Remove two similaritys

shared/inc/values/Similarity.hpp

@@ -6,9 +6,10 @@ namespace Similarity
   // float euclidean_distance(Dna *d1, Dna *d2); direct distance betwen vector. wont give 0 and 1
   //  float dot_product(Dna *d1, Dna *d2); doent return betwen 0 to 1
   float cosine_similarity(Dna *d1, Dna *d2);
+  float cosine_similarity_int(Dna *d1, Dna *d2);
   float hamming_distance(Dna *d1, Dna *d2);
-  float jaccard_index(Dna *d1, Dna *d2);
-  float levenshtein_distance(Dna *d1, Dna *d2);
+  // float jaccard_index(Dna *d1, Dna *d2); // primerja unio genov naprimer gleda ce je gen za nebo isti z genom za barvo za liste, to nerabimo
+  // float levenshtein_distance(Dna *d1, Dna *d2); // odstranjen ker mi vrne iste podatke kot hamming distance ki je bolj enostaven za izracun
   // float needleman_wunsch(Dna *d1, Dna *d2); used for bioinformatics and aligment. Dont need its aligned alredy
 
   typedef float(simil_func)(Dna *d1, Dna *d2);

shared/src/values/Similarity.cpp

@@ -7,7 +7,10 @@
 
 namespace Similarity
 {
-
+  // todo: use int8_t insted of uint8_t and map data
+  // 0 -> -128
+  // 255 -> 127
+  // int8_t = uint8_t - 128
   float cosine_similarity(Dna *d1, Dna *d2)
   {
     uint8_t *d1a = (uint8_t *)d1;
@@ -28,6 +31,31 @@ namespace Similarity
     return dot_prod / (mag1 * mag2);
   }
 
+  float cosine_similarity_int(Dna *d1, Dna *d2)
+  {
+    auto map = [](uint8_t a) -> int8_t
+    { return a - 128; };
+
+    uint8_t *d1a = (uint8_t *)d1;
+    uint8_t *d2a = (uint8_t *)d2;
+
+    float mag1 = 0.0f;
+    float mag2 = 0.0f;
+    float dot_prod = 0.0f;
+    for (size_t i = 0; i < sizeof(Dna); i++)
+    {
+      int8_t a = map(d1a[i]);
+      int8_t b = map(d2a[i]);
+      dot_prod += a * b;
+      mag1 += a * a;
+      mag2 += b * b;
+    }
+    mag1 = sqrt(mag1);
+    mag2 = sqrt(mag2);
+
+    return dot_prod / (mag1 * mag2);
+  }
+
   float hamming_distance(Dna *d1, Dna *d2)
   {
     uint8_t *d1a = (uint8_t *)d1;
@@ -43,59 +71,6 @@ namespace Similarity
     return 1 - (distance / sizeof(Dna));
   }
 
-  float jaccard_index(Dna *d1, Dna *d2)
-  {
-    uint8_t *d1a = (uint8_t *)d1;
-    uint8_t *d2a = (uint8_t *)d2;
-    size_t intersection = 0;
-    size_t union_size = sizeof(Dna) + sizeof(Dna);
-
-    for (size_t i = 0; i < sizeof(Dna); i++)
-    {
-      for (size_t j = 0; j < sizeof(Dna); j++)
-      {
-        if (d1a[i] == d2a[j])
-        {
-          intersection++;
-          break;
-        }
-      }
-    }
-
-    union_size -= intersection;
-    return (float)intersection / union_size;
-  }
-
-  float levenshtein_distance(Dna *d1, Dna *d2)
-  {
-    auto min = [](uint8_t a, uint8_t b, uint8_t c) -> uint8_t
-    {
-      return (a < b ? (a < c ? a : c) : (b < c ? b : c));
-    };
-
-    uint8_t *d1a = (uint8_t *)d1;
-    uint8_t *d2a = (uint8_t *)d2;
-    float matrix[sizeof(Dna) + 1][sizeof(Dna) + 1];
-    for (size_t i = 0; i <= sizeof(Dna); i++)
-    {
-      matrix[i][0] = i;
-    }
-    for (size_t j = 0; j <= sizeof(Dna); j++)
-    {
-      matrix[0][j] = j;
-    }
-    for (size_t i = 1; i <= sizeof(Dna); i++)
-    {
-      for (size_t j = 1; j <= sizeof(Dna); j++)
-      {
-        uint8_t cost = (d1a[i - 1] == d2a[j - 1]) ? 0 : 1;
-        matrix[i][j] = min(matrix[i - 1][j] + 1, matrix[i][j - 1] + 1, matrix[i - 1][j - 1] + cost);
-      }
-    }
-    float ld = matrix[sizeof(Dna)][sizeof(Dna)];
-    return 1 - (ld / sizeof(Dna));
-  }
-
   float calc_similarity(std::vector<Dna> &vec, simil_func f)
   {
     size_t num_pairs = (vec.size() * (vec.size() - 1)) / 2;

view/inc/Vapp.hpp

@@ -45,5 +45,5 @@ private:
   int drawY = 0;
   void setUpManager();
 
-  std::array<float, 4> simil;
+  std::array<float, 3> simil;
 };

view/src/Vapp.cpp

@@ -102,9 +102,7 @@ void Vapp::update()
 
     simil[0] = Similarity::calc_similarity(manager.vector, Similarity::cosine_similarity);
     simil[1] = Similarity::calc_similarity(manager.vector, Similarity::hamming_distance);
-    simil[2] = Similarity::calc_similarity(manager.vector, Similarity::jaccard_index);
-    simil[3] = Similarity::calc_similarity(manager.vector, Similarity::levenshtein_distance);
-
+    simil[2] = Similarity::calc_similarity(manager.vector, Similarity::cosine_similarity_int);
     stageOfDrawing = DrawingStage::done;
     break;
 
@@ -174,8 +172,7 @@ void Vapp::draw()
     ImGui::Begin("Status", &showStats);
     ImGui::LabelText("##sim1", "cosine_similarity: %f", simil[0]);
     ImGui::LabelText("##sim2", "hamming_distance: %f", simil[1]);
-    ImGui::LabelText("##sim3", "jaccard_index: %f", simil[2]);
-    ImGui::LabelText("##sim4", "levenshtein_distance: %f", simil[3]);
+    ImGui::LabelText("##sim3", "cosine_similarity_int: %f", simil[2]);
     ImGui::End();
   }