explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-24 00:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update training examples to use "simple style"

Browse Source
This commit is contained in:
ines 2017-11-06 23:14:04 +01:00
parent 906aece532
commit fe498b3d5e
6 changed files with 116 additions and 153 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

81
examples/training/train_intent_parser.py
View File

@ -14,55 +14,49 @@ following types of relations: ROOT, PLACE, QUALITY, ATTRIBUTE, TIME, LOCATION.
('best', 'QUALITY', 'hotel') --> hotel with QUALITY best
('hotel', 'PLACE', 'show') --> show PLACE hotel
('berlin', 'LOCATION', 'hotel') --> hotel with LOCATION berlin
Developed for: spaCy 2.0.0a18
Last updated for: spaCy 2.0.0a19
"""
from __future__ import unicode_literals, print_function
import plac
import random
import spacy
from spacy.gold import GoldParse
from spacy.tokens import Doc
from pathlib import Path
# training data: words, head and dependency labels
# training data: texts, heads and dependency labels
# for no relation, we simply chose an arbitrary dependency label, e.g. '-'
TRAIN_DATA = [
(
['find', 'a', 'cafe', 'with', 'great', 'wifi'],
[0, 2, 0, 5, 5, 2], # index of token head
['ROOT', '-', 'PLACE', '-', 'QUALITY', 'ATTRIBUTE']
),
(
['find', 'a', 'hotel', 'near', 'the', 'beach'],
[0, 2, 0, 5, 5, 2],
['ROOT', '-', 'PLACE', 'QUALITY', '-', 'ATTRIBUTE']
),
(
['find', 'me', 'the', 'closest', 'gym', 'that', "'s", 'open', 'late'],
[0, 0, 4, 4, 0, 6, 4, 6, 6],
['ROOT', '-', '-', 'QUALITY', 'PLACE', '-', '-', 'ATTRIBUTE', 'TIME']
),
(
['show', 'me', 'the', 'cheapest', 'store', 'that', 'sells', 'flowers'],
[0, 0, 4, 4, 0, 4, 4, 4], # attach "flowers" to store!
['ROOT', '-', '-', 'QUALITY', 'PLACE', '-', '-', 'PRODUCT']
),
(
['find', 'a', 'nice', 'restaurant', 'in', 'london'],
[0, 3, 3, 0, 3, 3],
['ROOT', '-', 'QUALITY', 'PLACE', '-', 'LOCATION']
),
(
['show', 'me', 'the', 'coolest', 'hostel', 'in', 'berlin'],
[0, 0, 4, 4, 0, 4, 4],
['ROOT', '-', '-', 'QUALITY', 'PLACE', '-', 'LOCATION']
),
(
['find', 'a', 'good', 'italian', 'restaurant', 'near', 'work'],
[0, 4, 4, 4, 0, 4, 5],
['ROOT', '-', 'QUALITY', 'ATTRIBUTE', 'PLACE', 'ATTRIBUTE', 'LOCATION']
)
("find a cafe with great wifi", {
'heads': [0, 2, 0, 5, 5, 2], # index of token head
'deps': ['ROOT', '-', 'PLACE', '-', 'QUALITY', 'ATTRIBUTE']
}),
("find a hotel near the beach", {
'heads': [0, 2, 0, 5, 5, 2],
'deps': ['ROOT', '-', 'PLACE', 'QUALITY', '-', 'ATTRIBUTE']
}),
("find me the closest gym that's open late", {
'heads': [0, 0, 4, 4, 0, 6, 4, 6, 6],
'deps': ['ROOT', '-', '-', 'QUALITY', 'PLACE', '-', '-', 'ATTRIBUTE', 'TIME']
}),
("show me the cheapest store that sells flowers", {
'heads': [0, 0, 4, 4, 0, 4, 4, 4], # attach "flowers" to store!
'deps': ['ROOT', '-', '-', 'QUALITY', 'PLACE', '-', '-', 'PRODUCT']
}),
("find a nice restaurant in london", {
'heads': [0, 3, 3, 0, 3, 3],
'deps': ['ROOT', '-', 'QUALITY', 'PLACE', '-', 'LOCATION']
}),
("show me the coolest hostel in berlin", {
'heads': [0, 0, 4, 4, 0, 4, 4],
'deps': ['ROOT', '-', '-', 'QUALITY', 'PLACE', '-', 'LOCATION']
}),
("find a good italian restaurant near work", {
'heads': [0, 4, 4, 4, 0, 4, 5],
'deps': ['ROOT', '-', 'QUALITY', 'ATTRIBUTE', 'PLACE', 'ATTRIBUTE', 'LOCATION']
})
]
@ -88,8 +82,8 @@ def main(model=None, output_dir=None, n_iter=100):
else:
parser = nlp.get_pipe('parser')
for _, _, deps in TRAIN_DATA:
for dep in deps:
for text, annotations in TRAIN_DATA:
for dep in annotations.get('deps', []):
parser.add_label(dep)
other_pipes = [pipe for pipe in nlp.pipe_names if pipe != 'parser']
@ -98,10 +92,8 @@ def main(model=None, output_dir=None, n_iter=100):
for itn in range(n_iter):
random.shuffle(TRAIN_DATA)
losses = {}
for words, heads, deps in TRAIN_DATA:
doc = Doc(nlp.vocab, words=words)
gold = GoldParse(doc, heads=heads, deps=deps)
nlp.update([doc], [gold], sgd=optimizer, losses=losses)
for text, annotations in TRAIN_DATA:
nlp.update([text], [annotations], sgd=optimizer, losses=losses)
print(losses)
# test the trained model
@ -147,6 +139,7 @@ if __name__ == '__main__':
# ('find', 'ROOT', 'find'),
# ('cheapest', 'QUALITY', 'gym'),
# ('gym', 'PLACE', 'find')
# ('work', 'LOCATION', 'near')
# ]
# show me the best hotel in berlin
# [

63
examples/training/train_ner.py
View File

@ -8,22 +8,24 @@ For more details, see the documentation:
* NER: https://alpha.spacy.io/usage/linguistic-features#named-entities
Developed for: spaCy 2.0.0a18
Last updated for: spaCy 2.0.0a18
Last updated for: spaCy 2.0.0a19
"""
from __future__ import unicode_literals, print_function
import plac
import random
from pathlib import Path
import spacy
from spacy.gold import GoldParse, biluo_tags_from_offsets
# training data
TRAIN_DATA = [
('Who is Shaka Khan?', [(7, 17, 'PERSON')]),
('I like London and Berlin.', [(7, 13, 'LOC'), (18, 24, 'LOC')])
('Who is Shaka Khan?', {
'entities': [(7, 17, 'PERSON')]
}),
('I like London and Berlin.', {
'entities': [(7, 13, 'LOC'), (18, 24, 'LOC')]
})
]
@ -45,25 +47,28 @@ def main(model=None, output_dir=None, n_iter=100):
if 'ner' not in nlp.pipe_names:
ner = nlp.create_pipe('ner')
nlp.add_pipe(ner, last=True)
# otherwise, get it so we can add labels
else:
ner = nlp.get_pipe('ner')
# function that allows begin_training to get the training data
get_data = lambda: reformat_train_data(nlp.tokenizer, TRAIN_DATA)
# add labels
for _, annotations in TRAIN_DATA:
for ent in annotations.get('entities'):
ner.add_label(ent[2])
# get names of other pipes to disable them during training
other_pipes = [pipe for pipe in nlp.pipe_names if pipe != 'ner']
with nlp.disable_pipes(*other_pipes): # only train NER
optimizer = nlp.begin_training(get_data)
optimizer = nlp.begin_training()
for itn in range(n_iter):
random.shuffle(TRAIN_DATA)
losses = {}
for raw_text, entity_offsets in TRAIN_DATA:
doc = nlp.make_doc(raw_text)
gold = GoldParse(doc, entities=entity_offsets)
for text, annotations in TRAIN_DATA:
nlp.update(
[doc], # Batch of Doc objects
[gold], # Batch of GoldParse objects
drop=0.5, # Dropout -- make it harder to memorise data
sgd=optimizer, # Callable to update weights
[text], # batch of texts
[annotations], # batch of annotations
drop=0.5, # dropout - make it harder to memorise data
sgd=optimizer, # callable to update weights
losses=losses)
print(losses)
@ -90,25 +95,13 @@ def main(model=None, output_dir=None, n_iter=100):
print('Tokens', [(t.text, t.ent_type_, t.ent_iob) for t in doc])
def reformat_train_data(tokenizer, examples):
"""Reformat data to match JSON format.
https://alpha.spacy.io/api/annotation#json-input
tokenizer (Tokenizer): Tokenizer to process the raw text.
examples (list): The trainig data.
RETURNS (list): The reformatted training data."""
output = []
for i, (text, entity_offsets) in enumerate(examples):
doc = tokenizer(text)
ner_tags = biluo_tags_from_offsets(tokenizer(text), entity_offsets)
words = [w.text for w in doc]
tags = ['-'] * len(doc)
heads = [0] * len(doc)
deps = [''] * len(doc)
sentence = (range(len(doc)), words, tags, heads, deps, ner_tags)
output.append((text, [(sentence, [])]))
return output
if __name__ == '__main__':
plac.call(main)
# Expected output:
# Entities [('Shaka Khan', 'PERSON')]
# Tokens [('Who', '', 2), ('is', '', 2), ('Shaka', 'PERSON', 3),
# ('Khan', 'PERSON', 1), ('?', '', 2)]
# Entities [('London', 'LOC'), ('Berlin', 'LOC')]
# Tokens [('I', '', 2), ('like', '', 2), ('London', 'LOC', 3),
# ('and', '', 2), ('Berlin', 'LOC', 3), ('.', '', 2)]

55
examples/training/train_new_entity_type.py
View File

@ -24,16 +24,14 @@ For more details, see the documentation:
* NER: https://alpha.spacy.io/usage/linguistic-features#named-entities
Developed for: spaCy 2.0.0a18
Last updated for: spaCy 2.0.0a18
Last updated for: spaCy 2.0.0a19
"""
from __future__ import unicode_literals, print_function
import plac
import random
from pathlib import Path
import spacy
from spacy.gold import GoldParse, minibatch
# new entity label
@ -45,20 +43,29 @@ LABEL = 'ANIMAL'
# model might learn the new type, but "forget" what it previously knew.
# https://explosion.ai/blog/pseudo-rehearsal-catastrophic-forgetting
TRAIN_DATA = [
("Horses are too tall and they pretend to care about your feelings",
[(0, 6, 'ANIMAL')]),
("Horses are too tall and they pretend to care about your feelings", {
'entities': [(0, 6, 'ANIMAL')]
}),
("Do they bite?", []),
("Do they bite?", {
'entities': []
}),
("horses are too tall and they pretend to care about your feelings",
[(0, 6, 'ANIMAL')]),
("horses are too tall and they pretend to care about your feelings", {
'entities': [(0, 6, 'ANIMAL')]
}),
("horses pretend to care about your feelings", [(0, 6, 'ANIMAL')]),
("horses pretend to care about your feelings", {
'entities': [(0, 6, 'ANIMAL')]
}),
("they pretend to care about your feelings, those horses",
[(48, 54, 'ANIMAL')]),
("they pretend to care about your feelings, those horses", {
'entities': [(48, 54, 'ANIMAL')]
}),
("horses?", [(0, 6, 'ANIMAL')])
("horses?", {
'entities': [(0, 6, 'ANIMAL')]
})
]
@ -90,15 +97,13 @@ def main(model=None, new_model_name='animal', output_dir=None, n_iter=50):
# get names of other pipes to disable them during training
other_pipes = [pipe for pipe in nlp.pipe_names if pipe != 'ner']
with nlp.disable_pipes(*other_pipes): # only train NER
random.seed(0)
optimizer = nlp.begin_training()
for itn in range(n_iter):
random.shuffle(TRAIN_DATA)
losses = {}
gold_parses = get_gold_parses(nlp.make_doc, TRAIN_DATA)
for batch in minibatch(gold_parses, size=3):
docs, golds = zip(*batch)
nlp.update(docs, golds, losses=losses, sgd=optimizer,
drop=0.35)
for text, annotations in TRAIN_DATA:
nlp.update([text], [annotations], sgd=optimizer, drop=0.35,
losses=losses)
print(losses)
# test the trained model
@ -125,19 +130,5 @@ def main(model=None, new_model_name='animal', output_dir=None, n_iter=50):
print(ent.label_, ent.text)
def get_gold_parses(tokenizer, train_data):
"""Shuffle and create GoldParse objects.
tokenizer (Tokenizer): Tokenizer to processs the raw text.
train_data (list): The training data.
YIELDS (tuple): (doc, gold) tuples.
"""
random.shuffle(train_data)
for raw_text, entity_offsets in train_data:
doc = tokenizer(raw_text)
gold = GoldParse(doc, entities=entity_offsets)
yield doc, gold
if __name__ == '__main__':
plac.call(main)

33
examples/training/train_parser.py
View File

@ -13,24 +13,19 @@ from __future__ import unicode_literals, print_function
import plac
import random
from pathlib import Path
import spacy
from spacy.gold import GoldParse
from spacy.tokens import Doc
# training data
TRAIN_DATA = [
(
['They', 'trade', 'mortgage', '-', 'backed', 'securities', '.'],
[1, 1, 4, 4, 5, 1, 1],
['nsubj', 'ROOT', 'compound', 'punct', 'nmod', 'dobj', 'punct']
),
(
['I', 'like', 'London', 'and', 'Berlin', '.'],
[1, 1, 1, 2, 2, 1],
['nsubj', 'ROOT', 'dobj', 'cc', 'conj', 'punct']
)
("They trade mortgage-backed securities.", {
'heads': [1, 1, 4, 4, 5, 1, 1],
'deps': ['nsubj', 'ROOT', 'compound', 'punct', 'nmod', 'dobj', 'punct']
}),
("I like London and Berlin", {
'heads': [1, 1, 1, 2, 2, 1],
'deps': ['nsubj', 'ROOT', 'dobj', 'cc', 'conj', 'punct']
})
]
@ -38,7 +33,7 @@ TRAIN_DATA = [
model=("Model name. Defaults to blank 'en' model.", "option", "m", str),
output_dir=("Optional output directory", "option", "o", Path),
n_iter=("Number of training iterations", "option", "n", int))
def main(model=None, output_dir=None, n_iter=1000):
def main(model=None, output_dir=None, n_iter=10):
"""Load the model, set up the pipeline and train the parser."""
if model is not None:
nlp = spacy.load(model) # load existing spaCy model
@ -57,8 +52,8 @@ def main(model=None, output_dir=None, n_iter=1000):
parser = nlp.get_pipe('parser')
# add labels to the parser
for _, _, deps in TRAIN_DATA:
for dep in deps:
for _, annotations in TRAIN_DATA:
for dep in annotations.get('deps', []):
parser.add_label(dep)
# get names of other pipes to disable them during training
@ -68,10 +63,8 @@ def main(model=None, output_dir=None, n_iter=1000):
for itn in range(n_iter):
random.shuffle(TRAIN_DATA)
losses = {}
for words, heads, deps in TRAIN_DATA:
doc = Doc(nlp.vocab, words=words)
gold = GoldParse(doc, heads=heads, deps=deps)
nlp.update([doc], [gold], sgd=optimizer, losses=losses)
for text, annotations in TRAIN_DATA:
nlp.update([text], [annotations], sgd=optimizer, losses=losses)
print(losses)
# test the trained model

21
examples/training/train_tagger.py
View File

@ -9,17 +9,14 @@ the documentation:
* POS Tagging: https://alpha.spacy.io/usage/linguistic-features#pos-tagging
Developed for: spaCy 2.0.0a18
Last updated for: spaCy 2.0.0a18
Last updated for: spaCy 2.0.0a19
"""
from __future__ import unicode_literals, print_function
import plac
import random
from pathlib import Path
import spacy
from spacy.tokens import Doc
from spacy.gold import GoldParse
# You need to define a mapping from your data's part-of-speech tag names to the
@ -29,16 +26,16 @@ from spacy.gold import GoldParse
# You may also specify morphological features for your tags, from the universal
# scheme.
TAG_MAP = {
'N': {"pos": "NOUN"},
'V': {"pos": "VERB"},
'J': {"pos": "ADJ"}
'N': {'pos': 'NOUN'},
'V': {'pos': 'VERB'},
'J': {'pos': 'ADJ'}
}
# Usually you'll read this in, of course. Data formats vary.
# Ensure your strings are unicode.
TRAIN_DATA = [
(["I", "like", "green", "eggs"], ["N", "V", "J", "N"]),
(["Eat", "blue", "ham"], ["V", "J", "N"])
("I like green eggs", {'tags': ['N', 'V', 'J', 'N']}),
("Eat blue ham", {'tags': ['V', 'J', 'N']})
]
@ -64,10 +61,8 @@ def main(lang='en', output_dir=None, n_iter=25):
for i in range(n_iter):
random.shuffle(TRAIN_DATA)
losses = {}
for words, tags in TRAIN_DATA:
doc = Doc(nlp.vocab, words=words)
gold = GoldParse(doc, tags=tags)
nlp.update([doc], [gold], sgd=optimizer, losses=losses)
for text, annotations in TRAIN_DATA:
nlp.update([text], [annotations], sgd=optimizer, losses=losses)
print(losses)
# test the trained model

16
examples/training/train_textcat.py
View File

@ -9,7 +9,7 @@ see the documentation:
* Text classification: https://alpha.spacy.io/usage/text-classification
Developed for: spaCy 2.0.0a18
Last updated for: spaCy 2.0.0a18
Last updated for: spaCy 2.0.0a19
"""
from __future__ import unicode_literals, print_function
import plac
@ -18,9 +18,8 @@ from pathlib import Path
import thinc.extra.datasets
import spacy
from spacy.gold import GoldParse, minibatch
from spacy.gold import minibatch
from spacy.util import compounding
from spacy.pipeline import TextCategorizer
@plac.annotations(
@ -52,10 +51,8 @@ def main(model=None, output_dir=None, n_iter=20, n_texts=2000):
print("Loading IMDB data...")
(train_texts, train_cats), (dev_texts, dev_cats) = load_data(limit=n_texts)
print("Using %d training examples" % n_texts)
train_docs = [nlp.tokenizer(text) for text in train_texts]
train_gold = [GoldParse(doc, cats=cats) for doc, cats in
zip(train_docs, train_cats)]
train_data = list(zip(train_docs, train_gold))
train_data = list(zip(train_texts,
[{'cats': cats} for cats in train_cats]))
# get names of other pipes to disable them during training
other_pipes = [pipe for pipe in nlp.pipe_names if pipe != 'textcat']
@ -68,8 +65,9 @@ def main(model=None, output_dir=None, n_iter=20, n_texts=2000):
# batch up the examples using spaCy's minibatch
batches = minibatch(train_data, size=compounding(4., 32., 1.001))
for batch in batches:
docs, golds = zip(*batch)
nlp.update(docs, golds, sgd=optimizer, drop=0.2, losses=losses)
texts, annotations = zip(*batch)
nlp.update(texts, annotations, sgd=optimizer, drop=0.2,
losses=losses)
with textcat.model.use_params(optimizer.averages):
# evaluate on the dev data split off in load_data()
scores = evaluate(nlp.tokenizer, textcat, dev_texts, dev_cats)