 View on TensorFlow.org
|
 Run in Google Colab
|
 View on GitHub
|
 Download notebook
|
 See TF Hub model
|
This tutorial illustrates how to generate embeddings from a TensorFlow Hub (TF-Hub) module given input data, and build an approximate nearest neighbours (ANN) index using the extracted embeddings. The index can then be used for real-time similarity matching and retrieval.
When dealing with a large corpus of data, it's not efficient to perform exact matching by scanning the whole repository to find the most similar items to a given query in real-time. Thus, we use an approximate similarity matching algorithm which allows us to trade off a little bit of accuracy in finding exact nearest neighbor matches for a significant boost in speed.
In this tutorial, we show an example of real-time text search over a corpus of news headlines to find the headlines that are most similar to a query. Unlike keyword search, this captures the semantic similarity encoded in the text embedding.
The steps of this tutorial are:
- Download sample data.
- Generate embeddings for the data using a TF-Hub module
- Build an ANN index for the embeddings
- Use the index for similarity matching
We use Apache Beam to generate the embeddings from the TF-Hub module. We also use Spotify's ANNOY library to build the approximate nearest neighbours index.
More models
For models that have the same architecture but were trained on a different language, refer to this collection. Here you can find all text embeddings that are currently hosted on tfhub.dev.
Setup
Install the required libraries.
pip install -q apache_beampip install -q 'scikit_learn~=0.23.0' # For gaussian_random_matrix.pip install -q annoy
Import the required libraries
import os
import sys
import pickle
from collections import namedtuple
from datetime import datetime
import numpy as np
import apache_beam as beam
from apache_beam.transforms import util
import tensorflow as tf
import tensorflow_hub as hub
import annoy
from sklearn.random_projection import gaussian_random_matrix
print('TF version: {}'.format(tf.__version__))
print('TF-Hub version: {}'.format(hub.__version__))
print('Apache Beam version: {}'.format(beam.__version__))
TF version: 2.4.0 TF-Hub version: 0.11.0 Apache Beam version: 2.26.0
1. Download Sample Data
A Million News Headlines dataset contains news headlines published over a period of 15 years sourced from the reputable Australian Broadcasting Corp. (ABC). This news dataset has a summarised historical record of noteworthy events in the globe from early-2003 to end-2017 with a more granular focus on Australia.
Format: Tab-separated two-column data: 1) publication date and 2) headline text. We are only interested in the headline text.
wget 'https://dataverse.harvard.edu/api/access/datafile/3450625?format=tab&gbrecs=true' -O raw.tsvwc -l raw.tsvhead raw.tsv
--2021-01-07 12:50:08-- https://dataverse.harvard.edu/api/access/datafile/3450625?format=tab&gbrecs=true Resolving dataverse.harvard.edu (dataverse.harvard.edu)... 206.191.184.198 Connecting to dataverse.harvard.edu (dataverse.harvard.edu)|206.191.184.198|:443... connected. HTTP request sent, awaiting response... 200 OK Length: 57600231 (55M) [text/tab-separated-values] Saving to: ‘raw.tsv’ raw.tsv 100%[===================>] 54.93M 14.7MB/s in 4.4s 2021-01-07 12:50:14 (12.4 MB/s) - ‘raw.tsv’ saved [57600231/57600231] 1103664 raw.tsv publish_date headline_text 20030219 "aba decides against community broadcasting licence" 20030219 "act fire witnesses must be aware of defamation" 20030219 "a g calls for infrastructure protection summit" 20030219 "air nz staff in aust strike for pay rise" 20030219 "air nz strike to affect australian travellers" 20030219 "ambitious olsson wins triple jump" 20030219 "antic delighted with record breaking barca" 20030219 "aussie qualifier stosur wastes four memphis match" 20030219 "aust addresses un security council over iraq"
For simplicity, we only keep the headline text and remove the publication date
!rm -r corpus
!mkdir corpus
with open('corpus/text.txt', 'w') as out_file:
with open('raw.tsv', 'r') as in_file:
for line in in_file:
headline = line.split('\t')[1].strip().strip('"')
out_file.write(headline+"\n")
rm: cannot remove 'corpus': No such file or directory
tail corpus/text.txtsevere storms forecast for nye in south east queensland snake catcher pleads for people not to kill reptiles south australia prepares for party to welcome new year strikers cool off the heat with big win in adelaide stunning images from the sydney to hobart yacht the ashes smiths warners near miss liven up boxing day test timelapse: brisbanes new year fireworks what 2017 meant to the kids of australia what the papodopoulos meeting may mean for ausus who is george papadopoulos the former trump campaign aide
2. Generate Embeddings for the Data.
In this tutorial, we use the Neural Network Language Model (NNLM) to generate embeddings for the headline data. The sentence embeddings can then be easily used to compute sentence level meaning similarity. We run the embedding generation process using Apache Beam.
Embedding extraction method
embed_fn = None
def generate_embeddings(text, module_url, random_projection_matrix=None):
# Beam will run this function in different processes that need to
# import hub and load embed_fn (if not previously loaded)
global embed_fn
if embed_fn is None:
embed_fn = hub.load(module_url)
embedding = embed_fn(text).numpy()
if random_projection_matrix is not None:
embedding = embedding.dot(random_projection_matrix)
return text, embedding
Convert to tf.Example method
def to_tf_example(entries):
examples = []
text_list, embedding_list = entries
for i in range(len(text_list)):
text = text_list[i]
embedding = embedding_list[i]
features = {
'text': tf.train.Feature(
bytes_list=tf.train.BytesList(value=[text.encode('utf-8')])),
'embedding': tf.train.Feature(
float_list=tf.train.FloatList(value=embedding.tolist()))
}
example = tf.train.Example(
features=tf.train.Features(
feature=features)).SerializeToString(deterministic=True)
examples.append(example)
return examples
Beam pipeline
def run_hub2emb(args):
'''Runs the embedding generation pipeline'''
options = beam.options.pipeline_options.PipelineOptions(**args)
args = namedtuple("options", args.keys())(*args.values())
with beam.Pipeline(args.runner, options=options) as pipeline:
(
pipeline
| 'Read sentences from files' >> beam.io.ReadFromText(
file_pattern=args.data_dir)
| 'Batch elements' >> util.BatchElements(
min_batch_size=args.batch_size, max_batch_size=args.batch_size)
| 'Generate embeddings' >> beam.Map(
generate_embeddings, args.module_url, args.random_projection_matrix)
| 'Encode to tf example' >> beam.FlatMap(to_tf_example)
| 'Write to TFRecords files' >> beam.io.WriteToTFRecord(
file_path_prefix='{}/emb'.format(args.output_dir),
file_name_suffix='.tfrecords')
)
Generating Random Projection Weight Matrix
Random projection is a simple, yet powerful technique used to reduce the dimensionality of a set of points which lie in Euclidean space. For a theoretical background, see the Johnson-Lindenstrauss lemma.
Reducing the dimensionality of the embeddings with random projection means less time needed to build and query the ANN index.
In this tutorial we use Gaussian Random Projection from the Scikit-learn library.
def generate_random_projection_weights(original_dim, projected_dim):
random_projection_matrix = None
random_projection_matrix = gaussian_random_matrix(
n_components=projected_dim, n_features=original_dim).T
print("A Gaussian random weight matrix was creates with shape of {}".format(random_projection_matrix.shape))
print('Storing random projection matrix to disk...')
with open('random_projection_matrix', 'wb') as handle:
pickle.dump(random_projection_matrix,
handle, protocol=pickle.HIGHEST_PROTOCOL)
return random_projection_matrix
Set parameters
If you want to build an index using the original embedding space without random projection, set the projected_dim parameter to None. Note that this will slow down the indexing step for high-dimensional embeddings.
module_url = 'https://tfhub.dev/google/nnlm-en-dim128/2'
projected_dim = 64
Run pipeline
import tempfile
output_dir = tempfile.mkdtemp()
original_dim = hub.load(module_url)(['']).shape[1]
random_projection_matrix = None
if projected_dim:
random_projection_matrix = generate_random_projection_weights(
original_dim, projected_dim)
args = {
'job_name': 'hub2emb-{}'.format(datetime.utcnow().strftime('%y%m%d-%H%M%S')),
'runner': 'DirectRunner',
'batch_size': 1024,
'data_dir': 'corpus/*.txt',
'output_dir': output_dir,
'module_url': module_url,
'random_projection_matrix': random_projection_matrix,
}
print("Pipeline args are set.")
args
A Gaussian random weight matrix was creates with shape of (128, 64)
Storing random projection matrix to disk...
Pipeline args are set.
/tmpfs/src/tf_docs_env/lib/python3.6/site-packages/sklearn/utils/deprecation.py:86: FutureWarning: Function gaussian_random_matrix is deprecated; gaussian_random_matrix is deprecated in 0.22 and will be removed in version 0.24.
warnings.warn(msg, category=FutureWarning)
{'job_name': 'hub2emb-210107-125029',
'runner': 'DirectRunner',
'batch_size': 1024,
'data_dir': 'corpus/*.txt',
'output_dir': '/tmp/tmp0g361gzp',
'module_url': 'https://tfhub.dev/google/nnlm-en-dim128/2',
'random_projection_matrix': array([[-0.1349755 , -0.12082699, 0.07092581, ..., -0.02680793,
-0.0459312 , -0.20462361],
[-0.06197901, 0.01832142, 0.21362496, ..., 0.06641898,
0.14553738, -0.117217 ],
[ 0.03452009, 0.14239163, 0.01371371, ..., 0.10422342,
0.02966668, -0.07094185],
...,
[ 0.03384223, 0.05102025, 0.01941788, ..., -0.07500625,
0.09584965, -0.08593636],
[ 0.11010087, -0.10597793, 0.06668758, ..., -0.0518654 ,
-0.14681441, 0.08449293],
[ 0.26909502, -0.0291555 , 0.04305639, ..., -0.02295843,
0.1164921 , -0.04828371]])}
print("Running pipeline...")
%time run_hub2emb(args)
print("Pipeline is done.")
WARNING:apache_beam.runners.interactive.interactive_environment:Dependencies required for Interactive Beam PCollection visualization are not available, please use: `pip install apache-beam[interactive]` to install necessary dependencies to enable all data visualization features. Running pipeline... Warning:tensorflow:5 out of the last 5 calls to <function recreate_function.<locals>.restored_function_body at 0x7efcac3599d8> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. Warning:tensorflow:5 out of the last 5 calls to <function recreate_function.<locals>.restored_function_body at 0x7efcac3599d8> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. Warning:tensorflow:6 out of the last 6 calls to <function recreate_function.<locals>.restored_function_body at 0x7efcac475598> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. Warning:tensorflow:6 out of the last 6 calls to <function recreate_function.<locals>.restored_function_body at 0x7efcac475598> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has experimental_relax_shapes=True option that relaxes argument shapes that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details. WARNING:apache_beam.io.tfrecordio:Couldn't find python-snappy so the implementation of _TFRecordUtil._masked_crc32c is not as fast as it could be. CPU times: user 9min 4s, sys: 10min 14s, total: 19min 19s Wall time: 2min 30s Pipeline is done.
ls {output_dir}emb-00000-of-00001.tfrecords
Read some of the generated embeddings...
embed_file = os.path.join(output_dir, 'emb-00000-of-00001.tfrecords')
sample = 5
# Create a description of the features.
feature_description = {
'text': tf.io.FixedLenFeature([], tf.string),
'embedding': tf.io.FixedLenFeature([projected_dim], tf.float32)
}
def _parse_example(example):
# Parse the input `tf.Example` proto using the dictionary above.
return tf.io.parse_single_example(example, feature_description)
dataset = tf.data.TFRecordDataset(embed_file)
for record in dataset.take(sample).map(_parse_example):
print("{}: {}".format(record['text'].numpy().decode('utf-8'), record['embedding'].numpy()[:10]))
headline_text: [ 0.07743962 -0.10065071 -0.03604915 0.03902601 0.02538098 -0.01991337 -0.11972483 0.03102058 0.16498186 -0.04299153] aba decides against community broadcasting licence: [ 0.02420221 -0.07736929 0.05655728 -0.18739551 0.11344934 0.12652674 -0.18189304 0.00422473 0.13149698 0.01910412] act fire witnesses must be aware of defamation: [-0.17413895 -0.05418579 0.07769868 0.05096476 0.08622053 0.33112594 0.04067763 0.00448784 0.15882017 0.33829722] a g calls for infrastructure protection summit: [ 0.16939437 -0.18585566 -0.14201084 -0.21779229 -0.1374832 0.14933842 -0.19583155 0.12921487 0.09811856 0.099967 ] air nz staff in aust strike for pay rise: [ 0.0230642 -0.03269081 0.18271443 0.23761444 -0.01575144 0.06109515 -0.01963143 -0.05211507 0.06050447 -0.20023327]
3. Build the ANN Index for the Embeddings
ANNOY (Approximate Nearest Neighbors Oh Yeah) is a C++ library with Python bindings to search for points in space that are close to a given query point. It also creates large read-only file-based data structures that are mapped into memory. It is built and used by Spotify for music recommendations. If you are interested you can play along with other alternatives to ANNOY such as NGT, FAISS, etc.
def build_index(embedding_files_pattern, index_filename, vector_length,
metric='angular', num_trees=100):
'''Builds an ANNOY index'''
annoy_index = annoy.AnnoyIndex(vector_length, metric=metric)
# Mapping between the item and its identifier in the index
mapping = {}
embed_files = tf.io.gfile.glob(embedding_files_pattern)
num_files = len(embed_files)
print('Found {} embedding file(s).'.format(num_files))
item_counter = 0
for i, embed_file in enumerate(embed_files):
print('Loading embeddings in file {} of {}...'.format(i+1, num_files))
dataset = tf.data.TFRecordDataset(embed_file)
for record in dataset.map(_parse_example):
text = record['text'].numpy().decode("utf-8")
embedding = record['embedding'].numpy()
mapping[item_counter] = text
annoy_index.add_item(item_counter, embedding)
item_counter += 1
if item_counter % 100000 == 0:
print('{} items loaded to the index'.format(item_counter))
print('A total of {} items added to the index'.format(item_counter))
print('Building the index with {} trees...'.format(num_trees))
annoy_index.build(n_trees=num_trees)
print('Index is successfully built.')
print('Saving index to disk...')
annoy_index.save(index_filename)
print('Index is saved to disk.')
print("Index file size: {} GB".format(
round(os.path.getsize(index_filename) / float(1024 ** 3), 2)))
annoy_index.unload()
print('Saving mapping to disk...')
with open(index_filename + '.mapping', 'wb') as handle:
pickle.dump(mapping, handle, protocol=pickle.HIGHEST_PROTOCOL)
print('Mapping is saved to disk.')
print("Mapping file size: {} MB".format(
round(os.path.getsize(index_filename + '.mapping') / float(1024 ** 2), 2)))
embedding_files = "{}/emb-*.tfrecords".format(output_dir)
embedding_dimension = projected_dim
index_filename = "index"
!rm {index_filename}
!rm {index_filename}.mapping
%time build_index(embedding_files, index_filename, embedding_dimension)
rm: cannot remove 'index': No such file or directory rm: cannot remove 'index.mapping': No such file or directory Found 1 embedding file(s). Loading embeddings in file 1 of 1... 100000 items loaded to the index 200000 items loaded to the index 300000 items loaded to the index 400000 items loaded to the index 500000 items loaded to the index 600000 items loaded to the index 700000 items loaded to the index 800000 items loaded to the index 900000 items loaded to the index 1000000 items loaded to the index 1100000 items loaded to the index A total of 1103664 items added to the index Building the index with 100 trees... Index is successfully built. Saving index to disk... Index is saved to disk. Index file size: 1.61 GB Saving mapping to disk... Mapping is saved to disk. Mapping file size: 50.61 MB CPU times: user 9min 54s, sys: 53.9 s, total: 10min 48s Wall time: 5min 5s
lscorpus random_projection_matrix index raw.tsv index.mapping tf2_semantic_approximate_nearest_neighbors.ipynb
4. Use the Index for Similarity Matching
Now we can use the ANN index to find news headlines that are semantically close to an input query.
Load the index and the mapping files
index = annoy.AnnoyIndex(embedding_dimension)
index.load(index_filename, prefault=True)
print('Annoy index is loaded.')
with open(index_filename + '.mapping', 'rb') as handle:
mapping = pickle.load(handle)
print('Mapping file is loaded.')
Annoy index is loaded. /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/ipykernel_launcher.py:1: FutureWarning: The default argument for metric will be removed in future version of Annoy. Please pass metric='angular' explicitly. """Entry point for launching an IPython kernel. Mapping file is loaded.
Similarity matching method
def find_similar_items(embedding, num_matches=5):
'''Finds similar items to a given embedding in the ANN index'''
ids = index.get_nns_by_vector(
embedding, num_matches, search_k=-1, include_distances=False)
items = [mapping[i] for i in ids]
return items
Extract embedding from a given query
# Load the TF-Hub module
print("Loading the TF-Hub module...")
%time embed_fn = hub.load(module_url)
print("TF-Hub module is loaded.")
random_projection_matrix = None
if os.path.exists('random_projection_matrix'):
print("Loading random projection matrix...")
with open('random_projection_matrix', 'rb') as handle:
random_projection_matrix = pickle.load(handle)
print('random projection matrix is loaded.')
def extract_embeddings(query):
'''Generates the embedding for the query'''
query_embedding = embed_fn([query])[0].numpy()
if random_projection_matrix is not None:
query_embedding = query_embedding.dot(random_projection_matrix)
return query_embedding
Loading the TF-Hub module... CPU times: user 757 ms, sys: 619 ms, total: 1.38 s Wall time: 1.37 s TF-Hub module is loaded. Loading random projection matrix... random projection matrix is loaded.
extract_embeddings("Hello Machine Learning!")[:10]
array([ 0.12164804, 0.0162079 , -0.15466002, -0.14580576, 0.03926325,
-0.10124508, -0.1333948 , 0.0515029 , -0.14688903, -0.09971556])
Enter a query to find the most similar items
query = "confronting global challenges"
print("Generating embedding for the query...")
%time query_embedding = extract_embeddings(query)
print("")
print("Finding relevant items in the index...")
%time items = find_similar_items(query_embedding, 10)
print("")
print("Results:")
print("=========")
for item in items:
print(item)
Generating embedding for the query... CPU times: user 5.18 ms, sys: 596 µs, total: 5.77 ms Wall time: 2.19 ms Finding relevant items in the index... CPU times: user 555 µs, sys: 327 µs, total: 882 µs Wall time: 601 µs Results: ========= confronting global challenges emerging nations to help struggling global economy g7 warns of increasing global economic crisis world struggling to cope with global terrorism companies health to struggle amid global crisis external risks biggest threat to economy asian giants unite to tackle global crisis g7 ministers warn of slowing global growth experts to discuss global warming threat scientists warn of growing natural disasters
Want to learn more?
You can learn more about TensorFlow at tensorflow.org and see the TF-Hub API documentation at tensorflow.org/hub. Find available TensorFlow Hub modules at tfhub.dev including more text embedding modules and image feature vector modules.
Also check out the Machine Learning Crash Course which is Google's fast-paced, practical introduction to machine learning.