資源簡介
Diff-FSPM-master.zip
代碼片段和文件信息
#!?/usr/bin/env?python
#?encoding:?utf-8
‘‘‘?
Created?on?Apr?24?2014
@summary:?Diff-FSPM?Algorithm
????-?Usage:?python?Main.py
????-?Input?parameters:?epsilon?l_opt?dataset?min_sup
@author:?Lu?Guoqing??
‘‘‘
import?sys
sys.path.append(?‘conf‘?)
sys.path.append(?‘lib‘?)
import?Sanitizer
from?Reconstruction?import?*
from?NGramSet?import?*
from?GetOptLength?import?*?
from?base.dp_log?import?dplog
import?dp_conf?as?conf
def?init():
????‘‘‘
????@summary:?Initialization
????
????‘‘‘
????dplog.init_logger(?conf.LOG_FILE?)
def?Diff_FSPM():
????‘‘‘
????Diff-FSPM?算法分為如下3個步驟:
????????-?原始序列數據集局部轉換
????????????-?獲取最優序列長度?l_opt????????????ok
????????????-?截斷原始序列數據集????????????????ok
????????-?層次遍歷構建繞動閉前綴序列樹
????????????-?min_sup?約束剪枝
????????????-?閉等價關系?剪枝
????????????-?預測計數值?PK.?噪音計數值
????????-?描述上是挖掘FSP樹?實際直接輸出結果集
????????????
????@summary:?Diff-FSPM?algorithm
????‘‘‘
????dplog.info(?“?===?Phase?1:?Decomposing?input?sequence?dataset?to?n-grams?(%d<=n<=%d)?Begin?===“?%?(1?conf.l_opt)?)
????conf.l_opt?=?GetOptSeqLength(conf.dataset?conf.epsilon?mechanism=“Exponential“)
????ngram_set?=?NGramSet(?int(conf.l_opt)?N_max=int(conf.n_max)?)
????ngram_set.load_dataset(?conf.dataset?conf.dataset_ngrams?%?(conf.l_opt)?)
????dplog.info(?“?===?Phase?1:?Decomposing?input?sequence?dataset?to?n-grams?(%d<=n<=%d)?End?===“?%?(1?conf.l_opt)?)
????dplog.info(?“?===?Phase?2:?Sanitizing?n-grams?to?build?noisy?frequent?sequential?patterns?Tree?Begin?===“?)
????ngram_set?=?Sanitizer.ngram(?ngram_set?conf.n_max?conf.epsilon?conf.l_opt?conf.min_sup)
????ngram_set.dump(?conf.dataset_noisy?%?(conf.l_opt?conf.epsilon))
????dplog.info(?“?===?Phase?2:?Sanitizing?n-grams?to?build?noisy?frequent?sequential?patterns?Tree?End?===“?)
????
????dplog.info(?“?===?Phase?3:?Synthetic?frequent?sequential?patterns?from?santized?n-grams?Begin?===“?)
????factory?=?Reconstruction(?ngram_set?conf.min_sup?)
????factory.extend()
????factory.ngramset.dump(?conf.dataset_result?%?(conf.l_opt?conf.epsilon))
????dplog.info(?“?===?Phase?3:?Synthetic?frequent?sequential?patterns?from?santized?n-grams?End?===“?)
def?main():
????‘‘‘
????@summary:?main?entry
????‘‘‘
????
????init()
????
????logstr?=?“+“*8?+?“????Start?Diff-FSPM?Algorithm????“?+?“+“*8
????dplog.info(““)
????dplog.info(“+“?*?len(logstr))
????dplog.info(logstr)
????dplog.info(“+“?*?len(logstr))
????dplog.info(““)
????dplog.debug(“original?sequence?database?:?(%s)“%(conf.dataset))
????dplog.debug(“differential?privacy?budget?:?(%s)“%(conf.epsilon))
????dplog.debug(“minmum?support?value?:?(%s)“%(conf.min_sup))
????
????Diff_FSPM()
????logstr?=?“+“*8?+?“?????End?Diff-FSPM?Algorithm?????“?+?“+“*8
????dplog.info(““)
????dplog.info(“+“?*?len(logstr))
????dplog.success(logstr)
????dplog.info(“+“?*?len(logstr))
????dplog.info(““)
????
if?__name__?==?“__main__“:
????
????main()
?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2014-05-22?03:04??Diff-FSPM-master\
?????文件?????????483??2014-05-22?03:04??Diff-FSPM-master\.gitattributes
?????文件????????2643??2014-05-22?03:04??Diff-FSPM-master\.gitignore
?????文件????????3051??2014-05-22?03:04??Diff-FSPM-master\Main.py
?????文件?????????580??2014-05-22?03:04??Diff-FSPM-master\README.md
?????文件????????3460??2014-05-22?03:04??Diff-FSPM-master\Reconstruction.py
?????文件????????7847??2014-05-22?03:04??Diff-FSPM-master\Sanitizer.py
?????目錄???????????0??2014-05-22?03:04??Diff-FSPM-master\algorithm\
?????目錄???????????0??2014-05-22?03:04??Diff-FSPM-master\algorithm\ngramspan\
?????文件????????1906??2014-05-22?03:04??Diff-FSPM-master\algorithm\ngramspan\Main.py
?????目錄???????????0??2014-05-22?03:04??Diff-FSPM-master\algorithm\ngramspan\data\
?????文件????????5691??2014-05-22?03:04??Diff-FSPM-master\algorithm\ngramspan\data\msnbc-original-20grams.dat
?????文件???????13219??2014-05-22?03:04??Diff-FSPM-master\algorithm\ngramspan\data\msnbc-original-32grams.dat
?????文件????????3508??2014-05-22?03:04??Diff-FSPM-master\algorithm\ngramspan\data\msnbc-original-5grams.dat
?????文件????11591683??2014-05-22?03:04??Diff-FSPM-master\algorithm\ngramspan\data\msnbc.dat
?????目錄???????????0??2014-05-22?03:04??Diff-FSPM-master\algorithm\ngramspan\lib\
?????文件????????6659??2014-05-22?03:04??Diff-FSPM-master\algorithm\ngramspan\lib\NGramSet.py
?????文件?????????565??2014-05-22?03:04??Diff-FSPM-master\algorithm\ngramspan\lib\ProgressBar.py
?????文件????????1097??2014-05-22?03:04??Diff-FSPM-master\algorithm\ngramspan\lib\Utils.py
?????文件???????????0??2014-05-22?03:04??Diff-FSPM-master\algorithm\ngramspan\lib\__init__.py
?????目錄???????????0??2014-05-22?03:04??Diff-FSPM-master\algorithm\utility\
?????文件?????????160??2014-05-22?03:04??Diff-FSPM-master\algorithm\utility\run.sh
?????文件????????6041??2014-05-22?03:04??Diff-FSPM-master\algorithm\utility\utility.py
?????目錄???????????0??2014-05-22?03:04??Diff-FSPM-master\conf\
?????文件???????????0??2014-05-22?03:04??Diff-FSPM-master\conf\__init__.py
?????文件????????1536??2014-05-22?03:04??Diff-FSPM-master\conf\dp_conf.py
?????目錄???????????0??2014-05-22?03:04??Diff-FSPM-master\data\
?????目錄???????????0??2014-05-22?03:04??Diff-FSPM-master\data\input\
?????文件??????957429??2014-05-22?03:04??Diff-FSPM-master\data\input\BMS1_spmf.seq
?????文件?????4022055??2014-05-22?03:04??Diff-FSPM-master\data\input\T10I4D100K.dat
?????文件????35509823??2014-05-22?03:04??Diff-FSPM-master\data\input\accidents.dat
............此處省略89個文件信息
評論
共有 條評論