Merge branch 'develop' into spacy.io-develop

spacy/about.py

@@ -1,6 +1,6 @@
 # fmt: off
-__title__ = "spacy"
-__version__ = "3.0.0.dev13"
+__title__ = "spacy_nightly"
+__version__ = "3.0.0a0"
 __release__ = True
 __download_url__ = "https://github.com/explosion/spacy-models/releases/download"
 __compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json"

spacy/cli/train.py

@@ -332,13 +332,14 @@ def create_evaluation_callback(nlp, optimizer, corpus, cfg):
         )
 
         n_words = sum(len(ex.predicted) for ex in dev_examples)
+        batch_size = cfg.get("evaluation_batch_size", 128)
         start_time = timer()
 
         if optimizer.averages:
             with nlp.use_params(optimizer.averages):
-                scorer = nlp.evaluate(dev_examples, batch_size=32)
+                scorer = nlp.evaluate(dev_examples, batch_size=batch_size)
         else:
-            scorer = nlp.evaluate(dev_examples, batch_size=32)
+            scorer = nlp.evaluate(dev_examples, batch_size=batch_size)
         end_time = timer()
         wps = n_words / (end_time - start_time)
         scores = scorer.scores

spacy/gold/corpus.py

@@ -45,18 +45,22 @@ class Corpus:
 
     def make_examples(self, nlp, reference_docs, max_length=0):
         for reference in reference_docs:
-            if len(reference) >= max_length >= 1:
-                if reference.is_sentenced:
-                    for ref_sent in reference.sents:
-                        yield Example(
-                            nlp.make_doc(ref_sent.text),
-                            ref_sent.as_doc()
-                        )
-            else:
+            if len(reference) == 0:
+                continue
+            elif max_length == 0 or len(reference) < max_length:
                 yield Example(
                     nlp.make_doc(reference.text),
                     reference
                 )
+            elif reference.is_sentenced:
+                for ref_sent in reference.sents:
+                    if len(ref_sent) == 0:
+                        continue
+                    elif max_length == 0 or len(ref_sent) < max_length:
+                        yield Example(
+                            nlp.make_doc(ref_sent.text),
+                            ref_sent.as_doc()
+                        )
     
     def make_examples_gold_preproc(self, nlp, reference_docs):
         for reference in reference_docs:
@@ -65,7 +69,7 @@ class Corpus:
             else:
                 ref_sents = [reference]
             for ref_sent in ref_sents:
-                yield Example(
+                eg = Example(
                     Doc(
                         nlp.vocab, 
                         words=[w.text for w in ref_sent],
@@ -73,6 +77,8 @@ class Corpus:
                     ),
                     ref_sent
                 )
+                if len(eg.x):
+                    yield eg
 
     def read_docbin(self, vocab, locs):
         """ Yield training examples as example dicts """

spacy/syntax/nn_parser.pyx

@@ -449,7 +449,7 @@ cdef class Parser:
                 if component is self:
                     break
                 if hasattr(component, "pipe"):
-                    doc_sample = list(component.pipe(doc_sample))
+                    doc_sample = list(component.pipe(doc_sample, batch_size=8))
                 else:
                     doc_sample = [component(doc) for doc in doc_sample]
         if doc_sample:

website/src/components/button.js

@@ -27,7 +27,7 @@ Button.defaultProps = {
 }
 
 Button.propTypes = {
-    to: PropTypes.string.isRequired,
+    to: PropTypes.string,
     variant: PropTypes.oneOf(['primary', 'secondary', 'tertiary']),
     large: PropTypes.bool,
     icon: PropTypes.string,

website/src/pages/404.js

@@ -0,0 +1,47 @@
+import React from 'react'
+import { window } from 'browser-monads'
+import { graphql } from 'gatsby'
+
+import Template from '../templates/index'
+import { LandingHeader, LandingTitle } from '../components/landing'
+import Button from '../components/button'
+
+export default ({ data, location }) => {
+    const { nightly } = data.site.siteMetadata
+    const pageContext = { title: '404 Error', searchExclude: true, isIndex: false }
+    return (
+        <Template data={data} pageContext={pageContext} location={location}>
+            <LandingHeader style={{ minHeight: 400 }} nightly={nightly}>
+                <LandingTitle>
+                    Ooops, this page
+                    <br />
+                    does not exist!
+                </LandingTitle>
+                <br />
+                <Button onClick={() => window.history.go(-1)} variant="tertiary">
+                    Click here to go back
+                </Button>
+            </LandingHeader>
+        </Template>
+    )
+}
+
+export const pageQuery = graphql`
+    query {
+        site {
+            siteMetadata {
+                nightly
+                title
+                description
+                navigation {
+                    text
+                    url
+                }
+                docSearch {
+                    apiKey
+                    indexName
+                }
+            }
+        }
+    }
+`

website/src/pages/404.md

@@ -1,7 +0,0 @@
----
-title: 404 Error
----
-
-import Error from 'widgets/404.js'
-
-<Error />

website/src/widgets/404.js

@@ -1,19 +0,0 @@
-import React from 'react'
-import { window } from 'browser-monads'
-
-import { LandingHeader, LandingTitle } from '../components/landing'
-import Button from '../components/button'
-
-export default () => (
-    <LandingHeader style={{ minHeight: 400 }}>
-        <LandingTitle>
-            Ooops, this page
-            <br />
-            does not exist!
-        </LandingTitle>
-        <br />
-        <Button onClick={() => window.history.go(-1)} variant="tertiary">
-            Click here to go back
-        </Button>
-    </LandingHeader>
-)