What is the best way to compare two strings to see how similar they are?
Examples:
My String
My String With Extra Words
Or
My String
My Slightly Different String
What I am looking for is to determine how similar the first and second string in each pair is. I would like to score the comparison and if the strings are similar enough, I would consider them a matching pair.
Is there a good way to do this in C#?
static class LevenshteinDistance
{
public static int Compute(string s, string t)
{
if (string.IsNullOrEmpty(s))
{
if (string.IsNullOrEmpty(t))
return 0;
return t.Length;
}
if (string.IsNullOrEmpty(t))
{
return s.Length;
}
int n = s.Length;
int m = t.Length;
int[,] d = new int[n + 1, m + 1];
// initialize the top and right of the table to 0, 1, 2, ...
for (int i = 0; i <= n; d[i, 0] = i++);
for (int j = 1; j <= m; d[0, j] = j++);
for (int i = 1; i <= n; i++)
{
for (int j = 1; j <= m; j++)
{
int cost = (t[j - 1] == s[i - 1]) ? 0 : 1;
int min1 = d[i - 1, j] + 1;
int min2 = d[i, j - 1] + 1;
int min3 = d[i - 1, j - 1] + cost;
d[i, j] = Math.Min(Math.Min(min1, min2), min3);
}
}
return d[n, m];
}
}
If anyone was wondering what the C# equivalent of what #FrankSchwieterman posted is:
public static int GetDamerauLevenshteinDistance(string s, string t)
{
if (string.IsNullOrEmpty(s))
{
throw new ArgumentNullException(s, "String Cannot Be Null Or Empty");
}
if (string.IsNullOrEmpty(t))
{
throw new ArgumentNullException(t, "String Cannot Be Null Or Empty");
}
int n = s.Length; // length of s
int m = t.Length; // length of t
if (n == 0)
{
return m;
}
if (m == 0)
{
return n;
}
int[] p = new int[n + 1]; //'previous' cost array, horizontally
int[] d = new int[n + 1]; // cost array, horizontally
// indexes into strings s and t
int i; // iterates through s
int j; // iterates through t
for (i = 0; i <= n; i++)
{
p[i] = i;
}
for (j = 1; j <= m; j++)
{
char tJ = t[j - 1]; // jth character of t
d[0] = j;
for (i = 1; i <= n; i++)
{
int cost = s[i - 1] == tJ ? 0 : 1; // cost
// minimum of cell to the left+1, to the top+1, diagonally left and up +cost
d[i] = Math.Min(Math.Min(d[i - 1] + 1, p[i] + 1), p[i - 1] + cost);
}
// copy current distance counts to 'previous row' distance counts
int[] dPlaceholder = p; //placeholder to assist in swapping p and d
p = d;
d = dPlaceholder;
}
// our last action in the above loop was to switch d and p, so p now
// actually has the most recent cost counts
return p[n];
}
I am comparing two sentences like this
string[] vs = string1.Split(new char[] { ' ', '-', '/', '(', ')' },StringSplitOptions.RemoveEmptyEntries);
string[] vs1 = string2.Split(new char[] { ' ', '-', '/', '(', ')' }, StringSplitOptions.RemoveEmptyEntries);
vs.Intersect(vs1, StringComparer.OrdinalIgnoreCase).Count();
Intersect gives you a set of identical word lists , I continue by looking at the count and saying if it is more than 1, these two sentences contain similar words.
Related
so i have this function:
static int[] AddArrays(int[] a, int[] b)
{
int length1 = a.Length;
int length2 = b.Length;
int carry = 0;
int max_length = Math.Max(length1, length2) + 1;
int[] minimum_arr = new int[max_length - length1].Concat(a).ToArray();
int[] maximum_arr = new int[max_length - length2].Concat(b).ToArray();
int[] new_arr = new int[max_length];
for (int i = max_length - 1; i >= 0; i--)
{
int first_digit = maximum_arr[i];
int second_digit = i - (max_length - minimum_arr.Length) >= 0 ? minimum_arr[i - (max_length - minimum_arr.Length)] : 0;
if (second_digit + first_digit + carry > 9)
{
new_arr[i] = (second_digit + first_digit + carry) % 10;
carry = 1;
}
else
{
new_arr[i] = second_digit + first_digit + carry;
carry = 0;
}
}
if (carry == 1)
{
int[] result = new int[max_length + 1];
result[0] = 1;
Array.Copy(new_arr, 0, result, 1, max_length);
return result;
}
else
{
return new_arr;
}
}
it basically takes 2 lists of digits and adds them together. the point of this is that each array of digits represent a number that is bigger then the integer limits. now this function is close to working the results get innacurate at certein places and i honestly have no idea why. for example if the function is given these inputs:
"1481298410984109284109481491284901249018490849081048914820948019" and
"3475893498573573849739857349873498739487598" (both of these are being turned into a array of integers before being sent to the function)
the expected output is:
1,481,298,410,984,109,284,112,957,384,783,474,822,868,230,706,430,922,413,560,435,617
and what i get is:
1,481,298,410,984,109,284,457,070,841,142,258,634,158,894,233,092,241,356,043,561,7
i would very much appreciate some help with this ive been trying to figure it out for hours and i cant seem to get it to work perfectly.
I suggest Reverse arrays a and b and use good old school algorithm:
static int[] AddArrays(int[] a, int[] b) {
Array.Reverse(a);
Array.Reverse(b);
int[] result = new int[Math.Max(a.Length, b.Length) + 1];
int carry = 0;
int value = 0;
for (int i = 0; i < Math.Max(a.Length, b.Length); ++i) {
value = (i < a.Length ? a[i] : 0) + (i < b.Length ? b[i] : 0) + carry;
result[i] = value % 10;
carry = value / 10;
}
if (carry > 0)
result[result.Length - 1] = carry;
else
Array.Resize(ref result, result.Length - 1);
// Let's restore a and b
Array.Reverse(a);
Array.Reverse(b);
Array.Reverse(result);
return result;
}
Demo:
string a = "1481298410984109284109481491284901249018490849081048914820948019";
string b = "3475893498573573849739857349873498739487598";
string c = string.Concat(AddArrays(
a.Select(d => d - '0').ToArray(),
b.Select(d => d - '0').ToArray()));
Console.Write(c);
Output:
1481298410984109284112957384783474822868230706430922413560435617
I have a string that is produced by code but it may not be correct.
So i have a user screen that user checks and changes it.
I have to let user to change maximum of 5 characters.
I need to check how many characters are changed by user
with comparing two strings.
length of strings may be different.
Thanx in advance. (language c#)
You could compute the Levenshtein Distance between the two strings, which returns the number of character edits (removals, inserts, replacements) that must occur to get from string A to string B.
public static class LevenshteinDistance
{
/// <summary>
/// Compute the distance between two strings.
/// </summary>
public static int Compute(string s, string t)
{
int n = s.Length;
int m = t.Length;
int[,] d = new int[n + 1, m + 1];
// Step 1
if (n == 0) return m;
if (m == 0) return n;
// Step 2
for (int i = 0; i <= n; d[i, 0] = i++);
for (int j = 0; j <= m; d[0, j] = j++);
// Step 3
for (int i = 1; i <= n; i++)
{
//Step 4
for (int j = 1; j <= m; j++)
{
// Step 5
int cost = (t[j - 1] == s[i - 1]) ? 0 : 1;
// Step 6
d[i, j] = Math.Min(
Math.Min(d[i - 1, j] + 1, d[i, j - 1] + 1),
d[i - 1, j - 1] + cost);
}
}
// Step 7
return d[n, m];
}
}
Then handle it:
if (LevenshteinDistance.Compute(s1, s2) <= 5)
// Valid
else
// Invalid
I have a static phrase the I am searching an OCR'd image for.
string KeywordToFind = "Account Number"
string OcrPageText = "
GEORGIA
POWER
A SOUTHERN COMPANY
AecountNumber
122- 493
Pagel of2
Please Pay By
Jan 29,2014
Total Due
39.11
"
How can I find the word "AecountNumber" using my keyword "Account Number"?
I have tried using variations of the Levenshtein Distance Algorithm HERE with varied success. I've also tried regexes, but the OCR often converts the text differently, thus rendering the regex useless.
Suggestions? I can provide more code if the link doesn't give enough information. Also, Thanks!
Why not try something mostly arbitrary, like this -- while it would certainly match a lot more than just account number, the chances of the start and end characters existing elsewhere in that order is pretty slim.
A.?c.?.?nt ?N.?[mn]b.?r
http://regex101.com/r/zV1yM2
It'll match things like:
Account Number
AccntNumbr
Aecnt Nunber
Answered My Question with the use of sub-strings. Posting in case others run into the same type of problem. A little unorthodox, but it works great for me.
int TextLengthBuffer = (int)StaticTextLength - 1; //start looking for correct result with one less character than it should have.
int LowestLevenshteinNumber = 999999; //initialize insanely high maximum
decimal PossibleStringLength = (PossibleString.Length); //Length of string to search
decimal StaticTextLength = (StaticText.Length); //Length of text to search for
decimal NumberOfErrorsAllowed = Math.Round((StaticTextLength * (ErrorAllowance / 100)), MidpointRounding.AwayFromZero); //Find number of errors allowed with given ErrorAllowance percentage
//Look for best match with 1 less character than it should have, then the correct amount of characters.
//And last, with 1 more character. (This is because one letter can be recognized as
//two (W -> VV) and visa versa)
for (int i = 0; i < 3; i++)
{
for (int e = TextLengthBuffer; e <= (int)PossibleStringLength; e++)
{
string possibleResult = (PossibleString.Substring((e - TextLengthBuffer), TextLengthBuffer));
int lAllowance = (int)(Math.Round((possibleResult.Length - StaticTextLength) + (NumberOfErrorsAllowed), MidpointRounding.AwayFromZero));
int lNumber = LevenshteinAlgorithm(StaticText, possibleResult);
if (lNumber <= lAllowance && ((lNumber < LowestLevenshteinNumber) || (TextLengthBuffer == StaticText.Length && lNumber <= LowestLevenshteinNumber)))
{
PossibleResult = (new StaticTextResult { text = possibleResult, errors = lNumber });
LowestLevenshteinNumber = lNumber;
}
}
TextLengthBuffer++;
}
public static int LevenshteinAlgorithm(string s, string t) // Levenshtein Algorithm
{
int n = s.Length;
int m = t.Length;
int[,] d = new int[n + 1, m + 1];
if (n == 0)
{
return m;
}
if (m == 0)
{
return n;
}
for (int i = 0; i <= n; d[i, 0] = i++)
{
}
for (int j = 0; j <= m; d[0, j] = j++)
{
}
for (int i = 1; i <= n; i++)
{
for (int j = 1; j <= m; j++)
{
int cost = (t[j - 1] == s[i - 1]) ? 0 : 1;
d[i, j] = Math.Min(
Math.Min(d[i - 1, j] + 1, d[i, j - 1] + 1),
d[i - 1, j - 1] + cost);
}
}
return d[n, m];
}
I'm trying to do a string compare in C# with some allowance for error. For example, if my search term is "Welcome", but if my comparison string (generated through OCR) is "We1come" and my error allowance is 20%, that should match. That part isn't so difficult using something like the Levenshtein algorithm. The hard part is making it work within a larger block of text, like a regular expression. For example, maybe my OCR result is "Hello. My name is Ben. We1come to my StackOverflow question.", I would like to pick out that We1come as a good result compared to my search term.
Took quite a while, but this works well. Fun problem :)
string PossibleString = PossibleString.ToString().ToLower();
string StaticText = StaticText.ToLower();
decimal PossibleStringLength = (PossibleString.Length);
decimal StaticTextLength = (StaticText.Length);
decimal NumberOfErrorsAllowed = Math.Round((StaticTextLength * (ErrorAllowance / 100)), MidpointRounding.AwayFromZero);
int LevenshteinDistance = LevenshteinAlgorithm(StaticText, PossibleString);
string PossibleResult = string.Empty;
if (LevenshteinDistance == PossibleStringLength - StaticTextLength)
{
// Perfect match. no need to calculate.
PossibleResult = StaticText;
}
else
{
int TextLengthBuffer = (int)StaticTextLength - 1;
int LowestLevenshteinNumber = 999999;
for (int i = 0; i < 3; i++) // Check for best results with same amount of characters as expected, as well as +/- 1
{
for (int e = TextLengthBuffer; e <= (int)PossibleStringLength; e++)
{
string possibleResult = (PossibleString.Substring((e - TextLengthBuffer), TextLengthBuffer));
int lAllowance = (int)(Math.Round((possibleResult.Length - StaticTextLength) + (NumberOfErrorsAllowed), MidpointRounding.AwayFromZero));
int lNumber = LevenshteinAlgorithm(StaticText, possibleResult);
if (lNumber <= lAllowance && ((lNumber < LowestLevenshteinNumber) || (TextLengthBuffer == StaticText.Length && lNumber <= LowestLevenshteinNumber)))
{
PossibleResult = possibleResult;
LowestLevenshteinNumber = lNumber;
}
}
TextLengthBuffer++;
}
}
public static int LevenshteinAlgorithm(string s, string t)
{
int n = s.Length;
int m = t.Length;
int[,] d = new int[n + 1, m + 1];
if (n == 0)
{
return m;
}
if (m == 0)
{
return n;
}
for (int i = 0; i <= n; d[i, 0] = i++)
{
}
for (int j = 0; j <= m; d[0, j] = j++)
{
}
for (int i = 1; i <= n; i++)
{
for (int j = 1; j <= m; j++)
{
int cost = (t[j - 1] == s[i - 1]) ? 0 : 1;
d[i, j] = Math.Min(
Math.Min(d[i - 1, j] + 1, d[i, j - 1] + 1),
d[i - 1, j - 1] + cost);
}
}
return d[n, m];
}
If it is somehow predictable how the OCR can miss letters, I would replace the letters in the search with misses.
If the search is Welcome, the regex would be (?i)We[l1]come.
I have problems finding an implementation of closest match strings for .net
I would like to match a list of strings, example:
input string: "Publiczna Szkoła Podstawowa im. Bolesława Chrobrego w Wąsoszu"
List of strings:
Publiczna Szkoła Podstawowa im. B. Chrobrego w Wąsoszu
Szkoła Podstawowa Specjalna
Szkoła Podstawowa im.Henryka Sienkiewicza w Wąsoszu
Szkoła Podstawowa im. Romualda Traugutta w Wąsoszu Górnym
This would clearly need to be matched with "Publiczna Szkoła Podstawowa im. B. Chrobrego w Wąsoszu".
What algorithms are there available for .net?
Edit distance
Edit distance is a way of quantifying how dissimilar two strings
(e.g., words) are to one another by counting the minimum number of
operations required to transform one string into the other.
Levenshtein distance
Informally, the Levenshtein distance between two words is the minimum
number of single-character edits (i.e. insertions, deletions or
substitutions) required to change one word into the other.
Fast, memory efficient Levenshtein algorithm
C# Levenshtein
using System;
/// <summary>
/// Contains approximate string matching
/// </summary>
static class LevenshteinDistance
{
/// <summary>
/// Compute the distance between two strings.
/// </summary>
public static int Compute(string s, string t)
{
int n = s.Length;
int m = t.Length;
int[,] d = new int[n + 1, m + 1];
// Step 1
if (n == 0)
{
return m;
}
if (m == 0)
{
return n;
}
// Step 2
for (int i = 0; i <= n; d[i, 0] = i++)
{
}
for (int j = 0; j <= m; d[0, j] = j++)
{
}
// Step 3
for (int i = 1; i <= n; i++)
{
//Step 4
for (int j = 1; j <= m; j++)
{
// Step 5
int cost = (t[j - 1] == s[i - 1]) ? 0 : 1;
// Step 6
d[i, j] = Math.Min(
Math.Min(d[i - 1, j] + 1, d[i, j - 1] + 1),
d[i - 1, j - 1] + cost);
}
}
// Step 7
return d[n, m];
}
}
class Program
{
static void Main()
{
Console.WriteLine(LevenshteinDistance.Compute("aunt", "ant"));
Console.WriteLine(LevenshteinDistance.Compute("Sam", "Samantha"));
Console.WriteLine(LevenshteinDistance.Compute("flomax", "volmax"));
}
}
.NET does not supply anything out of the box - you need to implement a an Edit Distance algorithm yourself. For example, you can use Levenshtein Distance, like this:
// This code is an implementation of the pseudocode from the Wikipedia,
// showing a naive implementation.
// You should research an algorithm with better space complexity.
public static int LevenshteinDistance(string s, string t) {
int n = s.Length;
int m = t.Length;
int[,] d = new int[n + 1, m + 1];
if (n == 0) {
return m;
}
if (m == 0) {
return n;
}
for (int i = 0; i <= n; d[i, 0] = i++)
;
for (int j = 0; j <= m; d[0, j] = j++)
;
for (int i = 1; i <= n; i++) {
for (int j = 1; j <= m; j++) {
int cost = (t[j - 1] == s[i - 1]) ? 0 : 1;
d[i, j] = Math.Min(
Math.Min(d[i - 1, j] + 1, d[i, j - 1] + 1),
d[i - 1, j - 1] + cost);
}
}
return d[n, m];
}
Call LevenshteinDistance(targetString, possible[i]) for each i, then pick the string possible[i] for which LevenshteinDistance returns the smallest value.
Late to the party, but I had a similar requirement to #Ali123:
"ECM" is closer to "Open form for ECM" than "transcribe" phonetically
I found a simple solution that works for my use case, which is comparing sentences, and finding the sentence that has the most words in common:
public static string FindBestMatch(string stringToCompare, IEnumerable<string> strs) {
HashSet<string> strCompareHash = stringToCompare.Split(' ').ToHashSet();
int maxIntersectCount = 0;
string bestMatch = string.Empty;
foreach (string str in strs)
{
HashSet<string> strHash = str.Split(' ').ToHashSet();
int intersectCount = strCompareHash.Intersect(strCompareHash).Count();
if (intersectCount > maxIntersectCount)
{
maxIntersectCount = intersectCount;
bestMatch = str;
}
}
return bestMatch;
}