Difference between revisions of "Patent Data Processing - SQL Steps"

From edegan.com
Jump to navigation Jump to search
Line 1: Line 1:
 
** Assignees Data:
 
** Assignees Data:
 
CREATE TABLE assignees_temp2 (
 
CREATE TABLE assignees_temp2 (
 
 
lastname  varchar,
 
lastname  varchar,
 
firstname varchar,
 
firstname varchar,
Line 16: Line 15:
 
asgseq int,
 
asgseq int,
 
asgtype integer
 
asgtype integer
 
 
);
 
);
  
Line 40: Line 38:
 
PatentData:
 
PatentData:
 
  Column    |      Type        | Modifiers
 
  Column    |      Type        | Modifiers
-------------+-------------------+-----------
+
-------------+-------------------+-----------
 
  patent      | integer          |
 
  patent      | integer          |
 
  asgtype    | integer          |
 
  asgtype    | integer          |
Line 108: Line 106:
 
Patent_2015:
 
Patent_2015:
 
  Column    |  Type  | Modifiers
 
  Column    |  Type  | Modifiers
---------------+---------+-----------
+
---------------+---------+-----------
 
  lastname      | text    |
 
  lastname      | text    |
 
  firstname    | text    |
 
  firstname    | text    |
Line 186: Line 184:
  
  
 
+
Patentdata:
 
+
Column  |      Type        | Modifiers
Patentdata:
+
---------+-------------------+-----------
Column  |      Type        | Modifiers
 
---------+-------------------+-----------
 
 
  patent  | integer          |
 
  patent  | integer          |
 
  kind    | character varying |
 
  kind    | character varying |

Revision as of 16:20, 21 June 2016

    • Assignees Data:

CREATE TABLE assignees_temp2 ( lastname varchar, firstname varchar, address varchar, postcode varchar, orgname varchar, --assignee varchar, city varchar, --city2 varchar, country varchar, --country2 varchar, patentnumber int, --patent integer, state varchar, --state2 varchar, patentcountry varchar, nationality2 varchar, residence varchar, asgseq int, asgtype integer );

CREATE TABLE assignees ( lastname varchar, firstname varchar, address varchar, postcode varchar, orgname varchar, city varchar, country varchar, patentnumber int, state varchar, patentcountry varchar, nationality2 varchar, residence varchar, asgseq int, asgtype integer );


PatentData:

Column    |       Type        | Modifiers
-------------+-------------------+-----------
patent      | integer           |
asgtype     | integer           |
assignee    | character varying |
city        | character varying |
state       | character varying |
country     | character varying |
nationality | character varying |
residence   | character varying |
asgseq      | integer           |

(

patent int,
asgtype int,
assignee varchar ,
city varchar ,
state varchar ,
country varchar ,
nationality varchar ,
residence varchar ,
asgseq int           

)

INSERT INTO assignees_merge ( SELECT 'null', 'null', 'null', 'null', a.assignee, a.city, a.country, a.patent, a.state, 'null', a.nationality, a.residence, a.asgseq, a.asgtype FROM assignees a );

/// Reference: CREATE TABLE assignees_temp2 (

lastname varchar, firstname varchar, address varchar, postcode varchar, orgname varchar, --assignee varchar, city varchar, --city2 varchar, country varchar, --country2 varchar, patentnumber int, --patent integer, state varchar, --state2 varchar, patentcountry varchar, nationality2 varchar, residence varchar, asgseq int, asgtype integer

); //////


Patent_2015:

Column     |  Type   | Modifiers
---------------+---------+-----------
lastname      | text    |
firstname     | text    |
orgname       | text    |
city          | text    |
country       | text    |
patentcountry | text    |
patentnumber  | integer |
state         | text    |
address       | text    |
postcode      | text    |


(

lastname varchar,
firstname varchar,
orgname varchar,
city varchar,
country varchar,
patentcountry varchar,
patentnumber int,
state varchar,
address varchar,
postcode varchar

)

INSERT INTO assignees_merge ( SELECT assignees.lastname, assignees.firstname, assignees.address, assignees.postcode, assignees.orgname, assignees.city, assignees.country, assignees.patentnumber, assignees.state, assignees.patentcountry, 'null', 'null', -1, -1 FROM assignees );


\COPY assignees_merge TO '/tmp/assignees_merge_export.txt' DELIMITER AS E'\t' HEADER NULL AS CSV; \COPY assignees FROM '/tmp/assignees_merge_export.txt' DELIMITER AS E'\t' HEADER NULL AS CSV; --1607724

\COPY assignees_merge TO '/tmp/assignees_merge_export1.txt' DELIMITER AS E'\t' HEADER NULL AS CSV; \COPY assignees FROM '/tmp/assignees_merge_export1.txt' DELIMITER AS E'\t' HEADER NULL AS CSV; --3818842



SELECT count(*), * from assignees GROUP BY lastname, firstname, address, postcode, orgname, city, country, patentnumber, state, patentcountry, nationality2, residence, asgseq, asgtype HAVING COUNT(*) > 1

CREATE TABLE Assignees2 AS SELECT * from assignees GROUP BY lastname, firstname, address, postcode, orgname, city, country, patentnumber, state, patentcountry, nationality2, residence, asgseq, asgtype HAVING COUNT(*) = 1

DROP TABLE Assignees; ALTER TABLE Assignees2 RENAME TO Assignees;

--


Patentdata:
Column  |       Type        | Modifiers
---------+-------------------+-----------
patent  | integer           |
kind    | character varying |
claims  | integer           |
apptype | integer           |
appnum  | integer           |
gdate   | date              |
gyear   | integer           |
appdate | date              |
appyear | integer           |

Column Names:

patent int,
kind varchar,
claims int,
apptype int,
appnum int,
gdate date,
gyear int,
appdate date,
appyear int



Patent_2015:
            Column             |  Type   | Modifiers
-------------------------------+---------+-----------
 patentnumber                  | int | not null
 kind                          | varchar    |
 grantdate                     | date    |
 type                          | varchar    |
 applicationnumber             | varchar    |
 filingdate                    | date    |
 prioritydate                  | date    |
 prioritycountry               | varchar    |
 prioritypatentnumber          | varchar    |
 ussubclass                    | varchar    |
 maingroup                     | varchar    |
 subgroup                      | varchar    |
 cpcsubclass                   | varchar    |
 cpcmaingroup                  | varchar    |
 cpcsubgroup                   | varchar    |
 classificationnationalcountry | varchar    |
 classificationnationalclass   | varchar    |
 title                         | varchar    |
 numberofclaims                | int |
 primaryexaminerfirstname      | varchar    |
 primaryexaminerlastname       | varchar    |
 primaryexaminerdepartment     | varchar    |
 pctpatentnumber               | varchar    |
 filename                      | varchar    |
 
 Column Names:
   patentnumber int,
   kind varchar,
   grantdate date,
   type varchar,
   applicationnumber varchar,
   filingdate date,
   prioritydate date,
   prioritycountry varchar,
   prioritypatentnumber varchar,
   ussubclass varchar,
   maingroup varchar,
   subgroup varchar,
   cpcsubclass varchar,
   cpcmaingroup varchar,
   cpcsubgroup varchar,
   classificationnationalcountry varchar,
   classificationnationalclass varchar,
   title varchar,
   numberofclaims int,
   primaryexaminerfirstname varchar,
   primaryexaminerlastname varchar,
   primaryexaminerdepartment varchar,
   pctpatentnumber varchar,
   filename varchar

Combined Schema:

Column Names:

patent int,
kind varchar,
claims int,
apptype int,
appnum int,
gdate date,
gyear int,
appdate date,
appyear int


   patentnumber int, -- patent 
   kind varchar, -- kind
   grantdate date, --gdate
   type varchar,
   applicationnumber varchar,
   filingdate date,
   prioritydate date,
   prioritycountry varchar,
   prioritypatentnumber varchar,
   ussubclass varchar,
   maingroup varchar,
   subgroup varchar,
   cpcsubclass varchar,
   cpcmaingroup varchar,
   cpcsubgroup varchar,
   classificationnationalcountry varchar,
   classificationnationalclass varchar,
   title varchar,
   numberofclaims int,
   primaryexaminerfirstname varchar,
   primaryexaminerlastname varchar,
   primaryexaminerdepartment varchar,
   pctpatentnumber varchar,
   filename varchar
   claims int,
   apptype int,
   appnum int,
   gyear int,
   appdate date,
   appyear int
   
   
   Output Schema: patents
   
     CREATE TABLE patents_merged( 
       patentnumber int, 
       kind varchar, 
       grantdate date,
       type varchar,
       applicationnumber varchar,
       filingdate date,
       prioritydate date,
       prioritycountry varchar,
       prioritypatentnumber varchar,
       ussubclass varchar,
       maingroup varchar,
       subgroup varchar,
       cpcsubclass varchar,
       cpcmaingroup varchar,
       cpcsubgroup varchar,
       classificationnationalcountry varchar,
       classificationnationalclass varchar,
       title varchar,
       numberofclaims int,
       primaryexaminerfirstname varchar,
       primaryexaminerlastname varchar,
       primaryexaminerdepartment varchar,
       pctpatentnumber varchar,
       filename varchar,
       claims int,
       apptype int,
       appnum int,
       gyear int,
       appdate date,
       appyear int
       );
       
   
   patentdata:
   INSERT INTO patents_merged
   (
   		SELECT	
   		patent, 

kind, gdate, 'NULL', 'NULL', NULL, NULL, 'NULL', 'NULL', 'NULL', 'NULL', 'NULL', 'NULL', 'NULL', 'NULL', 'NULL', 'NULL', 'NULL', -1, 'NULL', 'NULL', 'NULL', 'NULL', 'NULL', claims, apptype, appnum, gyear, appdate,

       	appyear
       	FROM patents
   );
   -- RESULT : INSERT 0 3984771
   
   patent_2015:
   INSERT INTO patents_merged
   (
   	SELECT
   		patentnumber, 

kind, grantdate, type, applicationnumber, filingdate, prioritydate, prioritycountry, prioritypatentnumber, ussubclass, maingroup, subgroup, cpcsubclass, cpcmaingroup, cpcsubgroup, classificationnationalcountry, classificationnationalclass, title, numberofclaims, primaryexaminerfirstname, primaryexaminerlastname, primaryexaminerdepartment, pctpatentnumber, filename, -1, -1, -1, -1, NULL,

       	-1
   	FROM patents
   );
   -- RESULT : INSERT 0 1646225
   

COPY SCRIPTS: patentdata: \COPY patents_merged TO '/tmp/merged_patents_export1.txt' DELIMITER AS E'\t' HEADER NULL AS CSV; --COPY 3984771

patent_2015: \COPY patents_merged TO '/tmp/merged_patents_export.txt' DELIMITER AS E'\t' HEADER NULL AS CSV; --COPY 1646225

PATENTS TABLE \COPY patents FROM '/tmp/merged_patents_export1.txt' DELIMITER AS E'\t' HEADER NULL AS CSV; -- RESULT : COPY 3984771 \COPY patents FROM '/tmp/merged_patents_export.txt' DELIMITER AS E'\t' HEADER NULL AS CSV; -- RESULT : COPY 1646225


TESTING: select count(*) FROM (SELECT DISTINCT patentnumber FROM patents) AS t; --RESULT: 5411151 EXPECTED: 5426566

SELECT COUNT(*), * FROM patents GROUP BY patentnumber, kind, grantdate, type, applicationnumber, filingdate, prioritydate, prioritycountry, prioritypatentnumber, ussubclass, maingroup, subgroup, cpcsubclass, cpcmaingroup, cpcsubgroup, classificationnationalcountry, classificationnationalclass, title, numberofclaims, primaryexaminerfirstname, primaryexaminerlastname, primaryexaminerdepartment, pctpatentnumber, filename, claims, apptype, appnum, gyear, appdate, appyear HAVING COUNT(*) > 1;

SELECT patentnumber, count(*) FROM patents GROUP BY patentnumber HAVING count(*)>1; --7640598


SELECT * FROM patents op WHERE op.patentnumber IN ( SELECT ip.patentnumber FROM patents ip GROUP BY ip.patentnumber HAVING COUNT(*)>1 ) ORDER BY op.patentnumber;

( SELECT * INTO patentsCleaned FROM patents op WHERE op.patentnumber IN ( SELECT ip.patentnumber FROM patents ip GROUP BY ip.patentnumber HAVING COUNT(*)=1 ) ORDER BY op.patentnumber ) --SELECT 5191306


INSERT INTO patentsCleaned( SELECT * FROM patents op WHERE op.patentnumber IN ( SELECT ip.patentnumber FROM patents ip GROUP BY ip.patentnumber HAVING COUNT(*)>1 ) AND op.applicationnumber NOT LIKE 'NULL' ORDER BY op.patentnumber );

--219845

TESTING: allpatent=# select count(*) from patentsCleaned;

 count

5411151

(1 row)

allpatent=# select count(*), patentnumber FROM patentsCleaned group by patentnumber having count(*) > 1;

count | patentnumber

+--------------

(0 rows)


                    • INDEX CREATION **************

ALTER TABLE patents ADD PRIMARY KEY (patentnumber); -- RESULT : ALTER TABLE allpatent=# CREATE UNIQUE INDEX patent_idx ON patents (patentnumber);

allpatent=# CREATE INDEX ON assignees (orgname); CREATE INDEX




    • Patents

Patentdata: Column | Type | Modifiers


+-------------------+-----------

patent  | integer           |
kind    | character varying |
claims  | integer           |
apptype | integer           |
appnum  | integer           |
gdate   | date              |
gyear   | integer           |
appdate | date              |
appyear | integer           |

Column Names:

patent int,
kind varchar,
claims int,
apptype int,
appnum int,
gdate date,
gyear int,
appdate date,
appyear int



Patent_2015:
            Column             |  Type   | Modifiers
-------------------------------+---------+-----------
 patentnumber                  | int | not null
 kind                          | varchar    |
 grantdate                     | date    |
 type                          | varchar    |
 applicationnumber             | varchar    |
 filingdate                    | date    |
 prioritydate                  | date    |
 prioritycountry               | varchar    |
 prioritypatentnumber          | varchar    |
 ussubclass                    | varchar    |
 maingroup                     | varchar    |
 subgroup                      | varchar    |
 cpcsubclass                   | varchar    |
 cpcmaingroup                  | varchar    |
 cpcsubgroup                   | varchar    |
 classificationnationalcountry | varchar    |
 classificationnationalclass   | varchar    |
 title                         | varchar    |
 numberofclaims                | int |
 primaryexaminerfirstname      | varchar    |
 primaryexaminerlastname       | varchar    |
 primaryexaminerdepartment     | varchar    |
 pctpatentnumber               | varchar    |
 filename                      | varchar    |
 
 Column Names:
   patentnumber int,
   kind varchar,
   grantdate date,
   type varchar,
   applicationnumber varchar,
   filingdate date,
   prioritydate date,
   prioritycountry varchar,
   prioritypatentnumber varchar,
   ussubclass varchar,
   maingroup varchar,
   subgroup varchar,
   cpcsubclass varchar,
   cpcmaingroup varchar,
   cpcsubgroup varchar,
   classificationnationalcountry varchar,
   classificationnationalclass varchar,
   title varchar,
   numberofclaims int,
   primaryexaminerfirstname varchar,
   primaryexaminerlastname varchar,
   primaryexaminerdepartment varchar,
   pctpatentnumber varchar,
   filename varchar

Combined Schema:

Column Names:

patent int,
kind varchar,
claims int,
apptype int,
appnum int,
gdate date,
gyear int,
appdate date,
appyear int


   patentnumber int, -- patent 
   kind varchar, -- kind
   grantdate date, --gdate
   type varchar,
   applicationnumber varchar,
   filingdate date,
   prioritydate date,
   prioritycountry varchar,
   prioritypatentnumber varchar,
   ussubclass varchar,
   maingroup varchar,
   subgroup varchar,
   cpcsubclass varchar,
   cpcmaingroup varchar,
   cpcsubgroup varchar,
   classificationnationalcountry varchar,
   classificationnationalclass varchar,
   title varchar,
   numberofclaims int,
   primaryexaminerfirstname varchar,
   primaryexaminerlastname varchar,
   primaryexaminerdepartment varchar,
   pctpatentnumber varchar,
   filename varchar
   claims int,
   apptype int,
   appnum int,
   gyear int,
   appdate date,
   appyear int
   
   
   Output Schema: patents
   
     CREATE TABLE patents_merged( 
       patentnumber int, 
       kind varchar, 
       grantdate date,
       type varchar,
       applicationnumber varchar,
       filingdate date,
       prioritydate date,
       prioritycountry varchar,
       prioritypatentnumber varchar,
       ussubclass varchar,
       maingroup varchar,
       subgroup varchar,
       cpcsubclass varchar,
       cpcmaingroup varchar,
       cpcsubgroup varchar,
       classificationnationalcountry varchar,
       classificationnationalclass varchar,
       title varchar,
       numberofclaims int,
       primaryexaminerfirstname varchar,
       primaryexaminerlastname varchar,
       primaryexaminerdepartment varchar,
       pctpatentnumber varchar,
       filename varchar,
       claims int,
       apptype int,
       appnum int,
       gyear int,
       appdate date,
       appyear int
       );
       
   
   patentdata:
   INSERT INTO patents_merged
   (
   		SELECT	
   		patent, 

kind, gdate, 'NULL', 'NULL', NULL, NULL, 'NULL', 'NULL', 'NULL', 'NULL', 'NULL', 'NULL', 'NULL', 'NULL', 'NULL', 'NULL', 'NULL', -1, 'NULL', 'NULL', 'NULL', 'NULL', 'NULL', claims, apptype, appnum, gyear, appdate,

       	appyear
       	FROM patents
   );
   -- RESULT : INSERT 0 3984771
   
   patent_2015:
   INSERT INTO patents_merged
   (
   	SELECT
   		patentnumber, 

kind, grantdate, type, applicationnumber, filingdate, prioritydate, prioritycountry, prioritypatentnumber, ussubclass, maingroup, subgroup, cpcsubclass, cpcmaingroup, cpcsubgroup, classificationnationalcountry, classificationnationalclass, title, numberofclaims, primaryexaminerfirstname, primaryexaminerlastname, primaryexaminerdepartment, pctpatentnumber, filename, -1, -1, -1, -1, NULL,

       	-1
   	FROM patents
   );
   -- RESULT : INSERT 0 1646225
   

COPY SCRIPTS: patentdata: \COPY patents_merged TO '/tmp/merged_patents_export1.txt' DELIMITER AS E'\t' HEADER NULL AS CSV; --COPY 3984771

patent_2015: \COPY patents_merged TO '/tmp/merged_patents_export.txt' DELIMITER AS E'\t' HEADER NULL AS CSV; --COPY 1646225

PATENTS TABLE \COPY patents FROM '/tmp/merged_patents_export1.txt' DELIMITER AS E'\t' HEADER NULL AS CSV; -- RESULT : COPY 3984771 \COPY patents FROM '/tmp/merged_patents_export.txt' DELIMITER AS E'\t' HEADER NULL AS CSV; -- RESULT : COPY 1646225


TESTING: select count(*) FROM (SELECT DISTINCT patentnumber FROM patents) AS t; --RESULT: 5411151 EXPECTED: 5426566

SELECT COUNT(*), * FROM patents GROUP BY patentnumber, kind, grantdate, type, applicationnumber, filingdate, prioritydate, prioritycountry, prioritypatentnumber, ussubclass, maingroup, subgroup, cpcsubclass, cpcmaingroup, cpcsubgroup, classificationnationalcountry, classificationnationalclass, title, numberofclaims, primaryexaminerfirstname, primaryexaminerlastname, primaryexaminerdepartment, pctpatentnumber, filename, claims, apptype, appnum, gyear, appdate, appyear HAVING COUNT(*) > 1;

SELECT patentnumber, count(*) FROM patents GROUP BY patentnumber HAVING count(*)>1; --7640598


SELECT * FROM patents op WHERE op.patentnumber IN ( SELECT ip.patentnumber FROM patents ip GROUP BY ip.patentnumber HAVING COUNT(*)>1 ) ORDER BY op.patentnumber;

( SELECT * INTO patentsCleaned FROM patents op WHERE op.patentnumber IN ( SELECT ip.patentnumber FROM patents ip GROUP BY ip.patentnumber HAVING COUNT(*)=1 ) ORDER BY op.patentnumber ) --SELECT 5191306


INSERT INTO patentsCleaned( SELECT * FROM patents op WHERE op.patentnumber IN ( SELECT ip.patentnumber FROM patents ip GROUP BY ip.patentnumber HAVING COUNT(*)>1 ) AND op.applicationnumber NOT LIKE 'NULL' ORDER BY op.patentnumber );

--219845

TESTING: allpatent=# select count(*) from patentsCleaned;

 count

5411151

(1 row)

allpatent=# select count(*), patentnumber FROM patentsCleaned group by patentnumber having count(*) > 1;

count | patentnumber

+--------------

(0 rows)


                    • INDEX CREATION **************

ALTER TABLE patents ADD PRIMARY KEY (patentnumber); -- RESULT : ALTER TABLE allpatent=# CREATE UNIQUE INDEX patent_idx ON patents (patentnumber);

allpatent=# CREATE INDEX ON assignees (orgname); CREATE INDEX



    • Citations

To Extract Patents with Numbers Only and to Ignore Other RegExes CREATE OR REPLACE FUNCTION cleanpatno (text) RETURNS bigint AS $$ if ($_[0]) { my $var=$_[0]; if ($var=~/^\d*$/) {return $var;} return undef; } return undef; $$ LANGUAGE plperl;


                        • Columns *********************

patentdata:

Column    |       Type        | Modifiers

+-------------------+-----------

patent      | integer           |
cit_date    | date              |
cit_name    | character varying |
cit_kind    | character varying |
cit_country | character varying |
citation    | integer           |
category    | character varying |
citseq      | integer           |

SELECT patent as citingpatentnumber, citation AS citedpatentnumber INTO citations_merged FROM citations; --SELECT 38452957

patent_2015:

Column        |  Type   | Modifiers

+---------+-----------

citingpatentnumber  | integer |
citingpatentcountry | text    |
citedpatentnumber   | text    |
citedpatentcountry  | text    |

SELECT CAST(citingpatentnumber AS bigint), CAST(cleanpatno( citedpatentnumber) AS bigint) as citedpatentnumber INTO citations_merged FROM citations; -- RESULT : SELECT 59227881

FINAL TABLE:

CREATE TABLE citations ( citingpatentnumber bigint, citedpatentnumber bigint );


Copy Statements:

patentdata: \COPY citations_merged TO '/tmp/merged_citations_export1.txt' DELIMITER AS E'\t' HEADER NULL AS CSV; --COPY 38452957

patent_2015: \COPY citations_merged TO '/tmp/merged_citations_export.txt' DELIMITER AS E'\t' HEADER NULL AS CSV; -- RESULT : COPY 59227881

allpatent: \COPY citations FROM '/tmp/merged_citations_export.txt' DELIMITER AS E'\t' HEADER NULL AS CSV; --RESULT : COPY 59227881

\COPY citations FROM '/tmp/merged_citations_export1.txt' DELIMITER AS E'\t' HEADER NULL AS CSV; --RESULT: COPY 38452957


CLONING: CREATE DATABASE allpatentsProcessed WITH TEMPLATE allpatent OWNER researcher;

USPTO Consolidated Patent Data

Scripts:

/* creating patent data tables from : https://bulkdata.uspto.gov/data2/patent/maintenancefee/*/

CREATE TABLE PatentMaintenanceFee( patentnumber varchar, applicationnumber int, smallentity varchar, filingdate date, grantissuedate date, maintenancefeedate date, maintenancefeecode varchar );

\COPY PatentMaintenanceFee FROM '/bulk/USPTO_Consolidated/MaintFeeEvents_20160613.txt' DELIMITER AS E'\t' HEADER NULL AS CSV; -- RESULT : COPY 14042059

/* creating tables for historical patent data - USPTO */

CREATE TABLE HistoricalPatentData( applicationid int, pubno varchar, patentnumber varchar, NBER int, USPC varchar, USPC_sub varchar, applicationdate date, prioritydate date, pubdate date, displaydate date, disptype varchar, exp_dt date, exp_dt_max date, pta int );

\COPY historicalpatentdata FROM '/bulk/USPTO_Consolidated/HistoricalFiles/historical_masterfile.csv' DELIMITER AS ',' HEADER NULL AS CSV;

--COPY 11191813