Time series clustering

classic Classic list List threaded Threaded
3 messages Options
Reply | Threaded
Open this post in threaded view
|

Time series clustering

harry wills
Hi,
I am very new to data mining field.
I have a clustering problem to do and was wondering whether how I can
do it in Weka or anyone can suggest which method I have to use

my data format is

Object                  AttributeA                      AttributeB
              Year0  Year1 Year2  Year3       Year0  Year1 Year2 ... YearN
1              1000    950    880     450             20      25
2               950     N/A   470
3
.
.
.
n

I could understand it is a time series data.But I dont know how to
proceed to cluster it.
Please if somebody could suggest hpw I can do this using weka or any
other literature can help me a lot

thanks for your time
Wills

_______________________________________________
Wekalist mailing list
[hidden email]
https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
Reply | Threaded
Open this post in threaded view
|

Re: Time series clustering

Paul m
First off, you need to have only a single name for your attributes.
Accordingly the example of your data cannot have two names (eg,
AttributeA & Year0). It would be better to rename so that they are
unique attribute names (eg, AttributeA.0 ; AttributeA.1 ; AttributeA.2
; etc..).

To be honest, IMHO, the best way to learn about clustering (and many
other things) is to read.. There are many clustering algorithms
implemented in weka, however without understanding what you are using
them for - it will all be meaningless. One of the most popular is
kMeans.. have a search using this and read away...

/paul

On 7/20/05, harry wills <[hidden email]> wrote:

> Hi,
> I am very new to data mining field.
> I have a clustering problem to do and was wondering whether how I can
> do it in Weka or anyone can suggest which method I have to use
>
> my data format is
>
> Object                  AttributeA                      AttributeB
>               Year0  Year1 Year2  Year3       Year0  Year1 Year2 ... YearN
> 1              1000    950    880     450             20      25
> 2               950     N/A   470
> 3
> .
> .
> .
> n
>
> I could understand it is a time series data.But I dont know how to
> proceed to cluster it.
> Please if somebody could suggest hpw I can do this using weka or any
> other literature can help me a lot
>
> thanks for your time
> Wills
>
> _______________________________________________
> Wekalist mailing list
> [hidden email]
> https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
>

_______________________________________________
Wekalist mailing list
[hidden email]
https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
Reply | Threaded
Open this post in threaded view
|

Re: Time series clustering

Mary.Felkin
And would you please have any suggestions about what to read
concerning datamining time series? Something which would
explain in detail the working of the algorithms.

Thank you

Mary


Paul wrote:

> First off, you need to have only a single name for your attributes.
> Accordingly the example of your data cannot have two names (eg,
> AttributeA & Year0). It would be better to rename so that they are
> unique attribute names (eg, AttributeA.0 ; AttributeA.1 ; AttributeA.2
> ; etc..).
>
> To be honest, IMHO, the best way to learn about clustering (and many
> other things) is to read.. There are many clustering algorithms
> implemented in weka, however without understanding what you are using
> them for - it will all be meaningless. One of the most popular is
> kMeans.. have a search using this and read away...
>
> /paul
>
> On 7/20/05, harry wills <[hidden email]> wrote:
>
>>Hi,
>>I am very new to data mining field.
>>I have a clustering problem to do and was wondering whether how I can
>>do it in Weka or anyone can suggest which method I have to use
>>
>>my data format is
>>
>>Object                  AttributeA                      AttributeB
>>              Year0  Year1 Year2  Year3       Year0  Year1 Year2 ... YearN
>>1              1000    950    880     450             20      25
>>2               950     N/A   470
>>3
>>.
>>.
>>.
>>n
>>
>>I could understand it is a time series data.But I dont know how to
>>proceed to cluster it.
>>Please if somebody could suggest hpw I can do this using weka or any
>>other literature can help me a lot
>>
>>thanks for your time
>>Wills
>>
>>_______________________________________________
>>Wekalist mailing list
>>[hidden email]
>>https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
>>
>
>
> _______________________________________________
> Wekalist mailing list
> [hidden email]
> https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
>


_______________________________________________
Wekalist mailing list
[hidden email]
https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist