topic Re: hierarchical clustering syntax error in SAS Data Science

hierarchical clustering syntax error

ashmishah — Sat, 18 Mar 2017 17:10:32 GMT

I am learning sas and totally new to this field. I have 2 doubts:

1. I have to do hierarchical clustering for a dataset. How can i do hierarchical clustering using 2 dataset out of which one is demographic data and other is survey data.

2. I was trying to write a code to do clustering for survey data. Here is the code:

data a1;
infile "/folders/myfolders/pda.csv" dlm=',' firstobs=2;
input ID $ Innovator $ Use_message $ Use_cell $ Use_PIM $ Inf_passive $ INF_active $ remote_access $ Share_info $ Monitor $ Email $ Web $ M_media $ ergonomic $ monthly price;
run;

proc cluster simple noeigen method=centroid rmsstd rsquare nonorm outtree=a2;
id ID Innovator Use_message Use_cell Use_PIM Inf_passive INF_active remote_access Share_info Monitor Email Web M_media ergonomic;
var price monthly;
run;

But it is showing this again and again.

proc cluster simple noeigen method=centroid rmsstd rsquare nonorm outtree=a2;

63 id ID Innovator Use_message Use_cell Use_PIM Inf_passive INF_active remote_access Share_info Monitor Email Web M_media

_________

63 ! ergonomic;

ERROR 22-322: Expecting ;.

ERROR 76-322: Syntax error, statement will be ignored.

64 var price monthly;

65 run;

How can i proceed with it.

I am attaching one of the file here.

Re: hierarchical clustering syntax error

Reeza — Sat, 18 Mar 2017 21:34:09 GMT

Your ID statement is incorrect.

Looking at the documentation, it states that it requires a single variable, not variable(s), and is used to identify a record. It should be unique for each observation. I'm not sure what you're trying to do with this, so can't make suggestions beyond the correction.

ID Statement

ID variable;

The values of the ID variable identify observations in the displayed cluster history and in the OUTTREE= data set. If the ID statement is omitted, each observation is denoted by OBn, where n is the observation number.

http://support.sas.com/documentation/cdl/en/statug/68162/HTML/default/viewer.htm#statug_cluster_syntax05.htm

Re: hierarchical clustering syntax error

ashmishah — Sat, 18 Mar 2017 22:57:17 GMT

I have to Perform hierarchical cluster analysis on the PDA data. As all the other variables are categorical can i keep it in var statement?

I am attaching the description herewith.

Re: hierarchical clustering syntax error

Reeza — Sat, 18 Mar 2017 23:40:35 GMT

@ashmishah wrote:

I am learning sas and totally new to this field. I have 2 doubts:

1. I have to do hierarchical clustering for a dataset. How can i do hierarchical clustering using 2 dataset out of which one is demographic data and other is survey data.

2. I was trying to write a code to do clustering for survey data. Here is the code:

data a1;
infile "/folders/myfolders/pda.csv" dlm=',' firstobs=2;
input ID $ Innovator $ Use_message $ Use_cell $ Use_PIM $ Inf_passive $ INF_active $ remote_access $ Share_info $ Monitor $ Email $ Web $ M_media $ ergonomic $ monthly price;
run;

proc cluster simple noeigen method=centroid rmsstd rsquare nonorm outtree=a2;
id ID Innovator Use_message Use_cell Use_PIM Inf_passive INF_active remote_access Share_info Monitor Email Web M_media ergonomic;
var price monthly;
run;

But it is showing this again and again.

proc cluster simple noeigen method=centroid rmsstd rsquare nonorm outtree=a2;

63         id ID Innovator Use_message Use_cell Use_PIM Inf_passive INF_active remote_access Share_info Monitor Email Web M_media

                  _________

                  22

                  76

63       ! ergonomic;

ERROR 22-322: Expecting ;.

ERROR 76-322: Syntax error, statement will be ignored.

64         var price monthly;

65         run;

How can i proceed with it.

I am attaching one of the file here.

I personally have a policy of not answering homework questions. My advice would be to work through the examples in the documentation first or one from your textbook. These should give you enough of a basis to answer your homework questions.

Re: hierarchical clustering syntax error

Ksharp — Sun, 19 Mar 2017 02:35:23 GMT

I noticed you have some character variables.
proc cluster can not handle the character variables.

Try use PROC DISTANCE to get distance matrix and 
feed it into proc cluster .