public void Verbose_With_Levenstein()
{
const double latitude = 37.786971;
const double longitude = -122.399677;
IStringMetric metric = new Levenstein();
ITokenizer tokenizer = new Tokenizer();
var geopages = WikiApi.Geosearch(latitude, longitude);
foreach (var geopage in geopages)
{
output.WriteLine($"[{geopage.Pageid}] {geopage.Title}");
var images = WikiApi.Images(geopage.Pageid);
var imagesWithMetrics = images
.Select(image => new { Image = image, Similarity = image.CalcMetric(geopage.Title, tokenizer, metric) })
.ToList();
var title = imagesWithMetrics.Aggregate((image, next) => next.Similarity > image.Similarity ? next : image);
output.WriteLine($"\t*[{title.Image.Ns}] {title.Image.Title} {title.Similarity}");
foreach (var image in imagesWithMetrics)
{
output.WriteLine($"\t[{image.Image.Ns}] {image.Image.Title} {image.Similarity}");
}
}
}
public async Task <Dictionary <RaidbossPokemon, double> > GetSimilarRaidbossByNameAsync(string name, int limit = int.MaxValue)
{
var algorithm = new Levenstein();
var rankedList =
Pokemon.Select(e => new { Pokemon = e, Rank = algorithm.GetSimilarity(e.Name, name) })
.OrderByDescending(e => e.Rank)
.Where(e => e.Rank > 0.1f);
var raidbosses = RaidbossService.Raidbosses;
var pokemonWithBoss = new Dictionary <RaidbossPokemon, double>();
foreach (var pokemon in rankedList)
{
foreach (var raidboss in raidbosses)
{
if (pokemon.Pokemon.Id == raidboss.Id)
{
pokemonWithBoss.Add(new RaidbossPokemon(pokemon.Pokemon, raidboss), pokemon.Rank);
}
}
if (pokemonWithBoss.Count >= limit)
{
break;
}
}
return(await Task.FromResult(pokemonWithBoss));
//var rankedListFiltered = rankedList.Where(e => raidbosses.Contains(e.Pokemon.Id)).Take(limit);
//return await Task.FromResult(rankedListFiltered.ToDictionary(k => k.Pokemon, v => v.Rank));
}
public DefaultProductNameMetricConfig()
{
InnerMetric = new Levenstein();
NameCleaningConfig = new DefaultMatchNameCleaningConfig();
Tokeniser = new TokeniserWhitespace();
APositionalWeightingCoefficientPower = 1.5d;
BPositionalWeightingCoefficientPower = 0d;
ABCompoundPositionalWeightRatio = 0d;
}
public async Task <Dictionary <IPokemon, double> > GetSimilarPokemonByNameAsync(string name, int limit = int.MaxValue)
{
var algorithm = new Levenstein();
var rankedList =
Pokemon.Select(e => new { Pokemon = e, Rank = algorithm.GetSimilarity(e.Name, name) })
.OrderByDescending(e => e.Rank)
.Where(e => e.Rank > 0.1f)
.Take(limit);
return(await Task.FromResult(rankedList.ToDictionary(k => k.Pokemon, v => v.Rank)));
}
public int FindChannel(string Name, string country)
{
List <ChannelGrabberInfo> channels = GetChannelArrayList(country);
int retChan = -1;
if (channels == null)
{
return(retChan);
}
ChannelGrabberInfo ch;
Levenstein comparer = new Levenstein();
float bestSimilarity;
float similarity;
int mostSimilarChan = -1;
bestSimilarity = MIN_SIMILARITY;
for (int i = 0; i < channels.Count; i++)
{
ch = (ChannelGrabberInfo)channels[i];
if (ch.GrabberList == null)
{
continue;
}
if (Name.Equals(ch.FullName, StringComparison.OrdinalIgnoreCase))
{
retChan = i;
break;
}
if (ch.FullName.IndexOf(Name, StringComparison.OrdinalIgnoreCase) != -1)
{
retChan = i;
}
similarity = comparer.getSimilarity(Name, ch.FullName);
if (similarity > bestSimilarity)
{
mostSimilarChan = i;
bestSimilarity = similarity;
}
}
if (retChan < 0)
{
return(mostSimilarChan);
}
return(retChan);
}
private string Similarity()
{
if (_migrationContainer.Destination != null && _migrationContainer.Source != null)
{
return(Levenstein.Percent(_migrationContainer.Source.CurrentWorksheetName,
_migrationContainer.Destination.CurrentWorksheetName).ToString() + "%");
}
else
{
return("0%");
}
}
protected override bool CheckResult(string consoleOut)
{
var lines = consoleOut.Split(new string[] { "\r", "\n", "\r\n" }, StringSplitOptions.RemoveEmptyEntries);
var lastLine = lines[lines.Length - 1];
if (RequiredAccuracy == 1)
{
// No differences allowed
return(lastLine == ExpectedResult);
}
var comparer = new Levenstein();
var accuracy = comparer.GetSimilarity(lastLine, ExpectedResult);
return(accuracy >= RequiredAccuracy);
}
public ChannelGrabberInfo[] FindChannels(string[] NameList, string country)
{
List <ChannelGrabberInfo> channels = GetChannelArrayList(country);
ChannelGrabberInfo[] retList = new ChannelGrabberInfo[NameList.Length];
if (channels == null)
{
return(retList);
}
ChannelGrabberInfo ch;
Levenstein comparer = new Levenstein();
float bestSimilarity;
float similarity;
for (int k = 0; k < NameList.Length; k++)
{
bestSimilarity = MIN_SIMILARITY;
for (int i = 0; i < channels.Count; i++)
{
ch = (ChannelGrabberInfo)channels[i];
if (NameList[k] == ch.FullName)
{
retList[k] = ch;
break;
}
if (ch.FullName.IndexOf(NameList[k]) != -1)
{
retList[k] = ch;
break;
}
similarity = comparer.getSimilarity(NameList[k], ch.FullName);
if (similarity > bestSimilarity)
{
retList[k] = ch;
bestSimilarity = similarity;
}
}
}
return(retList);
}
private void DoLevenstein()
{
Levenstein lev = new Levenstein();
switch (_newObjectName.NameType)
{
case FisheryObjectNameType.CatchLocalName:
var localNameList = Names.LocalNameList;
foreach (var item in localNameList)
{
var similarity = lev.GetSimilarity(_newObjectName.NewName, item);
}
break;
case FisheryObjectNameType.GearLocalName:
break;
}
}
protected override bool CheckResult(string consoleOut)
{
// Normalise new line characters
var fixedConsoleOut = consoleOut.Replace("\r\n", "\n").Trim();
var fixedExpectedResult = ExpectedResult.Replace("\r\n", "\n").Trim();
const int magicNUmber = 1;
if (RequiredAccuracy == magicNUmber)
{
// No differences allowed
return(fixedConsoleOut == fixedExpectedResult);
}
var comparer = new Levenstein();
var accuracy = comparer.GetSimilarity(fixedConsoleOut, fixedExpectedResult);
return(accuracy >= RequiredAccuracy);
}
public void FillSourceIfFoundDestination(ColumnParser parser, string caption)
{
if (_migration.Source.ColumnCaptionsWithIndexDictionary.ContainsKey(caption))
{
parser.SourceColumnName = caption;
parser.SourceColumnIndex = _migration.Source.ColumnCaptionsWithIndexDictionary[caption];
}
else
{
if (_migration.Source.ColumnCaptionsWithIndexDictionary.ContainsKey(caption))
{
parser.SourceColumnName = caption;
parser.SourceColumnIndex = _migration.Source.ColumnCaptionsWithIndexDictionary[caption.ToLower()];
}
else
{
string highest = string.Empty;
int memory = 100;
foreach (var par in _migration.Source.ColumnCaptionList)
{
int distance = Levenstein.NettoDistance(par, caption);
if (distance < memory)
{
highest = par;
memory = distance;
}
}
if (memory <= 3)
{
parser.SourceColumnName = highest;
parser.SourceColumnIndex = _migration.Source.ColumnCaptionsWithIndexDictionary[highest];
}
else
{
var s = _migration.Source.ColumnCaptionsWithIndexDictionary.First();
parser.SourceColumnName = s.Key;
parser.SourceColumnIndex = s.Value;
}
}
}
}
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 Levenstein_button_Click(object sender, EventArgs e)
{
LevensteinRez.Text = Levenstein.Func(LevensteinText1.Text, LevensteinText2.Text).ToString();
}
private void button1_Click(object sender, EventArgs e)
{
Existing_Method ex_m = new Existing_Method();
Jaro m1;
JaroVincler m2;
Levenstein m3;
Stopwatch t = new Stopwatch();
double[] rez_mas = new double[20];
if (System.IO.File.Exists("data.txt"))
{
string[] mass = System.IO.File.ReadAllLines("data.txt");
System.IO.File.WriteAllText("ex_m.txt", "");
// Существующий тест
t.Start();
foreach (string s in mass)
{
string[] str = s.Split(' ');
System.IO.File.AppendAllText("ex_m.txt", ex_m.IndistinctMatching(4, str[0], str[1]).ToString() + Environment.NewLine);
}
t.Stop();
System.IO.File.AppendAllText("ex_m.txt", t.Elapsed.ToString());
System.IO.File.WriteAllText("m1.txt", "");
// Метод 1
t = new Stopwatch();
t.Start();
foreach (string s in mass)
{
string[] str = s.Split(' ');
m1 = new Jaro(str[0], str[1]);
System.IO.File.AppendAllText("m1.txt", (m1.Func() * 100).ToString() + Environment.NewLine);
}
t.Stop();
System.IO.File.AppendAllText("m1.txt", t.Elapsed.ToString());
System.IO.File.WriteAllText("m2.txt", "");
// Метод 2
t = new Stopwatch();
t.Start();
foreach (string s in mass)
{
string[] str = s.Split(' ');
m2 = new JaroVincler(str[0], str[1]);
if (m2.Func())
{
System.IO.File.AppendAllText("m2.txt", "100" + Environment.NewLine);
}
else
{
System.IO.File.AppendAllText("m2.txt", "0" + Environment.NewLine);
}
}
t.Stop();
System.IO.File.AppendAllText("m2.txt", t.Elapsed.ToString());
// Метод 3
System.IO.File.WriteAllText("m3.txt", "");
t = new Stopwatch();
t.Start();
foreach (string s in mass)
{
string[] str = s.Split(' ');
m3 = new Levenstein(str[0], str[1]);
System.IO.File.AppendAllText("m3.txt", (100 - m3.Func() * 100).ToString() + Environment.NewLine);
}
t.Stop();
System.IO.File.AppendAllText("m3.txt", t.Elapsed.ToString());
MessageBox.Show("Выполнено");
}
}
public static DsDevice[] Sort(DsDevice[] devices, params object[] arg)
{
try
{
if (devices == null)
{
return(devices);
}
if (devices.Length <= 1)
{
return(devices);
}
List <string> compareNames = new List <string>();
foreach (object obj in arg)
{
String name = obj as String;
if (!string.IsNullOrEmpty(name))
{
compareNames.Add(name);
continue;
}
DsDevice dev = obj as DsDevice;
if (dev == null)
{
continue;
}
if (dev.Name == null)
{
continue;
}
if (dev.Name.Length == 0)
{
continue;
}
compareNames.Add(dev.Name);
}
if (compareNames.Count == 0)
{
return(devices);
}
List <string> names = new List <string>();
for (int i = 0; i < devices.Length; ++i)
{
if (devices[i] == null)
{
continue;
}
if (devices[i].Name == null)
{
continue;
}
if (devices[i].Name.Length == 0)
{
continue;
}
names.Add(devices[i].Name);
}
//sort the devices based
float[] results = new float[devices.Length + 20];
for (int x = 0; x < results.Length; ++x)
{
results[x] = 0.0f;
}
for (int i = 0; i < compareNames.Count; ++i)
{
Levenstein comparer = new Levenstein();
float[] tmpResults = comparer.batchCompareSet(names.ToArray(), compareNames[i]);
for (int x = 0; x < tmpResults.Length; ++x)
{
results[x] += tmpResults[x];
}
}
List <SortItem> items = new List <SortItem>();
for (int i = 0; i < devices.Length; ++i)
{
SortItem item = new SortItem();
item.rate = results[i];
item.device = devices[i];
items.Add(item);
}
items.Sort();
DsDevice[] newDevices = new DsDevice[items.Count];
int index = 0;
foreach (SortItem item in items)
{
newDevices[index] = item.device;
index++;
}
return(newDevices);
}
catch (Exception ex)
{
Log.Log.Write(ex);
return(devices);
}
}
// сравнение
private List <string[]> Sravn(string[][] data)
{
List <string[]> rezlist = new List <string[]>();
foreach (string[] str in data)
{
// количество слов в строке
if (str.Count() != 2)
{
continue;
}
else
{
string[] mass;
SimMetricsMetricUtilities.Levenstein ex_l = new SimMetricsMetricUtilities.Levenstein();
Stopwatch t = new Stopwatch();
t.Start();
double rj1 = Math.Round(Jaro.Func(str[0], str[1]), 2);
string tj1 = Math.Round(t.Elapsed.TotalMilliseconds, 2).ToString();
t = new Stopwatch();
t.Start();
double rj2 = Math.Round(ExJaro.distance(str[0], str[1]), 2);
string tj2 = Math.Round(t.Elapsed.TotalMilliseconds, 2).ToString();
// -----
t = new Stopwatch();
t.Start();
double rjv1 = Math.Round(JaroVincler.Func(str[0], str[1]), 2);
string tjv1 = Math.Round(t.Elapsed.TotalMilliseconds, 2).ToString();
t = new Stopwatch();
t.Start();
double rjv2 = Math.Round(ExJaroWincler.distance(str[0], str[1]), 2);
string tjv2 = Math.Round(t.Elapsed.TotalMilliseconds, 2).ToString();
// ----
t = new Stopwatch();
t.Start();
double rl1 = Math.Round(Levenstein.Func(str[0], str[1]), 2);
string tl1 = Math.Round(t.Elapsed.TotalMilliseconds, 2).ToString();
t = new Stopwatch();
t.Start();
double rl2 = Math.Round(ex_l.GetSimilarity(str[0], str[1]), 2);
string tl2 = Math.Round(t.Elapsed.TotalMilliseconds, 2).ToString();
rezlist.Add(new string[14] {
rj1.ToString(), tj1, rj2.ToString(), tj2,
rjv1.ToString(), tjv1, rjv2.ToString(), tjv2,
rl1.ToString(), tl1, rl2.ToString(), tl2, str[0], str[1]
});
}
}
return(rezlist);
}
public void Test1()
{
Assert.Equal(3, Levenstein.LevensteinDynamic("Вар", "Баран"));
}
public void Test3()
{
Assert.Equal(4, Levenstein.LevensteinDynamic("", "test"));
}
private void mpListViewChannels_SelectedIndexChanged(object sender, EventArgs e)
{
mpListViewMapped.BeginUpdate();
try
{
mpListViewMapped.Items.Clear();
if (mpListViewChannels.SelectedIndices == null)
{
return;
}
if (mpListViewChannels.SelectedIndices.Count != 1)
{
return;
}
Card card = ((CardInfo)mpComboBoxCard.SelectedItem).Card;
ListViewItem selectedItem = mpListViewChannels.Items[mpListViewChannels.SelectedIndices[0]];
Channel selectedChannel = (Channel)selectedItem.Tag;
IList <Channel> allChannels = Channel.ListAll();
List <ListViewItem> items = new List <ListViewItem>();
NotifyForm dlg = new NotifyForm("Searching for Similar Channels...",
"This can take some time\n\nPlease be patient...");
dlg.Show(this);
dlg.WaitForDisplay();
foreach (Channel channel in allChannels)
{
if (channel.IsRadio == false)
{
continue;
}
bool isMapped = false;
IList <ChannelMap> list = channel.ReferringChannelMap();
foreach (ChannelMap map in list)
{
if (map.IdCard == card.IdCard)
{
isMapped = true;
break;
}
}
if (isMapped)
{
continue;
}
Levenstein comparer = new Levenstein();
float result = comparer.getSimilarity(selectedChannel.DisplayName, channel.DisplayName);
IList <TuningDetail> details = channel.ReferringTuningDetail();
int imageIndex = GetImageIndex(details);
ListViewItem item = new ListViewItem((result * 100f).ToString("f2") + "%", imageIndex);
item.Tag = channel;
item.SubItems.Add(channel.DisplayName);
items.Add(item);
}
mpListViewMapped.Items.AddRange(items.ToArray());
mpListViewMapped.Sort();
dlg.Close();
}
finally
{
mpListViewMapped.EndUpdate();
}
}
public bool ShouldCompareStringsPos(string s1, string s2, int level)
{
Levenstein algo = new Levenstein(level);
return(algo.IsTheSame(s1, s2));
}
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);
}
// [SetUp]
public LevensteinUnitTests()
{
LoadData();
myLevenstein = new Levenstein();
}
private void MergeCheckTextMatch()
{
if (IsSecondKeyChecked() && IsKeyChecked())
{
var keycolumn = from el in columnParsers
where el.IsKey == true
select el;
var matchcolumn = from el in columnParsers
where el.LookupMatch == true
select el;
if (keycolumn.Count() != 1 || matchcolumn.Count() != 1)
{
var msg = new MessageView("You cannot specify more than one first key!");
msg.Show();
}
else
{
var keycol = keycolumn.FirstOrDefault();
var matchcol = matchcolumn.FirstOrDefault();
Dictionary <string, int> sourceKeys = new Dictionary <string, int>();
Dictionary <string, int> destinationKeys = new Dictionary <string, int>();
sourceKeys = LoadColumn(_migration.Source, keycol.SourceColumnIndex);
destinationKeys = LoadColumn(_migration.Destination, keycol.DestinationColumnIndex);
SortedDictionary <string, int> sortedSourceKeys = new SortedDictionary <string, int>(sourceKeys);
Dictionary <string, int> sourceNames = new Dictionary <string, int>();
Dictionary <string, int> destinationNames = new Dictionary <string, int>();
sourceNames = LoadColumn(_migration.Source, matchcol.SourceColumnIndex);
destinationNames = LoadColumn(_migration.Destination, matchcol.DestinationColumnIndex);
int ifNotFoundKeyRow = LastEmptyRow(_migration.Destination);
bool permission = true;
int row = 0;
int columncaptionsindex = _migration.Destination.ColumnCaptionRow;
foreach (var cl in sortedSourceKeys)
{
if (cl.Key != string.Empty)
{
if (destinationKeys.ContainsKey(cl.Key))
{
row = destinationKeys[cl.Key] + columncaptionsindex;
int rowsource = sourceKeys[cl.Key] + columncaptionsindex;
decimal percent = Levenstein.Percent(
_migration.Source.ReadCell(rowsource, matchcol.SourceColumnIndex),
_migration.Destination.ReadCell(row, matchcol.DestinationColumnIndex)
);
if (percent < 80)
{
var elements = from el in destinationNames
where Levenstein.NettoDistance(cl.Key, el.Key) <= 3 && el.Key != string.Empty
select el;
if (elements.Count() > 0)
{
KeyValuePair <string, int> result = new KeyValuePair <string, int>();
var comp = new SimilarNames(elements, result);
comp.ShowDialog();
}
}
}
else
{
row = ifNotFoundKeyRow++;
}
FromSource2DestinationWithRelationByRow(row,
cl,
sourceKeys,
permission);
}
}
_migration.Destination.Save();
_migration.Source.Save();
}
}
}
