{"id":482,"date":"2014-09-13T20:38:00","date_gmt":"2014-09-13T12:38:00","guid":{"rendered":"http:\/\/note.systw.net\/note\/?p=482"},"modified":"2023-11-02T20:39:50","modified_gmt":"2023-11-02T12:39:50","slug":"mahout-recommend","status":"publish","type":"post","link":"https:\/\/systw.net\/note\/archives\/482","title":{"rendered":"Mahout Recommend"},"content":{"rendered":"\n

mahout Itembased Collaborative Filtering<\/p>\n\n\n\n

#mahout recommenditembased<\/strong>
Usage:
-i < input>
-o < output>
-n < number of Recommendations> \u63a8\u6578\u91cf
-b \u4e0d\u9700\u8a55\u5206\u6b04\u4f4d,\u53ea\u8981user,item\u9019\u5169\u500b\u6b04\u4f4d\u5373\u53ef
-s < similarityClassname >\u5e38\u7528\u7684\u6709\u4ee5\u4e0b
\u3000SIMILARITY_COOCCURRENCE,
\u3000SIMILARITY_LOGLIKELIHOOD,
\u3000SIMILARITY_TANIMOTO_COEFFICIENT,
\u3000SIMILARITY_CITY_BLOCK,
\u3000SIMILARITY_COSINE,
\u3000SIMILARITY_PEARSON_CORRELATION,
\u3000SIMILARITY_EUCLIDEAN_DISTANCE<\/p>\n\n\n\n


………………………..<\/p>\n\n\n\n

DEMO<\/p>\n\n\n\n

user x book \u8a55\u50f9\u8868(5\u70ba\u6700\u9ad8\u8a55\u50f9\uff0c1\u70ba\u6700\u4f4e\u8a55\u50f9) <\/p>\n\n\n\n

 <\/td>book 1 <\/td>book 2 <\/td>book 3 <\/td><\/tr>
user 1 <\/td> 5<\/td>4 <\/td>5 <\/td><\/tr>
user 2 <\/td> 4 <\/td>5 <\/td>4 <\/td><\/tr>
user 3 <\/td> 5<\/td>4 <\/td> <\/td><\/tr>
user 4 <\/td> 1<\/td>2 <\/td> <\/td><\/tr>
user 5 <\/td> 2 <\/td>1 <\/td>1 <\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n


#vi recom.data<\/strong>
1,1,5
1,2,4
1,3,5
2,1,4
2,2,5
2,3,4
3,1,5
3,2,4
4,1,1
4,2,2
5,1,2
5,2,1
5,3,1<\/p>\n\n\n\n

# hadoop fs -mkdir testdata
# hadoop fs -put recom.data testdata
# hadoop fs -ls -R testdata<\/strong>
-rw-r–r– 3 root hdfs 288374 2014-02-05 21:53 testdata\/recom.data<\/p>\n\n\n\n

#mahout recommenditembased -i testdata -o output -s SIMILARITY_EUCLIDEAN_DISTANCE<\/strong>
…omit…
{–booleanData=[false], –endPhase=[2147483647], –input=[tasteinput], –maxPrefsPerUser=[10], –maxPrefsPerUserInItemSimilarity=[1000], –maxSimilaritiesPerItem=[100], –minPrefsPerUser=[1], –numRecommendations=[10], –output=[tasteoutput], –similarityClassname=[SIMILARITY_EUCLIDEAN_DISTANCE], –startPhase=[0], –tempDir=[temp]}
14\/03\/02 09:52:37 INFO common.AbstractJob: Command line arguments: {–booleanData=[false], –endPhase=[2147483647], –input=[tasteinput], –maxPrefsPerUser=[1000], –minPrefsPerUser=[1], –output=[temp\/preparePreferenceMatrix], –ratingShift=[0.0], –startPhase=[0], –tempDir=[temp]}
…omit…
File Input Format Counters
Bytes Read=287
File Output Format Counters
Bytes Written=32
14\/09\/04 05:46:56 INFO driver.MahoutDriver: Program took 434965 ms (Minutes: 7.249416666666667)<\/p>\n\n\n\n


#hadoop fs -cat output\/part-r-00000
<\/strong>3 [3:4.4787264]
4 [3:1.5212735]<\/p>\n","protected":false},"excerpt":{"rendered":"

mahout Itembased Collaborative …<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"","fifu_image_alt":"","_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":false,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[13],"tags":[],"class_list":["post-482","post","type-post","status-publish","format-standard","hentry","category-dataanalysis"],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"jetpack-related-posts":[{"id":486,"url":"https:\/\/systw.net\/note\/archives\/486","url_meta":{"origin":482,"position":0},"title":"Mahout Logistic","author":"raymond","date":"2014 \u5e74 9 \u6708 11 \u65e5","format":false,"excerpt":"mahout logistic regressionmahout\u7684logistic regressi\u2026","rel":"","context":"\u5728\u300c\u6578\u64da\u5206\u6790\u300d\u4e2d","block_context":{"text":"\u6578\u64da\u5206\u6790","link":"https:\/\/systw.net\/note\/archives\/category\/dataanalysis"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":488,"url":"https:\/\/systw.net\/note\/archives\/488","url_meta":{"origin":482,"position":1},"title":"Mahout FPgrowth","author":"raymond","date":"2014 \u5e74 9 \u6708 18 \u65e5","format":false,"excerpt":"fpgrowth\u904b\u4f5c\u539f\u7406\u53ef\u53c3\u8003frequent pattern analysis( http:\/\/s\u2026","rel":"","context":"\u5728\u300c\u6578\u64da\u5206\u6790\u300d\u4e2d","block_context":{"text":"\u6578\u64da\u5206\u6790","link":"https:\/\/systw.net\/note\/archives\/category\/dataanalysis"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":480,"url":"https:\/\/systw.net\/note\/archives\/480","url_meta":{"origin":482,"position":2},"title":"Mahout Clustering","author":"raymond","date":"2014 \u5e74 9 \u6708 13 \u65e5","format":false,"excerpt":"Canopy\u5206\u7fa4\u6f14\u7b97\u6cd5#mahout org.apache.mahout.clustering.sy\u2026","rel":"","context":"\u5728\u300c\u6578\u64da\u5206\u6790\u300d\u4e2d","block_context":{"text":"\u6578\u64da\u5206\u6790","link":"https:\/\/systw.net\/note\/archives\/category\/dataanalysis"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":583,"url":"https:\/\/systw.net\/note\/archives\/583","url_meta":{"origin":482,"position":3},"title":"SQL DDL","author":"raymond","date":"2010 \u5e74 8 \u6708 24 \u65e5","format":false,"excerpt":"DDL \u5efa\u7acb\u8cc7\u6599\u8868create table < tablename>(< colu\u2026","rel":"","context":"\u5728\u300c\u8cc7\u6599\u5eab\u300d\u4e2d","block_context":{"text":"\u8cc7\u6599\u5eab","link":"https:\/\/systw.net\/note\/archives\/category\/develop\/database"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":740,"url":"https:\/\/systw.net\/note\/archives\/740","url_meta":{"origin":482,"position":4},"title":"\u7b97\u8853\u904b\u7b97\u7684\u65b9\u6cd5\u8207\u96fb\u8def","author":"raymond","date":"2009 \u5e74 10 \u6708 26 \u65e5","format":false,"excerpt":"\u6574\u6578\u7684\u8868\u793a\u6cd5\u6574\u6578\u7684\u8868\u793a\u6cd5\u6c7a\u5b9a\u904b\u7b97\u65b9\u6cd5\u6574\u6578\u7684\u9577\u5ea6\u6c7a\u5b9a\u53ef\u8868\u793a\u7bc4\u570d\u6574\u6578\u9577\u5ea6=\u7b97\u8853\u908f\u8f2f\u904b\u7b97\u55ae\u5143\u7684\u8cc7\u6599\u9577\u5ea6=w\u2026","rel":"","context":"\u5728\u300c\u8a08\u7b97\u6a5f\u7d44\u7e54\u8207\u7d50\u69cb\u300d\u4e2d","block_context":{"text":"\u8a08\u7b97\u6a5f\u7d44\u7e54\u8207\u7d50\u69cb","link":"https:\/\/systw.net\/note\/archives\/category\/system\/computerarchitecture"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":1232,"url":"https:\/\/systw.net\/note\/archives\/1232","url_meta":{"origin":482,"position":5},"title":"SQLi for Examining the DB","author":"raymond","date":"2023 \u5e74 2 \u6708 16 \u65e5","format":false,"excerpt":"\u70ba\u4e86\u5229\u7528 SQL \u6ce8\u5165\u6f0f\u6d1e\uff0c\u901a\u5e38\u9700\u8981\u5c0b\u627e\u6709\u95dc\u8cc7\u6599\u5eab\u7684\u8cc7\u8a0a\uff0c\u50cf\u662f\u6578\u64da\u5eab\u985e\u578b\u8207\u7248\u672c\uff0c\u4ee5\u53ca\u8cc7\u6599\u8868\u4fe1\u606f \u53d6\u5f97\u2026","rel":"","context":"\u5728\u300cServerSide\u300d\u4e2d","block_context":{"text":"ServerSide","link":"https:\/\/systw.net\/note\/archives\/category\/hackerthreat\/serverside"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]}],"_links":{"self":[{"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/posts\/482","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/comments?post=482"}],"version-history":[{"count":0,"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/posts\/482\/revisions"}],"wp:attachment":[{"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/media?parent=482"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/categories?post=482"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/tags?post=482"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}