From eef9430f0710562b4582c11d0692d7c56c5fd1da Mon Sep 17 00:00:00 2001 From: Justin DuJardin Date: Fri, 23 Mar 2018 12:49:01 -0700 Subject: [PATCH 1/2] Add example for visualizing word vectors with TensorBoard Projector Use: ```bash python vectors_tensorboard.py en_core_web_lg ./output_folder spaCy_large ``` --- examples/vectors_tensorboard.py | 82 +++++++++++++++++++++++++++++++++ 1 file changed, 82 insertions(+) create mode 100644 examples/vectors_tensorboard.py diff --git a/examples/vectors_tensorboard.py b/examples/vectors_tensorboard.py new file mode 100644 index 000000000..f29193345 --- /dev/null +++ b/examples/vectors_tensorboard.py @@ -0,0 +1,82 @@ +#!/usr/bin/env python +# coding: utf8 +"""Visualize spaCy word vectors in Tensorboard. + +Adapted from: https://gist.github.com/BrikerMan/7bd4e4bd0a00ac9076986148afc06507 +""" +from __future__ import unicode_literals + +from os import path + +import math +import numpy +import plac +import spacy +import tensorflow as tf +import tqdm +from tensorflow.contrib.tensorboard.plugins.projector import visualize_embeddings, ProjectorConfig + + +@plac.annotations( + vectors_loc=("Path to spaCy model that contains vectors", "positional", None, str), + out_loc=("Path to output folder for tensorboard session 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"): + meta_file = "{}.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)) + strings_stream = tqdm.tqdm(model.vocab.strings, total=len(model.vocab.strings), leave=False) + queries = [w for w in strings_stream if model.vocab.has_vector(w)] + vector_count = len(queries) + + print('Building Tensorboard Projector metadata for ({}) vectors: {}'.format(vector_count, out_meta_file)) + + # Store vector data in a tensorflow variable + tf_vectors_variable = numpy.zeros((vector_count, model.vocab.vectors.shape[1])) + + # 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(queries, total=len(queries), leave=False): + # https://github.com/tensorflow/tensorflow/issues/9094 + text = '' if text.lstrip() == '' else text + lex = model.vocab[text] + + # Store vector data and metadata + tf_vectors_variable[vec_index] = model.vocab.get_vector(text) + file_metadata.write("{}\t{}\n".format(text, math.exp(lex.prob) * vector_count).encode('utf-8')) + vec_index += 1 + + print('Running Tensorflow Session...') + sess = tf.InteractiveSession() + tf.Variable(tf_vectors_variable, trainable=False, name=name) + tf.global_variables_initializer().run() + saver = tf.train.Saver() + writer = tf.summary.FileWriter(out_loc, sess.graph) + + # Link the embeddings into the config + config = ProjectorConfig() + embed = config.embeddings.add() + embed.tensor_name = name + embed.metadata_path = meta_file + + # Tell the projector about the configured embeddings and metadata file + visualize_embeddings(writer, config) + + # Save session and print run command to the output + print('Saving Tensorboard Session...') + saver.save(sess, path.join(out_loc, '{}.ckpt'.format(name))) + print('Done. Run `tensorboard --logdir={0}` to view in Tensorboard'.format(out_loc)) + + +if __name__ == '__main__': + plac.call(main) From c7ff8ee66c8b47b2fa49d39dcf54c6ea6acbf539 Mon Sep 17 00:00:00 2001 From: Justin DuJardin Date: Fri, 23 Mar 2018 13:11:56 -0700 Subject: [PATCH 2/2] Add contributor agreement --- .github/contributors/justindujardin.md | 106 +++++++++++++++++++++++++ 1 file changed, 106 insertions(+) create mode 100644 .github/contributors/justindujardin.md diff --git a/.github/contributors/justindujardin.md b/.github/contributors/justindujardin.md new file mode 100644 index 000000000..35d403acb --- /dev/null +++ b/.github/contributors/justindujardin.md @@ -0,0 +1,106 @@ +# spaCy contributor agreement + +This spaCy Contributor Agreement (**"SCA"**) is based on the +[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf). +The SCA applies to any contribution that you make to any product or project +managed by us (the **"project"**), and sets out the intellectual property rights +you grant to us in the contributed materials. The term **"us"** shall mean +[ExplosionAI UG (haftungsbeschränkt)](https://explosion.ai/legal). The term +**"you"** shall mean the person or entity identified below. + +If you agree to be bound by these terms, fill in the information requested +below and include the filled-in version with your first pull request, under the +folder [`.github/contributors/`](/.github/contributors/). The name of the file +should be your GitHub username, with the extension `.md`. For example, the user +example_user would create the file `.github/contributors/example_user.md`. + +Read this agreement carefully before signing. These terms and conditions +constitute a binding legal agreement. + +## Contributor Agreement + +1. The term "contribution" or "contributed materials" means any source code, +object code, patch, tool, sample, graphic, specification, manual, +documentation, or any other material posted or submitted by you to the project. + +2. With respect to any worldwide copyrights, or copyright applications and +registrations, in your contribution: + + * you hereby assign to us joint ownership, and to the extent that such + assignment is or becomes invalid, ineffective or unenforceable, you hereby + grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge, + royalty-free, unrestricted license to exercise all rights under those + copyrights. This includes, at our option, the right to sublicense these same + rights to third parties through multiple levels of sublicensees or other + licensing arrangements; + + * you agree that each of us can do all things in relation to your + contribution as if each of us were the sole owners, and if one of us makes + a derivative work of your contribution, the one who makes the derivative + work (or has it made will be the sole owner of that derivative work; + + * you agree that you will not assert any moral rights in your contribution + against us, our licensees or transferees; + + * you agree that we may register a copyright in your contribution and + exercise all ownership rights associated with it; and + + * you agree that neither of us has any duty to consult with, obtain the + consent of, pay or render an accounting to the other for any use or + distribution of your contribution. + +3. With respect to any patents you own, or that you can license without payment +to any third party, you hereby grant to us a perpetual, irrevocable, +non-exclusive, worldwide, no-charge, royalty-free license to: + + * make, have made, use, sell, offer to sell, import, and otherwise transfer + your contribution in whole or in part, alone or in combination with or + included in any product, work or materials arising out of the project to + which your contribution was submitted, and + + * at our option, to sublicense these same rights to third parties through + multiple levels of sublicensees or other licensing arrangements. + +4. Except as set out above, you keep all right, title, and interest in your +contribution. The rights that you grant to us under these terms are effective +on the date you first submitted a contribution to us, even if your submission +took place before the date you sign these terms. + +5. You covenant, represent, warrant and agree that: + + * Each contribution that you submit is and shall be an original work of + authorship and you can legally grant the rights set out in this SCA; + + * to the best of your knowledge, each contribution will not violate any + third party's copyrights, trademarks, patents, or other intellectual + property rights; and + + * each contribution shall be in compliance with U.S. export control laws and + other applicable export and import laws. You agree to notify us if you + become aware of any circumstance which would make any of the foregoing + representations inaccurate in any respect. We may publicly disclose your + participation in the project, including the fact that you have signed the SCA. + +6. This SCA is governed by the laws of the State of California and applicable +U.S. Federal law. Any choice of law rules will not apply. + +7. Please place an “x” on one of the applicable statement below. Please do NOT +mark both statements: + + * [x] I am signing on behalf of myself as an individual and no other person + or entity, including my employer, has or will have rights with respect to my + contributions. + + * [ ] I am signing on behalf of my employer or a legal entity and I have the + actual authority to contractually bind that entity. + +## Contributor Details + +| Field | Entry | +|------------------------------- | -------------------- | +| Name | Justin DuJardin | +| Company name (if applicable) | DuJardin Consulting, LLC | +| Title or role (if applicable) | | +| Date | 2018-03-23 | +| GitHub username | justindujardin | +| Website (optional) | https://justindujardin.com |