from collections import defaultdict import json import matplotlib.pyplot as plt import numpy as np import pandas as pd import random import surprise as sp

ratings_set = pd.read_csv('ratings.csv') display(ratings_set)

movies_set = pd.read_csv('movies.csv') display(movies_set)

ratings_movies_set = ratings_set.merge(movies_set, how='inner', on='movieId') display(ratings_movies_set)

reader = sp.Reader(rating_scale=(0, 5)) dataset = sp.Dataset.load_from_df(ratings_set[['userId', 'movieId', 'rating']], reader)

# First we try to load best config from json file # If the file doesn't exists, we use GridSearchCV to tune algorithm best_params = {} with open('knn_params_best.json', 'r') as f: best_params = json.load(f) if not best_params: knn_params_grid = { 'min_k': [2], 'k': [10,30,40,50], 'verbose': [False], 'sim_options': { 'name': ['pearson', 'cosine'], 'min_support': [10,15,20], 'user_based': [True] } } gs = sp.model_selection.GridSearchCV( algo_class=sp.KNNBasic, param_grid=knn_params_grid, measures=['rmse'], cv=5, # using 5-fold cross-validation n_jobs=-1 ) gs.fit(dataset) print("best rmse score:", gs.best_score['rmse']) print("Best params: ", gs.best_params['rmse']) # Asign knn algorithm with the best accuracy knn = gs.best_estimator['rmse'] # writes best param to json file for later use with open('knn_params_best.json', 'w') as f: json.dump(gs.best_params['rmse'], f) else: print("Best params: ", best_params) knn = sp.KNNBasic(k=best_params['k'], min_k=best_params['min_k'], sim_options=best_params['sim_options'], verbose=False) sp.model_selection.cross_validate(knn, dataset, measures=['rmse'], cv=5, verbose=Fals, n_jobs=-1) knn.verbose = True

def predict_ratings(algo, user_id, movie_id): check = ratings_movies_set.query(f"userId == {user_id} and movieId == {movie_id}") if not check.empty: print(f"User {user_id} has already rate movie {movie_id}") display(check) else: display(f"User {user_id} ratings:", ratings_movies_set[ratings_movies_set['userId'] == user_id]) display(f"Movie {movie_id} ratings:", ratings_movies_set[ratings_movies_set['movieId'] == movie_id]) predict = algo.predict(uid=user_id, iid=movie_id) print(f"The estimation for user {user_id} and {movie_id} is: ", predict.est) print("More details:",predict)

knn.fit(dataset.build_full_trainset())

predict_ratings(knn, 11, 293)

predict_ratings(knn, 100, 72998)

def get_top_n(predictions, n=10): # First map the predictions to each user. top_n = defaultdict(list) for uid, iid, true_r, est, _ in predictions: top_n[uid].append((iid, est)) # Then sort the predictions for each user and retrieve the n highest ones. for uid, user_ratings in top_n.items(): user_ratings.sort(key=lambda x: x[1], reverse=True) top_n[uid] = user_ratings[:n] return top_n

train_set = dataset.build_full_trainset() # build test set for all pairs that are not in the training set test_set = train_set.build_anti_testset() knn.fit(train_set) predictions = knn.test(test_set) top_10 = get_top_n(predictions, n=10)

sample_top_10 = random.sample(top_10.items(), 50) counter = 0 for uid, user_ratings in sample_top_10: counter += 1 print(f"{counter}. User {uid} top 10 recommendations are:") for (iid, rating) in user_ratings: movie_title = movies_set[movies_set['movieId'] == iid].title.item() print(f"{movie_title} (id:{iid}), rating: {rating}") print("\n")