DEP bump pylangacq to 0.13.1 for chat parsing fix, add more talkbank …

…datasets in docs
jacksonllee · Mar 23, 2021 · 5542fde · 5542fde
1 parent 7c4b78c
commit 5542fde
Show file tree

Hide file tree

Showing 42 changed files with 121 additions and 332 deletions.
diff --git a/docs/.buildinfo b/docs/.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: 1b2c69900a20a5e6d404547532dec06c
+config: 76d7be4743f134d1ecb28043ff0666d5
 tags: 645f666f9bcd5a90fca523b33c5a78b7
diff --git a/docs/_modules/index.html b/docs/_modules/index.html
@@ -317,7 +317,7 @@ <h1>All modules for which code is available</h1>
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/_modules/pycantonese/corpus.html b/docs/_modules/pycantonese/corpus.html
@@ -703,7 +703,7 @@ <h1>Source code for pycantonese.corpus</h1><div class="highlight"><pre>
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/_modules/pycantonese/jyutping/characters.html b/docs/_modules/pycantonese/jyutping/characters.html
@@ -438,7 +438,7 @@ <h1>Source code for pycantonese.jyutping.characters</h1><div class="highlight"><
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/_modules/pycantonese/jyutping/parse_jyutping.html b/docs/_modules/pycantonese/jyutping/parse_jyutping.html
@@ -498,7 +498,7 @@ <h1>Source code for pycantonese.jyutping.parse_jyutping</h1><div class="highligh
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/_modules/pycantonese/jyutping/tipa.html b/docs/_modules/pycantonese/jyutping/tipa.html
@@ -447,7 +447,7 @@ <h1>Source code for pycantonese.jyutping.tipa</h1><div class="highlight"><pre>
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/_modules/pycantonese/jyutping/yale.html b/docs/_modules/pycantonese/jyutping/yale.html
@@ -625,7 +625,7 @@ <h1>Source code for pycantonese.jyutping.yale</h1><div class="highlight"><pre>
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/_modules/pycantonese/pos_tagging/hkcancor_to_ud.html b/docs/_modules/pycantonese/pos_tagging/hkcancor_to_ud.html
@@ -492,7 +492,7 @@ <h1>Source code for pycantonese.pos_tagging.hkcancor_to_ud</h1><div class="highl
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/_modules/pycantonese/pos_tagging/tagger.html b/docs/_modules/pycantonese/pos_tagging/tagger.html
@@ -660,7 +660,7 @@ <h1>Source code for pycantonese.pos_tagging.tagger</h1><div class="highlight"><p
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/_modules/pycantonese/stop_words.html b/docs/_modules/pycantonese/stop_words.html
@@ -465,7 +465,7 @@ <h1>Source code for pycantonese.stop_words</h1><div class="highlight"><pre>
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/_modules/pycantonese/word_segmentation.html b/docs/_modules/pycantonese/word_segmentation.html
@@ -426,7 +426,7 @@ <h1>Source code for pycantonese.word_segmentation</h1><div class="highlight"><pr
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/_modules/pylangacq/chat.html b/docs/_modules/pylangacq/chat.html
diff --git a/docs/_sources/data.rst.txt b/docs/_sources/data.rst.txt
@@ -65,6 +65,34 @@ the CC BY-NC-SA 3.0 license.
 As of March 2021, the following Cantonese-related datasets are
 available from CHILDES and TalkBank (in alphabetical order):
 
+.. invisible-code-block: python
+
+    >>> import os
+
+.. skip: start if(os.getenv("CI") == "true", reason="certain CHILDES data pulls fail in some but not all python versions for unknown reasons")
+
+* `Child Heritage Chinese Corpus <https://childes.talkbank.org/access/Biling/CHCC.html>`_
+
+    .. code-block:: python
+
+        >>> url = "https://childes.talkbank.org/data/Biling/CHCC.zip"
+        >>> corpus = pycantonese.read_chat(url)
+        >>> corpus.n_files()
+        190
+        >>> len(corpus.words())
+        533877
+
+* `Guthrie Bilingual Corpus <https://childes.talkbank.org/access/Biling/Guthrie.html>`_
+
+    .. code-block:: python
+
+        >>> url = "https://childes.talkbank.org/data/Biling/Guthrie.zip"
+        >>> corpus = pycantonese.read_chat(url)
+        >>> corpus.n_files()
+        36
+        >>> len(corpus.words())
+        70438
+
 * `HKU-70 Corpus <https://childes.talkbank.org/access/Chinese/Cantonese/HKU.html>`_
 
     .. code-block:: python
@@ -76,12 +104,6 @@ available from CHILDES and TalkBank (in alphabetical order):
         >>> len(corpus.words())
         178270
 
-.. invisible-code-block: python
-
-    >>> import os
-
-.. skip: start if(os.getenv("CI") == "true", reason="certain CHILDES data pulls fail in some but not all python versions for unknown reasons")
-
 * `Lee-Wong-Leung Corpus <https://childes.talkbank.org/access/Chinese/Cantonese/LeeWongLeung.html>`_
 
     .. code-block:: python

diff --git a/docs/api.html b/docs/api.html
@@ -1601,7 +1601,7 @@ <h2><a class="reference internal" href="#pycantonese.jyutping.Jyutping" title="p
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/changelog.html b/docs/changelog.html
@@ -641,7 +641,7 @@ <h2>[0.1] - 2014-12-17<a class="headerlink" href="#id40" title="Permalink to thi
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/data.html b/docs/data.html
@@ -350,6 +350,30 @@ <h2>CHILDES and TalkBank Data<a class="headerlink" href="#childes-and-talkbank-d
 <p>As of March 2021, the following Cantonese-related datasets are
 available from CHILDES and TalkBank (in alphabetical order):</p>
 <ul>
+<li><p><a class="reference external" href="https://childes.talkbank.org/access/Biling/CHCC.html">Child Heritage Chinese Corpus</a></p>
+<blockquote>
+<div><div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">url</span> <span class="o">=</span> <span class="s2">&quot;https://childes.talkbank.org/data/Biling/CHCC.zip&quot;</span>
+<span class="gp">&gt;&gt;&gt; </span><span class="n">corpus</span> <span class="o">=</span> <span class="n">pycantonese</span><span class="o">.</span><span class="n">read_chat</span><span class="p">(</span><span class="n">url</span><span class="p">)</span>
+<span class="gp">&gt;&gt;&gt; </span><span class="n">corpus</span><span class="o">.</span><span class="n">n_files</span><span class="p">()</span>
+<span class="go">190</span>
+<span class="gp">&gt;&gt;&gt; </span><span class="nb">len</span><span class="p">(</span><span class="n">corpus</span><span class="o">.</span><span class="n">words</span><span class="p">())</span>
+<span class="go">533877</span>
+</pre></div>
+</div>
+</div></blockquote>
+</li>
+<li><p><a class="reference external" href="https://childes.talkbank.org/access/Biling/Guthrie.html">Guthrie Bilingual Corpus</a></p>
+<blockquote>
+<div><div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">url</span> <span class="o">=</span> <span class="s2">&quot;https://childes.talkbank.org/data/Biling/Guthrie.zip&quot;</span>
+<span class="gp">&gt;&gt;&gt; </span><span class="n">corpus</span> <span class="o">=</span> <span class="n">pycantonese</span><span class="o">.</span><span class="n">read_chat</span><span class="p">(</span><span class="n">url</span><span class="p">)</span>
+<span class="gp">&gt;&gt;&gt; </span><span class="n">corpus</span><span class="o">.</span><span class="n">n_files</span><span class="p">()</span>
+<span class="go">36</span>
+<span class="gp">&gt;&gt;&gt; </span><span class="nb">len</span><span class="p">(</span><span class="n">corpus</span><span class="o">.</span><span class="n">words</span><span class="p">())</span>
+<span class="go">70438</span>
+</pre></div>
+</div>
+</div></blockquote>
+</li>
 <li><p><a class="reference external" href="https://childes.talkbank.org/access/Chinese/Cantonese/HKU.html">HKU-70 Corpus</a></p>
 <blockquote>
 <div><div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">url</span> <span class="o">=</span> <span class="s2">&quot;https://childes.talkbank.org/data/Chinese/Cantonese/HKU.zip&quot;</span>
@@ -362,8 +386,6 @@ <h2>CHILDES and TalkBank Data<a class="headerlink" href="#childes-and-talkbank-d
 </div>
 </div></blockquote>
 </li>
-</ul>
-<ul>
 <li><p><a class="reference external" href="https://childes.talkbank.org/access/Chinese/Cantonese/LeeWongLeung.html">Lee-Wong-Leung Corpus</a></p>
 <blockquote>
 <div><div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="gp">&gt;&gt;&gt; </span><span class="n">url</span> <span class="o">=</span> <span class="s2">&quot;https://childes.talkbank.org/data/Chinese/Cantonese/LeeWongLeung.zip&quot;</span>
@@ -456,7 +478,7 @@ <h2>Custom Data<a class="headerlink" href="#custom-data" title="Permalink to thi
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/generated/pycantonese.CHATReader.html b/docs/generated/pycantonese.CHATReader.html
@@ -593,7 +593,7 @@ <h1>pycantonese.CHATReader<a class="headerlink" href="#pycantonese-chatreader" t
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/generated/pycantonese.CHATReader.search.html b/docs/generated/pycantonese.CHATReader.search.html
@@ -400,7 +400,7 @@ <h1>pycantonese.CHATReader.search<a class="headerlink" href="#pycantonese-chatre
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/generated/pycantonese.characters_to_jyutping.html b/docs/generated/pycantonese.characters_to_jyutping.html
@@ -363,7 +363,7 @@ <h1>pycantonese.characters_to_jyutping<a class="headerlink" href="#pycantonese-c
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/generated/pycantonese.hkcancor.html b/docs/generated/pycantonese.hkcancor.html
@@ -337,7 +337,7 @@ <h1>pycantonese.hkcancor<a class="headerlink" href="#pycantonese-hkcancor" title
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/generated/pycantonese.jyutping_to_tipa.html b/docs/generated/pycantonese.jyutping_to_tipa.html
@@ -358,7 +358,7 @@ <h1>pycantonese.jyutping_to_tipa<a class="headerlink" href="#pycantonese-jyutpin
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/generated/pycantonese.jyutping_to_yale.html b/docs/generated/pycantonese.jyutping_to_yale.html
@@ -374,7 +374,7 @@ <h1>pycantonese.jyutping_to_yale<a class="headerlink" href="#pycantonese-jyutpin
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/generated/pycantonese.parse_jyutping.html b/docs/generated/pycantonese.parse_jyutping.html
@@ -357,7 +357,7 @@ <h1>pycantonese.parse_jyutping<a class="headerlink" href="#pycantonese-parse-jyu
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/generated/pycantonese.pos_tag.html b/docs/generated/pycantonese.pos_tag.html
@@ -382,7 +382,7 @@ <h1>pycantonese.pos_tag<a class="headerlink" href="#pycantonese-pos-tag" title="
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/generated/pycantonese.pos_tagging.hkcancor_to_ud.html b/docs/generated/pycantonese.pos_tagging.hkcancor_to_ud.html
@@ -363,7 +363,7 @@ <h1>pycantonese.pos_tagging.hkcancor_to_ud<a class="headerlink" href="#pycantone
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/generated/pycantonese.read_chat.html b/docs/generated/pycantonese.read_chat.html
@@ -366,7 +366,7 @@ <h1>pycantonese.read_chat<a class="headerlink" href="#pycantonese-read-chat" tit
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/generated/pycantonese.segment.html b/docs/generated/pycantonese.segment.html
@@ -370,7 +370,7 @@ <h1>pycantonese.segment<a class="headerlink" href="#pycantonese-segment" title="
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/generated/pycantonese.stop_words.html b/docs/generated/pycantonese.stop_words.html
@@ -364,7 +364,7 @@ <h1>pycantonese.stop_words<a class="headerlink" href="#pycantonese-stop-words" t
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/generated/pycantonese.word_segmentation.Segmenter.html b/docs/generated/pycantonese.word_segmentation.Segmenter.html
@@ -384,7 +384,7 @@ <h1>pycantonese.word_segmentation.Segmenter<a class="headerlink" href="#pycanton
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/genindex.html b/docs/genindex.html
@@ -570,7 +570,7 @@ <h2 id="W">W</h2>
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/index.html b/docs/index.html
@@ -476,7 +476,7 @@ <h2>Table of Contents<a class="headerlink" href="#table-of-contents" title="Perm
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/jyutping.html b/docs/jyutping.html
@@ -471,7 +471,7 @@ <h2>Jyutping-to-TIPA Conversion<a class="headerlink" href="#jyutping-to-tipa-con
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/papers.html b/docs/papers.html
@@ -329,7 +329,7 @@
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/pos_tagging.html b/docs/pos_tagging.html
@@ -366,7 +366,7 @@
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/reader.html b/docs/reader.html
@@ -591,7 +591,7 @@ <h2>Word Frequencies and Ngrams<a class="headerlink" href="#word-frequencies-and
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/search.html b/docs/search.html
@@ -321,7 +321,7 @@
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>

diff --git a/docs/searches.html b/docs/searches.html
@@ -584,7 +584,7 @@
   <div role="contentinfo">
     <p>
 
-        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 21, 2021
+        &copy; Copyright 2014-2021, Jackson L. Lee | Documentation last updated on March 23, 2021
 
     </p>
   </div>