import pandas as pd import numpy as np # 计算用户对歌曲的播放比例 triplet_dataset_sub_song_merged_sum_df = triplet_dataset_sub_song_mergedpd[['user', 'listen_count']].groupby('user').sum().reset_index() triplet_dataset_sub_song_merged_sum_df.rename(columns={'listen_count': 'total_listen_count'}, inplace=True) triplet_dataset_sub_song_merged = pd.merge(triplet_dataset_sub_song_mergedpd, triplet_dataset_sub_song_merged_sum_df) triplet_dataset_sub_song_mergedpd['fractional_play_count'] = triplet_dataset_sub_song_mergedpd['listen_count'] / triplet_dataset_sub_song_merged['total_listen_count'] # 将用户和歌曲编码为数字 small_set = triplet_dataset_sub_song_mergedpd user_codes = small_set.user.drop_duplicates().reset_index() song_codes = small_set.song.drop_duplicates().reset_index() user_codes.rename(columns={'index': 'user_index'}, inplace=True) song_codes.rename(columns={'index': 'song_index'}, inplace=True) song_codes['so_index_value'] = list(song_codes.index) user_codes['us_index_value'] = list(user_codes.index) small_set = pd.merge(small_set, song_codes, how='left') small_set = pd.merge(small_set, user_codes, how='left') # 将数据转换为稀疏矩阵形式 from scipy.sparse import coo_matrix mat_candidate = small_set[['us_index_value', 'so_index_value', 'fractional_play_count']] data_array = mat_candidate.fractional_play_count.values row_array = mat_candidate.us_index_value.values col_array = mat_candidate.so_index_value.values data_sparse = coo_matrix((data_array, (row_array, col_array)), dtype=float) # 使用SVD方法进行矩阵分解并进行推荐 from scipy.sparse import csc_matrix from scipy.sparse.linalg import svds import math as mt def compute_svd(urm, K): U, s, Vt = svds(urm, K) dim = (len(s), len(s)) S = np.zeros(dim, dtype=np.float32) for i in range(0, len(s)): S[i, i] = mt.sqrt(s[i]) U = csc_matrix(U, dtype=np.float32) S = csc_matrix(S, dtype=np.float32) Vt = csc_matrix(Vt, dtype=np.float32) return U, S, Vt def compute_estimated_matrix(urm, U, S, Vt, uTest, K, test): rightTerm = S * Vt max_recommendation = 250 estimatedRatings = np.zeros(shape=(MAX_UID, MAX_PID), dtype=np.float16) recomendRatings = np.zeros(shape=(MAX_UID, max_recommendation), dtype=np.float16) for userTest in uTest: prod = U[userTest, :] * rightTerm estimatedRatings[userTest, :] = prod.todense() recomendRatings[userTest, :] = (-estimatedRatings[userTest, :]).argsort()[:max_recommendation] return recomendRatings K = 50 urm = data_sparse MAX_PID = urm.shape[1] MAX_UID = urm.shape[0] U, S, Vt = compute_svd(urm, K) uTest = [4, 5, 6, 7, 8, 73, 23] # uTest=[1b5bb32767963cbc215d27a24fef1aa01e933025] uTest_recommended_items = compute_estimated_matrix(urm, U, S, Vt 继续将这段代码输出完整

, 并进行解释： ``` import pandas as pd import numpy as np # 计算用户对歌曲的播放比例 triplet_dataset_sub_song_merged_sum_df = triplet_dataset_sub_song_merged[['user', 'listen_count']].groupby('user').sum().reset_index() triplet_dataset_sub_song_merged_sum_df.rename(columns={'listen_count': 'total_listen_count'}, inplace=True) triplet_dataset_sub_song_merged = pd.merge(triplet_dataset_sub_song_merged, triplet_dataset_sub_song_merged_sum_df) triplet_dataset_sub_song_merged['fractional_play_count'] = triplet_dataset_sub_song_merged['listen_count'] / triplet_dataset_sub_song_merged['total_listen_count'] # 将用户和歌曲编码为数字 small_set = triplet_dataset_sub_song_merged user_codes = small_set.user.drop_duplicates().reset_index() song_codes = small_set.song.drop_duplicates().reset_index() user_codes.rename(columns={'index': 'user_index'}, inplace=True) song_codes.rename(columns={'index': 'song_index'}, inplace=True) song_codes['so_index_value'] = list(song_codes.index) user_codes['us_index_value'] = list(user_codes.index) small_set = pd.merge(small_set, song_codes, how='left') small_set = pd.merge(small_set, user_codes, how='left') # 将数据转换为稀疏矩阵形式 from scipy.sparse import coo_matrix mat_candidate = small_set[['us_index_value', 'so_index_value', 'fractional_play_count']] data_array = mat_candidate.fractional_play_count.values row_array = mat_candidate.us_index_value.values col_array = mat_candidate.so_index_value.values data_sparse = coo_matrix((data_array, (row_array, col_array)), dtype=float) # 使用SVD方法进行矩阵分解并进行推荐 from scipy.sparse import csc_matrix from scipy.sparse.linalg import svds import math as mt def compute_svd(urm, K): U, s, Vt = svds(urm, K) dim = (len(s), len(s)) S = np.zeros(dim, dtype=np.float32) for i in range(0, len(s)): S[i, i] = mt.sqrt(s[i]) U = csc_matrix(U, dtype=np.float32) S = csc_matrix(S, dtype=np.float32) Vt = csc_matrix(Vt, dtype=np.float32) return U, S, Vt def compute_estimated_matrix(urm, U, S, Vt, uTest, K, test): rightTerm = S * Vt max_recommendation = 250 estimatedRatings = np.zeros(shape=(MAX_UID, MAX_PID), dtype=np.float16) recomendRatings = np.zeros(shape=(MAX_UID, max_recommendation), dtype=np.float16) for userTest in uTest: prod = U[userTest, :] * rightTerm estimatedRatings[userTest, :] = prod.todense() recomendRatings[userTest, :] = (-estimatedRatings[userTest, :]).argsort()[:max_recommendation] return recomendRatings K = 50 urm = data_sparse MAX_PID = urm.shape[1] MAX_UID = urm.shape[0] U, S, Vt = compute_svd(urm, K) uTest = [4, 5, 6, 7, 8, 73, 23] # uTest=[1b5bb32767963cbc215d27a24fef1aa01e933025] uTest_recommended_items = compute_estimated_matrix(urm, U, S, Vt, uTest, K, test) ``` 这段代码实现了一个基于SVD方法的推荐系统，具体步骤如下： 1. 读入数据，计算每个用户对每首歌曲的播放比例。 2. 将用户和歌曲编码为数字，转换为稀疏矩阵形式。 3. 使用SVD方法进行矩阵分解，得到用户和歌曲的隐向量。 4. 对于给定的测试用户，使用隐向量和分解后的矩阵计算出该用户对每首歌曲的预测评分。 5. 根据预测评分，为该用户推荐最高的250首歌曲。 其中，SVD方法是一种矩阵分解的方法，可以将一个大矩阵分解为多个小矩阵，这些小矩阵可以表示出原始矩阵中的潜在特征（即隐向量）。通过计算用户和歌曲的隐向量，可以获得它们之间的相似度，从而进行推荐。