learn-spacy-one.py

# from https://course.spacy.io/chapter1
from spacy.lang.en import English

nlp = English()
doc = nlp("hello world!!! one 123")

for token in doc:
    print(token.text)

print(doc)

# a slice from a Doc is a Span object
span = doc[1:4]
print(span.text)

# lexical attributes
print("Lexical attributes")
print("========================================")
print("Index:\t", [token.i for token in doc])
print("Text:\t", [token.text for token in doc])
print("is_alphs:\t", [token.is_alpha for token in doc])
print("is_punct:\t", [token.is_punct for token in doc])
print("like_num:\t", [token.like_num for token in doc])

doc = nlp(
    "In 1990, more than 60% of people in East Asia were in extreme poverty. "
    "Now less than 4% are."
)

# Iterate over the tokens in the doc
# to find percentage figures in 'doc'
for token in doc:
    # Check if the token resembles a number
    if token.like_num:
        # Get the next token in the document
        # if token is like a number
        # we want to check if the next token is '%'
        next_token = doc[token.i + 1]
        # Check if the next token's text equals '%'
        if next_token.text == "%":
            print("Percentage found:", token.text)