Finding similar users in the dataset is a critical step in movie recommendations, and this process is explained next.
- We will create a new Python file and import the following packages:
import json import numpy as np from pearson _dist_score import pearson _dist_score
- First, define a function for the input user that will find the similar users. For this, three arguments are needed: the number of similar users, the input user, and the database. Check whether the user is present in the database. If they are present, calculate the Pearson correlation score between the users present in the database and the input user:
# Finds a specified number of users who are similar to the input user
def search_similar_user (dataset, input_user, users_number):
if input_user not in dataset:
raiseTypeError('User ' + input_user + ' not present in the dataset')
# Calculate Pearson scores for all the users
scores = np.array([[x,...