Scientific names extracted from Ruhoff 1980

The goal of this project is to extract scientific names from Ruhoff 1980

Cleaned up data file

Process

• Make OCR

• Concatenate lines

• Fix spaces in species names

• Fix commas which were recognized as periods.

• Fix years

• Extract name part (06-names.csv first column is the place to fix errors)

• Reformat name part

• Fix spellings in names

• Run reconciliation using GNverifier with OpenRefine

Stats

Names	Number	Percentage
Total	35487	100%
All Matches	26799	75.4%
No Match	8688	24.6%
Canonical + Auth. Match	22311	62.8%
Canonical Match	3448	9.7%
Fuzzy Canonical Match	1040	2.9%