Update docs

docs/build/html/_sources/examples.rst.txt

@@ -5,6 +5,6 @@ Examples
 
 Installation/Usage:
 *******************
-As the package has not been published on PyPi yet, it CANNOT be install using pip.
+As the package has not been published on PyPi yet, it CANNOT be installed using pip.
 
 For now, the suggested method is to download the zipped package or use the online version at  `https://huggingface.co/spaces/mikeee/radiobee-aligner/  <https://huggingface.co/spaces/mikeee/radiobee-aligner/>`_

docs/build/html/_sources/userguide-zh.rst.txt

@@ -5,6 +5,7 @@
 
 -  ``radiobee`` 目前仅支持中英、英中对齐。
 -  ``radiobee`` 目前仅支持纯文本文件上载 (txt, md, csv 等)。 以后可能会支持 ``docx``, ``pdf``, ``srt``, ``html`` 等格式。
+-  ``file 2`` 为空白时，``radiobee`` 则会视 ``file 1`` 为中英文混合文本及试着分离中英文，然后进行对齐。
 -  第二次上载文件前请点击"Clear"。
 -  ``tf_type`` ``idf_type`` ``dl_type`` ``norm``: 一般无需理会这些参数。
 -  ``esp`` 和 ``min_samples`` 的建议值 -- ``esp`` (最小 ``epsilon``): 8-12, ``min_samples``: 4-8.

docs/build/html/_sources/userguide.rst.txt

@@ -4,6 +4,8 @@ How to use
 -   ``radiobee aligner`` is a sibling of `bumblebee aligner`. To know more about these aligners, please join qq group `316287378`.
 
 -   Uploaded files should be in pure text format (txt, md, csv etc). ``docx``, ``pdf``, ``srt``, ``html`` etc may be supported later on.
+- If ``file 2`` is left blank, ``radiobee`` will treat ``file 1`` as mixed English-Chinese text and attempt to separate English and Chinese texts before procedding to align them.
+
 -   Click "Clear" first for subsequent submits when uploading files.
 -  ``tf_type`` ``idf_type`` ``dl_type`` ``norm``: Normally there is no need to touch these unless you know what you are doing.
 -   Suggested ``esp`` and ``min_samples`` values -- ``esp`` (minimum epsilon): 8-12, ``min_samples``: 4-8.

docs/build/html/examples.html

@@ -78,7 +78,7 @@
 <p><code class="docutils literal notranslate"><span class="pre">radiobee</span></code> has in-built examples. Just click one of the rows in the <code class="docutils literal notranslate"><span class="pre">Examples</span></code> table and click <code class="docutils literal notranslate"><span class="pre">Submit</span></code> to testrun.</p>
 <section id="installation-usage">
 <h2>Installation/Usage:<a class="headerlink" href="#installation-usage" title="Permalink to this headline"></a></h2>
-<p>As the package has not been published on PyPi yet, it CANNOT be install using pip.</p>
+<p>As the package has not been published on PyPi yet, it CANNOT be installed using pip.</p>
 <p>For now, the suggested method is to download the zipped package or use the online version at  <a class="reference external" href="https://huggingface.co/spaces/mikeee/radiobee-aligner/">https://huggingface.co/spaces/mikeee/radiobee-aligner/</a></p>
 </section>
 </section>

docs/build/html/searchindex.js

@@ -1 +1 @@
-Search.setIndex({docnames:["examples","index","intro","modules","radiobee","userguide","userguide-zh"],envversion:{"sphinx.domains.c":2,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":4,"sphinx.domains.index":1,"sphinx.domains.javascript":2,"sphinx.domains.math":2,"sphinx.domains.python":3,"sphinx.domains.rst":2,"sphinx.domains.std":2,sphinx:56},filenames:["examples.rst","index.rst","intro.rst","modules.rst","radiobee.rst","userguide.rst","userguide-zh.rst"],objects:{},objnames:{},objtypes:{},terms:{"12":[5,6],"3":2,"316287378":[5,6],"4":[5,6],"8":[5,6],"\u4e00\u822c\u65e0\u9700\u7406\u4f1a\u8fd9\u4e9b\u53c2\u6570":6,"\u4e86\u89e3\u8fd9\u4e9b\u5bf9\u9f50\u5de5\u5177":6,"\u4ee5\u540e\u53ef\u80fd\u4f1a\u652f\u6301":6,"\u4f18\u8d28\u5bf9":6,"\u4f7f\u7528\u8bf4\u660e":1,"\u53e6\u4e00\u65b9\u9762":6,"\u53ef\u4ee5\u4ee5\u540e\u4f1a\u652f\u6301":[],"\u53ef\u4ee5\u53f3\u51fb\u62f7\u51fa\u56fe\u7684\u94fe\u63a5\u7528\u6d4f\u89c8\u5668\u72ec\u7acb\u8bbf\u95ee\u62f7\u51fa\u6765\u7684\u94fe\u63a5\u6216\u53f3\u51fb\u5b58\u76d8\u518d\u7528\u770b\u56fe\u7a0b\u5e8f\u6253\u5f00\u5b58\u76d8\u7684\u56fe\u6587\u4ef6":6,"\u548c":6,"\u5acc\u56fe\u592a\u5c0f\u7684\u8bdd":6,"\u5b58\u4e0b\u6709\u5173\u53c2\u6570\u67e5\u770b\u6216\u901a\u77e5\u5f00\u53d1\u8005":6,"\u662f":6,"\u6700\u5c0f":6,"\u7684\u5b6a\u751f\u5144\u5f1f":6,"\u7684\u5efa\u8bae\u503c":6,"\u76ee\u524d\u4ec5\u652f\u6301\u4e2d\u82f1":6,"\u76ee\u524d\u4ec5\u652f\u6301\u7eaf\u6587\u672c\u6587\u4ef6\u4e0a\u8f7d":6,"\u7b2c\u4e8c\u6b21\u4e0a\u8f7d\u6587\u4ef6\u524d\u8bf7\u70b9\u51fb":6,"\u7b49":6,"\u7b49\u683c\u5f0f":6,"\u82f1\u4e2d\u5bf9\u9f50":6,"\u8bbe\u5927\u4e9b\u5219\u4f1a\u5f97\u5230\u5c11\u4e00\u4e9b\u5bf9\u9f50\u5bf9\u56e0\u4e3a\u53ef\u80fd\u9519\u5931\u4e86\u4e00\u4e9b":6,"\u8bbe\u5927\u4e9b\u5219\u53ef\u80fd\u4f1a\u9519\u5931\u4e00\u4e9b":[],"\u8bbe\u5927\u4e9b\u6216":6,"\u8bbe\u5c0f\u4e9b\u53ef\u4ee5\u5f97\u5230\u66f4\u591a\u7684\u5bf9\u9f50\u5bf9\u4f46\u4e5f\u4f1a":[],"\u8bbe\u5c0f\u4e9b\u53ef\u4ee5\u5f97\u5230\u66f4\u591a\u7684\u5bf9\u9f50\u5bf9\u4f46\u4e5f\u4f1a\u6709\u66f4\u591a":6,"\u8bbe\u5c0f\u4e9b\u6216":6,"\u8bef\u62a5\u5bf9":6,"\u8bf7\u52a0\u5165qq\u7fa4":6,"\u8fd0\u884c\u51fa\u9519\u65f6\u53ef\u4ee5\u70b9\u51fb":6,"\u9519\u8bef\u5224\u65ad\u4e3a\u5bf9\u9f50\u7684\u5bf9":6,"\u9519\u8bef\u5bf9":[],"do":5,"new":5,As:0,For:0,If:[2,5],On:5,The:2,To:5,about:5,ad:2,address:5,aim:2,align:[0,2,5,6],align_s:[1,3],align_text:[1,3],also:5,although:2,amend_avec:[1,3],an:2,app:[1,3],applic:2,ar:[2,5],been:[0,2],better:5,browser:5,built:0,bumblebe:[5,6],can:5,candid:5,cannot:0,cat:2,clear:[5,6],click:[0,5],cmat2tset:[1,3],co:0,contact:2,content:3,copi:5,csv:[5,6],current:2,de:2,develop:[2,5],dl_type:[5,6],docterm_scor:[1,3],docx:[5,6],download:0,dual:2,dualtext:2,e:2,ebook:2,educ:2,en2zh:[1,3],en2zh_token:[1,3],en:2,epsilon:[5,6],esp:[5,6],etc:[2,5],exampl:[1,2],fals:5,file2text:[1,3],file:5,files2df:[1,3],find:2,first:5,flag:[5,6],format:5,full:2,further:2,g:2,gen_aset:[1,3],gen_eps_minsampl:[1,3],gen_model:[1,3],gen_pset:[1,3],gen_row_align:[1,3],go:5,good:5,gradio:2,group:5,ha:[0,2],hand:5,have:5,help:2,here:2,how:1,html:[5,6],http:0,huggingfac:0,identifi:5,idf_typ:[5,6],imag:5,implement:2,index:1,inform:5,insert_spac:[1,3],instal:1,interfac:2,interpolate_pset:[1,3],introduct:1,ja:2,join:5,just:0,know:5,languag:2,larger:5,later:5,learn:2,limit:1,lists2cmat:[1,3],loadtext:[1,3],look:5,machin:2,mai:5,md:[5,6],mdx_e2c:[1,3],method:0,mikee:0,min_sampl:[5,6],minimum:5,miss:5,modul:[1,3],more:5,motiv:1,need:5,norm:[5,6],normal:5,now:0,one:0,onli:2,onlin:0,open:5,other:5,output:5,packag:[0,1,3],page:1,pair:[2,5],paragraph:2,particular:2,pdf:[5,6],permit:2,pip:0,pleas:5,plot_cmat:[1,3],plot_df:[1,3],posit:5,power:2,process_upload:[1,3],properli:2,provid:2,publish:0,pure:5,pypi:0,python:2,qq:5,radiobe:[0,2,5,6],result:5,right:5,row:0,ru:2,save:5,search:1,seg_text:[1,3],select:5,sentenc:2,should:5,shuffle_s:[1,3],sibl:5,smaller:5,smatrix:[1,3],someth:5,space:0,srt:[5,6],submit:[0,5],submodul:[1,3],subsequ:5,suggest:[0,5],support:[2,5],tab:5,tabl:0,tend:5,term:2,testrun:0,text:[2,5],tf_type:[5,6],time:2,tmx:2,touch:5,translat:2,trim_df:[1,3],two:2,txt:[5,6],unless:5,upload:5,us:[0,1],usag:1,valu:5,version:0,wa:2,welcom:2,what:5,when:[2,5],willing:2,wrong:5,yet:0,you:[2,5],zh:2,zip:0},titles:["Examples","Welcome to radiobee\u2019s documentation!","Introduction","radiobee","radiobee package","How to use","\u4f7f\u7528\u8bf4\u660e"],titleterms:{"\u4f7f\u7528\u8bf4\u660e":6,align_s:4,align_text:4,amend_avec:4,app:4,cmat2tset:4,content:[1,4],docterm_scor:4,document:1,en2zh:4,en2zh_token:4,exampl:0,file2text:4,files2df:4,gen_aset:4,gen_eps_minsampl:4,gen_model:4,gen_pset:4,gen_row_align:4,how:5,indic:1,insert_spac:4,instal:0,interpolate_pset:4,introduct:2,limit:2,lists2cmat:4,loadtext:4,mdx_e2c:4,modul:4,motiv:2,packag:4,plot_cmat:4,plot_df:4,process_upload:4,radiobe:[1,3,4],s:1,seg_text:4,shuffle_s:4,smatrix:4,submodul:4,tabl:1,trim_df:4,us:5,usag:0,welcom:1}})
+Search.setIndex({docnames:["examples","index","intro","modules","radiobee","userguide","userguide-zh"],envversion:{"sphinx.domains.c":2,"sphinx.domains.changeset":1,"sphinx.domains.citation":1,"sphinx.domains.cpp":4,"sphinx.domains.index":1,"sphinx.domains.javascript":2,"sphinx.domains.math":2,"sphinx.domains.python":3,"sphinx.domains.rst":2,"sphinx.domains.std":2,sphinx:56},filenames:["examples.rst","index.rst","intro.rst","modules.rst","radiobee.rst","userguide.rst","userguide-zh.rst"],objects:{},objnames:{},objtypes:{},terms:{"1":[5,6],"12":[5,6],"2":[5,6],"3":2,"316287378":[5,6],"4":[5,6],"8":[5,6],"\u4e00\u822c\u65e0\u9700\u7406\u4f1a\u8fd9\u4e9b\u53c2\u6570":6,"\u4e3a\u4e2d\u82f1\u6587\u6df7\u5408\u6587\u672c\u53ca\u8bd5\u7740\u5206\u79bb\u4e2d\u82f1\u6587":6,"\u4e3a\u7a7a\u767d\u65f6":6,"\u4e86\u89e3\u8fd9\u4e9b\u5bf9\u9f50\u5de5\u5177":6,"\u4ee5\u540e\u53ef\u80fd\u4f1a\u652f\u6301":6,"\u4f18\u8d28\u5bf9":6,"\u4f7f\u7528\u8bf4\u660e":1,"\u5219\u4f1a\u89c6":6,"\u53e6\u4e00\u65b9\u9762":6,"\u53ef\u4ee5\u4ee5\u540e\u4f1a\u652f\u6301":[],"\u53ef\u4ee5\u53f3\u51fb\u62f7\u51fa\u56fe\u7684\u94fe\u63a5\u7528\u6d4f\u89c8\u5668\u72ec\u7acb\u8bbf\u95ee\u62f7\u51fa\u6765\u7684\u94fe\u63a5\u6216\u53f3\u51fb\u5b58\u76d8\u518d\u7528\u770b\u56fe\u7a0b\u5e8f\u6253\u5f00\u5b58\u76d8\u7684\u56fe\u6587\u4ef6":6,"\u548c":6,"\u5acc\u56fe\u592a\u5c0f\u7684\u8bdd":6,"\u5b58\u4e0b\u6709\u5173\u53c2\u6570\u67e5\u770b\u6216\u901a\u77e5\u5f00\u53d1\u8005":6,"\u662f":6,"\u6700\u5c0f":6,"\u7136\u540e\u8fdb\u884c\u5bf9\u9f50":6,"\u7684\u5b6a\u751f\u5144\u5f1f":6,"\u7684\u5efa\u8bae\u503c":6,"\u76ee\u524d\u4ec5\u652f\u6301\u4e2d\u82f1":6,"\u76ee\u524d\u4ec5\u652f\u6301\u7eaf\u6587\u672c\u6587\u4ef6\u4e0a\u8f7d":6,"\u7b2c\u4e8c\u6b21\u4e0a\u8f7d\u6587\u4ef6\u524d\u8bf7\u70b9\u51fb":6,"\u7b49":6,"\u7b49\u683c\u5f0f":6,"\u82f1\u4e2d\u5bf9\u9f50":6,"\u8bbe\u5927\u4e9b\u5219\u4f1a\u5f97\u5230\u5c11\u4e00\u4e9b\u5bf9\u9f50\u5bf9\u56e0\u4e3a\u53ef\u80fd\u9519\u5931\u4e86\u4e00\u4e9b":6,"\u8bbe\u5927\u4e9b\u5219\u53ef\u80fd\u4f1a\u9519\u5931\u4e00\u4e9b":[],"\u8bbe\u5927\u4e9b\u6216":6,"\u8bbe\u5c0f\u4e9b\u53ef\u4ee5\u5f97\u5230\u66f4\u591a\u7684\u5bf9\u9f50\u5bf9\u4f46\u4e5f\u4f1a":[],"\u8bbe\u5c0f\u4e9b\u53ef\u4ee5\u5f97\u5230\u66f4\u591a\u7684\u5bf9\u9f50\u5bf9\u4f46\u4e5f\u4f1a\u6709\u66f4\u591a":6,"\u8bbe\u5c0f\u4e9b\u6216":6,"\u8bef\u62a5\u5bf9":6,"\u8bf7\u52a0\u5165qq\u7fa4":6,"\u8fd0\u884c\u51fa\u9519\u65f6\u53ef\u4ee5\u70b9\u51fb":6,"\u9519\u8bef\u5224\u65ad\u4e3a\u5bf9\u9f50\u7684\u5bf9":6,"\u9519\u8bef\u5bf9":[],"do":5,"new":5,As:0,For:0,If:[2,5],On:5,The:2,To:5,about:5,ad:2,address:5,aim:2,align:[0,2,5,6],align_s:[1,3],align_text:[1,3],also:5,although:2,amend_avec:[1,3],an:2,app:[1,3],applic:2,ar:[2,5],attempt:5,been:[0,2],befor:5,better:5,blank:5,browser:5,built:0,bumblebe:[5,6],can:5,candid:5,cannot:0,cat:2,chines:5,clear:[5,6],click:[0,5],cmat2tset:[1,3],co:0,contact:2,content:3,copi:5,csv:[5,6],current:2,de:2,develop:[2,5],dl_type:[5,6],docterm_scor:[1,3],docx:[5,6],download:0,dual:2,dualtext:2,e:2,ebook:2,educ:2,en2zh:[1,3],en2zh_token:[1,3],en:2,english:5,epsilon:[5,6],esp:[5,6],etc:[2,5],exampl:[1,2],fals:5,file2text:[1,3],file:[5,6],files2df:[1,3],find:2,first:5,flag:[5,6],format:5,full:2,further:2,g:2,gen_aset:[1,3],gen_eps_minsampl:[1,3],gen_model:[1,3],gen_pset:[1,3],gen_row_align:[1,3],go:5,good:5,gradio:2,group:5,ha:[0,2],hand:5,have:5,help:2,here:2,how:1,html:[5,6],http:0,huggingfac:0,identifi:5,idf_typ:[5,6],imag:5,implement:2,index:1,inform:5,insert_spac:[1,3],instal:1,interfac:2,interpolate_pset:[1,3],introduct:1,ja:2,join:5,just:0,know:5,languag:2,larger:5,later:5,learn:2,left:5,limit:1,lists2cmat:[1,3],loadtext:[1,3],look:5,machin:2,mai:5,md:[5,6],mdx_e2c:[1,3],method:0,mikee:0,min_sampl:[5,6],minimum:5,miss:5,mix:5,modul:[1,3],more:5,motiv:1,need:5,norm:[5,6],normal:5,now:0,one:0,onli:2,onlin:0,open:5,other:5,output:5,packag:[0,1,3],page:1,pair:[2,5],paragraph:2,particular:2,pdf:[5,6],permit:2,pip:0,pleas:5,plot_cmat:[1,3],plot_df:[1,3],posit:5,power:2,proced:5,process_upload:[1,3],properli:2,provid:2,publish:0,pure:5,pypi:0,python:2,qq:5,radiobe:[0,2,5,6],result:5,right:5,row:0,ru:2,save:5,search:1,seg_text:[1,3],select:5,sentenc:2,separ:5,should:5,shuffle_s:[1,3],sibl:5,smaller:5,smatrix:[1,3],someth:5,space:0,srt:[5,6],submit:[0,5],submodul:[1,3],subsequ:5,suggest:[0,5],support:[2,5],tab:5,tabl:0,tend:5,term:2,testrun:0,text:[2,5],tf_type:[5,6],them:5,time:2,tmx:2,touch:5,translat:2,treat:5,trim_df:[1,3],two:2,txt:[5,6],unless:5,upload:5,us:[0,1],usag:1,valu:5,version:0,wa:2,welcom:2,what:5,when:[2,5],willing:2,wrong:5,yet:0,you:[2,5],zh:2,zip:0},titles:["Examples","Welcome to radiobee\u2019s documentation!","Introduction","radiobee","radiobee package","How to use","\u4f7f\u7528\u8bf4\u660e"],titleterms:{"\u4f7f\u7528\u8bf4\u660e":6,align_s:4,align_text:4,amend_avec:4,app:4,cmat2tset:4,content:[1,4],docterm_scor:4,document:1,en2zh:4,en2zh_token:4,exampl:0,file2text:4,files2df:4,gen_aset:4,gen_eps_minsampl:4,gen_model:4,gen_pset:4,gen_row_align:4,how:5,indic:1,insert_spac:4,instal:0,interpolate_pset:4,introduct:2,limit:2,lists2cmat:4,loadtext:4,mdx_e2c:4,modul:4,motiv:2,packag:4,plot_cmat:4,plot_df:4,process_upload:4,radiobe:[1,3,4],s:1,seg_text:4,shuffle_s:4,smatrix:4,submodul:4,tabl:1,trim_df:4,us:5,usag:0,welcom:1}})

docs/build/html/userguide-zh.html

@@ -76,6 +76,7 @@
 <li><p><code class="docutils literal notranslate"><span class="pre">radiobee</span> <span class="pre">aligner</span></code> 是 <code class="docutils literal notranslate"><span class="pre">bumblebee</span> <span class="pre">aligner</span></code> 的孪生兄弟。请加入qq群 <code class="docutils literal notranslate"><span class="pre">316287378</span></code> 了解这些对齐工具。</p></li>
 <li><p><code class="docutils literal notranslate"><span class="pre">radiobee</span></code> 目前仅支持中英、英中对齐。</p></li>
 <li><p><code class="docutils literal notranslate"><span class="pre">radiobee</span></code> 目前仅支持纯文本文件上载 (txt, md, csv 等)。 以后可能会支持 <code class="docutils literal notranslate"><span class="pre">docx</span></code>, <code class="docutils literal notranslate"><span class="pre">pdf</span></code>, <code class="docutils literal notranslate"><span class="pre">srt</span></code>, <code class="docutils literal notranslate"><span class="pre">html</span></code> 等格式。</p></li>
+<li><p><code class="docutils literal notranslate"><span class="pre">file</span> <span class="pre">2</span></code> 为空白时，<code class="docutils literal notranslate"><span class="pre">radiobee</span></code> 则会视 <code class="docutils literal notranslate"><span class="pre">file</span> <span class="pre">1</span></code> 为中英文混合文本及试着分离中英文，然后进行对齐。</p></li>
 <li><p>第二次上载文件前请点击”Clear”。</p></li>
 <li><p><code class="docutils literal notranslate"><span class="pre">tf_type</span></code> <code class="docutils literal notranslate"><span class="pre">idf_type</span></code> <code class="docutils literal notranslate"><span class="pre">dl_type</span></code> <code class="docutils literal notranslate"><span class="pre">norm</span></code>: 一般无需理会这些参数。</p></li>
 <li><p><code class="docutils literal notranslate"><span class="pre">esp</span></code> 和 <code class="docutils literal notranslate"><span class="pre">min_samples</span></code> 的建议值 – <code class="docutils literal notranslate"><span class="pre">esp</span></code> (最小 <code class="docutils literal notranslate"><span class="pre">epsilon</span></code>): 8-12, <code class="docutils literal notranslate"><span class="pre">min_samples</span></code>: 4-8.</p>

docs/build/html/userguide.html

@@ -75,6 +75,7 @@
 <ul class="simple">
 <li><p><code class="docutils literal notranslate"><span class="pre">radiobee</span> <span class="pre">aligner</span></code> is a sibling of <cite>bumblebee aligner</cite>. To know more about these aligners, please join qq group <cite>316287378</cite>.</p></li>
 <li><p>Uploaded files should be in pure text format (txt, md, csv etc). <code class="docutils literal notranslate"><span class="pre">docx</span></code>, <code class="docutils literal notranslate"><span class="pre">pdf</span></code>, <code class="docutils literal notranslate"><span class="pre">srt</span></code>, <code class="docutils literal notranslate"><span class="pre">html</span></code> etc may be supported later on.</p></li>
+<li><p>If <code class="docutils literal notranslate"><span class="pre">file</span> <span class="pre">2</span></code> is left blank, <code class="docutils literal notranslate"><span class="pre">radiobee</span></code> will treat <code class="docutils literal notranslate"><span class="pre">file</span> <span class="pre">1</span></code> as mixed English-Chinese text and attempt to separate English and Chinese texts before procedding to align them.</p></li>
 <li><p>Click “Clear” first for subsequent submits when uploading files.</p></li>
 <li><p><code class="docutils literal notranslate"><span class="pre">tf_type</span></code> <code class="docutils literal notranslate"><span class="pre">idf_type</span></code> <code class="docutils literal notranslate"><span class="pre">dl_type</span></code> <code class="docutils literal notranslate"><span class="pre">norm</span></code>: Normally there is no need to touch these unless you know what you are doing.</p></li>
 <li><p>Suggested <code class="docutils literal notranslate"><span class="pre">esp</span></code> and <code class="docutils literal notranslate"><span class="pre">min_samples</span></code> values – <code class="docutils literal notranslate"><span class="pre">esp</span></code> (minimum epsilon): 8-12, <code class="docutils literal notranslate"><span class="pre">min_samples</span></code>: 4-8.</p></li>

docs/source/examples.rst

@@ -5,6 +5,6 @@ Examples
 
 Installation/Usage:
 *******************
-As the package has not been published on PyPi yet, it CANNOT be install using pip.
+As the package has not been published on PyPi yet, it CANNOT be installed using pip.
 
 For now, the suggested method is to download the zipped package or use the online version at  `https://huggingface.co/spaces/mikeee/radiobee-aligner/  <https://huggingface.co/spaces/mikeee/radiobee-aligner/>`_

docs/source/userguide.rst

@@ -4,7 +4,7 @@ How to use
 -   ``radiobee aligner`` is a sibling of `bumblebee aligner`. To know more about these aligners, please join qq group `316287378`.
 
 -   Uploaded files should be in pure text format (txt, md, csv etc). ``docx``, ``pdf``, ``srt``, ``html`` etc may be supported later on.
-- If ``file 2`` is left blank, ``radibee`` will treat ``file 1`` as mixed English-Chinese text and attempt to separate English and Chinese texts before procedding to align them.
+- If ``file 2`` is left blank, ``radiobee`` will treat ``file 1`` as mixed English-Chinese text and attempt to separate English and Chinese texts before procedding to align them.
 
 -   Click "Clear" first for subsequent submits when uploading files.
 -  ``tf_type`` ``idf_type`` ``dl_type`` ``norm``: Normally there is no need to touch these unless you know what you are doing.

radiobee/__main__.py

@@ -280,6 +280,7 @@ if __name__ == "__main__":
         out_file_dl,
         out_file_dl_excel,
         out_df_aligned,
+        gr.outputs.HTML(),
     ]
     # outputs = ["dataframe", "plot", "plot"]  # wont work
     # outputs = ["dataframe"]

radiobee/gradiobee.py

@@ -28,6 +28,7 @@ from radiobee.text2lists import text2lists
 
 sns.set()
 sns.set_style("darkgrid")
+pd.options.display.float_format = "{:,.2f}".format
 
 debug = False
 debug = True
@@ -313,6 +314,33 @@ def gradiobee(
     df_aligned = df_aligned[["text2", "text1", "likelihood"]]
     df_aligned.columns = ["text1", "text2", "likelihood"]
 
+    # round the last column to 2
+    # df_aligned.likelihood = df_aligned.likelihood.round(2)
+    # df_aligned = df_aligned.round({"likelihood": 2})
+
+    # df_aligned.likelihood = df_aligned.likelihood.apply(lambda x: np.nan if x in [""] else x)
+
+    # style
+    styled = df_aligned.style.set_properties(
+        **{
+            "font-size": "10pt",
+            "border-color": "black",
+            "border": "1px black solid !important"
+        }
+        # border-color="black",
+    ).set_table_styles([{
+        "selector": "",  # noqs
+        "props": [("border", "2px black solid !important")]}]  # noqs
+    ).format(
+        precision=2
+    )
+    # .bar(subset="likelihood", color="#5fba7d")
+
+    # .background_gradient("Greys")
+
+    # df_html = df_aligned.to_html()
+    df_html = styled.to_html()
+
     # ===
     if plot_dia:
         output_plot = "img/plt.png"
@@ -330,6 +358,8 @@ def gradiobee(
     # return df_trimmed, plt, file_dl, file_dl_xlsx, df_aligned
 
     # output_plot: gr.outputs.Image(type="auto", label="...")
-    return df_trimmed, output_plot, file_dl, file_dl_xlsx, df_aligned
+    # return df_trimmed, output_plot, file_dl, file_dl_xlsx, df_aligned
+    # return df_trimmed, output_plot, file_dl, file_dl_xlsx, styled, df_html  # gradio cant handle style
+    return df_trimmed, output_plot, file_dl, file_dl_xlsx, df_aligned, df_html
 
     # modi outputs