NLP with spaCy_Day66(5)

 

---

# Import the English language class
from spacy.lang.en import English

# Create the nlp object
nlp = English()

# Process a text
doc = nlp("This is a sentence.")

# Print the document text
print(doc.text)

# Import the Spanish language class
from spacy.lang.es import Spanish
​
# Create the nlp object
nlp = Spanish()
​
# Process a text (this is Spanish for: "How are you?")
doc = nlp("¿Cómo estás?")
​
# Print the document text
print(doc.text)

---

# Import the English language class and create the nlp object
from spacy.lang.en import English

nlp = English()

# Process the text
doc = nlp("I like tree kangaroos and narwhals.")

# Select the first token
first_token = doc[0]

# Print the first token's text
print(first_token.text)

# Import the English language class and create the nlp object
from spacy.lang.en import English

nlp = English()

# Process the text
doc = nlp("I like tree kangaroos and narwhals.")

# A slice of the Doc for "tree kangaroos"
tree_kangaroos = doc[2:4]
print(tree_kangaroos.text)

# A slice of the Doc for "tree kangaroos and narwhals" (without the ".")
tree_kangaroos_and_narwhals = doc[2:6]
print(tree_kangaroos_and_narwhals.text)

 

---

from spacy.lang.en import English

nlp = English()

# Process the text
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
for token in doc:
    # Check if the token resembles a number
    if token.like_num:
        # Get the next token in the document
        next_token = doc[token.i + 1]
        # Check if the next token's text equals "%"
        if next_token.text == "%":
            print("Percentage found:", token.text)

 

---

Statistical models

 

 

 

 

출처 : course.spacy.io/en/

Advanced NLP with spaCy · A free online course