"Text Mining"

Nancy

Hi,

I am working with TextMining with a huge dataset. I have applied Tokeiniser,Stemmer and EnglishStopWordFilter.I am getting the result  as '0' in TFIDF. The same code I have tried with another system and it is working fine.

Please find the attached code

<operator name="Root" class="Process" expanded="yes">
    <operator name="TextInput" class="TextInput" expanded="yes">
        <list key="texts">
          <parameter key="review" value="C:\Documents and Settings\ADMIN\Desktop\dd"/>
        </list>
        <list key="namespaces">
        </list>
        <operator name="StringTokenizer" class="StringTokenizer">
        </operator>
        <operator name="EnglishStopwordFilter" class="EnglishStopwordFilter">
        </operator>
        <operator name="TokenLengthFilter" class="TokenLengthFilter">
        </operator>
    </operator>
</operator>


Thanks,
Nancy :-[

land

Hi,
this process works for me with the newsgroup texts. Did you control if there are any texts at all? Make a breakpoint inside the TextInput operator.
Depending on the texts this might be correct, for example if all words are occurring the same time in all texts. Then the TFIDF would be 0.

Greetings,
Sebastian

Nancy

Hi Sebastain,

Now its working fine.I have applied FPGrowth and I got the result.In result conatins 'support' header .What it really means?

Thanks
Nancy

fischer

See

http://en.wikipedia.org/wiki/Association_rule_learning
http://en.wikipedia.org/wiki/Support_%28measure_theory%29

Cheers,
Simon