Last active
October 26, 2021 00:10
-
-
Save kenfdev/aed2a55031b346dab1c2bfed9722b7c4 to your computer and use it in GitHub Desktop.
CSharp
This file contains 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
static string[] INVALID_WORDS = new string[] { | |
"the", "and", "a", "to", "of", "he", "was", "in", "his", "that", "it", "with", "you", "I", "but", "they", "for", "had", "The", "as", "at", "she", "on", "He", "this", "be", "all", "not", "him", "so", "were", "then", "by", "if", "her", "There", "would", "or", "when", "their", "from", "don't", "an", "could", "have", "But", "there", "what", "been", "is" | |
}; | |
void Main() | |
{ | |
var result = GetTopWords(@"C:\Users\kenfdev\Desktop\tomsawyer.txt"); | |
result.Dump(); | |
} | |
private static IDictionary<string, uint> GetTopWords(string path) { | |
return File.ReadLines(path) | |
.AsParallel() | |
.Aggregate ( | |
() => new Dictionary<string, uint>(StringComparer.InvariantCultureIgnoreCase), | |
(localDic, line) => { | |
foreach (var word in line.Split(" ", StringSplitOptions.RemoveEmptyEntries)) | |
{ | |
if (!IsValidWord(word)) | |
continue; | |
TrackWordsOccurence(localDic, word); | |
} | |
return localDic; | |
}, | |
(finalResult, localDic) => { | |
foreach (var pair in localDic) | |
{ | |
var key = pair.Key; | |
if (finalResult.ContainsKey(key)) { | |
finalResult[key] += pair.Value; | |
} else { | |
finalResult[key] = pair.Value; | |
} | |
} | |
return finalResult; | |
}, | |
finalResult => finalResult | |
.OrderByDescending(kv => kv.Value) | |
.Take(10) | |
.ToDictionary(kv => kv.Key, kv => kv.Value) | |
); | |
} | |
private static void TrackWordsOccurence(IDictionary<string, uint> wordCounts, string word) | |
{ | |
if (wordCounts.TryGetValue(word, out uint count)) { | |
wordCounts[word] = count + 1; | |
} else { | |
wordCounts[word] = 1; | |
} | |
} | |
private static bool IsValidWord(string word) => !INVALID_WORDS.Contains(word); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment