2013-12-17 25 views
0

每當我在讀我的CSV文件正在一個輸出這樣我們如何去除輸出內容中的不需要的值?

['At Home', '0.0023042115'] 
['Family', '0.0001275907'] 
['Time', '0.0005935242'] 
['Work', '0.0012768792'] 
['Past Actions', '0.0001357854'] 
['Games', '0.0032438747'] 
['Internet', '0.0008639338'] 
['Location', '0.00'] 
['Fun', '0.0035238147'] 
['Food/Clothes', '0.0080727641'] 
['Poetic', '4.691183298570359e+AC0-06'] 
['Books/Movies', '2.1300704813858456e+AC0-06'] 
['Religion', '0'] 
['Romance', '0.0005935134'] 
['Swearing', '3.217031124518803e+AC0-05'] 
['Politics', '0.0075492962'] 
['Music', '7.224535286344926e+AC0-05'] 
['School', '2.0853873920424672e+AC0-06'] 
['Business', '0.0056130667'] 
['end+AF8-with+AF8-able', '0.001345825'] 
['end+AF8-with+AF8-al', '0.0024110161'] 
['end+AF8-with+AF8-ful', '0.0013767934'] 
['end+AF8-with+AF8-ible', '0.0022098726'] 
['end+AF8-with+AF8-ic', '0.0023514306'] 
['end+AF8-with+AF8-ive', '0.0037701555'] 
['end+AF8-with+AF8-less', '0.0010593697'] 
['end+AF8AXw-with+AF8-ly', '7.89403499813603e+AC0-05'] 
['end+AF8-with+AF8-ous', '9.940547915993254e+AC0-05'] 
['sorry+AF8-word', '5.662225052323463e+AC0-05'] 
['Starting+AF8-with+AF8-Apolog', '0.0003042999'] 
['Help+ACE-', '0.0003773039'] 
['I understand', '0.0001320813'] 
['+ACI-Attention', ' please+ACE-+ACI-', '0'] 
['+ACI-Ok', ' I see+ACI-', '0'] 
['Damn+ACE-', '0'] 
['How sweet+ACE-', '2.0201595541210387e+AC0-06'] 
["That's too bad", '0'] 
['Come on+ACE-', '0.0014614134'] 
['Whatever', '0'] 
["That's bad", '0'] 
["It's cold", '0'] 
["That's dumb", '0'] 
['Help+ACE-', '0.0003773039'] 
['Oh no+ACE-', '0'] 
['What?', '0'] 
['Is that right?', '0'] 
['Disgusting', '0.0001809821'] 
['This is hopeless', '0'] 
['Really?', '0.0004255353'] 
["I'm angry", '0'] 
['I wonder', '0'] 
["I don't like this", '0'] 
['Really?', '0.0004255353'] 
["Let's celebrate+ACE-", '0'] 
['Disgusting', '0.0001809821'] 
["I don't know", '0'] 
['Yes', '0'] 
['Lovely', '0.0001642891'] 
["I'm so evil+ACE-", '0'] 
['No', '0.0005265143'] 
['+ACI-No', " it isn't+ACE-/Did not+ACE-+ACI-", '0'] 
['I see', '0.0013579047'] 
['Fancy+ACE-', '0'] 
['Wonderful+ACE-', '0.0006769606'] 
["I'm exerting myself", '0'] 
["I didn't mean to do that", '0'] 
['That hurts', '0'] 
['+ACI-Hey', ' you+ACE-+ACI-', '0'] 
['Oh no...', '0'] 
['It stinks+ACE-', '0'] 
["That's nothing", '0'] 
['That was close+ACE-', '0.0010088511'] 
['+ACI-Whispering+ACE-Hey', ' you+ACE-+ACI-', '0'] 
["I can't believe this+ACE-", '0'] 
['Be quiet', '0'] 
['Go away', '0'] 
['Disappointing', '0'] 
['Yes', '0'] 
['Oh no+ACE-', '0'] 
['No', '0.0005265143'] 
['+ACI-Wait', " I'm thinking+ACI-", '0'] 
['This is fun+ACE-', '0.0016848004'] 
['Unbelievable+ACE-', '0'] 
['Amazing+ACE-', '0.0005387173'] 
["Let's celebrate+ACE-", '0'] 
['Yes+ACE-', '0.0003639123'] 
['Yes+ACE-', '0.0003639123'] 
["I'm excited+ACE-", '0'] 
['Hey you+ACE-', '0'] 
['+ACI-Yes', ' it is+ACE- Or Did so+ACE-+ACI-', '0'] 
['Disgusting+ACE-', '0'] 
['+ACI-Haha', ' well said+ACE-+ACI-', '0'] 
["+ACI-+AFs-'CD'", " 'CC'", " 'CD'+AF0-+ACI-", '0.0003041055'] 
["+ACI-+AFs-'DT'", " 'CC'", " 'CD'+AF0-+ACI-", '0.0003041055'] 
["+ACI-+AFs-'EX'", " 'CC'", " 'CD'+AF0-+ACI-", '0.0002694121'] 
["+ACI-+AFs-'JJ'", " 'CC'", " 'CD'+AF0-+ACI-", '0.0003041055'] 
["+ACI-+AFs-'JJR'", " 'CC'", " 'CD'+AF0-+ACI-", '0.0003427676'] 
["+ACI-+AFs-'JJS'", " 'CC'", " 'CD'+AF0-+ACI-", '0.0029483492'] 
["+ACI-+AFs-'NN'", " 'CC'", " 'CD'+AF0-+ACI-", '0.0001060578'] 
["+ACI-+AFs-'RBR'", " 'CC'", " 'CD'+AF0-+ACI-", '0.0002081336'] 
["+ACI-+AFs-'VBD'", " 'CC'", " 'CD'+AF0-+ACI-", '0.0001925713'] 
["+ACI-+AFs-'VBG'", " 'CC'", " 'CD'+AF0-+ACI-", '9.068096527379936e+AC0-06'] 
["+ACI-+AFs-'VBN'", " 'CC'", " 'CD'+AF0-+ACI-", '0.0011585203'] 
["+ACI-+AFs-'VBP'", " 'CC'", " 'CD'+AF0-+ACI-", '0.000277034'] 
["+ACI-+AFs-'VBZ'", " 'CC'", " 'CD'+AF0-+ACI-", '0.0009891459'] 
["+ACI-+AFs-'WDT'", " 'CC'", " 'CD'+AF0-+ACI-", '0.0015045239'] 
["+ACI-+AFs-'WP'", " 'CC'", " 'CD'+AF0-+ACI-", '0.0013222853'] 
["+ACI-+AFs-'CD'", " 'CD'", " 'DT'+AF0-+ACI-", '0.0002694121'] 
["+ACI-+AFs-'DT'", " 'CD'", " 'DT'+AF0-+ACI-", '0.0003605792'] 
["+ACI-+AFs-'EX'", " 'CD'", " 'DT'+AF0-+ACI-", '0.0003605792'] 
["+ACI-+AFs-'JJ'", " 'CD'", " 'DT'+AF0-+ACI-", '0.0003605792'] 
["+ACI-+AFs-'JJR'", " 'CD'", " 'DT'+AF0-+ACI-", '0.0003623141'] 
["+ACI-+AFs-'JJS'", " 'CD'", " 'DT'+AF0-+ACI-", '0.0028113198'] 
["+ACI-+AFs-'NN'", " 'CD'", " 'DT'+AF0-+ACI-", '0.0002380414'] 
["+ACI-+AFs-'RBR'", " 'CD'", " 'DT'+AF0-+ACI-", '0.0002524272'] 
["+ACI-+AFs-'VBD'", " 'CD'", " 'DT'+AF0-+ACI-", '0.0002694121'] 
["+ACI-+AFs-'VBG'", " 'CD'", " 'DT'+AF0-+ACI-", '6.8763849316489e+AC0-07'] 
["+ACI-+AFs-'VBN'", " 'CD'", " 'DT'+AF0-+ACI-", '0.0013536177'] 
["+ACI-+AFs-'VBP'", " 'CD'", " 'DT'+AF0-+ACI-", '0.000228122'] 
["+ACI-+AFs-'VBZ'", " 'CD'", " 'DT'+AF0-+ACI-", '0.0011060342'] 
["+ACI-+AFs-'WDT'", " 'CD'", " 'DT'+AF0-+ACI-", '0.0018250935'] 
["+ACI-+AFs-'WP'", " 'CD'", " 'DT'+AF0-+ACI-", '0.0013798266'] 
["+ACI-+AFs-'CD'", " 'DT'", " 'EX'+AF0-+ACI-", '0.0005956604'] 
["+ACI-+AFs-'DT'", " 'DT'", " 'EX'+AF0-+ACI-", '0.000739265'] 
["+ACI-+AFs-'EX'", " 'DT'", " 'EX'+AF0-+ACI-", '0.0005909166'] 
["+ACI-+AFs-'JJ'", " 'DT'", " 'EX'+AF0-+ACI-", '0.0005909166'] 
["+ACI-+AFs-'JJR'", " 'DT'", " 'EX'+AF0-+ACI-", '0.000548832'] 
["+ACI-+AFs-'NN'", " 'DT'", " 'EX'+AF0-+ACI-", '0.0007274935'] 
["+ACI-+AFs-'RBR'", " 'DT'", " 'EX'+AF0-+ACI-", '0.0006394694'] 
["+ACI-+AFs-'VBD'", " 'DT'", " 'EX'+AF0-+ACI-", '0.0003994929'] 
["+ACI-+AFs-'VBG'", " 'DT'", " 'EX'+AF0-+ACI-", '0.000165679'] 
["+ACI-+AFs-'VBN'", " 'DT'", " 'EX'+AF0-+ACI-", '0.0007330517'] 
["+ACI-+AFs-'VBP'", " 'DT'", " 'EX'+AF0-+ACI-", '0.0003164934'] 
["+ACI-+AFs-'VBZ'", " 'DT'", " 'EX'+AF0-+ACI-", '0.0006952293'] 
["+ACI-+AFs-'WDT'", " 'DT'", " 'EX'+AF0-+ACI-", '0.0009373422'] 
["+ACI-+AFs-'CD'", " 'IN'", " 'JJ'+AF0-+ACI-", '2.3855039963693414e+AC0-05'] 
["+ACI-+AFs-'DT'", " 'IN'", " 'JJ'+AF0-+ACI-", '0.0004035301'] 
["+ACI-+AFs-'EX'", " 'IN'", " 'JJ'+AF0-+ACI-", '3.612301342137506e+AC0-05'] 
["+ACI-+AFs-'JJ'", " 'IN'", " 'JJ'+AF0-+ACI-", '0.0001610457'] 

mycode的是如下:

with open("Dataset/MALE_Training/MI_score_Male.csv","r")as finp :   
    fv_raeder = csv.reader(finp) 
    heading = fv_raeder.next()        
    for row in fv_raeder : 
     print row 

這是什麼+ACI-+AFs'EX'+AF0-+ACI等是什麼意思?我怎樣才能刪除這個?你能爲我的問題提出一些解決方案嗎?

CSV文件包含:

Conversation 0.0010855412 
    At Home 0.0023042115 
    Family 0.0001275907 
    Time 0.0005935242 
    Work 0.0012768792 
    Past Actions 0.0001357854 
    Games 0.0032438747 
    Internet 0.0008639338 
    Location 0.00
    Fun 0.0035238147 
    Food/Clothes 0.0080727641 
    Poetic 4.691183298570359e-06 
    Books/Movies 2.1300704813858456e-06 
    Religion 0 
    Romance 0.0005935134 
    Swearing 3.217031124518803e-05 
    Politics 0.0075492962 
    Music 7.224535286344926e-05 
    School 2.0853873920424672e-06 
    Business 0.0056130667 
    end_with_able 0.001345825 
    end_with_al 0.0024110161 
    end_with_ful 0.0013767934 
    end_with_ible 0.0022098726 
    end_with_ic 0.0023514306 
    end_with_ive 0.0037701555 
    end_with_less 0.0010593697 
    end__with_ly 7.89403499813603e-05 
    end_with_ous 9.940547915993254e-05 
    sorry_word 5.662225052323463e-05 
    Starting_with_Apolog 0.0003042999 
    Help! 0.0003773039 
    I understand 0.0001320813 
    Attention, please! 0 
    Ok, I see 0 
    Damn! 0 
    How sweet! 2.0201595541210387e-06 
    That's too bad 0 
    Come on! 0.0014614134 
    Whatever 0 
    That's bad 0 
    It's cold 0 
    That's dumb 0 
    Help! 0.0003773039 
    Oh no! 0 
    What? 0 
    Is that right? 0 
    Disgusting 0.0001809821 
    This is hopeless 0 
    Really? 0.0004255353 
    I'm angry 0 
    I wonder 0 
    I don't like this 0 
    Really? 0.0004255353 
    Let's celebrate! 0 
    Disgusting 0.0001809821 
    I don't know 0 
    Yes 0 
    Lovely 0.0001642891 
    I'm so evil! 0 
    No 0.0005265143 
    No, it isn't!/Did not! 0 
    I see 0.0013579047 
    Fancy! 0 
    Wonderful! 0.0006769606 
    I'm exerting myself 0 
    I didn't mean to do that 0 
    That hurts 0 
    Hey, you! 0 
    Oh no... 0 
    It stinks! 0 
    That's nothing 0 
    That was close! 0.0010088511 
    Whispering!Hey, you! 0 
    I can't believe this! 0 
    Be quiet 0 
    Go away 0 
    Disappointing 0 
    Yes 0 
    Oh no! 0 
    No 0.0005265143 
    Wait, I'm thinking 0 
    This is fun! 0.0016848004 
    Unbelievable! 0 
    Amazing! 0.0005387173 
    Let's celebrate! 0 
    Yes! 0.0003639123 
    Yes! 0.0003639123 
    I'm excited! 0 
    Hey you! 0 
    Yes, it is! Or Did so! 0 
    Disgusting! 0 
    Haha, well said! 0 
    ['CD', 'CC', 'CD'] 0.0003041055 
    ['DT', 'CC', 'CD'] 0.0003041055 
    ['EX', 'CC', 'CD'] 0.0002694121 
    ['JJ', 'CC', 'CD'] 0.0003041055 
    ['JJR', 'CC', 'CD'] 0.0003427676 
    ['JJS', 'CC', 'CD'] 0.0029483492 
    ['NN', 'CC', 'CD'] 0.0001060578 
    ['RBR', 'CC', 'CD'] 0.0002081336 
    ['VBD', 'CC', 'CD'] 0.0001925713 
    ['VBG', 'CC', 'CD'] 9.068096527379936e-06 
    ['VBN', 'CC', 'CD'] 0.0011585203 
    ['VBP', 'CC', 'CD'] 0.000277034 
    ['VBZ', 'CC', 'CD'] 0.0009891459 
    ['WDT', 'CC', 'CD'] 0.0015045239 
    ['WP', 'CC', 'CD'] 0.0013222853 
    ['CD', 'CD', 'DT'] 0.0002694121 
    ['DT', 'CD', 'DT'] 0.0003605792 
    ['EX', 'CD', 'DT'] 0.0003605792 
    ['JJ', 'CD', 'DT'] 0.0003605792 
    ['JJR', 'CD', 'DT'] 0.0003623141 
    ['JJS', 'CD', 'DT'] 0.0028113198 
    ['NN', 'CD', 'DT'] 0.0002380414 
    ['RBR', 'CD', 'DT'] 0.0002524272 
    ['VBD', 'CD', 'DT'] 0.0002694121 
    ['VBG', 'CD', 'DT'] 6.8763849316489e-07 
    ['VBN', 'CD', 'DT'] 0.0013536177 
    ['VBP', 'CD', 'DT'] 0.000228122 
    ['VBZ', 'CD', 'DT'] 0.0011060342 
    ['WDT', 'CD', 'DT'] 0.0018250935 
    ['WP', 'CD', 'DT'] 0.0013798266 
    ['CD', 'DT', 'EX'] 0.0005956604 
    ['DT', 'DT', 'EX'] 0.000739265 
    ['EX', 'DT', 'EX'] 0.0005909166 
    ['JJ', 'DT', 'EX'] 0.0005909166 
    ['JJR', 'DT', 'EX'] 0.000548832 
    ['NN', 'DT', 'EX'] 0.0007274935 
    ['RBR', 'DT', 'EX'] 0.0006394694 
    ['VBD', 'DT', 'EX'] 0.0003994929 
    ['VBG', 'DT', 'EX'] 0.000165679 
    ['VBN', 'DT', 'EX'] 0.0007330517 
    ['VBP', 'DT', 'EX'] 0.0003164934 
    ['VBZ', 'DT', 'EX'] 0.0006952293 
    ['WDT', 'DT', 'EX'] 0.0009373422 
    ['CD', 'IN', 'JJ'] 2.3855039963693414e-05 
    ['DT', 'IN', 'JJ'] 0.0004035301 
    ['EX', 'IN', 'JJ'] 3.612301342137506e-05 
    ['JJ', 'IN', 'JJ'] 0.0001610457 
    ['JJR', 'IN', 'JJ'] 0.0001610457 
    ['JJS', 'IN', 'JJ'] 0.0033707076 
    ['NN', 'IN', 'JJ'] 0.0007419509 
    ['RBR', 'IN', 'JJ'] 7.329654519463405e-08 
    ['VBD', 'IN', 'JJ'] 5.950344732515763e-05 
    ['VBG', 'IN', 'JJ'] 0.0007109534 
    ['VBN', 'IN', 'JJ'] 0.0006920679 
    ['VBP', 'IN', 'JJ'] 3.6209960493105995e-05 
    ['VBZ', 'IN', 'JJ'] 0.0018789858 
    ['WDT', 'IN', 'JJ'] 0.0037640204 
    ['WP', 'IN', 'JJ'] 0.0011824782 
    ['CD', 'JJ', 'JJR'] 0.003625445 
    ['DT', 'JJ', 'JJR'] 0.0028113198 

    ['VB', 'WDT'] 0.0013284551 
    ['VBD', 'WDT'] 0.0005987498 
    ['VBG', 'WDT'] 0.0017245536 
    ['VBN', 'WDT'] 0.0008969116 
    ['VBP', 'WDT'] 0.0016863023 
    ['VBZ', 'WDT'] 0.0020814437 
    CC 5.111969137490955e-05 
    CD 0.0004017943 
    DT 0 
    EX 0.0005909166 
    IN 0 
    JJ 0.0001610457 
    JJR 0.003469816 
    JJS 0.0010446082 
    CC 5.111969137490955e-05 
    CD 0.0004017943 
    DT 0 
    EX 0.0005909166 
    IN 0 
    JJ 0.0001610457 
    JJR 0.003469816 
    JJS 0.0010446082 
    MD 0.0006791731 
    NN 0 
    NNS 5.149809586568776e-05 
    PRP 0.0014294222 
    RB 0.0004972152 
    RBR 0.0007214601 
    RP 0.0001474277 
    TO 1.8888999939422496e-05 
    VB 3.6038046948563265e-05 
    VBD 0.0011007132 
    VBG 0.0006148222 
    VBN 2.3115793700478806e-07 
    VBP 0.0016502422 
    VBZ 0.0032336121 
    WDT 0.0011788791 
    WP 3.35853998744088e-05 
    WRB 2.4547859289217235e-05 
+0

你列出所有數據來自CSV文件,除非你有沒有與我們分享額外的代碼。 –

+0

是所有數據都是從相同的CSV中讀取 – user104853

+2

看起來像[UTF-7](http://en.m.wikipedia.org/wiki/UTF-7)。可能完成的目的很可能。 – tripleee

回答

0

正如@tripleee提到,這是UTF-7編碼。通過使用codecs.open,你可以在後臺對其進行解碼:

from codecs import open 

with open("Dataset/MALE_Training/MI_score_Male.csv", encoding='utf-7') as finp: 
    csv_reader = csv.reader(finp) 
    heading = next(csv_reader)        
    for row in csv_reader: 
     print row 
+0

謝謝你的作品...非常感謝你.. :-) – user104853

相關問題