"Frequent Item Set Mining in DB2"

svpriyan

Hai,
I am intend to test about the Frequent Item Set Mining using FP Growth Algorithm
I am trying to use the above data.
This is what I have right did it.
• DatabaseExampleSource
• UserBasedDiscretization
• FPGrowth
• AssociationRuleGenerator

<operator name="Root" class="Process" expanded="yes">     <operator name="DatabaseExampleSource" class="DatabaseExampleSource">         <parameter key="database_system" value="IBM DB2"/>         <parameter key="database_url" value="jdbc:db2://145.120.22.169:50000/assign"/>         <parameter key="password" value="ZTibyKBik1eB4c4bNtIQjQ=="/>         <parameter key="query" value="SELECT * FROM &quot;SALES&quot;"/>         <parameter key="table_name" value="SALES"/>         <parameter key="username" value="svpriyan"/>     </operator>     <operator name="UserBasedDiscretization" class="UserBasedDiscretization">         <list key="classes">           <parameter key="yes" value="1.0"/>           <parameter key="no" value="0.0"/>         </list>     </operator>     <operator name="FPGrowth" class="FPGrowth">         <parameter key="keep_example_set" value="true"/>         <parameter key="min_support" value="0.1"/>     </operator>     <operator name="AssociationRuleGenerator" class="AssociationRuleGenerator">         <parameter key="keep_frequent_item_sets" value="true"/>         <parameter key="min_confidence" value="0.1"/>     </operator> </operator>

Though I realized it is not a sufficient one to get the result, could you please tell some advice in which way can I modify the above code? 

Thanks
Priyan


[attachment deleted by admin]

land

Hi,
unfortunately this exceeds somehow the frame of this forum. I cannot build the complete process for you. Not only because we live on the money we earn by consulting, but although because I cann't build such a process without data.
I just can give you some hints:
You have to aggregate your data, so that all items which might occur are represented by an attribute. If this item occurs in an transaction, the attribute needs to become true. Otherwise false. This is called binominal value.

Good luck,
  Sebastian Land