Extracting only names [closed]

I have a data as shown below and I have to extract only names out of it. May I know how could it be done? I am using Spacy for this problem and using entity label_=="PERSON" but this approach is getting failed when we have a single name like,

Ordered by: Potter


The data is shown below

Data="""

Ordered by: Jacob Green
Ordered by: nurse
Ordered by: doctor
Ordered by: Potter
Ordered by: MD
Ordered by: Doctor
Ordered by Morgan Olivia
Ordered by a physician
Ordered by: Dr. Ali Zafar
"""


Expected Output:

Jacob Green
Potter
Morgan Olivia
Ali Zafar


Please edit the question to limit it to a specific problem with enough detail to identify an adequate answer. Avoid asking multiple distinct questions at once. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

3 Answers
3

I guess the best you can do is to assume that a person is someone at the end of a line whose one or more names (separated by white spaces) start with a capital letter and contain only lower-case letters:

import re
lines = Data.split('n')

# You may want to play with the definition of a "name"
is_name = re.compile(r'([A-Z][a-z]+(?:s+[A-Z][a-z]+)*)s*$')

[is_name.findall(line) for line in lines]
#[['Jacob Green'],
# ,
# ,
# ['Potter'],
# ['Morgan Olivia'],
# ,
# ['Ali Zafar']]


I assume there are always "by" prefixes, and separators are spaces or tabs:

re.findall(r"(?:bby:?[ t]*(?:Dr.?[ t]*)?)([A-Z][a-z]+(?:[ t]+[A-Z][a-z]+)*)",Data)
Out: ['Jacob Green', 'Potter', 'Morgan Olivia', 'Ali Zafar']


([A-Z][a-z]+(?:[ t]+[A-Z][a-z]+)*) We capture only the name.

Although the NER is failing in this case, the POS tagging is still tagging this as a PROPN (proper noun). Perhaps you could use that feature as a double check on any lines that don't yield a named entity?

Data="""
Ordered by: Potter
"""

doc = nlp(Data)

for token in doc:
print(token.text + ' ' + token.pos_)

SPACE
Ordered VERB
by ADP
: PUNCT
Potter PROPN