220
edits
Changes
Jump to navigation
Jump to search
→Cleaning mas table
Now when you re-run the matcher on portcokeys and masdistinctkeys1 you will get 428 errors and excluding Undisclosed fields gets you down to 356.
In Excel create a column to exclude any entries where the announced date occurs before the firstinvdate. Afterwards, manually flag the other duplicate mismatches picking the earlier announced date.
==Import Flagged Matcher Data Into PSQL==
After everything in the matcher output files is manually flagged create two new tables in Excel for iposmatcherouput and masmatcheroutput and copy those files into the tables.
CREATE TABLE masmatcheroutputwithexcludeflag(
file1coname varchar(255),
file2targetname varchar(255),
warningmsg varchar(255),
file1coname1 varchar(255),
file1statecode varchar(2),
file1datefirstinv date, --mm-dd-yyyy
file2targetname2 varchar(255),
file2statecode varchar(2),
file2announceddate date,
exclude boolean,
excludemaster boolean,
excludemanual boolean,
excludemanualmaster boolean,
excludefinal boolean
);
\COPY masmatcheroutputwithexcludeflag FROM 'masmatcheroutput-nohead.txt' WITH DELIMITER AS E'\t' HEADER NULL AS '' CSV
--9400
CREATE TABLE ipomatcheroutputwithexcludeflag(
file1coname varchar(255),
file2issuer varchar(255),
warningmsg varchar(255),
file1coname1 varchar(255),
file1statecode varchar(2),
file1datefirstinv date, --mm-dd-yyyy
file2issuer1 varchar(255),
file2issuedate date,
file2statecode varchar(2),
excludedate boolean,
excludemaster boolean,
excludemanual boolean,
excludemanualmaster boolean,
excludefinal boolean
);
\COPY ipomatcheroutputwithexcludeflag FROM 'iposmatcheroutput-nohead.txt' WITH DELIMITER AS E'\t' HEADER NULL AS '' CSV
--2591
