-
Notifications
You must be signed in to change notification settings - Fork 0
/
euclidean_score.py
41 lines (29 loc) · 1.11 KB
/
euclidean_score.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
import json
import numpy as np
# Returns the Euclidean distance score between user1 and user2
def euclidean_score(dataset, user1, user2):
if user1 not in dataset:
raise TypeError('User ' + user1 + ' not present in the dataset')
if user2 not in dataset:
raise TypeError('User ' + user2 + ' not present in the dataset')
# Movies rated by both user1 and user2
rated_by_both = {}
for item in dataset[user1]:
if item in dataset[user2]:
rated_by_both[item] = 1
# If there are no common movies, the score is 0
if len(rated_by_both) == 0:
return 0
squared_differences = []
for item in dataset[user1]:
if item in dataset[user2]:
squared_differences.append(np.square(dataset[user1][item] - dataset[user2][item]))
return 1 / (1 + np.sqrt(np.sum(squared_differences)))
if __name__=='__main__':
data_file = 'movie_ratings.json'
with open(data_file, 'r') as f:
data = json.loads(f.read())
user1 = 'Mansi Jain'
user2 = 'Rohit Chugh'
print('\nEuclidean score:')
print(euclidean_score(data, user1, user2))