{"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,"_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}]}}