实验1—将所有数据处理为矩阵

 trainMatrix, testRatings = load_data('yelp.rating')

def load_data(ratingFile, testRatio=0.1):
    user_count = item_count = 0
    ratings = []
    for line in open(ratingFile):
        arr = line.strip().split()
        user_id = int(arr[0])
        item_id = int(arr[1])
        score = float(arr[2])
        timestamp = long(arr[3])
        ratings.append((user_id, item_id, score, timestamp))
        user_count = max(user_count, user_id)
        item_count = max(item_count, item_id)    
    user_count += 1
    item_count += 1
    
    ratings = sorted(ratings, key=lambda x: x[3])   # sort by timestamp
    
    test_count = int(len(ratings) * testRatio)
    count = 0
    trainMatrix = sp.lil_matrix((user_count, item_count))
    testRatings = []
    for rating in ratings:
        if count < len(ratings) - t