1219.2 | |
| 5-7.5 | 5'7.5 | 5 | 7.5 | 1714.5 | |
| 5'91/2\ Lt" | 5'9 1/2 | 5 | 9.5 | 1765.3 | |
| 5'5-7 1/2 | 5'7 1/2 | 5 | 7.5 | 1714.5 | |
| 5'7 1/2l | 5'7 1/2 | 5 | 7.5 | 1714.5 | |
| 5'9' | 5'9 | 5 | 9 | 1752.6 | |
| 5'109 | 5'10 | 5 | 10 | 1778 | |
| 6'- | 6'0 | 6 | 0 | 1828.8 | |
| 5 ' | 5'0 | 5 | 0 | 1524 | |
| 5'8+ | 5'8 | 5 | 8 | 1727.2 | |
| 5'+ | 5'0 | 5 | 0 | 1524 | |
| 5' 5\ (2)" | 5'5 | 5 | 5 | 1651 | |
| 5'? | 5'0 | 5 | 0 | 1524 | |
| 5 ft. 6in. | 5'6 | 5 | 6 | 1676.4 | |
| 5ft' 7 in. | 5'7 | 5 | 7 | 1701.8 | |
| 5 ft. 8 in | 5'8 | 5 | 8 | 1727.2 | |
| 5 ft 4 in. | 5'4 | 5 | 4 | 1625.6 | |
| 5 ft. 4 in. | 5'4' | 5 | 4 | 1625.6 | |
| 5'4'5 | 5'4.5 | 5 | 4.5 | 1638.3 | |
| 5,' 0 | 5'0 | 5 | 0 | 1524 | |
| 5'8 | 5'8 | 5 | 8 | 1727.2 | |
| 5'5t 1/4 | 5'5 1/4 | 5 | 5.25 | 1657.35 | |
| 5''11 1/2 | 5'11 1/2 | 5 | 11.5 | 1816.1 | |
| 6 ' 11/2 | 6'1 1/2 | 6 | 1.5 | 1866.9 | |
| 5-8.5 | 5'8.5 | 5 | 8.5 | 1739.9 | |
| 6; 1/2 | 6'0 1/2 | 6 | 0.5 | 1841.5 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #crew = read.csv("crewlist.csv", stringsAsFactors = FALSE) | |
| #nrow(crew) | |
| #names(crew) | |
| library(stringr) | |
| im_your_father_luke = function(h){ | |
| ## there is a lot of code dealing with NAs here because the example data set had them | |
| ## it would probably be cleaner if we didn't bother | |
| ## clean out a bunch of initial guff | |
| h = gsub("[\"\\-]", "", h) | |
| h = gsub("^ *$", "", h) | |
| h = gsub("^(5|6)'([1-9]|10|11)*([13]\\/[248]).*$", "\\1'\\2 \\3", h) | |
| h = gsub("^5'5(7|9)(.*$)", "5'\\1\\2", h) | |
| ## This is the workhorse regexp | |
| pattern = "^ *([1-7]) *(ft[.']?|'{1,2}|,'?|;|\\.)? *([0-9]{1,2})? *(['t]|in\\.*)?([ ]+(1\\/2|([12])\\/3|(1|3)\\/4|([15])\\/6|([1-7])\\/8|1\\/12)|(\\.?[0-9]{1,3}))?[ +\\?`l (2)]*$" | |
| ## produces a matrix with 11 columns | |
| ## column 2 should have the feet, column 4 should have the inches, columm 6 will have the fraction if there is one, column will have the decimal if there is one | |
| m = str_match(h, pattern) | |
| ## helper function to evaluate the fractions | |
| convertFracs = function(x){ | |
| if(is.na(x)){ | |
| return(NA) | |
| }else{ | |
| return(25.4 * eval(parse(text=x))) | |
| } | |
| } | |
| ## covert the feet, inches and fraction into millimetres | |
| mm = cbind(as.numeric(m[,2])*12*25.4, as.numeric(m[,4])*25.4 , | |
| apply(cbind(sapply(m[,6], convertFracs, USE.NAMES = FALSE), sapply(m[,11], convertFracs, USE.NAMES = FALSE)), 1, function(row){ | |
| if(all(is.na(row))){ | |
| return(NA) | |
| }else if(all(!is.na(row))){ | |
| return(-1) | |
| }else if(is.na(row[1]) & !is.na(row[2])){ | |
| return(row[2]) | |
| }else{ | |
| return(row[1]) | |
| } | |
| })) | |
| ## appropriate columns to get a single figure | |
| toMM = function(row){ | |
| if(all(is.na(row))){ | |
| return(NA) | |
| }else if(!is.na(row[1]) & is.na(row[2]) & is.na(row[3])){ | |
| return(row[1]) | |
| }else if(!is.na(row[1]) & !is.na(row[2]) & is.na(row[3])){ | |
| return(row[1] + row[2]) | |
| }else if(!is.na(row[1]) & is.na(row[2]) & !is.na(row[3])){ | |
| return(row[1] + row[3]) | |
| }else{ | |
| return(sum(row)) | |
| } | |
| } | |
| return(data.frame(input = h, output = apply(mm, 1, toMM))) | |
| } | |
| DLMTestCases = read.csv("DLMTest.csv", stringsAsFactors = FALSE) | |
| mine = im_your_father_luke(DLMTestCases$raw) | |
| fails = DLMTestCases[abs(DLMTestCases$mm - mine$output) > 0.001,] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment