public BasicCompletionData(string text, string textTarget)
{
this.Text = text;
var engine = new JaroWinkler();
Priority = engine.Similarity(textTarget, text);
}
public async Task <ActionResult <IEnumerable <Symbol> > > GetSymbolByName(string name)
{
var symbol = await _context.Symbols
.Where(symbol => symbol.Name.ToLower() == name.ToLower())
.ToListAsync();
if (symbol.Count == 0)
{
var symbols = await _context.Symbols.ToListAsync();
var jw = new JaroWinkler();
foreach (var sbl in symbols)
{
var comp = jw.Similarity(name.ToLower(), sbl.Name.ToLower());
if (comp > 0.85)
{
symbol.Add(sbl);
}
}
if (symbol.Count == 0)
{
return(NotFound());
}
}
return(symbol);
}
public void TestDistance()
{
var instance = new JaroWinkler();
NullEmptyTests.TestDistance(instance);
// TODO: regular (non-null/empty) distance tests
}
public void Similarity_DifferentStrings_ReturnsDoubleValue()
{
const string val1 = "A String";
const string val2 = "Another String";
double actual = JaroWinkler.Similarity(val1, val2);
Console.WriteLine(String.Format("Similarity result = {0}", actual));
Assert.IsInstanceOf <double>(actual);
Assert.Less(actual, 1.0);
}
public void TestSimilarityBothEmpty()
{
var instance = new JaroWinkler();
Assert.Equal(
expected: 1,
actual: instance.Similarity(string.Empty, string.Empty),
precision: 6 // 0.000001
);
}
public void Similarity_SameStrings_ReturnOneAsDouble()
{
const string val1 = "A String";
const string val2 = "A String";
double actual = JaroWinkler.Similarity(val1, val2);
Console.WriteLine(String.Format("Similarity result = {0}", actual));
Assert.IsInstanceOf <double>(actual);
Assert.AreEqual(1.0, actual);
}
/// <summary>
/// Webページの一致率を調べます。
/// </summary>
/// <returns>一致率(%)</returns>
public async Task <double> CheckAsync()
{
string archive = await ReadArchiveAsync();
string webpage = await GetWebPageAsync();
JaroWinkler jaroWinkler = new JaroWinkler();
return(jaroWinkler.Similarity(archive, webpage));
}
public void JaroWinklerCase()
{
var jw = new JaroWinkler();
var twitter = jw.Similarity("Twitter", "twitter");
var chien = jw.Similarity(("chien"), ("niche"));
var twitterv1v2 = jw.Similarity("twitter v1", "Twitter v2");
var Shazam = jw.Similarity("ShazamIphone", "ShazamAndroid");
var FamosInstagramSW = jw.Similarity("Famos Instagram SW", "Famous Instagram");
var IntFacebook1 = jw.Similarity("Int Facebook", "CI Facebook");
var IntFacebook2 = jw.Similarity("Int Facebook", "Instagram Int");
}
public async Task Handle(GetPoem message, IMessageHandlerContext context)
{
try
{
Console.WriteLine("Start GetPoem");
using (var client = new HttpClient())
using (var db = new LimeContext())
{
var response = await client.GetAsync("https://www.poemist.com/api/v1/randompoems");
var json = await response.Content.ReadAsStringAsync();
var poems = JsonConvert.DeserializeObject <List <PoemsModel> >(json);
if (poems.Count > 0)
{
var poem = new Poem
{
Author = poems[0].Poet.Name,
Content = poems[0].Content,
Title = poems[0].Title,
Url = poems[0].Url,
People_Id = message.PeopleId
};
var sentences = poems[0].Content.Split('.');
var number = 0;
double distance = 0;
while (number != sentences.Length - 1 && !string.IsNullOrEmpty(sentences[number + 1]))
{
distance = distance + JaroWinkler.RateSimilarity(sentences[number], sentences[++number]);
}
distance = distance != 0 && number != 0 ? distance / number : 0;
poem.Distance = distance;
db.Poems.Add(poem);
await db.SaveChangesAsync();
}
}
}
catch (Exception e)
{
Console.WriteLine(e);
}
finally
{
Console.WriteLine("End GetPoem");
}
}
public void BoundedIsLowerThanNonBounded()
{
var unboundedMetric = new JaroWinkler();
var originalStrings = new []
{
"ab",
"abcd",
"abcd",
"abcd",
"abcd",
"abcd",
"abcd",
"abcd",
"abcd",
"abcd",
"abcd"
};
var modifiedStrings = new[]
{
"ab",
"acbd",
"adbc",
"badc",
"axcd",
"abxd",
"axyd",
"axbcd",
"abcxd",
"axbcd",
"axbcyd"
};
Assert.AreEqual(originalStrings.Length, modifiedStrings.Length);
for (var i = 0; i < originalStrings.Length; i++)
{
var original = originalStrings[i];
var modified = modifiedStrings[i];
var similarity = unboundedMetric.Similarity(original, modified);
var boundedSimilarity = StringMetric.Similarity(original, modified);
Assert.IsTrue(boundedSimilarity <= similarity);
}
}
private async Task <YoutubeDTO> GetInfoFromYouTubeSearchAPI(string steemTitle, string steemDescription, double steemDuration, string steemAuthor)
{
var client = new RestClient("https://www.googleapis.com/youtube/v3/");
var request = new RestRequest("search", Method.GET);
request.AddQueryParameter("part", "snippet");
request.AddQueryParameter("q", steemTitle);
request.AddQueryParameter("type", "video");
request.AddQueryParameter("maxResults", "1");
request.AddQueryParameter("fields", "items(snippet(publishedAt,title,description,channelTitle,channelId),id(videoId))");
request.AddQueryParameter("key", _configurationManager.YouTubeApiKey);
IRestResponse response = await client.ExecuteTaskAsync(request);
YouTubeRoot resp = JsonConvert.DeserializeObject <YouTubeRoot>(response.Content);
if (resp == null || resp.Items.Length == 0)
{
return new YoutubeDTO {
ErrorMessage = "pas de réponse de YouTube"
}
}
;
YouTubeSnippet video = resp.Items[0].Snippet;
YouTubeId id = resp.Items[0].Id;
// similitudes
var jw = new JaroWinkler();
double distanceTitle = FormatScore(jw.Similarity(steemTitle, video.Title));
double distanceDescription = FormatScore(jw.Similarity(steemDescription, video.Description));
double distanceAuthor = FormatScore(jw.Similarity(steemAuthor, video.ChannelTitle));
var dto = new YoutubeDTO
{
Success = true,
VideoId = id.VideoId,
VideoTitle = video.Title,
ChannelId = video.ChannelId,
ChannelTitle = video.ChannelTitle,
PublishedAt = video.PublishedAt,
DistanceTitle = distanceTitle,
DistanceDescription = distanceDescription,
DistanceAuthor = distanceAuthor
};
return(dto);
}
public void TestSimilarity()
{
var instance = new JaroWinkler();
Assert.Equal(
expected: 0.974074,
actual: instance.Similarity("My string", "My tsring"),
precision: 6 // 0.000001
);
Assert.Equal(
expected: 0.896296,
actual: instance.Similarity("My string", "My ntrisg"),
precision: 6 // 0.000001
);
}
public async Task <Dictionary <IGym, double> > GetSimilarGymsByNameAsync(string name, FenceConfiguration[] fences = null, int limit = int.MaxValue)
{
if (string.IsNullOrWhiteSpace(name))
{
return(new Dictionary <IGym, double>());
}
var algorithm = new JaroWinkler();
var gyms = GetGyms(fences);
var rankedList =
gyms.Select(e => new { Gym = e, Rank = algorithm.GetSimilarity(TrimString(e.Name), TrimString(name)) })
.OrderByDescending(e => e.Rank)
.Where(e => e.Rank > 0.5f)
.Take(limit);
return(await Task.FromResult(rankedList.ToDictionary(k => k.Gym, v => v.Rank)));
}
public void JaroWinklerAnalisys(CallsInfo[] calls)
{
_logger.LogInformation("Анализ похожих методом JaroWinkler");
var l = new JaroWinkler();
foreach (var call in calls)
{
if (call.Text == null)
{
continue;
}
var words = call.Text.Split(' ');
foreach (var announcement in call.Announcements)
{
if (announcement.Street == default)
{
continue;
}
double max_similarity = default;
string best_word = default;
foreach (var word in words)
{
var similarity = l.Similarity(word.ToLower(), announcement.Street.ToLower());
if (similarity >= max_similarity)
{
best_word = word;
max_similarity = similarity;
}
}
announcement.Features.Add(new FeatureInfo
{
Name = FeatureInfo.JARO,
Weight = max_similarity,
Data = best_word ?? ""
});
}
}
_logger.LogInformation("Закончили");
}
void database_search(string bytes, bool jaro_state = false, double jaro_rate = 0)
{
var jw = new JaroWinkler();
string[] bytes_splitted = bytes.Split(',');
StreamReader database = new StreamReader(jsonz);
string json = database.ReadToEnd();
dynamic DynamicData = JsonConvert.DeserializeObject(json);
foreach (string bytex in bytes_splitted)
{
for (int i = 0; i < DynamicData.Data.Count; i++)
{
for (int x = 0; x < DynamicData.Data[i].Bytes.Count; x++)
{
if (jaro_state == true)
{
double jaro = jw.Similarity(Convert.ToString(DynamicData.Data[i].Bytes[x]), bytex);
if (jaro > jaro_rate)
{
//MessageBox.Show(String.Format("Found a match: {0} and {1} with jaro rate {2} in {3}", bytex, DynamicData.Data[i].Bytes[x], jaro_rate, DynamicData.Data[i].Name));
DataGridViewRow row = (DataGridViewRow)gunaDataGridView2.Rows[0].Clone();
row.Cells[0].Value = bytex;
row.Cells[1].Value = DynamicData.Data[i].Bytes[x];
row.Cells[2].Value = Math.Round(jaro, 2);
row.Cells[3].Value = DynamicData.Data[i].Name;
gunaDataGridView2.Invoke(new Action(() => { gunaDataGridView2.Rows.Add(row); }));
}
}
}
if (jaro_state == false)
{
if (Convert.ToString(DynamicData.Data[i].Bytes).Contains(bytex))
{
//MessageBox.Show(String.Format("Found a match: {0} in {1}", bytex, DynamicData.Data[i].Name));
DataGridViewRow row = (DataGridViewRow)gunaDataGridView2.Rows[0].Clone();
row.Cells[0].Value = bytex;
row.Cells[3].Value = DynamicData.Data[i].Name;
gunaDataGridView2.Invoke(new Action(() => { gunaDataGridView2.Rows.Add(row); }));
}
}
}
}
}
public List <OutgestionMapItemModel> AutoMap(List <CoreTableDetailsModel> source, List <TemplateDetailModel> target)
{
List <OutgestionMapItemModel> matched = new List <OutgestionMapItemModel>();
var instance = new JaroWinkler();
source.ForEach(s => {
target.ForEach(t => {
if ((instance.Similarity(s.ColumnName.ToLower(), t.columnName.ToLower())) * 100 == 100)
{
matched.Add(new OutgestionMapItemModel {
Source = s, Target = t
});
}
});
});
return(matched);
}
public static List <Blocks.blocking_match> MakeBlockingMatches(IEnumerable <DataObjects.person_identifiers_pair> pairs, List <string> matchFields)
{
var jw = new JaroWinkler();
var matchVectors = new ConcurrentBag <Blocks.blocking_match>();
Parallel.ForEach(pairs, pair => {
var matchVector = new Blocks.blocking_match();
matchVector.person_unique_entity_id_1 = pair.person_identifiers_1.person_unique_entity_id;
matchVector.person_unique_entity_id_2 = pair.person_identifiers_2.person_unique_entity_id;
matchVector.person_first_name = matchFields.Contains("person_first_name") &&
jw.GetSimilarity(pair.person_identifiers_1.person_first_name, pair.person_identifiers_2.person_first_name) > .90 ? 1 : 0;
matchVector.person_middle_names = matchFields.Contains("person_middle_names") &&
jw.GetSimilarity(pair.person_identifiers_1.person_middle_names, pair.person_identifiers_2.person_middle_names) > .9 ? 1 : 0;
matchVector.person_last_name = matchFields.Contains("person_last_name") &&
jw.GetSimilarity(pair.person_identifiers_1.person_last_name, pair.person_identifiers_2.person_last_name) > .90 ? 1 : 0;
matchVector.person_dob_day = matchFields.Contains("person_dob_day") &&
Int16.Parse(pair.person_identifiers_1.person_dob_day) == Int16.Parse(pair.person_identifiers_2.person_dob_day) ? 1 : 0;
matchVector.person_dob_month = matchFields.Contains("person_dob_month") &&
Int16.Parse(pair.person_identifiers_1.person_dob_month) == Int16.Parse(pair.person_identifiers_2.person_dob_month) ? 1 : 0;
matchVector.person_dob_year = matchFields.Contains("person_dob_year") &&
Int16.Parse(pair.person_identifiers_1.person_dob_year) == Int16.Parse(pair.person_identifiers_2.person_dob_year) ? 1 : 0;
matchVector.person_gender = matchFields.Contains("person_gender") &&
pair.person_identifiers_1.person_gender == pair.person_identifiers_2.person_gender ? 1 : 0;
matchVector.person_fips_5 = matchFields.Contains("person_fips_5") &&
pair.person_identifiers_1.person_fips_5 == pair.person_identifiers_2.person_fips_5 ? 1 : 0;
matchVector.person_email = matchFields.Contains("person_email") &&
pair.person_identifiers_1.person_email == pair.person_identifiers_2.person_email ? 1 : 0;
matchVector.person_phone = matchFields.Contains("person_phone") &&
pair.person_identifiers_1.person_phone == pair.person_identifiers_2.person_phone ? 1 : 0;
matchVector.person_match_id_1 = matchFields.Contains("person_match_id_1") &&
pair.person_identifiers_1.person_match_id_1 == pair.person_identifiers_2.person_match_id_1 ? 1 : 0;
matchVector.person_match_id_2 = matchFields.Contains("person_match_id_2") &&
pair.person_identifiers_1.person_match_id_2 == pair.person_identifiers_2.person_match_id_2 ? 1 : 0;
matchVector.person_match_id_3 = matchFields.Contains("person_match_id_3") &&
pair.person_identifiers_1.person_match_id_3 == pair.person_identifiers_2.person_match_id_3 ? 1 : 0;
matchVector.person_identifiers_pair.person_identifiers_1 = pair.person_identifiers_1;
matchVector.person_identifiers_pair.person_identifiers_2 = pair.person_identifiers_2;
matchVectors.Add(matchVector);
});
return(matchVectors.ToList <Blocks.blocking_match>());
}
public async Task <LoadResult> GetSimilarVendorNames(int fieldVendorId, DataSourceLoadOptions loadOptions)
{
var fieldVendor = await _context.FieldVendor.SingleAsync(fv => fv.Id == fieldVendorId);
var companyName = fieldVendor?.CompanyName;
var jw = new JaroWinkler();
var query = _context.Company
.Where(c => c.IsActive)
.OrderBy(c => c.Id)
.Select(c => new
{
c.Id,
c.Name,
Similarity = jw.Similarity(c.Name, companyName),
});
return(await DataSourceLoader.LoadAsync(query, loadOptions));
}
void tryAnswer()
{
//Challenge challenge = challenges[currentChallengeIndex];
// First iteration.
// Only change answer to lowercase.
string input = answerInput.text.ToLower();
string tempAnswer = "";
// Get list of correct answers from Firebase database
IList answers = (IList)((IDictionary)DatabaseControllerScript.challenges[currentChallengeIndex])["answers"];
foreach (string answer in answers)
{
if (input == answer)
{
correctAnswer(input);
return;
}
}
// Second iteration.
// Remove non letters and change to english letters
input = removeNonLetters(input);
input = parseIcelandicLetters(input);
for (int i = 0; i < answers.Count; i++)
{
tempAnswer = removeNonLetters((string)answers[i]);
tempAnswer = parseIcelandicLetters(tempAnswer);
if (input == tempAnswer || JaroWinkler.Similarity(input, tempAnswer) > 0.9)
{
correctAnswer((string)answers[i]);
return;
}
}
// Did not find the correct answer
wrongAnswer();
return;
}
internal async Task <IEnumerable <Symbol> > GetCompanyNameMatches(string companyId)
{
//get list of symbols from cache or Finnhub
var symbolsList = await GetSymbolsFromCache();
var matches = new List <Symbol>();
var jw = new JaroWinkler();
//is user input either a company name or ticker
foreach (var symbol in symbolsList)
{
var comparisonName = jw.Similarity(companyId.ToLower(), symbol.Name.ToLower());
var comparisonTicker = jw.Similarity(companyId.ToLower(), symbol.Ticker.ToLower());
if (comparisonName > 0.85 || comparisonTicker > 0.90)
{
matches.Add(symbol);
}
}
return(matches);
}
///// <summary>
///// Calcualtes the Levenshtein distance between two strings
///// </summary>
///// Source: https://en.wikibooks.org/wiki/Algorithm_Implementation/Strings/Levenshtein_distance#C.23
///// Explanation: https://en.wikipedia.org/wiki/Levenshtein_distance
//private Int32 levenshtein(String a, String b)
//{
// if (string.IsNullOrEmpty(a))
// {
// if (!string.IsNullOrEmpty(b))
// {
// return b.Length;
// }
// return 0;
// }
// if (string.IsNullOrEmpty(b))
// {
// if (!string.IsNullOrEmpty(a))
// {
// return a.Length;
// }
// return 0;
// }
// Int32 cost;
// Int32[,] d = new int[a.Length + 1, b.Length + 1];
// Int32 min1;
// Int32 min2;
// Int32 min3;
// for (Int32 i = 0; i <= d.GetUpperBound(0); i += 1)
// {
// d[i, 0] = i;
// }
// for (Int32 i = 0; i <= d.GetUpperBound(1); i += 1)
// {
// d[0, i] = i;
// }
// for (Int32 i = 1; i <= d.GetUpperBound(0); i += 1)
// {
// for (Int32 j = 1; j <= d.GetUpperBound(1); j += 1)
// {
// cost = Convert.ToInt32(!(a[i - 1] == b[j - 1]));
// min1 = d[i - 1, j] + 1;
// min2 = d[i, j - 1] + 1;
// min3 = d[i - 1, j - 1] + cost;
// d[i, j] = Math.Min(Math.Min(min1, min2), min3);
// }
// }
// return d[d.GetUpperBound(0), d.GetUpperBound(1)];
//}
///// <summary>
///// String-similarity computed with levenshtein-distance
///// </summary>
//private double similarityLevenshtein(string a, string b)
//{
// if (a.Equals(b))
// {
// return 1.0;
// }
// else
// {
// if (!(a.Length == 0 || b.Length == 0))
// {
// double sim = 1 - (levenshtein(a, b) / Convert.ToDouble(Math.Min(a.Length, b.Length)));
// return sim;
// }
// else
// return 0.0;
// }
//}
///// <summary>
///// String-similarity computed with Dice Coefficient
///// </summary>
///// Source: https://en.wikibooks.org/wiki/Algorithm_Implementation/Strings/Dice%27s_coefficient#C.23
///// Explanation: https://en.wikipedia.org/wiki/S%C3%B8rensen%E2%80%93Dice_coefficient
//private double similarityDiceCoefficient(string a, string b)
//{
// //Workaround for |a| == |b| == 1
// if (a.Length <= 1 && b.Length <= 1)
// {
// if (a.Equals(b))
// return 1.0;
// else
// return 0.0;
// }
// HashSet<string> setA = new HashSet<string>();
// HashSet<string> setB = new HashSet<string>();
// for (int i = 0; i < a.Length - 1; ++i)
// setA.Add(a.Substring(i, 2));
// for (int i = 0; i < b.Length - 1; ++i)
// setB.Add(b.Substring(i, 2));
// HashSet<string> intersection = new HashSet<string>(setA);
// intersection.IntersectWith(setB);
// return (2.0 * intersection.Count) / (setA.Count + setB.Count);
//}
/// <summary>
/// Combines multiple String-similarities with equal weight
/// </summary>
private double similarity(string a, string b)
{
List <double> similarities = new List <double>();
double output = 0.0;
var l = new NormalizedLevenshtein();
similarities.Add(l.Similarity(a, b));
var jw = new JaroWinkler();
similarities.Add(jw.Similarity(a, b));
var jac = new Jaccard();
similarities.Add(jac.Similarity(a, b));
foreach (double sim in similarities)
{
output += sim;
}
return(output / similarities.Count);
}
public async Task <RegisterUserContainer> TryRegisterUserAsync(ulong userID, string userName)
{
using var scope = _scopeFactory.CreateScope();
var activitiesDB = scope.ServiceProvider.GetRequiredService <IClanActivitiesDB>();
if (activitiesDB.IsDiscordUserRegistered(userID))
{
return(null);
}
var jw = new JaroWinkler();
var users = await activitiesDB.GetUsersAsync();
var mostSimilar = users
.Select(x => (jw.Similarity(userName.ToLower(), x.UserName.ToLower()), x))
.MaxBy(x => x.Item1);
if (mostSimilar.x.DiscordUserID is null && mostSimilar.Item1 >= 0.9)
{
if (await activitiesDB.RegisterUserAsync(mostSimilar.x.UserID, userID))
{
return new RegisterUserContainer
{
IsSuccessful = true,
UserName = mostSimilar.x.UserName,
Platform = ((BungieMembershipType)mostSimilar.x.MembershipType).ToString().Replace("Tiger", string.Empty)
}
}
;
}
return(new RegisterUserContainer
{
IsSuccessful = false
});
}
}
public ActionResult CheckTitle(string title)
{
var jw = new JaroWinkler();
// double t = jw.Similarity("My string", "My tsring");
var lstPost = GetListPosts();
var posts = new List <PostViewModel>();
foreach (var item in lstPost)
{
var check = jw.Similarity(title, item.Title);
if (check >= 0.7)
{
posts.Add(item);
}
}
if (posts.Count() > 0)
{
//var viewposts = Mapper.Map<IEnumerable<Posts>, IEnumerable<PostViewModel>>(posts);
return(PartialView("_ListBooksPartial", posts));
}
return(null);
}
private static double CalculateResemblance(string s1, string s2, double cutoff)
{
double output;
if (string.IsNullOrEmpty(s1) || string.IsNullOrEmpty(s2))
{
output = -1;
}
else
{
double score = JaroWinkler.RateSimilarity(s1, s2);
if (score >= cutoff)
{
output = score;
}
else
{
output = 0;
}
}
return(output);
}
public double GetSimilarity(string str1, string str2, string type)
{
IStringMetric stringMetric;
switch (type)
{
case AlgorithmTypes.BlockDistance:
stringMetric = new BlockDistance();
break;
case AlgorithmTypes.ChapmanLengthDeviation:
stringMetric = new ChapmanLengthDeviation();
break;
case AlgorithmTypes.ChapmanMeanLength:
stringMetric = new ChapmanMeanLength();
break;
case AlgorithmTypes.CosineSimilarity:
stringMetric = new CosineSimilarity();
break;
case AlgorithmTypes.DiceSimilarity:
stringMetric = new DiceSimilarity();
break;
case AlgorithmTypes.EuclideanDistance:
stringMetric = new EuclideanDistance();
break;
case AlgorithmTypes.JaccardSimilarity:
stringMetric = new JaccardSimilarity();
break;
case AlgorithmTypes.Jaro:
stringMetric = new Jaro();
break;
case AlgorithmTypes.JaroWinkler:
stringMetric = new JaroWinkler();
break;
case AlgorithmTypes.Levenstein:
stringMetric = new Levenstein();
break;
case AlgorithmTypes.MatchingCoefficient:
stringMetric = new MatchingCoefficient();
break;
case AlgorithmTypes.MongeElkan:
stringMetric = new MongeElkan();
break;
case AlgorithmTypes.NeedlemanWunch:
stringMetric = new NeedlemanWunch();
break;
case AlgorithmTypes.OverlapCoefficient:
stringMetric = new OverlapCoefficient();
break;
case AlgorithmTypes.QGramsDistance:
stringMetric = new QGramsDistance();
break;
case AlgorithmTypes.SmithWaterman:
stringMetric = new SmithWaterman();
break;
case AlgorithmTypes.SmithWatermanGotoh:
stringMetric = new SmithWatermanGotoh();
break;
case AlgorithmTypes.SmithWatermanGotohWindowedAffine:
stringMetric = new SmithWatermanGotohWindowedAffine();
break;
default:
stringMetric = new SmithWatermanGotoh();
break;
}
var similarity = stringMetric.GetSimilarity(str1.Trim(), str2.Trim());
return(similarity);
}
public void Initializate()
{
_jaroWinkler = new JaroWinkler();
}
private void ButtonGo_Click(object sender, EventArgs e)
{
if (orgItems != null && newItems != null && outStream != null && (ListItem)comboBoxOrg1.SelectedItem != null && (ListItem)comboBoxNew1.SelectedItem != null && running == false)
{
running = true;
Thread.CurrentThread.Name = "Main";
ListItem ItemOrg1 = (ListItem)comboBoxOrg1.SelectedItem;
ListItem ItemOrg2 = (ListItem)comboBoxOrg2.SelectedItem;
ListItem ItemNew1 = (ListItem)comboBoxNew1.SelectedItem;
ListItem ItemNew2 = (ListItem)comboBoxNew1.SelectedItem;
double threshold = ((double)trackBar1.Value) / 100;
progressBar1.Maximum = newItems.Count;
var prog = new Progress <int>();
var progfound = new Progress <int>();
prog.ProgressChanged += (senderOfProgressChanged, nextItem) =>
{ progressBar1.Value = nextItem; if (nextItem == newItems.Count - 1)
{
running = false;
}
};
progfound.ProgressChanged += (senderOfProgressChanged, nextItem) =>
{ label10.Text = "found " + nextItem + " new Entries"; };
var task = Task.Run(() =>
{
using (StreamWriter sw = new StreamWriter(outStream))
{
// retrive indexes
int indexOrg1 = ItemOrg1.Index;
int indexNew1 = ItemNew1.Index;
int indexOrg2 = -1;
int indexNew2 = -1;
Console.WriteLine("th: " + threshold);
if (ItemNew2 != null && ItemOrg2 != null)
{
indexOrg2 = ItemOrg2.Index;
indexNew2 = ItemNew2.Index;
}
// comperator
var jw = new JaroWinkler();
// create header line
string headerLine = "";
foreach (string header in newHeader)
{
headerLine += "new-" + header + ",";
}
foreach (string header in orgHeader)
{
headerLine += "org-" + header + ",";
}
headerLine = headerLine.Substring(0, headerLine.Length - 1);
sw.WriteLine(headerLine);
int index = 0;
int found = 0;
int incompleteNew = 0;
int incompleteOrg = 0;
int incompleteOptional = 0;
foreach (string[] newItemLine in newItems)
{
if (newItemLine.Length > indexNew1)
{
string element1 = newItemLine[indexNew1];
string element2 = null;
if (indexNew2 > -1 && indexOrg2 > -1)
{
if (newItemLine.Length > indexNew2)
{
element2 = newItemLine[indexNew2];
}
else
{
incompleteOptional++;
}
}
string[] closest = null;
double closestVal = -1;
foreach (string[] orgItemLine in orgItems)
{
if (orgItemLine.Length > indexOrg1)
{
string canidate1 = orgItemLine[indexNew1];
string canidate2 = null;
if (indexNew2 > -1 && indexOrg2 > -1)
{
if (orgItemLine.Length > indexOrg2)
{
canidate2 = orgItemLine[indexOrg2];
}
else
{
incompleteOptional++;
}
}
double similarity1 = jw.Similarity(element1, canidate1);
double similarity2 = 1.0;
if (canidate2 != null)
{
similarity2 = jw.Similarity(element1, canidate2);
}
double similarity = similarity1 * similarity2;
if (similarity > closestVal)
{
closestVal = similarity;
closest = orgItemLine;
}
}
else
{
incompleteOrg++;
}
}
if (closestVal > -1 && !(closestVal > threshold))
{
string newLine = "";
foreach (string itm in newItemLine)
{
newLine += itm + ",";
}
foreach (string itm in closest)
{
newLine += itm + ",";
}
newLine = newLine.Substring(0, newLine.Length - 1);
sw.WriteLine(newLine);
found++;
((IProgress <int>)progfound).Report(found);
}
index++;
((IProgress <int>)prog).Report(index);
}
else
{
incompleteNew++;
}
}
Console.Write("finished");
}
});
}
else
{
Help.ShowPopup(buttonGo, "Incomplete Config", new Point(buttonGo.Right, this.buttonGo.Bottom));
}
}
public static double ApproximatelyEquals(this string firstWord, string secondWord, SimMetricType simMetricType = SimMetricType.Levenstein)
{
switch (simMetricType)
{
case SimMetricType.BlockDistance:
var sim2 = new BlockDistance();
return(sim2.GetSimilarity(firstWord, secondWord));
case SimMetricType.ChapmanLengthDeviation:
var sim3 = new ChapmanLengthDeviation();
return(sim3.GetSimilarity(firstWord, secondWord));
case SimMetricType.CosineSimilarity:
var sim4 = new CosineSimilarity();
return(sim4.GetSimilarity(firstWord, secondWord));
case SimMetricType.DiceSimilarity:
var sim5 = new DiceSimilarity();
return(sim5.GetSimilarity(firstWord, secondWord));
case SimMetricType.EuclideanDistance:
var sim6 = new EuclideanDistance();
return(sim6.GetSimilarity(firstWord, secondWord));
case SimMetricType.JaccardSimilarity:
var sim7 = new JaccardSimilarity();
return(sim7.GetSimilarity(firstWord, secondWord));
case SimMetricType.Jaro:
var sim8 = new Jaro();
return(sim8.GetSimilarity(firstWord, secondWord));
case SimMetricType.JaroWinkler:
var sim9 = new JaroWinkler();
return(sim9.GetSimilarity(firstWord, secondWord));
case SimMetricType.MatchingCoefficient:
var sim10 = new MatchingCoefficient();
return(sim10.GetSimilarity(firstWord, secondWord));
case SimMetricType.MongeElkan:
var sim11 = new MongeElkan();
return(sim11.GetSimilarity(firstWord, secondWord));
case SimMetricType.NeedlemanWunch:
var sim12 = new NeedlemanWunch();
return(sim12.GetSimilarity(firstWord, secondWord));
case SimMetricType.OverlapCoefficient:
var sim13 = new OverlapCoefficient();
return(sim13.GetSimilarity(firstWord, secondWord));
case SimMetricType.QGramsDistance:
var sim14 = new QGramsDistance();
return(sim14.GetSimilarity(firstWord, secondWord));
case SimMetricType.SmithWaterman:
var sim15 = new SmithWaterman();
return(sim15.GetSimilarity(firstWord, secondWord));
case SimMetricType.SmithWatermanGotoh:
var sim16 = new SmithWatermanGotoh();
return(sim16.GetSimilarity(firstWord, secondWord));
case SimMetricType.SmithWatermanGotohWindowedAffine:
var sim17 = new SmithWatermanGotohWindowedAffine();
return(sim17.GetSimilarity(firstWord, secondWord));
case SimMetricType.ChapmanMeanLength:
var sim18 = new ChapmanMeanLength();
return(sim18.GetSimilarity(firstWord, secondWord));
default:
var sim1 = new Levenstein();
return(sim1.GetSimilarity(firstWord, secondWord));
}
}
private void StringCompareTest(string input, string[] testCases)
{
Debug.WriteLine("Dice Coefficient for {0}:", input);
foreach (var name in testCases)
{
StringFuzzyComparer dice = new DiceCoefficent();
double diceValue = dice.Compare(input, name);
Debug.WriteLine("\t{0} against {1}", diceValue.ToString("###,###.00000"), name);
}
Debug.WriteLine("");
Debug.WriteLine("Jaccard Coefficient for {0}:", input);
foreach (var name in testCases)
{
StringFuzzyComparer jaccard = new Jaccard();
double jaccardValue = jaccard.Compare(input, name);
Debug.WriteLine("\t{0} against {1}", jaccardValue.ToString("###,###.00000"), name);
}
Debug.WriteLine("");
Debug.WriteLine("ExtendedJaccard Coefficient for {0}:", input);
foreach (var name in testCases)
{
StringFuzzyComparer exjaccard = new ExtendedJaccard();
double exjaccardValue = exjaccard.Compare(input, name);
Debug.WriteLine("\t{0} against {1}", exjaccardValue.ToString("###,###.00000"), name);
}
Debug.WriteLine("");
Debug.WriteLine("DamerauLevenshteinDistance for {0}:", input);
foreach (var name in testCases)
{
StringFuzzyComparer lev = new DamerauLevenshteinDistance();
var levenStein = lev.Compare(input, name);
Debug.WriteLine("\t{0}, against {1}", levenStein, name);
}
Debug.WriteLine("");
Debug.WriteLine("JaroWinkler for {0}:", input);
foreach (var name in testCases)
{
StringFuzzyComparer jw = new JaroWinkler();
var jwValue = jw.Compare(input, name);
Debug.WriteLine("\t{0}, against {1}", jwValue, name);
}
Debug.WriteLine("");
Debug.WriteLine("Monge-Elkan for {0}:", input);
foreach (var name in testCases)
{
StringFuzzyComparer me = new MongeElkan();
var meValue = me.Compare(input, name);
Debug.WriteLine("\t{0}, against {1}", meValue, name);
}
Debug.WriteLine("");
Debug.WriteLine("NGramDistance(2) for {0}:", input);
foreach (var name in testCases)
{
StringFuzzyComparer ngram2 = new NGramDistance();
(ngram2 as NGramDistance).NGramLength = 2;
var ngramValue2 = ngram2.Compare(input, name);
Debug.WriteLine("\t{0}, against {1}", ngramValue2, name);
}
Debug.WriteLine("");
Debug.WriteLine("SmithWaterman for {0}:", input);
foreach (var name in testCases)
{
StringFuzzyComparer sw = new SmithWaterman();
var swValue = sw.Compare(input, name);
Debug.WriteLine("\t{0}, against {1}", swValue, name);
}
Debug.WriteLine("");
Debug.WriteLine("Extended Editex for {0}:", input);
foreach (var name in testCases)
{
StringFuzzyComparer edx = new ExtendedEditex();
var edxValue = edx.Compare(input, name);
Debug.WriteLine("\t{0}, against {1}", edxValue, name);
}
Debug.WriteLine("");
Debug.WriteLine("Longest Common Subsequence for {0}:", input);
foreach (var name in testCases)
{
StringFuzzyComparer lcs = new LongestCommonSubsequence();
var lcsValue = lcs.Compare(input, name);
Debug.WriteLine("\t{0}, against {1}", lcsValue.ToString("###,###.00000"), name);
}
Debug.WriteLine("");
}
public void Init()
{
// Setup code goes here...
_comparator = new JaroWinkler();
}
