/// <summary>
/// Compute QGram distance using precomputed profiles.
/// </summary>
/// <param name="profile1"></param>
/// <param name="profile2"></param>
/// <returns></returns>
public double Distance(IDictionary <string, int> profile1, IDictionary <string, int> profile2)
{
//var union = new HashSet<string>();
var union = new HashCollection <string>();
union.UnionWith(profile1.Keys);
union.UnionWith(profile2.Keys);
int agg = 0;
foreach (var key in union)
{
int v1 = 0;
int v2 = 0;
if (profile1.TryGetValue(key, out var iv1))
{
v1 = iv1;
}
if (profile2.TryGetValue(key, out var iv2))
{
v2 = iv2;
}
agg += Math.Abs(v1 - v2);
}
return(agg);
}
/// <summary>
/// Compute jaccard index: |A inter B| / |A union B|.
/// </summary>
/// <param name="s1">The first string to compare.</param>
/// <param name="s2">The second string to compare.</param>
/// <returns>The Jaccard index in the range [0, 1]</returns>
/// <exception cref="ArgumentNullException">If s1 or s2 is null.</exception>
public double Similarity(string s1, string s2)
{
if (s1 == null)
{
throw new ArgumentNullException(nameof(s1));
}
if (s2 == null)
{
throw new ArgumentNullException(nameof(s2));
}
if (s1.Equals(s2))
{
return(1);
}
var profile1 = GetProfile(s1);
var profile2 = GetProfile(s2);
//var union = new HashSet<string>();
var union = new HashCollection <string>();
union.UnionWith(profile1.Keys);
union.UnionWith(profile2.Keys);
int inter = profile1.Keys.Count + profile2.Keys.Count
- union.Count;
return(1.0 * inter / union.Count);
}
/// <summary>
/// Similarity is computed as 2 * |A inter B| / (|A| + |B|).
/// </summary>
/// <param name="s1">The first string to compare.</param>
/// <param name="s2">The second string to compare.</param>
/// <returns>The computed Sorensen-Dice similarity.</returns>
/// <exception cref="ArgumentNullException">If s1 or s2 is null.</exception>
public double Similarity(string s1, string s2)
{
if (s1 == null)
{
throw new ArgumentNullException(nameof(s1));
}
if (s2 == null)
{
throw new ArgumentNullException(nameof(s2));
}
if (s1.Equals(s2))
{
return(1);
}
var profile1 = GetProfile(s1);
var profile2 = GetProfile(s2);
//var union = new HashSet<string>();
var union = new HashCollection <string>();
union.UnionWith(profile1.Keys);
union.UnionWith(profile2.Keys);
int inter = 0;
foreach (var key in union)
{
if (profile1.ContainsKey(key) && profile2.ContainsKey(key))
{
inter++;
}
}
return(2.0 * inter / (profile1.Count + profile2.Count));
}