trust_v2.py 文件源码

def calcuate_similarity(pivot_table, user_data, product_data, i, j, w_lambda):
    if i==j:
        return 0
    normalize_freq = np.max(product_data['count'].values)
    common = (pivot_table[i]*pivot_table[j]).nonzero()

    rating_i = pivot_table[i][common[0]]
    rating_j = pivot_table[j][common[0]]
    rating_i = rating_i - user_data.iloc[i, 0]
    rating_j = rating_j - user_data.iloc[j, 0]
    variance = rating_i*rating_j

    reputation = product_data.iloc[common[0], 0].as_matrix()/5
    frequency = product_data.iloc[common[0], 2]/normalize_freq
    val = np.sum(np.sqrt(w_lambda*np.square(np.reciprocal(reputation))+(1-w_lambda)*np.square(np.reciprocal(frequency))))
    return val/ ( max(user_data.iloc[i, 1], 1)*max(user_data.iloc[j, 1], 1) )

#create pandas dataframe
# df = pd.read_csv('dataset/ratings_Electronics_compressed.csv', 
#   header=None, 
#   names=['reviewerID', 'productID', 'overall', 'unixReviewTime'], 
#   sep=',', 
#   dtype={'reviewerID':int, 'productID':int, 'overall':int, 'unixReviewTime':int})