From 241973c09ac0716c61304aad5bc4b7c9ac23b114 Mon Sep 17 00:00:00 2001
From: Toru Takahashi <takahashi@treasure-data.com>
Date: Sun, 1 Dec 2024 00:01:49 +0900
Subject: [PATCH] Add ID Unification example (#411)

---
 tool-box/id-unification-samples/README.md     |   9 ++
 .../id-unification-samples/conifg/params.yml  |   5 +
 .../queries/generate_samples_ex1.sql          | 103 +++++++++++++++++
 .../queries/generate_samples_ex2.sql          | 105 ++++++++++++++++++
 .../queries/generate_samples_ex4.sql          |  13 +++
 .../queries/insert_samples_ex5.sql            |  63 +++++++++++
 .../test_id_unification_ex1.dig               |  33 ++++++
 .../test_id_unification_ex2.dig               |  34 ++++++
 .../test_id_unification_ex3.dig               |  34 ++++++
 .../test_id_unification_ex4.dig               |  33 ++++++
 .../test_id_unification_ex5.dig               |  37 ++++++
 .../unification_ex1.yml                       |  59 ++++++++++
 .../unification_ex2.yml                       |  72 ++++++++++++
 .../unification_ex3.yml                       |  77 +++++++++++++
 .../unification_ex4.yml                       |  37 ++++++
 .../unification_ex5.yml                       |  58 ++++++++++
 16 files changed, 772 insertions(+)
 create mode 100644 tool-box/id-unification-samples/README.md
 create mode 100644 tool-box/id-unification-samples/conifg/params.yml
 create mode 100644 tool-box/id-unification-samples/queries/generate_samples_ex1.sql
 create mode 100644 tool-box/id-unification-samples/queries/generate_samples_ex2.sql
 create mode 100644 tool-box/id-unification-samples/queries/generate_samples_ex4.sql
 create mode 100644 tool-box/id-unification-samples/queries/insert_samples_ex5.sql
 create mode 100644 tool-box/id-unification-samples/test_id_unification_ex1.dig
 create mode 100644 tool-box/id-unification-samples/test_id_unification_ex2.dig
 create mode 100644 tool-box/id-unification-samples/test_id_unification_ex3.dig
 create mode 100644 tool-box/id-unification-samples/test_id_unification_ex4.dig
 create mode 100644 tool-box/id-unification-samples/test_id_unification_ex5.dig
 create mode 100644 tool-box/id-unification-samples/unification_ex1.yml
 create mode 100644 tool-box/id-unification-samples/unification_ex2.yml
 create mode 100644 tool-box/id-unification-samples/unification_ex3.yml
 create mode 100644 tool-box/id-unification-samples/unification_ex4.yml
 create mode 100644 tool-box/id-unification-samples/unification_ex5.yml

diff --git a/tool-box/id-unification-samples/README.md b/tool-box/id-unification-samples/README.md
new file mode 100644
index 00000000..6a403393
--- /dev/null
+++ b/tool-box/id-unification-samples/README.md
@@ -0,0 +1,9 @@
+# ID Unification Workflow Samples
+
+ID Unification is the process of stitching together multiple tables using various identifiers to assign a unique customer ID (canonical_id or persistent_id) to each user. In simpler terms, it consolidates identifiers like cookie_id and email addresses from various user data sources to identify and group "the same person."
+
+Since customer data often contains different identifiers across different data sources, simply aggregating this data doesn't link these sources together. This necessitates the ID Unification process to make the data usable.
+
+These workflow samples are used for the following API documentation
+
+- [API Documentation](https://api-docs.treasuredata.com/)
\ No newline at end of file
diff --git a/tool-box/id-unification-samples/conifg/params.yml b/tool-box/id-unification-samples/conifg/params.yml
new file mode 100644
index 00000000..32fe61af
--- /dev/null
+++ b/tool-box/id-unification-samples/conifg/params.yml
@@ -0,0 +1,5 @@
+td:
+  tbl_aaa: site_aaa
+  tbl_xxx: site_xxx
+  tbl_yyy: site_yyy
+  tbl_zzz: site_zzz
\ No newline at end of file
diff --git a/tool-box/id-unification-samples/queries/generate_samples_ex1.sql b/tool-box/id-unification-samples/queries/generate_samples_ex1.sql
new file mode 100644
index 00000000..c5450fc4
--- /dev/null
+++ b/tool-box/id-unification-samples/queries/generate_samples_ex1.sql
@@ -0,0 +1,103 @@
+DROP TABLE IF EXISTS ${td.database}.${td.tbl_aaa};
+CREATE TABLE ${td.database}.${td.tbl_aaa} AS
+SELECT
+  time, site, td_client_id, td_global_id
+FROM
+  ( VALUES
+       (TD_TIME_PARSE('2023/01/05'), 'aaa.jp','aaa_001','3rd_001')
+      ,(TD_TIME_PARSE('2023/01/15'), 'aaa.jp','aaa_001','3rd_002')
+      ,(TD_TIME_PARSE('2023/01/25'), 'aaa.jp','aaa_001','3rd_003')
+      ,(TD_TIME_PARSE('2023/02/05'), 'aaa.jp','aaa_001','3rd_004')
+      ,(TD_TIME_PARSE('2023/02/15'), 'aaa.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/02/25'), 'aaa.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/03/05'), 'aaa.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/03/15'), 'aaa.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/03/25'), 'aaa.jp','aaa_002','3rd_009')
+      ,(TD_TIME_PARSE('2023/04/05'), 'aaa.jp','aaa_002','3rd_010')
+      ,(TD_TIME_PARSE('2023/04/15'), 'aaa.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/04/25'), 'aaa.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/05/05'), 'aaa.jp','aaa_003','3rd_013')
+      ,(TD_TIME_PARSE('2023/05/15'), 'aaa.jp','aaa_003','3rd_014')
+      ,(TD_TIME_PARSE('2023/05/25'), 'aaa.jp','aaa_003','3rd_015')
+      ,(TD_TIME_PARSE('2023/06/05'), 'aaa.jp','aaa_003','3rd_016')
+      ,(TD_TIME_PARSE('2023/06/15'), 'aaa.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/06/25'), 'aaa.jp',NULL,NULL)
+  ) AS t(time, site, td_client_id, td_global_id);
+
+DROP TABLE IF EXISTS ${td.database}.${td.tbl_xxx};
+CREATE TABLE ${td.database}.${td.tbl_xxx} AS
+SELECT
+  time, site, td_client_id, td_global_id
+FROM
+  ( VALUES
+       (TD_TIME_PARSE('2023/01/05'),'xxx.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/01/15'),'xxx.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/01/25'),'xxx.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/02/05'),'xxx.jp','xxx_001','3rd_004')
+      ,(TD_TIME_PARSE('2023/02/15'),'xxx.jp','xxx_001','3rd_005')
+      ,(TD_TIME_PARSE('2023/02/25'),'xxx.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/03/05'),'xxx.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/03/15'),'xxx.jp','xxx_002','3rd_008')
+      ,(TD_TIME_PARSE('2023/03/25'),'xxx.jp','xxx_002','3rd_009')
+      ,(TD_TIME_PARSE('2023/04/05'),'xxx.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/04/15'),'xxx.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/04/25'),'xxx.jp','xxx_003','3rd_012')
+      ,(TD_TIME_PARSE('2023/05/05'),'xxx.jp','xxx_003','3rd_013')
+      ,(TD_TIME_PARSE('2023/05/15'),'xxx.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/05/25'),'xxx.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/06/05'),'xxx.jp','xxx_004','3rd_016')
+      ,(TD_TIME_PARSE('2023/06/15'),'xxx.jp','xxx_004','3rd_017')
+      ,(TD_TIME_PARSE('2023/06/25'),'xxx.jp',NULL,NULL)
+  ) AS t(time, site, td_client_id, td_global_id);
+
+DROP TABLE IF EXISTS ${td.database}.${td.tbl_yyy};
+CREATE TABLE ${td.database}.${td.tbl_yyy} AS
+SELECT
+  time, site, td_client_id, td_global_id
+FROM
+  ( VALUES
+       (TD_TIME_PARSE('2023/01/05'),'yyy.jp','yyy_001','3rd_001')
+      ,(TD_TIME_PARSE('2023/01/15'),'yyy.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/01/25'),'yyy.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/02/05'),'yyy.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/02/15'),'yyy.jp','yyy_002','3rd_005')
+      ,(TD_TIME_PARSE('2023/02/25'),'yyy.jp','yyy_002','3rd_006')
+      ,(TD_TIME_PARSE('2023/03/05'),'yyy.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/03/15'),'yyy.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/03/25'),'yyy.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/04/05'),'yyy.jp','yyy_003','3rd_010')
+      ,(TD_TIME_PARSE('2023/04/15'),'yyy.jp','yyy_003','3rd_011')
+      ,(TD_TIME_PARSE('2023/04/25'),'yyy.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/05/05'),'yyy.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/05/15'),'yyy.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/05/25'),'yyy.jp','yyy_004','3rd_015')
+      ,(TD_TIME_PARSE('2023/06/05'),'yyy.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/06/15'),'yyy.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/06/25'),'yyy.jp','yyy_005','3rd_018')
+  ) AS t(time, site, td_client_id, td_global_id);
+
+DROP TABLE IF EXISTS ${td.database}.${td.tbl_zzz};
+CREATE TABLE ${td.database}.${td.tbl_zzz} AS
+SELECT
+  time, site, td_client_id, td_global_id
+FROM
+  ( VALUES
+       (TD_TIME_PARSE('2023/01/05'),'zzz.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/01/15'),'zzz.jp','zzz_001','3rd_002')
+      ,(TD_TIME_PARSE('2023/01/25'),'zzz.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/02/05'),'zzz.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/02/15'),'zzz.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/02/25'),'zzz.jp','zzz_003','3rd_006')
+      ,(TD_TIME_PARSE('2023/03/05'),'zzz.jp','zzz_003','3rd_007')
+      ,(TD_TIME_PARSE('2023/03/15'),'zzz.jp','zzz_003','3rd_008')
+      ,(TD_TIME_PARSE('2023/03/25'),'zzz.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/04/05'),'zzz.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/04/15'),'zzz.jp','zzz_004','3rd_011')
+      ,(TD_TIME_PARSE('2023/04/25'),'zzz.jp','zzz_004','3rd_012')
+      ,(TD_TIME_PARSE('2023/05/05'),'zzz.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/05/15'),'zzz.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/05/25'),'zzz.jp','zzz_005','3rd_015')
+      ,(TD_TIME_PARSE('2023/06/05'),'zzz.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/06/15'),'zzz.jp','zzz_005','3rd_017')
+      ,(TD_TIME_PARSE('2023/06/25'),'zzz.jp','zzz_005','3rd_018')
+  ) AS t(time, site, td_client_id, td_global_id);
\ No newline at end of file
diff --git a/tool-box/id-unification-samples/queries/generate_samples_ex2.sql b/tool-box/id-unification-samples/queries/generate_samples_ex2.sql
new file mode 100644
index 00000000..c5fc82da
--- /dev/null
+++ b/tool-box/id-unification-samples/queries/generate_samples_ex2.sql
@@ -0,0 +1,105 @@
+DROP TABLE IF EXISTS ${td.database}.${td.tbl_aaa};
+CREATE TABLE ${td.database}.${td.tbl_aaa} AS
+SELECT
+  time, site, td_client_id, td_global_id, td_ssc_id
+FROM
+  ( VALUES
+     (TD_TIME_PARSE('2023/01/05'),'aaa.jp','aaa_001','3rd_001','ssc_001')
+    ,(TD_TIME_PARSE('2023/01/15'),'aaa.jp','aaa_001','3rd_002','ssc_001')
+    ,(TD_TIME_PARSE('2023/01/25'),'aaa.jp','aaa_001','3rd_003','ssc_001')
+    ,(TD_TIME_PARSE('2023/02/05'),'aaa.jp','aaa_001','3rd_004','ssc_001')
+    ,(TD_TIME_PARSE('2023/02/15'),'aaa.jp',NULL,NULL,NULL)
+    ,(TD_TIME_PARSE('2023/02/25'),'aaa.jp',NULL,NULL,NULL)
+    ,(TD_TIME_PARSE('2023/03/05'),'aaa.jp',NULL,NULL,NULL)
+    ,(TD_TIME_PARSE('2023/03/15'),'aaa.jp',NULL,NULL,NULL)
+    ,(TD_TIME_PARSE('2023/03/25'),'aaa.jp','aaa_002','3rd_009','ssc_002')
+    ,(TD_TIME_PARSE('2023/04/05'),'aaa.jp','aaa_002','3rd_010','ssc_002')
+    ,(TD_TIME_PARSE('2023/04/15'),'aaa.jp',NULL,NULL,NULL)
+    ,(TD_TIME_PARSE('2023/04/25'),'aaa.jp',NULL,NULL,NULL)
+    ,(TD_TIME_PARSE('2023/05/05'),'aaa.jp','aaa_003','3rd_013','ssc_003')
+    ,(TD_TIME_PARSE('2023/05/15'),'aaa.jp','aaa_003','3rd_014','ssc_003')
+    ,(TD_TIME_PARSE('2023/05/25'),'aaa.jp','aaa_003','3rd_015','ssc_004')
+    ,(TD_TIME_PARSE('2023/06/05'),'aaa.jp','aaa_003','3rd_016','ssc_004')
+    ,(TD_TIME_PARSE('2023/06/15'),'aaa.jp',NULL,NULL,NULL)
+    ,(TD_TIME_PARSE('2023/06/25'),'aaa.jp',NULL,NULL,NULL)
+  ) AS t(time, site, td_client_id, td_global_id, td_ssc_id);
+
+DROP TABLE IF EXISTS ${td.database}.${td.tbl_xxx};
+CREATE TABLE ${td.database}.${td.tbl_xxx} AS
+
+SELECT
+  time, site, td_ssc_id, td_global_id
+FROM
+  ( VALUES
+     (TD_TIME_PARSE('2023/01/05'),'xxx.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/01/15'),'xxx.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/01/25'),'xxx.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/02/05'),'xxx.jp','ssc_001','3rd_004')
+    ,(TD_TIME_PARSE('2023/02/15'),'xxx.jp','ssc_001','3rd_005')
+    ,(TD_TIME_PARSE('2023/02/25'),'xxx.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/03/05'),'xxx.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/03/15'),'xxx.jp','ssc_001','3rd_008')
+    ,(TD_TIME_PARSE('2023/03/25'),'xxx.jp','ssc_001','3rd_009')
+    ,(TD_TIME_PARSE('2023/04/05'),'xxx.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/04/15'),'xxx.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/04/25'),'xxx.jp','ssc_002','3rd_010')
+    ,(TD_TIME_PARSE('2023/05/05'),'xxx.jp','ssc_002','3rd_013')
+    ,(TD_TIME_PARSE('2023/05/15'),'xxx.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/05/25'),'xxx.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/06/05'),'xxx.jp','ssc_003','3rd_016')
+    ,(TD_TIME_PARSE('2023/06/15'),'xxx.jp','ssc_003','3rd_017')
+    ,(TD_TIME_PARSE('2023/06/25'),'xxx.jp',NULL,NULL)
+  ) AS t(time, site, td_ssc_id, td_global_id);
+
+DROP TABLE IF EXISTS ${td.database}.${td.tbl_yyy};
+CREATE TABLE ${td.database}.${td.tbl_yyy} AS
+SELECT
+  time, site, email, td_ssc_id
+FROM
+  ( VALUES
+
+     (TD_TIME_PARSE('2023/01/05'),'yyy.jp','a@ex.com','ssc_001')
+    ,(TD_TIME_PARSE('2023/01/15'),'yyy.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/01/25'),'yyy.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/02/05'),'yyy.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/02/15'),'yyy.jp','a@ex.com','ssc_001')
+    ,(TD_TIME_PARSE('2023/02/25'),'yyy.jp','a@ex.com','ssc_001')
+    ,(TD_TIME_PARSE('2023/03/05'),'yyy.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/03/15'),'yyy.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/03/25'),'yyy.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/04/05'),'yyy.jp','b@ex.com','ssc_003')
+    ,(TD_TIME_PARSE('2023/04/15'),'yyy.jp','b@ex.com','ssc_003')
+    ,(TD_TIME_PARSE('2023/04/25'),'yyy.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/05/05'),'yyy.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/05/15'),'yyy.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/05/25'),'yyy.jp','c@ex.com','ssc_003')
+    ,(TD_TIME_PARSE('2023/06/05'),'yyy.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/06/15'),'yyy.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/06/25'),'yyy.jp','c@ex.com','ssc_004')
+  ) AS t(time, site, email, td_ssc_id);
+
+DROP TABLE IF EXISTS ${td.database}.${td.tbl_zzz};
+CREATE TABLE ${td.database}.${td.tbl_zzz} AS
+SELECT
+  time, site, td_client_id, email
+FROM
+  ( VALUES
+     (TD_TIME_PARSE('2023/01/05'),'zzz.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/01/15'),'zzz.jp','zzz_001','a@ex.com')
+    ,(TD_TIME_PARSE('2023/01/25'),'zzz.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/02/05'),'zzz.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/02/15'),'zzz.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/02/25'),'zzz.jp','zzz_003','a@ex.com')
+    ,(TD_TIME_PARSE('2023/03/05'),'zzz.jp','zzz_003','a@ex.com')
+    ,(TD_TIME_PARSE('2023/03/15'),'zzz.jp','zzz_003','a@ex.com')
+    ,(TD_TIME_PARSE('2023/03/25'),'zzz.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/04/05'),'zzz.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/04/15'),'zzz.jp','zzz_004','b@ex.com')
+    ,(TD_TIME_PARSE('2023/04/25'),'zzz.jp','zzz_004','c@ex.com')
+    ,(TD_TIME_PARSE('2023/05/05'),'zzz.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/05/15'),'zzz.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/05/25'),'zzz.jp','zzz_005','c@ex.com')
+    ,(TD_TIME_PARSE('2023/06/05'),'zzz.jp',NULL,NULL)
+    ,(TD_TIME_PARSE('2023/06/15'),'zzz.jp','zzz_005','c@ex.com')
+    ,(TD_TIME_PARSE('2023/06/25'),'zzz.jp','zzz_005','c@ex.com')
+  ) AS t(time, site, td_client_id, email);
\ No newline at end of file
diff --git a/tool-box/id-unification-samples/queries/generate_samples_ex4.sql b/tool-box/id-unification-samples/queries/generate_samples_ex4.sql
new file mode 100644
index 00000000..17a879a5
--- /dev/null
+++ b/tool-box/id-unification-samples/queries/generate_samples_ex4.sql
@@ -0,0 +1,13 @@
+DROP TABLE IF EXISTS ${td.database}.${td.tbl_aaa};
+CREATE TABLE ${td.database}.${td.tbl_aaa} AS
+SELECT
+  member_id, email, tel, name
+FROM
+  ( VALUES
+     ('1', 'a@ex.com',1111,'Taka')
+    ,('2', 'a@ex.com',2222,'Tatsuo')
+    ,('3', 'b@ex.com',3333,'Naruse')
+    ,('3', 'b@ex.com',4444,'Yuichiro')
+    ,(NULL,'c@ex.com',5555,'Minero')
+    ,(NULL,'c@ex.com',6666,'Kaz')
+  ) AS t(member_id, email, tel, name);
\ No newline at end of file
diff --git a/tool-box/id-unification-samples/queries/insert_samples_ex5.sql b/tool-box/id-unification-samples/queries/insert_samples_ex5.sql
new file mode 100644
index 00000000..c3fd95b0
--- /dev/null
+++ b/tool-box/id-unification-samples/queries/insert_samples_ex5.sql
@@ -0,0 +1,63 @@
+INSERT INTO ${td.database}.${td.tbl_aaa}
+SELECT
+  time, site, td_client_id, td_global_id
+FROM
+  ( VALUES
+       (TD_TIME_PARSE('2023/06/05'), 'aaa.jp','aaa_003','3rd_016')
+      ,(TD_TIME_PARSE('2023/06/15'), 'aaa.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/06/25'), 'aaa.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/07/05'), 'aaa.jp','aaa_004','3rd_017')
+      ,(TD_TIME_PARSE('2023/07/15'), 'aaa.jp','aaa_004','3rd_018')
+      ,(TD_TIME_PARSE('2023/07/25'), 'aaa.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/08/05'), 'aaa.jp','aaa_005','3rd_018')
+      ,(TD_TIME_PARSE('2023/08/15'), 'aaa.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/08/25'), 'aaa.jp','aaa_005','3rd_019')
+  ) AS t(time, site, td_client_id, td_global_id);
+
+INSERT INTO ${td.database}.${td.tbl_xxx}
+SELECT
+  time, site, td_client_id, td_global_id
+FROM
+  ( VALUES
+       (TD_TIME_PARSE('2023/06/05'), 'xxx.jp','xxx_004','3rd_016')
+      ,(TD_TIME_PARSE('2023/06/15'), 'xxx.jp','xxx_004','3rd_017')
+      ,(TD_TIME_PARSE('2023/06/25'), 'xxx.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/07/05'), 'xxx.jp','xxx_005','3rd_018')
+      ,(TD_TIME_PARSE('2023/07/15'), 'xxx.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/07/25'), 'xxx.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/08/05'), 'xxx.jp','xxx_005','3rd_018')
+      ,(TD_TIME_PARSE('2023/08/15'), 'xxx.jp','xxx_006','3rd_019')
+      ,(TD_TIME_PARSE('2023/08/25'), 'xxx.jp',NULL,NULL)
+  ) AS t(time, site, td_client_id, td_global_id);
+
+INSERT INTO ${td.database}.${td.tbl_yyy}
+SELECT
+  time, site, td_client_id, td_global_id
+FROM
+  ( VALUES
+       (TD_TIME_PARSE('2023/06/05'), 'yyy.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/06/15'), 'yyy.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/06/25'), 'yyy.jp','yyy_005','3rd_018')
+      ,(TD_TIME_PARSE('2023/07/05'), 'yyy.jp','yyy_006','3rd_019')
+      ,(TD_TIME_PARSE('2023/07/15'), 'yyy.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/07/25'), 'yyy.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/08/05'), 'yyy.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/08/15'), 'yyy.jp','yyy_006','3rd_019')
+      ,(TD_TIME_PARSE('2023/08/25'), 'yyy.jp','yyy_007','3rd_019')
+  ) AS t(time, site, td_client_id, td_global_id);
+
+INSERT INTO ${td.database}.${td.tbl_zzz}
+SELECT
+  time, site, td_client_id, td_global_id
+FROM
+  ( VALUES
+       (TD_TIME_PARSE('2023/06/05'), 'zzz.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/06/15'), 'zzz.jp','zzz_005','3rd_017')
+      ,(TD_TIME_PARSE('2023/06/25'), 'zzz.jp','zzz_005','3rd_018')
+      ,(TD_TIME_PARSE('2023/07/05'), 'zzz.jp','zzz_006','3rd_018')
+      ,(TD_TIME_PARSE('2023/07/15'), 'zzz.jp','zzz_007','3rd_018')
+      ,(TD_TIME_PARSE('2023/07/25'), 'zzz.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/08/05'), 'zzz.jp',NULL,NULL)
+      ,(TD_TIME_PARSE('2023/08/15'), 'zzz.jp','zzz_008','3rd_019')
+      ,(TD_TIME_PARSE('2023/08/25'), 'zzz.jp',NULL,NULL)
+  ) AS t(time, site, td_client_id, td_global_id);
\ No newline at end of file
diff --git a/tool-box/id-unification-samples/test_id_unification_ex1.dig b/tool-box/id-unification-samples/test_id_unification_ex1.dig
new file mode 100644
index 00000000..093d4cbc
--- /dev/null
+++ b/tool-box/id-unification-samples/test_id_unification_ex1.dig
@@ -0,0 +1,33 @@
+_export:
+  td:
+    database:  test_id_unification_ex1
+    unif_name: test_id_unification_ex1
+    ms_name: master_table_ex1
+  !include : config/params.yml
+
+##### Comment out all but the first execution.
++prepare_dbs:
+  td_ddl>:
+  create_databases: ["${td.database}"]
+
++generate_samples:
+  td>: queries/generate_samples_ex1.sql
+#####
+
++call_unification:
+  http_call>: https://api-cdp.treasuredata.com/unifications/workflow_call  
+  headers:
+    - authorization: ${secret:td.apikey}
+  method: POST
+  retry: true
+  content_format: json
+  content:
+    run_canonical_ids: true
+    run_enrichments: true
+    run_master_tables: true
+
+    full_refresh: true
+    keep_debug_tables: true
+
+    unification:
+      !include : unification_ex1.yml
\ No newline at end of file
diff --git a/tool-box/id-unification-samples/test_id_unification_ex2.dig b/tool-box/id-unification-samples/test_id_unification_ex2.dig
new file mode 100644
index 00000000..25cedf43
--- /dev/null
+++ b/tool-box/id-unification-samples/test_id_unification_ex2.dig
@@ -0,0 +1,34 @@
+_export:
+  td:
+    database:  test_id_unification_ex2
+    unif_name: test_id_unification_ex2
+    ms_name: master_table_ex2
+  !include : config/params.yml
+
+##### Comment out all but the first execution.
++prepare_dbs:
+  td_ddl>:
+  create_databases: ["${td.database}"]
+
++generate_samples:
+  td>: queries/generate_samples_ex2.sql
+#####
+
+
++call_unification:
+  http_call>: https://api-cdp.treasuredata.com/unifications/workflow_call  
+  headers:
+    - authorization: ${secret:td.apikey}
+  method: POST
+  retry: true
+  content_format: json
+  content:
+    run_canonical_ids: true
+    run_enrichments: true
+    run_master_tables: true
+
+    full_refresh: true
+    keep_debug_tables: true
+
+    unification:
+      !include : unification_ex2.yml
\ No newline at end of file
diff --git a/tool-box/id-unification-samples/test_id_unification_ex3.dig b/tool-box/id-unification-samples/test_id_unification_ex3.dig
new file mode 100644
index 00000000..5e7c311f
--- /dev/null
+++ b/tool-box/id-unification-samples/test_id_unification_ex3.dig
@@ -0,0 +1,34 @@
+_export:
+  td:
+    database:  test_id_unification_ex1 # not ex3 but ex1
+    unif_name: test_id_unification_ex3
+    ms_name: master_table_ex3
+  !include : config/params.yml
+
+##### Comment out all but the first execution.
+# Samples are stored in the ex1 database.
+# +prepare_dbs:
+#   td_ddl>:
+#   create_databases: ["${td.database}"]
+#
+# +generate_samples:
+#   td>: queries/generate_samples_ex1.sql
+#####
+
++call_unification:
+  http_call>: https://api-cdp.treasuredata.com/unifications/workflow_call  
+  headers:
+    - authorization: ${secret:td.apikey}
+  method: POST
+  retry: true
+  content_format: json
+  content:
+    run_canonical_ids: true
+    run_enrichments: true
+    run_master_tables: true
+
+    full_refresh: true
+    keep_debug_tables: true
+
+    unification:
+      !include : unification_ex3.yml
\ No newline at end of file
diff --git a/tool-box/id-unification-samples/test_id_unification_ex4.dig b/tool-box/id-unification-samples/test_id_unification_ex4.dig
new file mode 100644
index 00000000..0c8897ff
--- /dev/null
+++ b/tool-box/id-unification-samples/test_id_unification_ex4.dig
@@ -0,0 +1,33 @@
+_export:
+  td:
+    database:  test_id_unification_ex4
+    unif_name: test_id_unification_ex4
+    ms_name: master_table_ex4
+  !include : config/params.yml
+
+##### Comment out all but the first execution.
++prepare_dbs:
+  td_ddl>:
+  create_databases: ["${td.database}"]
+
++generate_samples:
+  td>: queries/generate_samples_ex4.sql
+#####
+
++call_unification:
+  http_call>: https://api-cdp.treasuredata.com/unifications/workflow_call  
+  headers:
+    - authorization: ${secret:td.apikey}
+  method: POST
+  retry: true
+  content_format: json
+  content:
+    run_canonical_ids: true
+    run_enrichments: true
+    run_master_tables: true
+
+    full_refresh: true
+    keep_debug_tables: true
+
+    unification:
+      !include : unification_ex4.yml
\ No newline at end of file
diff --git a/tool-box/id-unification-samples/test_id_unification_ex5.dig b/tool-box/id-unification-samples/test_id_unification_ex5.dig
new file mode 100644
index 00000000..147f0ef4
--- /dev/null
+++ b/tool-box/id-unification-samples/test_id_unification_ex5.dig
@@ -0,0 +1,37 @@
+timezone: UTC #Asia/Tokyo
+schedule:
+  daily>: 09:00:00
+
+_export:
+  td:
+    database:  test_id_unification_ex5
+    unif_name: test_id_unification_ex5
+    ms_name: master_table_ex5
+  !include : config/params.yml
+
+##### Comment out all but the first execution.
++prepare_dbs:
+  td_ddl>:
+  create_databases: ["${td.database}"]
+
++generate_samples:
+  td>: queries/generate_samples_ex1.sql
+#####
+
++call_unification:
+  http_call>: https://api-cdp.treasuredata.com/unifications/workflow_call  
+  headers:
+    - authorization: ${secret:td.apikey}
+  method: POST
+  retry: true
+  content_format: json
+  content:
+    run_canonical_ids: true
+    run_enrichments: true
+    run_master_tables: true
+
+    full_refresh: false
+    keep_debug_tables: true
+
+    unification:
+      !include : unification_ex5.yml
\ No newline at end of file
diff --git a/tool-box/id-unification-samples/unification_ex1.yml b/tool-box/id-unification-samples/unification_ex1.yml
new file mode 100644
index 00000000..66f42ce4
--- /dev/null
+++ b/tool-box/id-unification-samples/unification_ex1.yml
@@ -0,0 +1,59 @@
+name: ${td.unif_name}
+
+keys:
+  - name: td_client_id
+    invalid_texts: ['']
+
+  - name: td_global_id
+    valid_regexp: "3rd_*"
+    invalid_texts: ['']
+
+tables:
+  - database: ${td.database}
+    table: ${td.tbl_aaa}
+    key_columns:
+      - {column: td_client_id, key: td_client_id}
+      - {column: td_global_id, key: td_global_id}
+  - database: ${td.database}
+    table: ${td.tbl_xxx}
+    key_columns:
+      - {column: td_client_id, key: td_client_id}
+      - {column: td_global_id, key: td_global_id}
+
+  - database: ${td.database}
+    table: ${td.tbl_yyy}
+    key_columns:
+      - {column: td_client_id, key: td_client_id}
+      - {column: td_global_id, key: td_global_id}
+
+  - database: ${td.database}
+    table: ${td.tbl_zzz}
+    key_columns:
+      - {column: td_client_id, key: td_client_id}
+      - {column: td_global_id, key: td_global_id}
+
+canonical_ids:
+  - name: unified_cookie_id
+    merge_by_keys: [td_client_id, td_global_id]
+    merge_iterations: 5
+
+master_tables:
+  - name: ${td.ms_name}
+    canonical_id: unified_cookie_id
+    attributes:
+      - name: td_client_id
+        invalid_texts: ['']
+        array_elements: 5
+        source_columns:
+          - {table: '${td.tbl_aaa}', order: first, order_by: td_client_id, priority: 1}
+          - {table: '${td.tbl_xxx}', order: first, order_by: td_client_id, priority: 2}
+          - {table: '${td.tbl_yyy}', order: first, order_by: td_client_id, priority: 3}
+          - {table: '${td.tbl_zzz}', order: first, order_by: td_client_id, priority: 4}
+      - name: td_global_id
+        valid_regexp: "3rd_*"
+        invalid_texts: ['']
+        source_columns:
+          - {table: '${td.tbl_aaa}', order: last, order_by: time, priority: 1}
+          - {table: '${td.tbl_xxx}', order: last, order_by: time, priority: 1}
+          - {table: '${td.tbl_yyy}', order: last, order_by: time, priority: 1}
+          - {table: '${td.tbl_zzz}', order: last, order_by: time, priority: 1}                    
\ No newline at end of file
diff --git a/tool-box/id-unification-samples/unification_ex2.yml b/tool-box/id-unification-samples/unification_ex2.yml
new file mode 100644
index 00000000..29c5e9cf
--- /dev/null
+++ b/tool-box/id-unification-samples/unification_ex2.yml
@@ -0,0 +1,72 @@
+name: ${td.unif_name}
+
+keys:
+  - name: td_client_id
+    invalid_texts: ['']
+
+  - name: td_global_id
+    valid_regexp: "3rd_*"
+    invalid_texts: ['']
+
+  - name: td_ssc_id
+    valid_regexp: "ssc_*"
+    invalid_texts: ['']
+
+  - name: email
+    valid_regexp: ".*@.*"
+    invalid_texts: ['']
+
+tables:
+  - database: ${td.database}
+    table: ${td.tbl_aaa}
+    key_columns:
+      - {column: td_client_id, key: td_client_id}
+      - {column: td_global_id, key: td_global_id}
+      - {column: td_ssc_id, key: td_ssc_id}
+
+  - database: ${td.database}
+    table: ${td.tbl_xxx}
+    key_columns:
+      - {column: td_ssc_id, key: td_ssc_id}
+      - {column: td_global_id, key: td_global_id}
+
+  - database: ${td.database}
+    table: ${td.tbl_yyy}
+    key_columns:
+      - {column: email, key: email}
+      - {column: td_ssc_id, key: td_ssc_id}
+
+  - database: ${td.database}
+    table: ${td.tbl_zzz}
+    key_columns:
+      - {column: td_client_id, key: td_client_id}
+      - {column: email, key: email}
+
+canonical_ids:
+  - name: person_id
+    merge_by_keys: [email, td_ssc_id, td_client_id, td_global_id]
+    merge_iterations: 5
+
+master_tables:
+  - name: ${td.ms_name}
+    canonical_id: person_id
+    attributes:
+      - name: email
+        source_columns:
+          - {table: '${td.tbl_yyy}', order: last, order_by: time, priority: 1}
+          - {table: '${td.tbl_zzz}', order: last, order_by: time, priority: 1}
+      - name: td_ssc_id
+        array_elements: 5
+        source_columns:
+          - {table: '${td.tbl_xxx}', order: last, order_by: time, priority: 1}
+          - {table: '${td.tbl_yyy}', order: last, order_by: time, priority: 2}
+      - name: td_client_id
+        array_elements: 5
+        source_columns:
+          - {table: '${td.tbl_aaa}', order: last, order_by: time, priority: 1}
+          - {table: '${td.tbl_zzz}', order: last, order_by: time, priority: 4}
+      - name: td_global_id
+        array_elements: 5
+        source_columns:
+          - {table: '${td.tbl_aaa}', order: last, order_by: time, priority: 1}
+          - {table: '${td.tbl_xxx}', order: last, order_by: time, priority: 2}
\ No newline at end of file
diff --git a/tool-box/id-unification-samples/unification_ex3.yml b/tool-box/id-unification-samples/unification_ex3.yml
new file mode 100644
index 00000000..7024d935
--- /dev/null
+++ b/tool-box/id-unification-samples/unification_ex3.yml
@@ -0,0 +1,77 @@
+name: ${td.unif_name}
+
+keys:
+  - name: td_client_id
+    invalid_texts: ['']
+
+  - name: td_global_id
+    valid_regexp: "3rd_*"
+    invalid_texts: ['']
+
+tables:
+  - database: ${td.database}
+    table: ${td.tbl_aaa}
+    key_columns:
+      - {column: td_client_id, key: td_client_id}
+      - {column: td_global_id, key: td_global_id}
+
+  - database: ${td.database}
+    table: ${td.tbl_xxx}
+    key_columns:
+      - {column: td_client_id, key: td_client_id}
+      - {column: td_global_id, key: td_global_id}
+
+  - database: ${td.database}
+    table: ${td.tbl_yyy}
+    key_columns:
+      - {column: td_client_id, key: td_client_id}
+      - {column: td_global_id, key: td_global_id}
+
+  - database: ${td.database}
+    table: ${td.tbl_zzz}
+    key_columns:
+      - {column: td_client_id, key: td_client_id}
+      - {column: td_global_id, key: td_global_id}
+
+canonical_ids:
+  - name: brand_id_ax
+    merge_by_keys: [td_client_id, td_global_id]
+    source_tables: ['${td.tbl_aaa}','${td.tbl_xxx}']
+    merge_iterations: 5
+
+  - name: brand_id_yz
+    merge_by_keys: [td_client_id, td_global_id]
+    source_tables: ['${td.tbl_yyy}','${td.tbl_zzz}']
+    merge_iterations: 5
+
+  - name: unified_brand_id
+    merge_by_keys: []
+    merge_by_canonical_ids: [brand_id_ax, brand_id_yz]
+    merge_iterations: 5
+
+master_tables:
+  - name: ${td.ms_name}
+    canonical_id: unified_brand_id
+
+    attributes:
+      - name: brand_id_ax
+        source_canonical_id: brand_id_ax
+
+      - name: brand_id_yz
+        source_canonical_id: brand_id_yz
+
+      - name: td_client_id
+        invalid_texts: ['']
+        source_columns:
+          - {table: '${td.tbl_aaa}', order: first, order_by: td_client_id, priority: 1}
+          - {table: '${td.tbl_xxx}', order: first, order_by: td_client_id, priority: 1}
+          - {table: '${td.tbl_yyy}', order: first, order_by: td_client_id, priority: 1}
+          - {table: '${td.tbl_zzz}', order: first, order_by: td_client_id, priority: 1}
+      - name: td_global_id
+        valid_regexp: "3rd_*"
+        invalid_texts: ['']
+        source_columns:
+          - {table: '${td.tbl_aaa}', order: last, order_by: time, priority: 1}
+          - {table: '${td.tbl_xxx}', order: last, order_by: time, priority: 1}
+          - {table: '${td.tbl_yyy}', order: last, order_by: time, priority: 1}
+          - {table: '${td.tbl_zzz}', order: last, order_by: time, priority: 1}
\ No newline at end of file
diff --git a/tool-box/id-unification-samples/unification_ex4.yml b/tool-box/id-unification-samples/unification_ex4.yml
new file mode 100644
index 00000000..c6013704
--- /dev/null
+++ b/tool-box/id-unification-samples/unification_ex4.yml
@@ -0,0 +1,37 @@
+name: ${td.unif_name}
+
+keys:
+  - name: member_id
+  - name: email
+
+tables:
+  - database: ${td.database}
+    table: ${td.tbl_aaa}
+    key_columns:
+      - {column: member_id, key: member_id}
+      - {column: email, key: email}
+
+canonical_ids:
+  - name: person_id
+    merge_by_keys: [member_id, email]
+    merge_iterations: 3
+    do_not_merge_key: member_id
+
+master_tables:
+  - name: ${td.ms_name}
+    canonical_id: person_id
+    attributes:
+      - name: member_id
+        source_columns:
+          - {table: '${td.tbl_aaa}', priority: 1}
+      - name: email
+        source_columns:
+          - {table: '${td.tbl_aaa}', priority: 1}
+      - name: tel
+        array_elements: 2
+        source_columns:
+          - {table: '${td.tbl_aaa}', priority: 1}
+      - name: name
+        array_elements: 2
+        source_columns:
+          - {table: '${td.tbl_aaa}', priority: 1}
\ No newline at end of file
diff --git a/tool-box/id-unification-samples/unification_ex5.yml b/tool-box/id-unification-samples/unification_ex5.yml
new file mode 100644
index 00000000..77034685
--- /dev/null
+++ b/tool-box/id-unification-samples/unification_ex5.yml
@@ -0,0 +1,58 @@
+name: ${td.unif_name}
+
+keys:
+  - name: td_client_id
+  - name: td_global_id
+
+tables:
+  - database: ${td.database}
+    table: ${td.tbl_aaa}
+    incremental_columns: [time]
+    key_columns:
+      - {column: td_client_id, key: td_client_id}
+      - {column: td_global_id, key: td_global_id}
+  - database: ${td.database}
+    table: ${td.tbl_xxx}
+    incremental_columns: [time]
+    key_columns:
+      - {column: td_client_id, key: td_client_id}
+      - {column: td_global_id, key: td_global_id}
+
+  - database: ${td.database}
+    table: ${td.tbl_yyy}
+    incremental_columns: [time]
+    key_columns:
+      - {column: td_client_id, key: td_client_id}
+      - {column: td_global_id, key: td_global_id}
+
+  - database: ${td.database}
+    table: ${td.tbl_zzz}
+    incremental_columns: [time]
+    key_columns:
+      - {column: td_client_id, key: td_client_id}
+      - {column: td_global_id, key: td_global_id}
+
+canonical_ids:
+  - name: unified_cookie_id
+    merge_by_keys: [td_client_id, td_global_id]
+    merge_iterations: 5
+    incremental_merge_iterations: 3
+
+master_tables:
+  - name: ${td.ms_name}
+    canonical_id: unified_cookie_id
+    attributes:
+      - name: td_client_id
+        array_elements: 5
+        source_columns:
+          - {table: '${td.tbl_aaa}', order: last, order_by: time, priority: 1}
+          - {table: '${td.tbl_xxx}', order: last, order_by: time, priority: 1}
+          - {table: '${td.tbl_yyy}', order: last, order_by: time, priority: 1}
+          - {table: '${td.tbl_zzz}', order: last, order_by: time, priority: 1}
+      - name: td_global_id
+        array_elements: 5
+        source_columns:
+          - {table: '${td.tbl_aaa}', order: last, order_by: time, priority: 1}
+          - {table: '${td.tbl_xxx}', order: last, order_by: time, priority: 1}
+          - {table: '${td.tbl_yyy}', order: last, order_by: time, priority: 1}
+          - {table: '${td.tbl_zzz}', order: last, order_by: time, priority: 1}
\ No newline at end of file