如何在Python中构建一个简单的推荐系统

pip install pandas scikit-learn

import pandas as pd
from sklearn.model_selection import train_test_split

# 加载数据集
data = pd.read_csv('ratings.csv')

train_data, test_data = train_test_split(data, test_size=0.2, random_state=42)

# 计算用户之间的相似度
def calculate_similarity(train_data):
    similarity = dict()
    for user in train_data['userId'].unique():
        similarity[user] = dict()
        user_ratings = train_data[train_data['userId'] == user]
        for movie in user_ratings['movieId'].unique():
            similarity[user][movie] = 1.0

    return similarity

# 计算用户之间的相似度得分
def calculate_similarity_score(train_data, similarity):
    for user1 in similarity.keys():
        for user2 in similarity.keys():
            if user1 != user2:
                user1_ratings = train_data[train_data['userId'] == user1]
                user2_ratings = train_data[train_data['userId'] == user2]
                num_ratings = 0
                sum_of_squares = 0
                for movie in user1_ratings['movieId'].unique():
                    if movie in user2_ratings['movieId'].unique():
                        num_ratings += 1
                        rating1 = user1_ratings[user1_ratings['movieId'] == movie]['rating'].values[0]
                        rating2 = user2_ratings[user2_ratings['movieId'] == movie]['rating'].values[0]
                        sum_of_squares += (rating1 - rating2) ** 2
                similarity[user1][user2] = 1 / (1 + (sum_of_squares / num_ratings) ** 0.5)

    return similarity

# 计算电影之间的相似度得分
def calculate_movie_similarity_score(train_data, similarity):
    movie_similarity = dict()
    for user in similarity.keys():
        for movie in train_data[train_data['userId'] == user]['movieId'].unique():
            if movie not in movie_similarity.keys():
                movie_similarity[movie] = dict()

            for other_movie in train_data[train_data['userId'] == user]['movieId'].unique():
                if movie != other_movie:
                    movie_similarity[movie][other_movie] = similarity[user][other_user]

    return movie_similarity

# 构建推荐系统
def build_recommendation_system(train_data, similarity, movie_similarity):
    recommendations = dict()
    for user in train_data['userId'].unique():
        user_ratings = train_data[train_data['userId'] == user]
        recommendations[user] = dict()
        for movie in train_data['movieId'].unique():
            if movie not in user_ratings['movieId'].unique():
                rating = 0
                num_movies = 0
                for other_user in similarity[user].keys():
                    if movie in train_data[train_data['userId'] == other_user]['movieId'].unique():
                        rating += similarity[user][other_user] * train_data[(train_data['userId'] == other_user) & (train_data['movieId'] == movie)]['rating'].values[0]
                        num_movies += 1
                if num_movies > 0:
                    recommendations[user][movie] = rating / num_movies

    return recommendations

# 计算评价指标
def calculate_metrics(recommendations, test_data):
    num_users = 0
    sum_of_squared_error = 0
    for user in recommendations.keys():
        if user in test_data['userId'].unique():
            num_users += 1
            for movie in recommendations[user].keys():
                if movie in test_data[test_data['userId'] == user]['movieId'].unique():
                    predicted_rating = recommendations[user][movie]
                    actual_rating = test_data[(test_data['userId'] == user) & (test_data['movieId'] == movie)]['rating'].values[0]
                    sum_of_squared_error += (predicted_rating - actual_rating) ** 2
    rmse = (sum_of_squared_error / num_users) ** 0.5

    return rmse

# 计算用户之间的相似度
similarity = calculate_similarity(train_data)

# 计算用户之间的相似度得分
similarity = calculate_similarity_score(train_data, similarity)

# 计算电影之间的相似度得分
movie_similarity = calculate_movie_similarity_score(train_data, similarity)

# 构建推荐系统
recommendations = build_recommendation_system(train_data, similarity, movie_similarity)

# 计算评价指标
rmse = calculate_metrics(recommendations, test_data)

print(recommendations)
print('RMSE:', rmse)