推荐经典算法实现之SVDBias(python+MovieLen)

# coding:utf-8  
'''
@author: Jason.F
@data: 2019.07.15
@function: Implementation: SVDBias 
           Datatset: Movielen-1m 
           Evaluation: hitradio,ndcg
           Squared loss function with explicit rating.
'''
import pandas as pd
import numpy as np
import math
from collections import defaultdict
import heapq
import random

#1.Loading the  MovienLen dataset, ml-1m
def load_rating_file_as_list(filename):
    ratingList = []
    with open(filename, "r") as f:
        line = f.readline()
        while line != None and line != "":
            arr = line.split("\t")
            user, item = int(arr[0]), int(arr[1])
            ratingList.append([user, item])
            line = f.readline()
    return ratingList

def load_negative_file_as_list(filename):
    negativeList = []
    with open(filename, "r") as f:
        line = f.readline()
        while line != None and line != "":
            arr = line.split("\t")
            negatives = []
            for x in arr[1: ]:
                negatives.append(int(x))
            negativeList.append(negatives)
            line = f.readline()
    return negativeList
def load_rating_file_as_matrix(filename):
    #Read .rating file and Return dok matrix.
    #The first line of .rating file is: num_users\t num_items
    # Get number of users and items
    num_users, num_items = 0, 0
    with open(filename, "r") as f:
        line = f.readline()
        while line != None and line != "":
            arr = line.split("\t")
            u, i = int(arr[0]), int(arr[1])
            num_users = max(num_users, u)
            num_items = max(num_items, i)