Case sensitive in name

[jenny-hm-lee]

I have tried the AnalyzerEngine() with the following two text and get different answers. The only difference between them is their upper vs lower cases.

1. text = 'THOMAS, PATRICIA JANE'
2. text = "Thomas, Patricia Jane"

How can I correctly detect the person name in text 1?

Code:
`from presidio_analyzer import AnalyzerEngine

text = 'THOMAS, PATRICIA JANE'
analyzer = AnalyzerEngine()
analyzer_results = analyzer.analyze(text=text, language="en")
print(text)
print(analyzer_results)
print('-----')

text = "Thomas, Patricia Jane"
analyzer = AnalyzerEngine()
analyzer_results = analyzer.analyze(text=text, language="en")
print(text)
print(analyzer_results)
print('-----')`

Result

[omri374]

Hi, the default spaCy model has limited accuracy on uppercase and lowercase words. I would suggest to try a few model examples on the demo website and change the underlying model. There are lots of examples showing how to do this.

https://huggingface.co/spaces/presidio/presidio_demo

[jenny-hm-lee]

thanks