fpgrowth\u904b\u4f5c\u539f\u7406\u53ef\u53c3\u8003
frequent pattern analysis( https:\/\/systw.net\/note\/af\/sblog\/more.php?id=265 )<\/p>\n\n\n\n
…<\/p>\n\n\n\n demo<\/p>\n\n\n\n #wget http:\/\/fimi.ua.ac.be\/data\/retail.dat #mahout fpg -i retail\/retail.dat -o retail\/patterns -method mapreduce -regex [‘ ‘] -s 2<\/strong> # hadoop fs -ls retail\/patterns<\/strong> \u986f\u793a\u7d50\u679c \u8aaa\u660e fpgrowth\u904b\u4f5c\u539f\u7406\u53ef\u53c3\u8003frequent patter …<\/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-488","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":482,"url":"https:\/\/systw.net\/note\/archives\/482","url_meta":{"origin":488,"position":0},"title":"Mahout Recommend","author":"raymond","date":"2014 \u5e74 9 \u6708 13 \u65e5","format":false,"excerpt":"mahout Itembased Collaborative Filtering #mahout r\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":486,"url":"https:\/\/systw.net\/note\/archives\/486","url_meta":{"origin":488,"position":1},"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":480,"url":"https:\/\/systw.net\/note\/archives\/480","url_meta":{"origin":488,"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":1776,"url":"https:\/\/systw.net\/note\/archives\/1776","url_meta":{"origin":488,"position":3},"title":"ffuf","author":"raymond","date":"2023 \u5e74 4 \u6708 10 \u65e5","format":false,"excerpt":"ffuf(Fuzz Faster U Fool)\u662f\u7528\u65bcWeb \u6a21\u7cca\u6e2c\u8a66\u7684\u5de5\u5177\uff0c\u53ef\u7528\u65bc\u76ee\u9304\u548c\u53c3\u6578\u6a21\u7cca\u6e2c\u2026","rel":"","context":"\u5728\u300cred team\u300d\u4e2d","block_context":{"text":"red team","link":"https:\/\/systw.net\/note\/archives\/category\/securitytool\/red-team"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":677,"url":"https:\/\/systw.net\/note\/archives\/677","url_meta":{"origin":488,"position":4},"title":"Squid Proxy","author":"raymond","date":"2012 \u5e74 11 \u6708 21 \u65e5","format":false,"excerpt":"Squid(http:\/\/www.squid-cache.org)Squid=\u4e3b\u8981\u670d\u52d9\u7a0b\u5f0f+DNS\u67e5\u2026","rel":"","context":"\u5728\u300cLinux\u670d\u52d9\u300d\u4e2d","block_context":{"text":"Linux\u670d\u52d9","link":"https:\/\/systw.net\/note\/archives\/category\/system\/linuxservice"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":271,"url":"https:\/\/systw.net\/note\/archives\/271","url_meta":{"origin":488,"position":5},"title":"SQLMap basic","author":"raymond","date":"2019 \u5e74 10 \u6708 21 \u65e5","format":false,"excerpt":"sqlmap\u662f\u4e00\u4e2a\u958b\u6e90\u7684\u6e17\u900f\u6e2c\u8a66\u5de5\u5177\uff0c\u53ef\u900f\u904esql injection\u7684\u624b\u6cd5\u505a\u81ea\u52d5\u5316\u6aa2\u6e2c\uff0c\u6aa2\u6e2c\u7bc4\u570d\u5305\u2026","rel":"","context":"\u5728\u300cred team\u300d\u4e2d","block_context":{"text":"red team","link":"https:\/\/systw.net\/note\/archives\/category\/securitytool\/red-team"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]}],"_links":{"self":[{"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/posts\/488","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=488"}],"version-history":[{"count":0,"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/posts\/488\/revisions"}],"wp:attachment":[{"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/media?parent=488"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/categories?post=488"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/systw.net\/note\/wp-json\/wp\/v2\/tags?post=488"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
mahout fpg<\/strong>
\u5e38\u898b\u53c3\u6578\u5982\u4e0b
-k: \u627e\u51fa\u524dn\u9805pattern, default is 50
-regex: This is the regular expression to split every line
-method: \u4f7f\u7528sequential \u6216 MapReduce
-s < minSupport>: This is the minimum number of times a transaction should be present<\/p>\n\n\n\n
#hadoop fs -mkdir retail
#hadoop fs -put retail.dat retail\/retail.dat
#hadoop fs -ls retail<\/strong>
-rw-r–r– 3 root hdfs 101891 2014-02-05 11:44 retail\/retail.dat<\/p>\n\n\n\n
…omit…
14\/02\/05 22:35:15 INFO driver.MahoutDriver: Program took 415 ms (Minutes: 0.0069166666666666664)<\/p>\n\n\n\n
Found 4 items
-rw-r–r– 3 root hdfs 101891 2014-02-05 11:44 retail\/patterns\/fList
drwxr-xr-x – root hdfs 0 2014-02-05 11:44 retail\/patterns\/fpgrowth
drwxr-xr-x – root hdfs 0 2014-02-05 11:45 retail\/patterns\/frequentpatterns
drwxr-xr-x – root hdfs 0 2014-02-05 11:44 retail\/patterns\/parallelcounting
ps:
fList: These are sequence files that contain the occurrence of the item for every item inside the
transaction database<\/p>\n\n\n\n
#mahout seqdumper -i retail\/patterns\/fpgrowth -o patterns.txt
#cat patterns.txt<\/strong>
…omit…
Key: 0: Value: ([0],26), ([39, 0],14), ([39, 48, 41, 32, 616, 0, 1314],2), ([39, 41, 0,])
Key: 954: Value: ([39, 954],2)
Key: 953: Value: ([39, 953],2)
Key: 933: Value: ([933],2)
Count: 4849<\/p>\n\n\n\n
Key: 0: Value: ([0],26), ([39, 0],14), ([39, 48, 41, 32, 616, 0, 1314],2), ([39, 41, 0,])
It describes the number of associations found between item 0 and others within the whole transaction database.
([0],26) means that the item 0 appears in 26 transactions.
([39,0],14) confirms that the item 0 coupled with the item 39 appears in 14 transactions<\/p>\n","protected":false},"excerpt":{"rendered":"