Get Tests to 100%, Closes #220

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

@@ -91,10 +91,10 @@ Now we are ready to call the FeatureBuilder on our data. All we need to do is de
 		speaker_id_col = "speaker_nickname",
 		message_col = "message",
 		timestamp_col = "timestamp",
-		grouping_keys = ["batch_num", "round_num"],
+		grouping_keys = ["batch_num", "round_num"], # NOTE: This example demonstrates grouping. Use conversation_id_col if you have a single conversation identifier.
 		vector_directory = "./vector_data/",
 		output_file_base = "jury_output",
-		turns = True
+		turns = True # NOTE: This defaults to False. Decide whether you want to combine successive 'utterances' by the same person as a 'turn.'
 	)
 	jury_feature_builder.featurize()
 
@@ -219,6 +219,12 @@ Regenerating Vector Cache
 
 	* By default, **we assume that, if your output file is named the same, that the underlying vectors are the same**. If this isn't true, you should set **regenerate_vectors = True** in order to clear out the cache and re-generate the RoBERTa and SBERT outputs.
 
+
+Generating Vectors using GPU
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+By default, we use the CPU to generate sentence vectors and cached RoBERTa sentimets. To override this feature and use a GPU when available (which will speed up the computation of the vectors), turn ``use_gpu`` to True.
+
+
 Custom Features
 ~~~~~~~~~~~~~~~~~
 

docs/build/html/examples.html

@@ -158,10 +158,10 @@ <h3>Configuring the FeatureBuilder<a class="headerlink" href="#configuring-the-f
         <span class="n">speaker_id_col</span> <span class="o">=</span> <span class="s2">&quot;speaker_nickname&quot;</span><span class="p">,</span>
         <span class="n">message_col</span> <span class="o">=</span> <span class="s2">&quot;message&quot;</span><span class="p">,</span>
         <span class="n">timestamp_col</span> <span class="o">=</span> <span class="s2">&quot;timestamp&quot;</span><span class="p">,</span>
-        <span class="n">grouping_keys</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;batch_num&quot;</span><span class="p">,</span> <span class="s2">&quot;round_num&quot;</span><span class="p">],</span>
+        <span class="n">grouping_keys</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;batch_num&quot;</span><span class="p">,</span> <span class="s2">&quot;round_num&quot;</span><span class="p">],</span> <span class="c1"># NOTE: This example demonstrates grouping. Use conversation_id_col if you have a single conversation identifier.</span>
         <span class="n">vector_directory</span> <span class="o">=</span> <span class="s2">&quot;./vector_data/&quot;</span><span class="p">,</span>
         <span class="n">output_file_base</span> <span class="o">=</span> <span class="s2">&quot;jury_output&quot;</span><span class="p">,</span>
-        <span class="n">turns</span> <span class="o">=</span> <span class="kc">True</span>
+        <span class="n">turns</span> <span class="o">=</span> <span class="kc">True</span> <span class="c1"># NOTE: This defaults to False. Decide whether you want to combine successive &#39;utterances&#39; by the same person as a &#39;turn.&#39;</span>
 <span class="p">)</span>
 <span class="n">jury_feature_builder</span><span class="o">.</span><span class="n">featurize</span><span class="p">()</span>
 </pre></div>
@@ -302,6 +302,10 @@ <h5>Regenerating Vector Cache<a class="headerlink" href="#regenerating-vector-ca
 </li>
 </ul>
 </section>
+<section id="generating-vectors-using-gpu">
+<h5>Generating Vectors using GPU<a class="headerlink" href="#generating-vectors-using-gpu" title="Link to this heading"></a></h5>
+<p>By default, we use the CPU to generate sentence vectors and cached RoBERTa sentimets. To override this feature and use a GPU when available (which will speed up the computation of the vectors), turn <code class="docutils literal notranslate"><span class="pre">use_gpu</span></code> to True.</p>
+</section>
 <section id="custom-features">
 <h5>Custom Features<a class="headerlink" href="#custom-features" title="Link to this heading"></a></h5>
 <ul>

docs/build/html/features/temporal_features.html

@@ -60,7 +60,6 @@
 <li class="toctree-l3"><a class="reference internal" href="politeness_features.html">politeness_features module</a></li>
 <li class="toctree-l3"><a class="reference internal" href="hedge.html">hedge module</a></li>
 <li class="toctree-l3 current"><a class="current reference internal" href="#">temporal_features module</a><ul>
-<li class="toctree-l4"><a class="reference internal" href="#features.temporal_features.coerce_to_date_or_number"><code class="docutils literal notranslate"><span class="pre">coerce_to_date_or_number()</span></code></a></li>
 <li class="toctree-l4"><a class="reference internal" href="#features.temporal_features.get_time_diff"><code class="docutils literal notranslate"><span class="pre">get_time_diff()</span></code></a></li>
 <li class="toctree-l4"><a class="reference internal" href="#features.temporal_features.get_time_diff_startend"><code class="docutils literal notranslate"><span class="pre">get_time_diff_startend()</span></code></a></li>
 </ul>
@@ -111,21 +110,6 @@
 
   <section id="module-features.temporal_features">
 <span id="temporal-features-module"></span><h1>temporal_features module<a class="headerlink" href="#module-features.temporal_features" title="Link to this heading"></a></h1>
-<dl class="py function">
-<dt class="sig sig-object py" id="features.temporal_features.coerce_to_date_or_number">
-<span class="sig-prename descclassname"><span class="pre">features.temporal_features.</span></span><span class="sig-name descname"><span class="pre">coerce_to_date_or_number</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">value</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#features.temporal_features.coerce_to_date_or_number" title="Link to this definition"></a></dt>
-<dd><p>Helper function in which we check that the timestamp column contains either a datetime value or a number
-that can be interpreted as a time elapsed; otherwise, sets it equal to none.</p>
-<dl class="field-list simple">
-<dt class="field-odd">Parameters<span class="colon">:</span></dt>
-<dd class="field-odd"><p><strong>value</strong> – The value to check; type can be anything</p>
-</dd>
-<dt class="field-even">Returns<span class="colon">:</span></dt>
-<dd class="field-even"><p>Either the value itself (if it is a valid timestamp value) or None otherwise</p>
-</dd>
-</dl>
-</dd></dl>
-
 <dl class="py function">
 <dt class="sig sig-object py" id="features.temporal_features.get_time_diff">
 <span class="sig-prename descclassname"><span class="pre">features.temporal_features.</span></span><span class="sig-name descname"><span class="pre">get_time_diff</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">df</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">on_column</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">conversation_id_col</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">timestamp_unit</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#features.temporal_features.get_time_diff" title="Link to this definition"></a></dt>

docs/build/html/genindex.html

@@ -96,6 +96,7 @@ <h1 id="index">Index</h1>
  | <a href="#S"><strong>S</strong></a>
  | <a href="#T"><strong>T</strong></a>
  | <a href="#U"><strong>U</strong></a>
+ | <a href="#V"><strong>V</strong></a>
  | <a href="#W"><strong>W</strong></a>
 
 </div>
@@ -106,8 +107,6 @@ <h2 id="A">A</h2>
 </li>
   </ul></td>
   <td style="width: 33%; vertical-align: top;"><ul>
-      <li><a href="utils/preprocess.html#utils.preprocess.assert_key_columns_present">assert_key_columns_present() (in module utils.preprocess)</a>
-</li>
       <li><a href="utils/assign_chunk_nums.html#utils.assign_chunk_nums.assign_chunk_nums">assign_chunk_nums() (in module utils.assign_chunk_nums)</a>
 </li>
   </ul></td>
@@ -169,8 +168,6 @@ <h2 id="C">C</h2>
       <li><a href="features/readability.html#features.readability.classify_text_dalechall">classify_text_dalechall() (in module features.readability)</a>
 </li>
       <li><a href="features/politeness_v2_helper.html#features.politeness_v2_helper.clean_text">clean_text() (in module features.politeness_v2_helper)</a>
-</li>
-      <li><a href="features/temporal_features.html#features.temporal_features.coerce_to_date_or_number">coerce_to_date_or_number() (in module features.temporal_features)</a>
 </li>
       <li><a href="features/politeness_v2_helper.html#features.politeness_v2_helper.commit_data">commit_data() (in module features.politeness_v2_helper)</a>
 </li>
@@ -186,10 +183,10 @@ <h2 id="C">C</h2>
 </li>
       <li><a href="features/politeness_v2_helper.html#features.politeness_v2_helper.conjection_seperator">conjection_seperator() (in module features.politeness_v2_helper)</a>
 </li>
-  </ul></td>
-  <td style="width: 33%; vertical-align: top;"><ul>
       <li><a href="features/word_mimicry.html#features.word_mimicry.Content_mimicry_score">Content_mimicry_score() (in module features.word_mimicry)</a>
 </li>
+  </ul></td>
+  <td style="width: 33%; vertical-align: top;"><ul>
       <li><a href="features/word_mimicry.html#features.word_mimicry.Content_mimicry_score_per_conv">Content_mimicry_score_per_conv() (in module features.word_mimicry)</a>
 </li>
       <li><a href="feature_builder.html#feature_builder.FeatureBuilder.conv_level_features">conv_level_features() (feature_builder.FeatureBuilder method)</a>
@@ -932,6 +929,14 @@ <h2 id="U">U</h2>
   </ul></td>
 </tr></table>
 
+<h2 id="V">V</h2>
+<table style="width: 100%" class="indextable genindextable"><tr>
+  <td style="width: 33%; vertical-align: top;"><ul>
+      <li><a href="feature_builder.html#feature_builder.FeatureBuilder.verify_timestamp_format">verify_timestamp_format() (feature_builder.FeatureBuilder method)</a>
+</li>
+  </ul></td>
+</tr></table>
+
 <h2 id="W">W</h2>
 <table style="width: 100%" class="indextable genindextable"><tr>
   <td style="width: 33%; vertical-align: top;"><ul>

docs/build/html/utils/calculate_chat_level_features.html

@@ -348,8 +348,7 @@
 <dd><p>Calculate features relevant to the timestamps of each chat.</p>
 <p>This function calculates and appends the following temporal feature to the chat data:
 - Time difference between messages sent</p>
-<p>It checks whether the ‘timestamp’ column is available. If not, it tries to calculate
-using ‘timestamp_start’ and ‘timestamp_end’ columns.</p>
+<p>It assumes the ‘timestamp’ column is available, which is checked in feature_builder.py.</p>
 <dl class="field-list simple">
 <dt class="field-odd">Returns<span class="colon">:</span></dt>
 <dd class="field-odd"><p>None</p>