)
# Only tokenize the text
doc = nlp.make_doc(text)
print([token.text for token in doc])
import spacy
nlp = spacy.load("en_core_web_sm")
text = (
"Chick-fil-A is an American fast food restaurant chain headquartered in "
"the city of College Park, Georgia, specializing in chicken sandwiches."
)
# Disable the tagger and parser
with nlp.disable_pipes("tagger", "parser"):
# Process the text
doc = nlp(text)
# Print the entities in the doc
print(doc.ents)
# How training works (1)
# 1. Initialize the model weights randomly with nlp.begin_training
# 2. Predict a few examples with the current weights by calling nlp.update
# 3. Compare prediction with true labels
# 4. Calculate how to change weights to improve predictions
# 5. Update weights slightly
# 6. Go back to 2.
# Example: Training the entity recognizer
# The entity recognizer tags words and phrases in context
doc = nlp(u"I found these crisps at our local WalMart & figured I would give them a try. They were so yummy I may never go back to regular chips, not that I was a big chip fan anyway. The only problem is I can eat the entire bag in one sitting. I give these crisps a big thumbs up!")
print([(ent.text, ent.label_) for ent in doc.ents])
#Training a custom NLP model
import spacy
import random
train_data = [
(u"As soon as I tasted one and it tasted like a corn chip I checked the ingredients. ", {"entities": [(45, 49, "PRODUCT")]}),
(u"I found these crisps at our local WalMart & figured I would give them a try", {"entities": [(14, 20, "PRODUCT")]})
]
other_pipes = [pipe for pipe in nlp.pipe_names if pipe != "ner"]
with nlp.disable_pipes(*other_pipes):
optimizer = nlp.begin_training()
for i in range(10):
random.shuffle(train_data)
for text, annotations in train_data:
nlp.update([text], [annotations], sgd=optimizer)
nlp.to_disk("model/food_model")
#Prediction
import spacy
nlp = spacy.load("model/food_model")
text = nlp("I consume about a jar every two weeks of this, either adding it to fajitas or using it as a corn chip dip")
for entity in text.ents:
print(entity.text, entity.label_)
'\n')
######################################################################
# Selective processing:
text = ("Chick-fil-A is an American fast food restaurant chain "
"headquartered in the city of College Park, Georgia, specializing "
"in chicken sandwiches.")
# Only tokenize the text
doc = nlp.make_doc(text) # doc = nlp(text)
print([token.text for token in doc])
# Disable the tagger and parser
with nlp.disable_pipes('tagger', 'parser'):
# Process the text
doc = nlp(text)
# Print the entities in the doc
print(doc.ents)
######################################################################
# Creating training data:
# Two tokens whose lowercase forms match 'iphone' and 'x'
pattern1 = [{'LOWER': 'iphone'}, {'LOWER': 'x'}]
# Token whose lowercase form matches 'iphone' and an optional digit
pattern2 = [{'LOWER': 'iphone'}, {'OP': '?', 'IS_DIGIT': True}]
# Add patterns to the matcher
