diff options
Diffstat (limited to 'site/examples.html')
| -rw-r--r-- | site/examples.html | 60 |
1 files changed, 30 insertions, 30 deletions
diff --git a/site/examples.html b/site/examples.html index 5431f5dda..1be96be50 100644 --- a/site/examples.html +++ b/site/examples.html @@ -213,11 +213,11 @@ In this page, we will show examples using RDD API as well as examples using high <div class="tab-pane tab-pane-python active"> <div class="code code-tab"> -<div class="highlight"><pre><code class="language-python" data-lang="python"><span class="n">text_file</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="p">(</span><span class="s">"hdfs://..."</span><span class="p">)</span> +<figure class="highlight"><pre><code class="language-python" data-lang="python"><span class="n">text_file</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="p">(</span><span class="s">"hdfs://..."</span><span class="p">)</span> <span class="n">counts</span> <span class="o">=</span> <span class="n">text_file</span><span class="o">.</span><span class="n">flatMap</span><span class="p">(</span><span class="k">lambda</span> <span class="n">line</span><span class="p">:</span> <span class="n">line</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s">" "</span><span class="p">))</span> \ <span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">word</span><span class="p">:</span> <span class="p">(</span><span class="n">word</span><span class="p">,</span> <span class="mi">1</span><span class="p">))</span> \ <span class="o">.</span><span class="n">reduceByKey</span><span class="p">(</span><span class="k">lambda</span> <span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">:</span> <span class="n">a</span> <span class="o">+</span> <span class="n">b</span><span class="p">)</span> -<span class="n">counts</span><span class="o">.</span><span class="n">saveAsTextFile</span><span class="p">(</span><span class="s">"hdfs://..."</span><span class="p">)</span></code></pre></div> +<span class="n">counts</span><span class="o">.</span><span class="n">saveAsTextFile</span><span class="p">(</span><span class="s">"hdfs://..."</span><span class="p">)</span></code></pre></figure> </div> </div> @@ -225,11 +225,11 @@ In this page, we will show examples using RDD API as well as examples using high <div class="tab-pane tab-pane-scala"> <div class="code code-tab"> -<div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">val</span> <span class="n">textFile</span> <span class="k">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="o">(</span><span class="s">"hdfs://..."</span><span class="o">)</span> +<figure class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">val</span> <span class="n">textFile</span> <span class="k">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="o">(</span><span class="s">"hdfs://..."</span><span class="o">)</span> <span class="k">val</span> <span class="n">counts</span> <span class="k">=</span> <span class="n">textFile</span><span class="o">.</span><span class="n">flatMap</span><span class="o">(</span><span class="n">line</span> <span class="k">=></span> <span class="n">line</span><span class="o">.</span><span class="n">split</span><span class="o">(</span><span class="s">" "</span><span class="o">))</span> <span class="o">.</span><span class="n">map</span><span class="o">(</span><span class="n">word</span> <span class="k">=></span> <span class="o">(</span><span class="n">word</span><span class="o">,</span> <span class="mi">1</span><span class="o">))</span> <span class="o">.</span><span class="n">reduceByKey</span><span class="o">(</span><span class="k">_</span> <span class="o">+</span> <span class="k">_</span><span class="o">)</span> -<span class="n">counts</span><span class="o">.</span><span class="n">saveAsTextFile</span><span class="o">(</span><span class="s">"hdfs://..."</span><span class="o">)</span></code></pre></div> +<span class="n">counts</span><span class="o">.</span><span class="n">saveAsTextFile</span><span class="o">(</span><span class="s">"hdfs://..."</span><span class="o">)</span></code></pre></figure> </div> </div> @@ -237,7 +237,7 @@ In this page, we will show examples using RDD API as well as examples using high <div class="tab-pane tab-pane-java"> <div class="code code-tab"> -<div class="highlight"><pre><code class="language-java" data-lang="java"><span class="n">JavaRDD</span><span class="o"><</span><span class="n">String</span><span class="o">></span> <span class="n">textFile</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="na">textFile</span><span class="o">(</span><span class="s">"hdfs://..."</span><span class="o">);</span> +<figure class="highlight"><pre><code class="language-java" data-lang="java"><span class="n">JavaRDD</span><span class="o"><</span><span class="n">String</span><span class="o">></span> <span class="n">textFile</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="na">textFile</span><span class="o">(</span><span class="s">"hdfs://..."</span><span class="o">);</span> <span class="n">JavaRDD</span><span class="o"><</span><span class="n">String</span><span class="o">></span> <span class="n">words</span> <span class="o">=</span> <span class="n">textFile</span><span class="o">.</span><span class="na">flatMap</span><span class="o">(</span><span class="k">new</span> <span class="n">FlatMapFunction</span><span class="o"><</span><span class="n">String</span><span class="o">,</span> <span class="n">String</span><span class="o">>()</span> <span class="o">{</span> <span class="kd">public</span> <span class="n">Iterable</span><span class="o"><</span><span class="n">String</span><span class="o">></span> <span class="nf">call</span><span class="o">(</span><span class="n">String</span> <span class="n">s</span><span class="o">)</span> <span class="o">{</span> <span class="k">return</span> <span class="n">Arrays</span><span class="o">.</span><span class="na">asList</span><span class="o">(</span><span class="n">s</span><span class="o">.</span><span class="na">split</span><span class="o">(</span><span class="s">" "</span><span class="o">));</span> <span class="o">}</span> <span class="o">});</span> @@ -247,7 +247,7 @@ In this page, we will show examples using RDD API as well as examples using high <span class="n">JavaPairRDD</span><span class="o"><</span><span class="n">String</span><span class="o">,</span> <span class="n">Integer</span><span class="o">></span> <span class="n">counts</span> <span class="o">=</span> <span class="n">pairs</span><span class="o">.</span><span class="na">reduceByKey</span><span class="o">(</span><span class="k">new</span> <span class="n">Function2</span><span class="o"><</span><span class="n">Integer</span><span class="o">,</span> <span class="n">Integer</span><span class="o">,</span> <span class="n">Integer</span><span class="o">>()</span> <span class="o">{</span> <span class="kd">public</span> <span class="n">Integer</span> <span class="nf">call</span><span class="o">(</span><span class="n">Integer</span> <span class="n">a</span><span class="o">,</span> <span class="n">Integer</span> <span class="n">b</span><span class="o">)</span> <span class="o">{</span> <span class="k">return</span> <span class="n">a</span> <span class="o">+</span> <span class="n">b</span><span class="o">;</span> <span class="o">}</span> <span class="o">});</span> -<span class="n">counts</span><span class="o">.</span><span class="na">saveAsTextFile</span><span class="o">(</span><span class="s">"hdfs://..."</span><span class="o">);</span></code></pre></div> +<span class="n">counts</span><span class="o">.</span><span class="na">saveAsTextFile</span><span class="o">(</span><span class="s">"hdfs://..."</span><span class="o">);</span></code></pre></figure> </div> </div> @@ -266,13 +266,13 @@ In this page, we will show examples using RDD API as well as examples using high <div class="tab-pane tab-pane-python active"> <div class="code code-tab"> -<div class="highlight"><pre><code class="language-python" data-lang="python"><span class="k">def</span> <span class="nf">sample</span><span class="p">(</span><span class="n">p</span><span class="p">):</span> +<figure class="highlight"><pre><code class="language-python" data-lang="python"><span class="k">def</span> <span class="nf">sample</span><span class="p">(</span><span class="n">p</span><span class="p">):</span> <span class="n">x</span><span class="p">,</span> <span class="n">y</span> <span class="o">=</span> <span class="n">random</span><span class="p">(),</span> <span class="n">random</span><span class="p">()</span> <span class="k">return</span> <span class="mi">1</span> <span class="k">if</span> <span class="n">x</span><span class="o">*</span><span class="n">x</span> <span class="o">+</span> <span class="n">y</span><span class="o">*</span><span class="n">y</span> <span class="o"><</span> <span class="mi">1</span> <span class="k">else</span> <span class="mi">0</span> <span class="n">count</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="p">(</span><span class="nb">xrange</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">NUM_SAMPLES</span><span class="p">))</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="n">sample</span><span class="p">)</span> \ <span class="o">.</span><span class="n">reduce</span><span class="p">(</span><span class="k">lambda</span> <span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">:</span> <span class="n">a</span> <span class="o">+</span> <span class="n">b</span><span class="p">)</span> -<span class="k">print</span> <span class="s">"Pi is roughly </span><span class="si">%f</span><span class="s">"</span> <span class="o">%</span> <span class="p">(</span><span class="mf">4.0</span> <span class="o">*</span> <span class="n">count</span> <span class="o">/</span> <span class="n">NUM_SAMPLES</span><span class="p">)</span></code></pre></div> +<span class="k">print</span> <span class="s">"Pi is roughly </span><span class="si">%f</span><span class="s">"</span> <span class="o">%</span> <span class="p">(</span><span class="mf">4.0</span> <span class="o">*</span> <span class="n">count</span> <span class="o">/</span> <span class="n">NUM_SAMPLES</span><span class="p">)</span></code></pre></figure> </div> </div> @@ -280,12 +280,12 @@ In this page, we will show examples using RDD API as well as examples using high <div class="tab-pane tab-pane-scala"> <div class="code code-tab"> -<div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">val</span> <span class="n">count</span> <span class="k">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="o">(</span><span class="mi">1</span> <span class="n">to</span> <span class="nc">NUM_SAMPLES</span><span class="o">).</span><span class="n">map</span><span class="o">{</span><span class="n">i</span> <span class="k">=></span> +<figure class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">val</span> <span class="n">count</span> <span class="k">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">parallelize</span><span class="o">(</span><span class="mi">1</span> <span class="n">to</span> <span class="nc">NUM_SAMPLES</span><span class="o">).</span><span class="n">map</span><span class="o">{</span><span class="n">i</span> <span class="k">=></span> <span class="k">val</span> <span class="n">x</span> <span class="k">=</span> <span class="nc">Math</span><span class="o">.</span><span class="n">random</span><span class="o">()</span> <span class="k">val</span> <span class="n">y</span> <span class="k">=</span> <span class="nc">Math</span><span class="o">.</span><span class="n">random</span><span class="o">()</span> <span class="k">if</span> <span class="o">(</span><span class="n">x</span><span class="o">*</span><span class="n">x</span> <span class="o">+</span> <span class="n">y</span><span class="o">*</span><span class="n">y</span> <span class="o"><</span> <span class="mi">1</span><span class="o">)</span> <span class="mi">1</span> <span class="k">else</span> <span class="mi">0</span> <span class="o">}.</span><span class="n">reduce</span><span class="o">(</span><span class="k">_</span> <span class="o">+</span> <span class="k">_</span><span class="o">)</span> -<span class="n">println</span><span class="o">(</span><span class="s">"Pi is roughly "</span> <span class="o">+</span> <span class="mf">4.0</span> <span class="o">*</span> <span class="n">count</span> <span class="o">/</span> <span class="nc">NUM_SAMPLES</span><span class="o">)</span></code></pre></div> +<span class="n">println</span><span class="o">(</span><span class="s">"Pi is roughly "</span> <span class="o">+</span> <span class="mf">4.0</span> <span class="o">*</span> <span class="n">count</span> <span class="o">/</span> <span class="nc">NUM_SAMPLES</span><span class="o">)</span></code></pre></figure> </div> </div> @@ -293,7 +293,7 @@ In this page, we will show examples using RDD API as well as examples using high <div class="tab-pane tab-pane-java"> <div class="code code-tab"> -<div class="highlight"><pre><code class="language-java" data-lang="java"><span class="n">List</span><span class="o"><</span><span class="n">Integer</span><span class="o">></span> <span class="n">l</span> <span class="o">=</span> <span class="k">new</span> <span class="n">ArrayList</span><span class="o"><</span><span class="n">Integer</span><span class="o">>(</span><span class="n">NUM_SAMPLES</span><span class="o">);</span> +<figure class="highlight"><pre><code class="language-java" data-lang="java"><span class="n">List</span><span class="o"><</span><span class="n">Integer</span><span class="o">></span> <span class="n">l</span> <span class="o">=</span> <span class="k">new</span> <span class="n">ArrayList</span><span class="o"><</span><span class="n">Integer</span><span class="o">>(</span><span class="n">NUM_SAMPLES</span><span class="o">);</span> <span class="k">for</span> <span class="o">(</span><span class="kt">int</span> <span class="n">i</span> <span class="o">=</span> <span class="mi">0</span><span class="o">;</span> <span class="n">i</span> <span class="o"><</span> <span class="n">NUM_SAMPLES</span><span class="o">;</span> <span class="n">i</span><span class="o">++)</span> <span class="o">{</span> <span class="n">l</span><span class="o">.</span><span class="na">add</span><span class="o">(</span><span class="n">i</span><span class="o">);</span> <span class="o">}</span> @@ -305,7 +305,7 @@ In this page, we will show examples using RDD API as well as examples using high <span class="k">return</span> <span class="n">x</span><span class="o">*</span><span class="n">x</span> <span class="o">+</span> <span class="n">y</span><span class="o">*</span><span class="n">y</span> <span class="o"><</span> <span class="mi">1</span><span class="o">;</span> <span class="o">}</span> <span class="o">}).</span><span class="na">count</span><span class="o">();</span> -<span class="n">System</span><span class="o">.</span><span class="na">out</span><span class="o">.</span><span class="na">println</span><span class="o">(</span><span class="s">"Pi is roughly "</span> <span class="o">+</span> <span class="mf">4.0</span> <span class="o">*</span> <span class="n">count</span> <span class="o">/</span> <span class="n">NUM_SAMPLES</span><span class="o">);</span></code></pre></div> +<span class="n">System</span><span class="o">.</span><span class="na">out</span><span class="o">.</span><span class="na">println</span><span class="o">(</span><span class="s">"Pi is roughly "</span> <span class="o">+</span> <span class="mf">4.0</span> <span class="o">*</span> <span class="n">count</span> <span class="o">/</span> <span class="n">NUM_SAMPLES</span><span class="o">);</span></code></pre></figure> </div> </div> @@ -333,7 +333,7 @@ Also, programs based on DataFrame API will be automatically optimized by Sparkā <div class="tab-pane tab-pane-python active"> <div class="code code-tab"> -<div class="highlight"><pre><code class="language-python" data-lang="python"><span class="n">textFile</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="p">(</span><span class="s">"hdfs://..."</span><span class="p">)</span> +<figure class="highlight"><pre><code class="language-python" data-lang="python"><span class="n">textFile</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="p">(</span><span class="s">"hdfs://..."</span><span class="p">)</span> <span class="c"># Creates a DataFrame having a single column named "line"</span> <span class="n">df</span> <span class="o">=</span> <span class="n">textFile</span><span class="o">.</span><span class="n">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">r</span><span class="p">:</span> <span class="n">Row</span><span class="p">(</span><span class="n">r</span><span class="p">))</span><span class="o">.</span><span class="n">toDF</span><span class="p">([</span><span class="s">"line"</span><span class="p">])</span> @@ -343,7 +343,7 @@ Also, programs based on DataFrame API will be automatically optimized by Sparkā <span class="c"># Counts errors mentioning MySQL</span> <span class="n">errors</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s">"line"</span><span class="p">)</span><span class="o">.</span><span class="n">like</span><span class="p">(</span><span class="s">"%MySQL%"</span><span class="p">))</span><span class="o">.</span><span class="n">count</span><span class="p">()</span> <span class="c"># Fetches the MySQL errors as an array of strings</span> -<span class="n">errors</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s">"line"</span><span class="p">)</span><span class="o">.</span><span class="n">like</span><span class="p">(</span><span class="s">"%MySQL%"</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span></code></pre></div> +<span class="n">errors</span><span class="o">.</span><span class="n">filter</span><span class="p">(</span><span class="n">col</span><span class="p">(</span><span class="s">"line"</span><span class="p">)</span><span class="o">.</span><span class="n">like</span><span class="p">(</span><span class="s">"%MySQL%"</span><span class="p">))</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span></code></pre></figure> </div> </div> @@ -351,7 +351,7 @@ Also, programs based on DataFrame API will be automatically optimized by Sparkā <div class="tab-pane tab-pane-scala"> <div class="code code-tab"> -<div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">val</span> <span class="n">textFile</span> <span class="k">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="o">(</span><span class="s">"hdfs://..."</span><span class="o">)</span> +<figure class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="k">val</span> <span class="n">textFile</span> <span class="k">=</span> <span class="n">sc</span><span class="o">.</span><span class="n">textFile</span><span class="o">(</span><span class="s">"hdfs://..."</span><span class="o">)</span> <span class="c1">// Creates a DataFrame having a single column named "line"</span> <span class="k">val</span> <span class="n">df</span> <span class="k">=</span> <span class="n">textFile</span><span class="o">.</span><span class="n">toDF</span><span class="o">(</span><span class="s">"line"</span><span class="o">)</span> @@ -361,7 +361,7 @@ Also, programs based on DataFrame API will be automatically optimized by Sparkā <span class="c1">// Counts errors mentioning MySQL</span> <span class="n">errors</span><span class="o">.</span><span class="n">filter</span><span class="o">(</span><span class="n">col</span><span class="o">(</span><span class="s">"line"</span><span class="o">).</span><span class="n">like</span><span class="o">(</span><span class="s">"%MySQL%"</span><span class="o">)).</span><span class="n">count</span><span class="o">()</span> <span class="c1">// Fetches the MySQL errors as an array of strings</span> -<span class="n">errors</span><span class="o">.</span><span class="n">filter</span><span class="o">(</span><span class="n">col</span><span class="o">(</span><span class="s">"line"</span><span class="o">).</span><span class="n">like</span><span class="o">(</span><span class="s">"%MySQL%"</span><span class="o">)).</span><span class="n">collect</span><span class="o">()</span></code></pre></div> +<span class="n">errors</span><span class="o">.</span><span class="n">filter</span><span class="o">(</span><span class="n">col</span><span class="o">(</span><span class="s">"line"</span><span class="o">).</span><span class="n">like</span><span class="o">(</span><span class="s">"%MySQL%"</span><span class="o">)).</span><span class="n">collect</span><span class="o">()</span></code></pre></figure> </div> </div> @@ -369,7 +369,7 @@ Also, programs based on DataFrame API will be automatically optimized by Sparkā <div class="tab-pane tab-pane-java"> <div class="code code-tab"> -<div class="highlight"><pre><code class="language-java" data-lang="java"><span class="c1">// Creates a DataFrame having a single column named "line"</span> +<figure class="highlight"><pre><code class="language-java" data-lang="java"><span class="c1">// Creates a DataFrame having a single column named "line"</span> <span class="n">JavaRDD</span><span class="o"><</span><span class="n">String</span><span class="o">></span> <span class="n">textFile</span> <span class="o">=</span> <span class="n">sc</span><span class="o">.</span><span class="na">textFile</span><span class="o">(</span><span class="s">"hdfs://..."</span><span class="o">);</span> <span class="n">JavaRDD</span><span class="o"><</span><span class="n">Row</span><span class="o">></span> <span class="n">rowRDD</span> <span class="o">=</span> <span class="n">textFile</span><span class="o">.</span><span class="na">map</span><span class="o">(</span> <span class="k">new</span> <span class="n">Function</span><span class="o"><</span><span class="n">String</span><span class="o">,</span> <span class="n">Row</span><span class="o">>()</span> <span class="o">{</span> @@ -388,7 +388,7 @@ Also, programs based on DataFrame API will be automatically optimized by Sparkā <span class="c1">// Counts errors mentioning MySQL</span> <span class="n">errors</span><span class="o">.</span><span class="na">filter</span><span class="o">(</span><span class="n">col</span><span class="o">(</span><span class="s">"line"</span><span class="o">).</span><span class="na">like</span><span class="o">(</span><span class="s">"%MySQL%"</span><span class="o">)).</span><span class="na">count</span><span class="o">();</span> <span class="c1">// Fetches the MySQL errors as an array of strings</span> -<span class="n">errors</span><span class="o">.</span><span class="na">filter</span><span class="o">(</span><span class="n">col</span><span class="o">(</span><span class="s">"line"</span><span class="o">).</span><span class="na">like</span><span class="o">(</span><span class="s">"%MySQL%"</span><span class="o">)).</span><span class="na">collect</span><span class="o">();</span></code></pre></div> +<span class="n">errors</span><span class="o">.</span><span class="na">filter</span><span class="o">(</span><span class="n">col</span><span class="o">(</span><span class="s">"line"</span><span class="o">).</span><span class="na">like</span><span class="o">(</span><span class="s">"%MySQL%"</span><span class="o">)).</span><span class="na">collect</span><span class="o">();</span></code></pre></figure> </div> </div> @@ -412,7 +412,7 @@ A simple MySQL table "people" is used in the example and this table has two colu <div class="tab-pane tab-pane-python active"> <div class="code code-tab"> -<div class="highlight"><pre><code class="language-python" data-lang="python"><span class="c"># Creates a DataFrame based on a table named "people"</span> +<figure class="highlight"><pre><code class="language-python" data-lang="python"><span class="c"># Creates a DataFrame based on a table named "people"</span> <span class="c"># stored in a MySQL database.</span> <span class="n">url</span> <span class="o">=</span> \ <span class="s">"jdbc:mysql://yourIP:yourPort/test?user=yourUsername;password=yourPassword"</span> @@ -431,7 +431,7 @@ A simple MySQL table "people" is used in the example and this table has two colu <span class="n">countsByAge</span><span class="o">.</span><span class="n">show</span><span class="p">()</span> <span class="c"># Saves countsByAge to S3 in the JSON format.</span> -<span class="n">countsByAge</span><span class="o">.</span><span class="n">write</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="s">"json"</span><span class="p">)</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="s">"s3a://..."</span><span class="p">)</span></code></pre></div> +<span class="n">countsByAge</span><span class="o">.</span><span class="n">write</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="s">"json"</span><span class="p">)</span><span class="o">.</span><span class="n">save</span><span class="p">(</span><span class="s">"s3a://..."</span><span class="p">)</span></code></pre></figure> </div> </div> @@ -439,7 +439,7 @@ A simple MySQL table "people" is used in the example and this table has two colu <div class="tab-pane tab-pane-scala"> <div class="code code-tab"> -<div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="c1">// Creates a DataFrame based on a table named "people"</span> +<figure class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="c1">// Creates a DataFrame based on a table named "people"</span> <span class="c1">// stored in a MySQL database.</span> <span class="k">val</span> <span class="n">url</span> <span class="k">=</span> <span class="s">"jdbc:mysql://yourIP:yourPort/test?user=yourUsername;password=yourPassword"</span> @@ -458,7 +458,7 @@ A simple MySQL table "people" is used in the example and this table has two colu <span class="n">countsByAge</span><span class="o">.</span><span class="n">show</span><span class="o">()</span> <span class="c1">// Saves countsByAge to S3 in the JSON format.</span> -<span class="n">countsByAge</span><span class="o">.</span><span class="n">write</span><span class="o">.</span><span class="n">format</span><span class="o">(</span><span class="s">"json"</span><span class="o">).</span><span class="n">save</span><span class="o">(</span><span class="s">"s3a://..."</span><span class="o">)</span></code></pre></div> +<span class="n">countsByAge</span><span class="o">.</span><span class="n">write</span><span class="o">.</span><span class="n">format</span><span class="o">(</span><span class="s">"json"</span><span class="o">).</span><span class="n">save</span><span class="o">(</span><span class="s">"s3a://..."</span><span class="o">)</span></code></pre></figure> </div> </div> @@ -466,7 +466,7 @@ A simple MySQL table "people" is used in the example and this table has two colu <div class="tab-pane tab-pane-java"> <div class="code code-tab"> -<div class="highlight"><pre><code class="language-java" data-lang="java"><span class="c1">// Creates a DataFrame based on a table named "people"</span> +<figure class="highlight"><pre><code class="language-java" data-lang="java"><span class="c1">// Creates a DataFrame based on a table named "people"</span> <span class="c1">// stored in a MySQL database.</span> <span class="n">String</span> <span class="n">url</span> <span class="o">=</span> <span class="s">"jdbc:mysql://yourIP:yourPort/test?user=yourUsername;password=yourPassword"</span><span class="o">;</span> @@ -485,7 +485,7 @@ A simple MySQL table "people" is used in the example and this table has two colu <span class="n">countsByAge</span><span class="o">.</span><span class="na">show</span><span class="o">();</span> <span class="c1">// Saves countsByAge to S3 in the JSON format.</span> -<span class="n">countsByAge</span><span class="o">.</span><span class="na">write</span><span class="o">().</span><span class="na">format</span><span class="o">(</span><span class="s">"json"</span><span class="o">).</span><span class="na">save</span><span class="o">(</span><span class="s">"s3a://..."</span><span class="o">);</span></code></pre></div> +<span class="n">countsByAge</span><span class="o">.</span><span class="na">write</span><span class="o">().</span><span class="na">format</span><span class="o">(</span><span class="s">"json"</span><span class="o">).</span><span class="na">save</span><span class="o">(</span><span class="s">"s3a://..."</span><span class="o">);</span></code></pre></figure> </div> </div> @@ -516,7 +516,7 @@ We learn to predict the labels from feature vectors using the Logistic Regressio <div class="tab-pane tab-pane-python active"> <div class="code code-tab"> -<div class="highlight"><pre><code class="language-python" data-lang="python"><span class="c"># Every record of this DataFrame contains the label and</span> +<figure class="highlight"><pre><code class="language-python" data-lang="python"><span class="c"># Every record of this DataFrame contains the label and</span> <span class="c"># features represented by a vector.</span> <span class="n">df</span> <span class="o">=</span> <span class="n">sqlContext</span><span class="o">.</span><span class="n">createDataFrame</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="p">[</span><span class="s">"label"</span><span class="p">,</span> <span class="s">"features"</span><span class="p">])</span> @@ -528,7 +528,7 @@ We learn to predict the labels from feature vectors using the Logistic Regressio <span class="n">model</span> <span class="o">=</span> <span class="n">lr</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">df</span><span class="p">)</span> <span class="c"># Given a dataset, predict each point's label, and show the results.</span> -<span class="n">model</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">)</span><span class="o">.</span><span class="n">show</span><span class="p">()</span></code></pre></div> +<span class="n">model</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">)</span><span class="o">.</span><span class="n">show</span><span class="p">()</span></code></pre></figure> </div> </div> @@ -536,7 +536,7 @@ We learn to predict the labels from feature vectors using the Logistic Regressio <div class="tab-pane tab-pane-scala"> <div class="code code-tab"> -<div class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="c1">// Every record of this DataFrame contains the label and</span> +<figure class="highlight"><pre><code class="language-scala" data-lang="scala"><span class="c1">// Every record of this DataFrame contains the label and</span> <span class="c1">// features represented by a vector.</span> <span class="k">val</span> <span class="n">df</span> <span class="k">=</span> <span class="n">sqlContext</span><span class="o">.</span><span class="n">createDataFrame</span><span class="o">(</span><span class="n">data</span><span class="o">).</span><span class="n">toDF</span><span class="o">(</span><span class="s">"label"</span><span class="o">,</span> <span class="s">"features"</span><span class="o">)</span> @@ -551,7 +551,7 @@ We learn to predict the labels from feature vectors using the Logistic Regressio <span class="k">val</span> <span class="n">weights</span> <span class="k">=</span> <span class="n">model</span><span class="o">.</span><span class="n">weights</span> <span class="c1">// Given a dataset, predict each point's label, and show the results.</span> -<span class="n">model</span><span class="o">.</span><span class="n">transform</span><span class="o">(</span><span class="n">df</span><span class="o">).</span><span class="n">show</span><span class="o">()</span></code></pre></div> +<span class="n">model</span><span class="o">.</span><span class="n">transform</span><span class="o">(</span><span class="n">df</span><span class="o">).</span><span class="n">show</span><span class="o">()</span></code></pre></figure> </div> </div> @@ -559,7 +559,7 @@ We learn to predict the labels from feature vectors using the Logistic Regressio <div class="tab-pane tab-pane-java"> <div class="code code-tab"> -<div class="highlight"><pre><code class="language-java" data-lang="java"><span class="c1">// Every record of this DataFrame contains the label and</span> +<figure class="highlight"><pre><code class="language-java" data-lang="java"><span class="c1">// Every record of this DataFrame contains the label and</span> <span class="c1">// features represented by a vector.</span> <span class="n">StructType</span> <span class="n">schema</span> <span class="o">=</span> <span class="k">new</span> <span class="nf">StructType</span><span class="o">(</span><span class="k">new</span> <span class="n">StructField</span><span class="o">[]{</span> <span class="k">new</span> <span class="nf">StructField</span><span class="o">(</span><span class="s">"label"</span><span class="o">,</span> <span class="n">DataTypes</span><span class="o">.</span><span class="na">DoubleType</span><span class="o">,</span> <span class="kc">false</span><span class="o">,</span> <span class="n">Metadata</span><span class="o">.</span><span class="na">empty</span><span class="o">()),</span> @@ -578,7 +578,7 @@ We learn to predict the labels from feature vectors using the Logistic Regressio <span class="n">Vector</span> <span class="n">weights</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="na">weights</span><span class="o">();</span> <span class="c1">// Given a dataset, predict each point's label, and show the results.</span> -<span class="n">model</span><span class="o">.</span><span class="na">transform</span><span class="o">(</span><span class="n">df</span><span class="o">).</span><span class="na">show</span><span class="o">();</span></code></pre></div> +<span class="n">model</span><span class="o">.</span><span class="na">transform</span><span class="o">(</span><span class="n">df</span><span class="o">).</span><span class="na">show</span><span class="o">();</span></code></pre></figure> </div> </div> |