Euclidean Distance

collab-filter.py

 import csv
-
+from math import sqrt
 csvfile=open('movie-ratings.csv')
 read=csv.reader(csvfile)
 reading=[]
 for line in read:
 	reading.append(line)
+#########################
 f2 = open ("user_preference.csv")
-data = csv.reader(f2)
+user_data = csv.reader(f2)
 preference = []
-a=input("Your name :")
-preference.append(a)
-for line in data:
+preference.append(input("Your name :"))
+for line in user_data:
     preference.append(line)
 prefdict = dict( zip(preference[1],preference[2]))
-print(prefdict)
\ No newline at end of file
+####################
+# print(reading[1][6])
+header = reading[0]
+del reading[0]
+reviewers = [ s[0] for s in reading]
+reviewdic = []
+for line in reading:
+    dic = dict( (header[i],line[i]) for i in range(1,len(line)))
+    reviewdic.append(dic)
+dist=[]
+# print(reviewdic)
+for i in reviewdic:
+    sum=0
+    for j in prefdict.keys():
+        if(i[j] != -1 and prefdict[j] != -1):
+            sum+=sqrt((float(i[j])-float(prefdict[j]))**2)
+    dist.append(sum)
+# print(len(prefdict))
+# for i in reviewdic:
+order_dist = sorted(zip(reviewers,dist), key=lambda x: x[1],reverse=True)

user_preference.csv

-The Godfather,Pulp Fiction,The Clockwork Orange,Cinema Paradiso,Wild Strawberries,Amadeus
-9,7,6,10,8,10
+The Godfather,Pulp Fiction,Gone With the Wind,12 Angry Men,Lawrence of Arabia,Raging Bull,The Clockwork Orange,Cinema Paradiso,Wild Strawberries,Amadeus
+9,7,6,10,8,10,-1,-1,-1,-1