This commit is contained in:
Matthew Honnibal 2018-03-27 13:36:37 +02:00
commit d4680e4d83
2 changed files with 104 additions and 3 deletions

View File

@ -0,0 +1,88 @@
#!/usr/bin/env python
# coding: utf8
"""Export spaCy model vectors for use in TensorBoard's standalone embedding projector.
https://github.com/tensorflow/embedding-projector-standalone
Usage:
python vectors_tensorboard_standalone.py ./myVectorModel ./output [name]
This outputs two files that have to be copied into the "oss_data" of the standalone projector:
[name]_labels.tsv - metadata such as human readable labels for vectors
[name]_tensors.bytes - numpy.ndarray of numpy.float32 precision vectors
"""
from __future__ import unicode_literals
import json
import math
from os import path
import numpy
import plac
import spacy
import tqdm
@plac.annotations(
vectors_loc=("Path to spaCy model that contains vectors", "positional", None, str),
out_loc=("Path to output folder writing tensors and labels data", "positional", None, str),
name=("Human readable name for tsv file and vectors tensor", "positional", None, str),
)
def main(vectors_loc, out_loc, name="spaCy_vectors"):
# A tab-separated file that contains information about the vectors for visualization
#
# Learn more: https://www.tensorflow.org/programmers_guide/embedding#metadata
meta_file = "{}_labels.tsv".format(name)
out_meta_file = path.join(out_loc, meta_file)
print('Loading spaCy vectors model: {}'.format(vectors_loc))
model = spacy.load(vectors_loc)
print('Finding lexemes with vectors attached: {}'.format(vectors_loc))
voacb_strings = [
w for w in tqdm.tqdm(model.vocab.strings, total=len(model.vocab.strings), leave=False)
if model.vocab.has_vector(w)
]
vector_count = len(voacb_strings)
print('Building Projector labels for {} vectors: {}'.format(vector_count, out_meta_file))
vector_dimensions = model.vocab.vectors.shape[1]
tf_vectors_variable = numpy.zeros((vector_count, vector_dimensions), dtype=numpy.float32)
# Write a tab-separated file that contains information about the vectors for visualization
#
# Reference: https://www.tensorflow.org/programmers_guide/embedding#metadata
with open(out_meta_file, 'wb') as file_metadata:
# Define columns in the first row
file_metadata.write("Text\tFrequency\n".encode('utf-8'))
# Write out a row for each vector that we add to the tensorflow variable we created
vec_index = 0
for text in tqdm.tqdm(voacb_strings, total=len(voacb_strings), leave=False):
# https://github.com/tensorflow/tensorflow/issues/9094
text = '<Space>' if text.lstrip() == '' else text
lex = model.vocab[text]
# Store vector data and metadata
tf_vectors_variable[vec_index] = numpy.float64(model.vocab.get_vector(text))
file_metadata.write("{}\t{}\n".format(text, math.exp(lex.prob) * len(voacb_strings)).encode('utf-8'))
vec_index += 1
# Write out "[name]_tensors.bytes" file for standalone embeddings projector to load
tensor_path = '{}_tensors.bytes'.format(name)
tf_vectors_variable.tofile(path.join(out_loc, tensor_path))
print('Done.')
print('Add the following entry to "oss_data/oss_demo_projector_config.json"')
print(json.dumps({
"tensorName": name,
"tensorShape": [vector_count, vector_dimensions],
"tensorPath": 'oss_data/{}'.format(tensor_path),
"metadataPath": 'oss_data/{}'.format(meta_file)
}, indent=2))
if __name__ == '__main__':
plac.call(main)

View File

@ -1,7 +1,7 @@
# encoding: utf8
from __future__ import unicode_literals
from ...symbols import ORTH, LEMMA, POS, ADV, ADJ, NOUN
from ...symbols import ORTH, LEMMA, POS, ADV, ADJ, NOUN, ADP
_exc = {}
@ -12,11 +12,24 @@ for exc_data in [
{ORTH: "mgr.", LEMMA: "magister", POS: NOUN},
{ORTH: "tzn.", LEMMA: "to znaczy", POS: ADV},
{ORTH: "tj.", LEMMA: "to jest", POS: ADV},
{ORTH: "tzw.", LEMMA: "tak zwany", POS: ADJ}]:
{ORTH: "tzw.", LEMMA: "tak zwany", POS: ADJ},
{ORTH: "adw.", LEMMA: "adwokat", POS: NOUN},
{ORTH: "afr.", LEMMA: "afrykański", POS: ADJ},
{ORTH: "c.b.d.o.", LEMMA: "co było do okazania", POS: ADV},
{ORTH: "cbdu.", LEMMA: "co było do udowodnienia", POS: ADV},
{ORTH: "mn.w.", LEMMA: "mniej więcej", POS: ADV},
{ORTH: "nt.", LEMMA: "na temat", POS: ADP},
{ORTH: "ok.", LEMMA: "około"},
{ORTH: "n.p.u.", LEMMA: "na psa urok"},
{ORTH: "ww.", LEMMA: "wyżej wymieniony", POS: ADV}]:
_exc[exc_data[ORTH]] = [exc_data]
for orth in [
"w.", "r."]:
"w.", "r.", "br.", "bm.", "b.r.", "amer.", "am.", "bdb.", "św.", "p.", "lit.",
"wym.", "czyt.", "daw.", "d.", "zob.", "gw.", "dn.", "dyr.", "im.", "mł.",
"min.", "dot.", "muz.", "k.k.", "k.p.a.", "k.p.c.", "n.p.m.", "p.p.m.", "nb.",
"ob.", "n.e.", "p.n.e.", "zw.", "zool.", "zach.", "żarg.", "żart.", "wzgl.",
"wyj.", "xx.", "ks.", "x.", "wyd.", "wsch.", "o.o."]:
_exc[orth] = [{ORTH: orth}]