Merge pull request #374 from wellcometrust/release-version-2.0.0

Release 2.0.0
wellcometrust · Nov 8, 2021 · 539fd83 · 539fd83
2 parents 2b712ed + 96359e3
commit 539fd83
Show file tree

Hide file tree

Showing 37 changed files with 761 additions and 3,533 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,3 +1,20 @@
+# 2.0.0
+Release date: 05/11/2021
+
+Improvements:
+- #328: Expose build_model to CNNClassifier and don't rebuild in fit
+- #372: Add more fine grained extras to make vanilla WellcomeML light (109MB)
+- #368: Expand LOGGING_LEVEL to TF_CPP_MIN_LOG_LEVEL
+- #332: Add `wellcomeml.viz` to vizualize clusters
+- #344: Add filter by variable in visualize clusters
+
+Breaking changes:
+- #371: Delete `wellcomeml.ml.__init__` so all ml models need to be explicitly imported
+
+Bug fixes:
+- #357: Fix sent2vec test error
+
+
 # 1.2.1
 Release date: 05/08/2021
 

diff --git a/Makefile b/Makefile
@@ -18,7 +18,7 @@ $(VIRTUALENV)/.installed:
 	$(VENV_BIN)/pip3 install --upgrade pip
 	$(VENV_BIN)/pip3 install -r requirements_test.txt
 	$(VENV_BIN)/pip3 install -r docs/requirements.txt # Installs requirements to docs
-	$(VENV_BIN)/pip3 install -e .[tensorflow,spacy,torch]
+	$(VENV_BIN)/pip3 install -e .[tensorflow,spacy,torch,core,transformers]
 	$(VENV_BIN)/pip3 install hdbscan --no-cache-dir --no-binary :all: --no-build-isolation
 	touch $@
 

diff --git a/docs/_build/doctrees/clustering.doctree b/docs/_build/doctrees/clustering.doctree
diff --git a/docs/_build/doctrees/environment.pickle b/docs/_build/doctrees/environment.pickle
diff --git a/docs/_build/doctrees/examples.doctree b/docs/_build/doctrees/examples.doctree
diff --git a/docs/_build/doctrees/index.doctree b/docs/_build/doctrees/index.doctree
diff --git a/docs/_build/doctrees/modules.doctree b/docs/_build/doctrees/modules.doctree
diff --git a/docs/_build/doctrees/wellcomeml.datasets.doctree b/docs/_build/doctrees/wellcomeml.datasets.doctree
diff --git a/docs/_build/doctrees/wellcomeml.doctree b/docs/_build/doctrees/wellcomeml.doctree
diff --git a/docs/_build/doctrees/wellcomeml.io.doctree b/docs/_build/doctrees/wellcomeml.io.doctree
diff --git a/docs/_build/doctrees/wellcomeml.metrics.doctree b/docs/_build/doctrees/wellcomeml.metrics.doctree
diff --git a/docs/_build/doctrees/wellcomeml.ml.doctree b/docs/_build/doctrees/wellcomeml.ml.doctree
diff --git a/docs/_build/doctrees/wellcomeml.spacy.doctree b/docs/_build/doctrees/wellcomeml.spacy.doctree
diff --git a/docs/_build/doctrees/wellcomeml.viz.doctree b/docs/_build/doctrees/wellcomeml.viz.doctree
diff --git a/docs/_build/html/.buildinfo b/docs/_build/html/.buildinfo
@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 286bb32e20741d33e836f72215724592
+config: 2596c300e2e41b399fd316a9409defb1
 tags: 645f666f9bcd5a90fca523b33c5a78b7
diff --git a/docs/_build/html/_sources/examples.rst.txt b/docs/_build/html/_sources/examples.rst.txt
@@ -12,7 +12,7 @@ In order to transform text:
 
 .. code-block:: python
 
-    from wellcomeml.ml import BertVectorizer
+    from wellcomeml.ml.bert_vectorizer import BertVectorizer
 
 
     X = [
@@ -38,7 +38,7 @@ using a :class:`BertClassifier <wellcomeml.ml.bert_classifier>`
 
     import numpy as np
 
-    from wellcomeml.ml import BertClassifier
+    from wellcomeml.ml.bert_classifier import BertClassifier
 
     X = ["Hot and cold", "Hot", "Cold"]
     Y = np.array([[1,1],[1,0],[0,1]])
@@ -56,7 +56,7 @@ Retrain a `spaCy NER classifier <https://spacy.io/usage/training#ner>`_ on new d
 
     import random
 
-    from wellcomeml.ml import SpacyNER
+    from wellcomeml.ml.spacy_ner import SpacyNER
 
     X_train = [
         "n Journal of Psychiatry 158: 2071–4\nFreeman MP, Hibbeln JR, Wisner KL et al. (2006)\n",
@@ -106,7 +106,7 @@ Link sentences to the most similar document in a corpus using :class:`Similarity
 
 .. code-block:: python
 
-    from wellcomeml.ml import SimilarityEntityLinker
+    from wellcomeml.ml.similarity_entity_linking import SimilarityEntityLinker
 
     entities_kb = {
         "Michelle Williams (actor)": (

diff --git a/docs/_build/html/_static/css/theme.css b/docs/_build/html/_static/css/theme.css
diff --git a/docs/_build/html/_static/documentation_options.js b/docs/_build/html/_static/documentation_options.js
@@ -1,6 +1,6 @@
 var DOCUMENTATION_OPTIONS = {
     URL_ROOT: document.getElementById("documentation_options").getAttribute('data-url_root'),
-    VERSION: '1.2.1',
+    VERSION: '2.0.0',
     LANGUAGE: 'None',
     COLLAPSE_INDEX: false,
     BUILDER: 'html',

diff --git a/docs/_build/html/_static/js/theme.js b/docs/_build/html/_static/js/theme.js
diff --git a/docs/_build/html/_static/searchtools.js b/docs/_build/html/_static/searchtools.js
@@ -282,7 +282,10 @@ var Search = {
                   complete: function(jqxhr, textstatus) {
                     var data = jqxhr.responseText;
                     if (data !== '' && data !== undefined) {
-                      listItem.append(Search.makeSearchSummary(data, searchterms, hlterms));
+                      var summary = Search.makeSearchSummary(data, searchterms, hlterms);
+                      if (summary) {
+                        listItem.append(summary);
+                      }
                     }
                     Search.output.append(listItem);
                     setTimeout(function() {
@@ -498,6 +501,9 @@ var Search = {
    */
   makeSearchSummary : function(htmlText, keywords, hlwords) {
     var text = Search.htmlToText(htmlText);
+    if (text == "") {
+      return null;
+    }
     var textLower = text.toLowerCase();
     var start = 0;
     $.each(keywords, function() {