Item-Based Recommendations with Hadoop

Mahout在MapReduce上实现了Item-Based Collaborative Filtering,这里我尝试运行一下。

  1. 安装Hadoop

  2. 从下载Mahout并解压

  3. 准备数据

    下载1 Million MovieLens Dataset,解压得到ratings.dat,用

    sed 's/:😦[0-9]{1,}):😦[0-9]{1})::[0-9]{1,}$/,\1,\2/' ratings.dat

    处理成需要的格式。

  4. 运行

    mahout recommenditembased -s SIMILARITY_LOGLIKELIHOOD -i /path/to/input/file -o /path/to/desired/output -n 25

    参数:

    MAHOUT-JOB: /home/laxe/apple/mahout/mahout-examples-0.11.0-job.jar
    Job-Specific Options:
    --input (-i) input Path to job input directory.
    --output (-o) output The directory pathname for output.
    --numRecommendations (-n) numRecommendations Number of recommendations per user.
    --usersFile usersFile File of users to recommend for.
    --itemsFile itemsFile File of items to recommend for.
    --filterFile (-f) filterFile File containing comma-separated userID,itemID pairs. Used to exclude the item from the recommendations for that user(optional).
    --userItemFile (-uif) userItemFile File containing comma-separated userID,itemID pairs(optional). Used to include only these items into recommendations. Cannot be used together with usersFile or itemsFile.
    --booleanData (-b) booleanData Treat input as without prefvalues.
    --maxPrefsPerUser (-mxp) maxPrefsPerUser Maximum number of preferences considered per user in final recommendation phase.
    --minPrefsPerUser (-mp) minPrefsPerUser Ignore users with less preferences than this in the similarity computation (default: 1).
    --maxSimilaritiesPerItem (-m) maxSimilaritiesPerItem Maximum number of similarities considered per item.
    --maxPrefsInItemSimilarity (-mpiis) maxPrefsInItemSimilarity Max number of preferences to consider per user or item in the item similarity computation phase, users or items with more preferences will be sampled down(default: 500).
    --similarityClassname (-s) similarityClassname Name of distributed similarity measures class to instantiate,
    alternatively use one of the predefined similarities([SIMILARITY_COOCCURRENCE, SIMILARITY_LOGLIKELIHOOD, SIMILARITY_TANIMOTO_COEFFICIENT, SIMILARITY_CITY_BLOCK, SIMILARITY_COSINE, SIMILARITY_PEARSON_CORRELATION, SIMILARITY_EUCLIDEAN_DISTANCE])
    --threshold (-tr) threshold Discard item pairs with a similarity value below this.
    --outputPathForSimilarityMatrix (-opfsm) outputPathForSimilarityMatrix Write the items imilarity matrix to this path(optional).
    --randomSeed randomSeed Use this seed for sampling.
    --sequencefileOutput Write the output into a Sequence File instead of a text file.
    --help (-h) Print out help.
    --tempDir tempDir Intermediate output directory.
    --startPhase startPhase First phase to run.
    --endPhase endPhase Last phase to run specify HDFS directories while running on hadoop; else specify local file system directories.

参考
Introduction to Item-Based Recommendations with Hadoop
mahout分布式:Item-based推荐

相关推荐
TDengine (老段)5 小时前
TDengine 使用最佳实践(2)
大数据·数据库·物联网·时序数据库·iot·tdengine·涛思数据
Deng9452013146 小时前
基于大数据的电力系统故障诊断技术研究
大数据·matplotlib·深度特征提取·随机森林分类算法·标签编码
C182981825757 小时前
分布式ID 与自增区别
分布式
小菜鸡06269 小时前
FlinkSQL通解
大数据·flink
寅鸷10 小时前
es里为什么node和shard不是一对一的关系
大数据·elasticsearch
码字的字节11 小时前
深入解析Hadoop RPC:技术细节与推广应用
hadoop·rpc
码字的字节11 小时前
深入解析Hadoop架构设计:原理、组件与应用
大数据·hadoop·分布式·hadoop架构设计
阿里云大数据AI技术13 小时前
云上AI推理平台全掌握 (3):服务接入与全球调度
大数据·人工智能·深度学习
时序数据说14 小时前
如何选择时序数据库:关键因素与实用指南
大数据·数据库·物联网·时序数据库·iotdb
金牌服务刘14 小时前
选择一个系统作为主数据源的优势与考量
大数据·数据分析·连续集成