Skip to Content
avatar image
Former Member

Could I get a solution for agglomerate clustering for the below input data

I would like to find a solution to cluster the below table based on the scores, e.g the data set belonging to the range of scores 0,0.1 should come under one cluster.

Customer ID 1Customer ID2Score35356457647654654746760.1346265445674574740.15464565445645650.2647567886546546450.36786786786767867896890.3345455454654640.534346356356546560.6353453453675676780.83453434678679789780.85578689934756786780

i got he below code for a sample data from the SCN network for using agglomerate clustering but I am not sure what would be the parameter values for the parameter table for my data.

DROP TABLE DATA_TBL;

CREATE COLUMN TABLE DATA_TBL like DATA_T;

INSERT INTO DATA_TBL VALUES ('0' , 0.5, 0.5, 'A');

INSERT INTO DATA_TBL VALUES ('1' , 1.5, 0.5, 'B');

INSERT INTO DATA_TBL VALUES ('2' , 1.5, 1.5, 'B');

INSERT INTO DATA_TBL VALUES ('3' , 0.5, 1.5, 'B');

INSERT INTO DATA_TBL VALUES ('4' , 1.1, 1.2, 'B');

INSERT INTO DATA_TBL VALUES ('5' , 0.5, 15.5, 'B');

INSERT INTO DATA_TBL VALUES ('6' , 1.5, 15.5, 'C');

INSERT INTO DATA_TBL VALUES ('7' , 1.5, 16.5, 'C');

INSERT INTO DATA_TBL VALUES ('8' , 0.5, 16.5, 'C');

INSERT INTO DATA_TBL VALUES ('9' , 1.2, 16.1, 'C');

INSERT INTO DATA_TBL VALUES ('10', 15.5, 15.5, 'C');

INSERT INTO DATA_TBL VALUES ('11', 16.5, 15.5, 'D');

INSERT INTO DATA_TBL VALUES ('12', 16.5, 16.5, 'D');

INSERT INTO DATA_TBL VALUES ('13', 15.5, 16.5, 'D');

INSERT INTO DATA_TBL VALUES ('14', 15.6, 16.2, 'D');

INSERT INTO DATA_TBL VALUES ('15', 15.5, 0.5, 'D');

INSERT INTO DATA_TBL VALUES ('16', 16.5, 0.5, 'A');

INSERT INTO DATA_TBL VALUES ('17', 16.5, 1.5, 'A');

INSERT INTO DATA_TBL VALUES ('18', 15.5, 1.5, 'A');

INSERT INTO DATA_TBL VALUES ('19', 15.7, 1.6, 'A');

DROP TABLE PARAMETERS_TBL;

CREATE COLUMN TABLE PARAMETERS_TBL like PARAMETERS_T;

INSERT INTO PARAMETERS_TBL VALUES ('THREAD_NUM',8,null,null);

INSERT INTO PARAMETERS_TBL VALUES ('CLUSTER_NUM',4,null,null);

INSERT INTO PARAMETERS_TBL VALUES ('CLUSTER_METHOD',4,null,null);

INSERT INTO PARAMETERS_TBL VALUES ('DISTANCE_FUNC',10,null,null);

INSERT INTO PARAMETERS_TBL VALUES ('DISTANCE_DIMENSION',null,3,null);

INSERT INTO PARAMETERS_TBL VALUES ('NORMALIZWEIGHTS',null,0.1,null);

INSERT INTO PARAMETERS_TBL VALUES ('CATEGORY_COL',3,null,null);

E_TYPE',0,null,null);

Please let me know how I could implement this with my input table.

SQL
Add comment
10|10000 characters needed characters exceeded

  • This question _looks like_ it is referring to SAP HANA PAL functions but lacks a lot of context.

    Please describe in more detail what software (versions) you use and what you actually want to achieve, i.e. what is the business question you want to answer by using "agglomerate clustering"?

  • Get RSS Feed

1 Answer

  • avatar image
    Former Member
    Nov 18, 2016 at 05:55 AM

    input-datatable.txt Attaching the input data table to be clustered based on the SCORES column as previously shared table was unreadable.

    Add comment
    10|10000 characters needed characters exceeded