Distill/SortApprox.Rmd at main · AbidAliShaikh/Distill · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
---
title: "SortingApproximately"
author: "Abid Ali Shaikh"
date: "12/31/2021"
output:
  html_document:
    code_folding: show
    theme:
      bg: "#202123"
      fg: "#B8BCC2"
      primary: "#EA80FC"
      base_font:
        google: Prompt
      heading_font:
        google: Proza Libre
      version: 3
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

```{css}
pre code {
  font-size: 14px; /* Adjust the font size as desired */
}
```

### Sampling & Re-grouping

```{r grouping by approximate sorting, size=16}
names <- sample(c(
  "John", "Jon", "Jhon", "Jonh",
  "Michael", "Micheal", "Michel",
  "Emily", "Emili", "Emely", "Emiley",
  "Sarah", "Sara", "Sera", "Serah",
  "Matthew", "Mathew", "Mathhew",
  "Jessica", "Jessika", "Jesica", "Jessicah",
  "Daniel", "Daniele", "Danial",
  "Elizabeth", "Elisabeth", "Elisabet",
  "David", "Davi", "Davide",
  "Jennifer", "Jennipher", "Jenifer",
  "Christopher", "Cristopher", "Christoper",
  "Amanda", "Amandah", "Amandaa",
  "Andrew", "Andrw", "Andew",
  "Stephanie", "Stephany", "Stephaine",
  "Joshua", "Josh", "Jshua"
), replace = FALSE)

group <- function(names)
{

val2=NULL
for (i in names)
{
  val=agrep(i,names)
   val2=c(val2,val)

}
val2=unique(val2)


return(names[val2])
}

group(names)

```