Семантический поиск с приближенными ближайшими соседями и встраиванием текста

pip install -q apache_beam
pip install -q 'scikit_learn~=0.23.0'  # For gaussian_random_matrix.
pip install -q annoy

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

wget 'https://dataverse.harvard.edu/api/access/datafile/3450625?format=tab&gbrecs=true' -O raw.tsv
wc -l raw.tsv
head 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"

!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.txt

severe 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

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

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

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')
    )

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

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

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]

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

ls

corpus         random_projection_matrix
index          raw.tsv
index.mapping  tf2_semantic_approximate_nearest_neighbors.ipynb

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.

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

# 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])

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