資源簡介
ID3算法及蘑菇數(shù)據(jù)集,幼兒園數(shù)據(jù)集
ID3算法及蘑菇數(shù)據(jù)集,幼兒園數(shù)據(jù)集
ID3算法及蘑菇數(shù)據(jù)集,幼兒園數(shù)據(jù)集
代碼片段和文件信息
import?numpy?as?np
import?copy
import?pickle
from?sklearn.model_selection?import?train_test_split
def?storedata(datain?filename):
????fw?=?open(filename?‘wb+‘)
????pickle.dump(datain?fw?protocol=-1)
????fw.close()
def?grabdata(filename):
????fr?=?open(filename?‘rb+‘)
????return?pickle.load(fr)
“““
def?datasp(filename?testfile?trainfile?percent):
????dataset?=?grabdata(filename)
????datasetnew?=?copy.deepcopy(dataset)
????for?simple?in?dataset:
????????if?dataset.count(simple)?!=?1:
????????????datasetnew.remove(simple)
????splitdata?=?{}
????for?simple?in?datasetnew:
????????if?simple[-1]?not?in?splitdata.keys():
????????????data?=?[]
????????????splitdata[simple[-1]]?=?data
????????????splitdata[simple[-1]].append(simple)
????testdata?=?[]
????traindata?=?copy.deepcopy(datasetnew)
????for?label?in?splitdata.keys():
????????for?simple?in?splitdata[label]:
????????????if?np.random.randint(1?100)?<=?percent:
????????????????testdata.append(simple)
????????????????traindata.remove(simple)
????storedata(testdata?testfile)
????storedata(traindata?trainfile)
datasp(‘mushroomdata100_pickle.txt‘?‘mushroomtest100_pickle.txt‘?‘mushroomtrain100_pickle.txt‘?70)
te?=?grabdata(‘mushroomtest100_pickle.txt‘)
tr?=?grabdata(‘mushroomtrain100_pickle.txt‘)
print(‘testdata:\n‘?len(te)?‘\n‘?te)
print(‘traindata:\n‘?len(tr)?‘\n‘?tr)
“““
dataset?=?grabdata(‘pickle_nursery.txt‘)
traindata?testdata?=?train_test_split(dataset?test_size=0.1?random_state=None?stratify=None)
storedata(testdata?‘pickle_nurserytest.txt‘)
storedata(traindata?‘pickle_nurserytrain.txt‘)
print(testdata‘\n‘)
print(traindata?‘\n‘)
?屬性????????????大小?????日期????時(shí)間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2017-09-05?22:15??ID3\
?????目錄???????????0??2017-09-05?22:13??ID3\ID3\
?????目錄???????????0??2017-09-05?22:14??ID3\ID3\.idea\
?????文件?????????528??2017-08-30?21:15??ID3\ID3\.idea\ID3_03.iml
?????目錄???????????0??2017-09-03?20:48??ID3\ID3\.idea\inspectionProfiles\
?????文件?????????404??2017-09-03?18:29??ID3\ID3\.idea\inspectionProfiles\Project_Default.xm
?????文件?????????221??2017-08-30?21:15??ID3\ID3\.idea\misc.xm
?????文件?????????264??2017-08-18?14:50??ID3\ID3\.idea\modules.xm
?????文件???????34573??2017-09-05?22:14??ID3\ID3\.idea\workspace.xm
?????文件????????1691??2017-09-05?22:02??ID3\ID3\datasplit.py
?????文件?????????363??2017-09-05?22:06??ID3\ID3\pk.py
?????文件????????5905??2017-09-05?22:11??ID3\ID3\treeMake.py
?????文件????????4131??2017-09-02?15:04??ID3\ID3\treePlotter.py
?????文件?????????764??2017-09-05?21:58??ID3\ID3\treeUse.py
?????目錄???????????0??2017-09-05?22:06??ID3\ID3\__pycache__\
?????文件??????309279??2017-09-03?16:29??ID3\ID3\__pycache__\pickle.cpython-36.pyc
?????文件?????????477??2017-09-05?22:06??ID3\ID3\__pycache__\pk.cpython-36.pyc
?????文件????????2768??2017-09-02?15:04??ID3\ID3\__pycache__\treePlotter.cpython-36.pyc
?????目錄???????????0??2017-09-05?22:16??ID3\MLiA_SourceCode\
?????目錄???????????0??2017-09-05?22:15??ID3\MLiA_SourceCode\Ch02\
?????文件???????35725??2012-03-01?15:40??ID3\MLiA_SourceCode\Ch02\datingTestSet.txt
?????文件???????27067??2012-03-01?15:39??ID3\MLiA_SourceCode\Ch02\datingTestSet2.txt
?????文件??????739988??2011-05-04?15:43??ID3\MLiA_SourceCode\Ch02\digits.zip
?????目錄???????????0??2017-09-05?22:15??ID3\MLiA_SourceCode\Ch02\EXTRAS\
?????文件????????2052??2010-10-27?08:32??ID3\MLiA_SourceCode\Ch02\EXTRAS\createDist.py
?????文件????????2162??2011-05-31?10:56??ID3\MLiA_SourceCode\Ch02\EXTRAS\createDist2.py
?????文件?????????561??2011-05-31?10:52??ID3\MLiA_SourceCode\Ch02\EXTRAS\createFirstPlot.py
?????文件?????????522??2011-04-29?08:14??ID3\MLiA_SourceCode\Ch02\EXTRAS\README.txt
?????文件???????????0??2010-10-27?08:42??ID3\MLiA_SourceCode\Ch02\EXTRAS\testSet.txt
?????文件????????4268??2011-05-31?11:45??ID3\MLiA_SourceCode\Ch02\kNN.py
?????文件????????4500??2011-05-31?11:07??ID3\MLiA_SourceCode\Ch02\kNN.pyc
............此處省略211個(gè)文件信息
評(píng)論
共有 條評(píng)論