spaCy/examples/training/train_parser.py
Sofie Van Landeghem fcbf899b08
Feature/example only (#5707)
* remove _convert_examples

* fix test_gold, raise TypeError if tuples are used instead of Example's

* throwing proper errors when the wrong type of objects are passed

* fix deprectated format in tests

* fix deprectated format in parser tests

* fix tests for NEL, morph, senter, tagger, textcat

* update regression tests with new Example format

* use make_doc

* more fixes to nlp.update calls

* few more small fixes for rehearse and evaluate

* only import ml_datasets if really necessary
2020-07-06 13:02:36 +02:00

111 lines
3.5 KiB
Python

#!/usr/bin/env python
# coding: utf8
"""Example of training spaCy dependency parser, starting off with an existing
model or a blank model. For more details, see the documentation:
* Training: https://spacy.io/usage/training
* Dependency Parse: https://spacy.io/usage/linguistic-features#dependency-parse
Compatible with: spaCy v2.0.0+
Last tested with: v2.1.0
"""
from __future__ import unicode_literals, print_function
import plac
import random
from pathlib import Path
import spacy
from spacy.gold import Example
from spacy.util import minibatch, compounding
# training data
TRAIN_DATA = [
(
"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"],
},
),
]
@plac.annotations(
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=15):
"""Load the model, set up the pipeline and train the parser."""
if model is not None:
nlp = spacy.load(model) # load existing spaCy model
print("Loaded model '%s'" % model)
else:
nlp = spacy.blank("en") # create blank Language class
print("Created blank 'en' model")
# add the parser to the pipeline if it doesn't exist
# nlp.create_pipe works for built-ins that are registered with spaCy
if "parser" not in nlp.pipe_names:
parser = nlp.create_pipe("parser")
nlp.add_pipe(parser, first=True)
# otherwise, get it, so we can add labels to it
else:
parser = nlp.get_pipe("parser")
# add labels to the parser and create the Example objects
train_examples = []
for text, annotations in TRAIN_DATA:
train_examples.append(Example.from_dict(nlp.make_doc(text), annotations))
for dep in annotations.get("deps", []):
parser.add_label(dep)
with nlp.select_pipes(enable="parser"): # only train parser
optimizer = nlp.begin_training()
for itn in range(n_iter):
random.shuffle(train_examples)
losses = {}
# batch up the examples using spaCy's minibatch
batches = minibatch(train_examples, size=compounding(4.0, 32.0, 1.001))
for batch in batches:
nlp.update(batch, sgd=optimizer, losses=losses)
print("Losses", losses)
# test the trained model
test_text = "I like securities."
doc = nlp(test_text)
print("Dependencies", [(t.text, t.dep_, t.head.text) for t in doc])
# save model to output directory
if output_dir is not None:
output_dir = Path(output_dir)
if not output_dir.exists():
output_dir.mkdir()
nlp.to_disk(output_dir)
print("Saved model to", output_dir)
# test the saved model
print("Loading from", output_dir)
nlp2 = spacy.load(output_dir)
doc = nlp2(test_text)
print("Dependencies", [(t.text, t.dep_, t.head.text) for t in doc])
if __name__ == "__main__":
plac.call(main)
# expected result:
# [
# ('I', 'nsubj', 'like'),
# ('like', 'ROOT', 'like'),
# ('securities', 'dobj', 'like'),
# ('.', 'punct', 'like')
# ]