Surprise官方文档练习

https://surprise.readthedocs.io/en/stable/

命令行输入参数：
python run.py -r rating.txt -i item_content.txt -p True

SVD on ml-100k

python3 BaselineMF.py -n_factors=50
from __future__ import (absolute_import, division, print_function, unicode_literals)
from surprise import SVDimport surprise
from surprise import Dataset
from surprise import accuracy
from surprise.model_selection import train_test_split
import osif __name__ == '__main__':datapath = '../SharedData/Movie/ml-100k/ml-100k_ratings.dat' file_path = os.path.expanduser(datapath)reader = surprise.Reader(line_format='user item rating timestamp', sep='::')data = Dataset.load_from_file(file_path, reader=reader)trainset, testset = train_test_split(data, test_size=.20)# Use the famous SVD algorithm.algo = SVD()algo.fit(trainset)predictions = algo.test(testset)# Then compute RMSEaccuracy.rmse(predictions)

SVD on Amazon dataset

python3 BaselineMF.py -n_factors 50
from __future__ import (absolute_import, division, print_function, unicode_literals)
from surprise import SVDimport surprise
from surprise import Dataset
from surprise import accuracy
from surprise.model_selection import train_test_split
import osif __name__ == '__main__':datapath = '../SharedData/Movie/aiv/AIV_sorted_ratings.txt'file_path = os.path.expanduser(datapath)reader = surprise.Reader(line_format='user item rating', sep='::')  # aiv-6data = Dataset.load_from_file(file_path, reader=reader)trainset, testset = train_test_split(data, test_size=.20)# Use the famous SVD algorithm.# algo = SVD()algo.fit(trainset)predictions = algo.test(testset)# Then compute RMSEaccuracy.rmse(predictions)

NMF on Amazon dataset

python3 BaselineMF.py -n_factors 50
from __future__ import (absolute_import, division, print_function, unicode_literals)
from surprise import NMFimport surprise
from surprise import Dataset
from surprise import accuracy
from surprise.model_selection import train_test_split
import osif __name__ == '__main__': datapath = '../SharedData/Movie/aiv/AIV_sorted_ratings.txt'file_path = os.path.expanduser(datapath)reader = surprise.Reader(line_format='user item rating timestamp', sep='::')data = Dataset.load_from_file(file_path, reader=reader)trainset, testset = train_test_split(data, test_size=.40)# Use the famous NMF algorithm.algo = NMF()algo.fit(trainset)predictions = algo.test(testset)# Then compute RMSEaccuracy.rmse(predictions)

PMF on Amazon dataset
You can choose to use an unbiased version of SVD algorithm, simply predicting:

CSDN怎么编辑公式
https://blog.csdn.net/gateway6143/article/details/23134225
在线 LaTeX 公式编辑器
https://private.codecogs.com/latex/eqneditor.php

This is equivalent to Probabilistic Matrix Factorization
(:cite:salakhutdinov2008a, section 2) and can be achieved by setting
the biased parameter to False.

execute the module by commend line: **python3 BaselineMF.py -biased False -n_factors 50**from __future__ import (absolute_import, division, print_function, unicode_literals)
from surprise import SVDimport surprise
from surprise import Dataset
from surprise import accuracy
from surprise.model_selection import train_test_split
import osif __name__ == '__main__':datapath = '../SharedData/Movie/aiv/AIV_sorted_ratings.txt'file_path = os.path.expanduser(datapath)reader = surprise.Reader(line_format='user item rating', sep='::')  # aiv-6data = Dataset.load_from_file(file_path, reader=reader)trainset, testset = train_test_split(data, test_size=.40)# Use the famous SVD algorithm.algo = SVD()  # PMF --biased Falsealgo.fit(trainset)predictions = algo.test(testset)# Then compute RMSEaccuracy.rmse(predictions)

Surprise官方文档练习相关推荐

OpenCV-Python官方文档学习笔记（上）
整理自OpenCV-Python官方文档一. OpenCV-Python Tutorials 1 安装及验证 2 图片读写,展示 3 视频读写,展示 4 绘图功能(绘制几何形状:线.圆.椭圆.矩形. ...
Ant Design 入门-参照官方文档使用组件
微信小程序开发交流qq群 173683895 承接微信小程序开发.扫码加微信. 先来一个按钮组件使用的对比,官方文档的(不能直接用)和实际能用的. 官网demo: import { Tabl ...
坑爹的微软官方文档：SQL无人值守安装
我在部署项目的时候,需要用批处理无人值守安装SQLserver,.Net等组件. 于是查了微软官方文档,其中一项内容如下: http://msdn.microsoft.com/zh-cn/librar ...
Tomcat官方文档关于数据源配置的内容
虽然有网上有网友自己总结的文章,但说明得总是不够清晰,还是参考官方文档理解得比较透彻: http://tomcat.apache.org/tomcat-7.0-doc/jdbc-pool.html h ...
python-66：BS4实例--下载BS4官方文档
2019独角兽企业重金招聘Python工程师标准>>> 前面已经对BS4有了简单的认识和讲解,该讲的都讲了,原本也已经想好了一个实例,但是现在想往后推一推,因为我实在受不了了,我们前 ...
k8s多master建议用几个_Kubernetes 教程之跟着官方文档从零搭建 K8S
前言本文将带领读者一起, 参照者 Kubernetes 官方文档, 对其安装部署进行讲解. Kubernetes 更新迭代很快, 书上.网上等教程可能并不能适用于新版本, 但官方文档能. 阅读这篇文 ...
文件标识符必须为双精度类型的整数值标量_【翻译】VTK官方文档 - vtk文件格式
本文翻译自vtk官方文档:vtk_file_format 文末有链接 VTK提供了许多源对象和编写器对象,用于读取和写入流行的数据文件格式,此外,VTK也提供了自己的文件格式.创建一种数据文件格式的主 ...
深入理解Java 8 Lambda表达式（Oracle官方文档版）
Java 8 问世三年了,9马上也要问世了,所以,嗯,我要开始学8了-- 官方文档:http://docs.oracle.com/javase/tutorial/java/javaOO/lambdae ...
《Redis官方文档》用Redis构建分布式锁
<Redis官方文档>用Redis构建分布式锁用Redis构建分布式锁在不同进程需要互斥地访问共享资源时,分布式锁是一种非常有用的技术手段. 有很多三方库和文章描述如何用Redis实现 ...
python数据科学和机器学习常用库的官方文档
文章目录 Matplotlib Numpy Pandas sklearn sklearn_crfsuite SciPy Matplotlib 进入matplotlib官网地址:https://matp ...

Surprise官方文档练习

Surprise官方文档练习相关推荐

最新文章

热门文章