comparison Code/eda.py @ 23:45e6f85d0ba4

List of clips downloaded

          "SOAKWCK12A8C139F81": [1, 4, 5, 3.5, 5, 1, 1, 5, 4, 1],
          "SOAKNZI12A58A79CAC": [1, 5, 3.5, 3, 4, 5, 1, 5, 4, 1],
          "SOAJZEP12A8C14379B": [5, 5, 4, 2, 1, 1, 1, 5, 4, 1],
          "SOAHQFM12A8C134B65": [2.5, 4, 4, 1, 1, 1, 1, 5, 4, 1]}
 
-'''
-Functions to compute similarity between items or between profiles
-'''
+#Functions to compute similarity between items or between profiles
+# Source: http://www.guidetodatamining.com
+def manhattan(vector1, vector2):
+    """Computes the Manhattan distance."""
+    distance = 0
+    total = 0
+    n = len(vector1)
+    for i in range(n):
+        distance += abs(vector1[i] - vector2[i])
+    return distance
+
+def computeNearestNeighbor(itemName, itemVector, items):
+    """creates a sorted list of items based on their distance to item"""
+    distances = []
+    for otherItem in items:
+        if otherItem != itemName:
+            distance = manhattan(itemVector, items[otherItem])
+            distances.append((distance, otherItem))
+        # sort based on distance -- closest first
+        distances.sort()
+    return distances
+
+def classify(user, itemName, itemVector):
+    """Classify the itemName based on user ratings
+    Should really have items and users as parameters"""
+    # first find nearest neighbor
+    nearest = computeNearestNeighbor(itemName, itemVector, items)[0][1]
+    rating = users[user][nearest]
+    return rating
+
+# Fitness function of EDA
+def Fitness(profile, user):
+    nearest = computeNearestNeighbor(itemName, itemVector, items)[0][1]
+    rating = users[user][nearest]
+    return rating
+
+    
 # Pearson Correlation Coefficient
-# Source: http://www.guidetodatamining.com
 def pearson(rating1, rating2):
     sum_xy = 0
     sum_x = 0
     sum_y = 0
     sum_x2 = 0

     if denominator == 0:
         return 0
     else:
         return sum_xy / denominator
 
-'''
-Fitness function of EDA
+
 '''
 def Fitness(profile, user_index):
     sim = 0
     sum_log = 0
     

     for username, songs in users.items():
         for song, rating in songs.items():
             sim = pearson(profile, items[song])
             #sum_log += log10(rating * sim)
     return sim
-
-'''
-Generation of M individuals uniformly
-'''
+'''
+# Generation of M individuals uniformly
 population_size = len(users)
 fraction_of_population = 0.5
 np.random.seed(len(users))
 M = np.random.uniform(size=population_size * len(items.values()[0]))
 M.shape = (-1, len(items.values()[0]))