Site updated: 2020-02-08 11:05:04

Author: xxg1413

Diff for: article/python-nlp-01/index.html

@@ -115,45 +115,11 @@ <h2 id="1-安装wordcloud"><a href="#1-安装wordcloud" class="headerlink" title
 <h2 id="2-准备红楼梦文本"><a href="#2-准备红楼梦文本" class="headerlink" title="2.准备红楼梦文本"></a>2.准备红楼梦文本</h2><p>文本可以用下面链接下载</p>
 <p><code>https://github.com/flypythoncom/flypython/blob/master/wordcloud_hlm_seg.txt</code></p>
 <p>或者可以自己写代码，对文本进行清洗，分词。<br>这里需要安装jieba分词，<code>pip install jieba</code></p>
-<pre><code>import jieba
-import re
+<figure class="highlight python"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br><span class="line">14</span><br><span class="line">15</span><br><span class="line">16</span><br><span class="line">17</span><br></pre></td><td class="code"><pre><span class="line"></span><br><span class="line"><span class="keyword">import</span> jieba</span><br><span class="line"><span class="keyword">import</span> re</span><br><span class="line"></span><br><span class="line">special_character_removal = re.compile(<span class="string">r'[，。、【 】“”：；（）《》‘’&#123;&#125;？！⑦%&gt;℃.^-——=&amp;#@￥『』]'</span>, re.IGNORECASE)</span><br><span class="line"></span><br><span class="line">fw=open(<span class="string">"hlm_seg.txt"</span>,<span class="string">"w"</span>,encoding=<span class="string">"utf-8"</span>)</span><br><span class="line"></span><br><span class="line"><span class="keyword">with</span> open(<span class="string">'hlm.txt'</span>,encoding=<span class="string">"utf-8"</span>) <span class="keyword">as</span> fp:</span><br><span class="line">    <span class="keyword">for</span> line <span class="keyword">in</span> fp:</span><br><span class="line">        l = special_character_removal.sub(<span class="string">''</span>, line.strip())</span><br><span class="line">        words=jieba.cut(l)</span><br><span class="line">        t=<span class="string">" "</span>.join(words)</span><br><span class="line">        fw.write(t)</span><br><span class="line">        fw.write(<span class="string">"\n"</span>)</span><br><span class="line"></span><br><span class="line">fw.close()</span><br></pre></td></tr></table></figure>
 
-special_character_removal = re.compile(r&apos;[，。、【 】“”：；（）《》‘’{}？！⑦%&gt;℃.^-——=&amp;#@￥『』]&apos;, re.IGNORECASE)
+<h2 id="3-编写词云python代码并运行"><a href="#3-编写词云python代码并运行" class="headerlink" title="3. 编写词云python代码并运行"></a>3. 编写词云python代码并运行</h2><figure class="highlight python"><table><tr><td class="gutter"><pre><span class="line">1</span><br><span class="line">2</span><br><span class="line">3</span><br><span class="line">4</span><br><span class="line">5</span><br><span class="line">6</span><br><span class="line">7</span><br><span class="line">8</span><br><span class="line">9</span><br><span class="line">10</span><br><span class="line">11</span><br><span class="line">12</span><br><span class="line">13</span><br><span class="line">14</span><br><span class="line">15</span><br><span class="line">16</span><br><span class="line">17</span><br><span class="line">18</span><br><span class="line">19</span><br><span class="line">20</span><br><span class="line">21</span><br><span class="line">22</span><br><span class="line">23</span><br><span class="line">24</span><br><span class="line">25</span><br><span class="line">26</span><br></pre></td><td class="code"><pre><span class="line"></span><br><span class="line"><span class="keyword">from</span> os <span class="keyword">import</span> path  </span><br><span class="line"><span class="keyword">from</span> wordcloud <span class="keyword">import</span> WordCloud</span><br><span class="line"></span><br><span class="line">d = path.dirname(__file__)  </span><br><span class="line"><span class="comment"># Read the whole text.  </span></span><br><span class="line">text = open(path.join(d, <span class="string">'hlm_seg.txt'</span>),encoding=<span class="string">"utf-8"</span>).read()  </span><br><span class="line"><span class="comment"># Generate a word cloud image  </span></span><br><span class="line"><span class="comment"># font=path.join(d, "simkai.ttf")  </span></span><br><span class="line">font=<span class="string">'C:/Windows/Fonts/simkai.ttf'</span>  </span><br><span class="line">wordcloud = WordCloud(font_path=font,<span class="comment">#设置中文字体，不指定就会出现中文不显示  </span></span><br><span class="line">  width=<span class="number">1024</span>,<span class="comment">#宽  </span></span><br><span class="line">  height=<span class="number">840</span>,<span class="comment">#高  </span></span><br><span class="line">  background_color=<span class="string">'white'</span>,<span class="comment">#设置背景色   </span></span><br><span class="line">  <span class="comment"># max_words=100,#最大词汇数  </span></span><br><span class="line">  <span class="comment"># max_font_size=100#最大号字体  </span></span><br><span class="line">  ).generate(text)  </span><br><span class="line">  </span><br><span class="line"><span class="comment"># Display the generated image:  </span></span><br><span class="line"><span class="comment"># the matplotlib way:  </span></span><br><span class="line"><span class="keyword">import</span> matplotlib.pyplot <span class="keyword">as</span> plt  </span><br><span class="line">  </span><br><span class="line">plt.figure()  </span><br><span class="line">plt.imshow(wordcloud)  </span><br><span class="line">plt.axis(<span class="string">"off"</span>)  </span><br><span class="line">plt.show()</span><br></pre></td></tr></table></figure>
 
-fw=open(&quot;hlm_seg.txt&quot;,&quot;w&quot;,encoding=&quot;utf-8&quot;)
-
-with open(&apos;hlm.txt&apos;,encoding=&quot;utf-8&quot;) as fp:
-    for line in fp:
-        l = special_character_removal.sub(&apos;&apos;, line.strip())
-        words=jieba.cut(l)
-        t=&quot; &quot;.join(words)
-        fw.write(t)
-        fw.write(&quot;\n&quot;)
-fw.close()</code></pre><h2 id="3-编写词云python代码并运行"><a href="#3-编写词云python代码并运行" class="headerlink" title="3. 编写词云python代码并运行"></a>3. 编写词云python代码并运行</h2><pre><code>from os import path  
-from wordcloud import WordCloud
-
-d = path.dirname(__file__)  
-# Read the whole text.  
-text = open(path.join(d, &apos;hlm_seg.txt&apos;),encoding=&quot;utf-8&quot;).read()  
-# Generate a word cloud image  
-# font=path.join(d, &quot;simkai.ttf&quot;)  
-font=&apos;C:/Windows/Fonts/simkai.ttf&apos;  
-wordcloud = WordCloud(font_path=font,#设置中文字体，不指定就会出现中文不显示  
-  width=1024,#宽  
-  height=840,#高  
-  background_color=&apos;white&apos;,#设置背景色   
-  # max_words=100,#最大词汇数  
-  # max_font_size=100#最大号字体  
-  ).generate(text)  
-
-# Display the generated image:  
-# the matplotlib way:  
-import matplotlib.pyplot as plt  
-
-plt.figure()  
-plt.imshow(wordcloud)  
-plt.axis(&quot;off&quot;)  
-plt.show()</code></pre><p>结果：</p>
+<p>结果：</p>
 <p><img src="http://jcjview.github.io/img/Figure_1.png" alt="词云运行结果"></p>
 <p>后台回复“词云”获得完整运行代码</p>
 <p><em>人生苦短，我用python早下班。如果觉得不错，对你工作中有帮助，请加我微信公众号flypython，我们一起探讨python相关问题</em></p>