Anomaly detection is a technique used to identify data objects that deviate from the normal behavior or model of the data. These anomalies, also known as outliers, can provide valuable information in various domains such as computer networks, medical imaging, credit card transactions, and space exploration. The PAL method utilizes the k-means algorithm to detect anomalies by grouping the data into clusters and identifying points that are far from all cluster centers.
------

SET SCHEMA DM_PAL;

DROP TABLE PAL_AD_DATA_TBL;
CREATE COLUMN TABLE PAL_AD_DATA_TBL(
	"ID" INTEGER,
	"V000" DOUBLE,
	"V001" DOUBLE
);
INSERT INTO PAL_AD_DATA_TBL VALUES (0 , 0.5, 0.5);
INSERT INTO PAL_AD_DATA_TBL VALUES (1 , 1.5, 0.5);
INSERT INTO PAL_AD_DATA_TBL VALUES (2 , 1.5, 1.5);
INSERT INTO PAL_AD_DATA_TBL VALUES (3 , 0.5, 1.5);
INSERT INTO PAL_AD_DATA_TBL VALUES (4 , 1.1, 1.2);

DROP TABLE #PAL_CONTROL_TBL;
CREATE LOCAL TEMPORARY COLUMN TABLE #PAL_CONTROL_TBL(
	"NAME" VARCHAR (100),
	"INTARGS" INTEGER,
	"DOUBLEARGS" DOUBLE,
	"STRINGARGS" VARCHAR(100)
);
INSERT INTO #PAL_CONTROL_TBL VALUES ('THREAD_NUMBER',2,null,null);
INSERT INTO #PAL_CONTROL_TBL VALUES ('GROUP_NUMBER',4,null,null);
INSERT INTO #PAL_CONTROL_TBL VALUES ('INIT_TYPE',4,null,null);
INSERT INTO #PAL_CONTROL_TBL VALUES ('DISTANCE_LEVEL',2,null,null);
INSERT INTO #PAL_CONTROL_TBL VALUES ('MAX_ITERATION',100,null,null);

CALL _SYS_AFL.PAL_ANOMALY_DETECTION(PAL_AD_DATA_TBL, #PAL_CONTROL_TBL, ?, ?, ?);

