Skip to content

Added new kmeans plusplus #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
farzadras wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Added new kmeans plusplus #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions bootstrap/algorithmspec.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,8 @@ CREATE TABLE benchmark.kmeans_kmeans_random(testitemname text, runid int, src_re

CREATE TABLE benchmark.kmeans_kmeans_canopy(testitemname text, runid int, src_relation text default null ,src_col_data text default null ,src_col_id text default null ,out_points text default null ,out_centroids text default null ,dist_metric text default null ,max_iter int default null ,conv_threshold float default null ,evaluate boolean default null ,verbosity boolean default null ,t1 float default null ,t2 float default null ,point_count bigint default null ,iterations int default null ,cost_func double precision default null ,silhouette double precision default null );

CREATE TABLE benchmark.kmeans_kmeans_new_plusplus_ctas(testitemname text, runid int, table_name text default null ,src_relation text default null ,src_col_data text default null ,k smallint default null ,dist_metrics text default null ,agg_mean text default null ,max_iter int default null ,conv_threshold double precision default null ,silhouette double precision default null ,objective_fn double precision default null ,frac_reassigned double precision default null ,num_iterations integer default null );

CREATE TABLE benchmark.kmeans_kmeans_new_cset_ctas(testitemname text, runid int, table_name text default null ,src_relation varchar default null ,src_col_data varchar default null ,init_cset_rel varchar default null ,init_cset_col varchar default null ,dist_metrics text[] default null ,agg_centroid varchar default null ,max_iter int default null ,conv_threshold float default null ,silhouette double precision default null );

CREATE TABLE benchmark.kmeans_kmeans_new_random_ctas(testitemname text, runid int, table_name text default null ,src_relation text default null ,src_col_data text default null ,k smallint default null ,dist_metrics text default null ,dist_metric_in_objective text default null ,agg_mean text default null ,max_iter int default null ,conv_threshold float default null ,silhouette double precision default null );
Expand Down
2 changes: 1 addition & 1 deletion bootstrap/analyticstool.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,4 +2,4 @@ DROP TABLE IF EXISTS benchmark.analyticstool cascade;

CREATE TABLE benchmark.analyticstool(username varchar(128),superuser varchar(128),kind varchar(128),master_dir text,name varchar(128),database varchar(128),toolversion varchar(128),host varchar(128),madlibversion varchar(128),env text,port int,segmentnum smallint);

INSERT INTO benchmark.analyticstool(username,superuser,kind,master_dir,name,database,toolversion,host,madlibversion,env,port,segmentnum)VALUES('iyerr3','iyerr3','greenplum','/Users/iyerr3/greenplum-db-data/master/gpseg-1','GPDB42','madmark','4.2.0.0','127.0.0.1','0.5','/Users/iyerr3/greenplum-db-devel/greenplum_path.sh',5432,2);
INSERT INTO benchmark.analyticstool(username,superuser,kind,master_dir,name,database,toolversion,host,madlibversion,env,port,segmentnum)VALUES('rastef','rastef','greenplum','/Users/rastef/greenplum-db-data/master/gpseg-1','GPDB42','madmark','4.2.0.0','127.0.0.1','0.5','/Users/rastef/greenplum-db-devel/greenplum_path.sh',5432,2);
7 changes: 0 additions & 7 deletions bootstrap/init_cases.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,7 +84,6 @@ CREATE OR REPLACE VIEW benchmark.testresultreport AS
WHEN trb.evaluation_function IS NULL AND trb.result_info <> tr.result_info
THEN 'FAILED : Expected result not matched'

<<<<<<< HEAD
WHEN (trb.itemname not like 'rf%' AND trb.itemname not like '%cross_validate%' AND trb.itemname not like 'svm%' AND (trb.evaluation_function IS NOT NULL AND ((trb.evaluation_function - tr.evaluation_function) between -0.0001 and 0.0001)))
OR ((trb.itemname like 'rf%' OR trb.itemname like '%cross_validate%' ) AND (trb.evaluation_function IS NOT NULL AND ((tr.evaluation_function / trb.evaluation_function) between 0.7 and 1.3 )))
OR ((trb.itemname like 'svm%' ) AND (trb.evaluation_function IS NOT NULL AND ((tr.evaluation_function / trb.evaluation_function) between 0.0000001 and 10000000 )))
Expand All @@ -107,12 +106,6 @@ CREATE OR REPLACE VIEW benchmark.testresultreport AS
WHEN (trb.itemname like 'kmeans_new_%' AND (trb.issuccessful <> tr.issuccessful OR tr.evaluation_function < trb.evaluation_function))
THEN 'FAILED'

WHEN (trb.itemname like 'kmeans_new_%' AND trb.issuccessful = tr.issuccessful AND tr.evaluation_function >= trb.evaluation_function)
THEN 'PASSED'

WHEN (trb.itemname like 'kmeans_new_%' AND (trb.issuccessful <> tr.issuccessful OR tr.evaluation_function < trb.evaluation_function))
THEN 'FAILED'

ELSE 'CASES NEED TO BE INVESTIGATE'

END AS testresult,
Expand Down
7 changes: 7 additions & 0 deletions bootstrap/post.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,13 @@ SET evaluation_function =
WHERE kmeans.runid = ts.runid AND kmeans.testitemname=ts.itemname)
WHERE itemname like 'kmeans_new_cset%';

UPDATE benchmark.testitemresult AS ts
SET evaluation_function =
(SELECT silhouette
FROM benchmark.kmeans_kmeans_new_plusplus_ctas AS kmeans
WHERE kmeans.runid = ts.runid AND kmeans.testitemname=ts.itemname)
WHERE itemname like 'kmeans_new_plusplus%';

UPDATE benchmark.testitemresult AS ts
SET evaluation_function =
(SELECT silhouette
Expand Down
Loading