Update documentation

UBC-CS · Nov 21, 2023 · f8db46d · f8db46d
1 parent bfccee9
commit f8db46d
Show file tree

Hide file tree

Showing 16 changed files with 26 additions and 47 deletions.
diff --git a/_images/19ee31296c28079dca87cbe98c175a34a9f3e3d23a43a986682afa9532a526b0.png b/_images/19ee31296c28079dca87cbe98c175a34a9f3e3d23a43a986682afa9532a526b0.png
diff --git a/_images/3617f59b6e67d54b0cfca10b157bf91440151a4f6d29be50dfc92e7d035ec88f.png b/_images/3617f59b6e67d54b0cfca10b157bf91440151a4f6d29be50dfc92e7d035ec88f.png
diff --git a/_images/48a5080bcd9cf4d13f1f354843c4d6d714c8339431fd608db9bb9626fc527b5b.png b/_images/48a5080bcd9cf4d13f1f354843c4d6d714c8339431fd608db9bb9626fc527b5b.png
diff --git a/_images/5150da95375430c2933d48e4fc388a55452908c508d4d2b6a556e8852f1b5b13.png b/_images/5150da95375430c2933d48e4fc388a55452908c508d4d2b6a556e8852f1b5b13.png
diff --git a/_images/64b0ca2f106c8f9db16acb3b0a4f3156b73e714bd7b584f7469f6c49cbefd5c6.png b/_images/64b0ca2f106c8f9db16acb3b0a4f3156b73e714bd7b584f7469f6c49cbefd5c6.png
diff --git a/_images/777cd77d4242c43cd2dd8b3c07aaeffce92915b2ff811e4548fc78cd6fd24136.png b/_images/777cd77d4242c43cd2dd8b3c07aaeffce92915b2ff811e4548fc78cd6fd24136.png
diff --git a/_images/9458098b2a8420566292cb093c606fe565322193a14c311edaf7abcda0ecd4b6.png b/_images/9458098b2a8420566292cb093c606fe565322193a14c311edaf7abcda0ecd4b6.png
diff --git a/_images/9619f321b7a88739bccaebf32e8e572304b9c607a05c8404d0e89f71e4a9e7ab.png b/_images/9619f321b7a88739bccaebf32e8e572304b9c607a05c8404d0e89f71e4a9e7ab.png
diff --git a/_images/b0a7e1d5a49f4ed2ed8a16cce855565a4b2be320bccefe01777eea067c3e4203.png b/_images/b0a7e1d5a49f4ed2ed8a16cce855565a4b2be320bccefe01777eea067c3e4203.png
diff --git a/_images/ba18b18b02c464f14da9f2d87f368ccb74c4c44097fa00d79994060a21cf0b86.png b/_images/ba18b18b02c464f14da9f2d87f368ccb74c4c44097fa00d79994060a21cf0b86.png
diff --git a/_sources/lectures/19_time-series.ipynb b/_sources/lectures/19_time-series.ipynb
@@ -4938,19 +4938,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "- Ok, that is fine, but what if we want to predict 5 months in the future? \n",
-    "- Well, we would not have access to our features!! We don't yet know the previous months sales, or two months prior! "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "- There are a few approaches which could be employed:\n",
-    "\n",
-    "1. Train a separate model for each number of months. E.g. one model that predicts sales for next month, another model that predicts sales in two months, etc. We can build these datasets.\n",
-    "2. Use a multi-output model that jointly predicts RainTomorrow, RainIn2Days, etc. However, multi-output models are outside the scope of CPSC 330. \n",
-    "3. Use one model and sequentially predict using a `for` loop. However, this requires predicting _all_ features into a model so may not be that useful here."
+    "- Now what if we want to predict 5 months in the future? \n",
+    "- We would not have access to our features!! We don't yet know the previous months sales, or two months prior! "
    ]
   },
   {
@@ -4961,7 +4950,7 @@
     }
    },
    "source": [
-    "If we decide to use approach 3, we would predict these values and then pretend they are true! For example, given that it's November 2022\n",
+    "If we decide to use approach 3 from above, we would predict these values and then pretend they are true! For example, given that it's November 2022\n",
     "\n",
     "1. Predict December 2022 sales\n",
     "2. Then, to predict for January 2023, we need to know December 2022 sales. Use our _prediction_ for December 2022 as the truth.\n",

diff --git a/lectures/17_natural-language-processing.html b/lectures/17_natural-language-processing.html
@@ -500,7 +500,7 @@ <h2>Imports<a class="headerlink" href="#imports" title="Permalink to this headin
 Intel MKL WARNING: Support of Intel(R) Streaming SIMD Extensions 4.2 (Intel(R) SSE4.2) enabled only processors has been deprecated. Intel oneAPI Math Kernel Library 2025.0 will require Intel(R) Advanced Vector Extensions (Intel(R) AVX) instructions.
 </pre></div>
 </div>
-<img alt="../_images/61c7334b48e238985956ba66ede1c3745130fde2f241bf07ad14b3f318a2d24f.png" src="../_images/61c7334b48e238985956ba66ede1c3745130fde2f241bf07ad14b3f318a2d24f.png" />
+<img alt="../_images/777cd77d4242c43cd2dd8b3c07aaeffce92915b2ff811e4548fc78cd6fd24136.png" src="../_images/777cd77d4242c43cd2dd8b3c07aaeffce92915b2ff811e4548fc78cd6fd24136.png" />
 </div>
 </div>
 <div class="cell docutils container">

diff --git a/lectures/19_time-series.html b/lectures/19_time-series.html
@@ -1807,9 +1807,7 @@ <h3>Encoding time of day as a categorical feature<a class="headerlink" href="#en
 </div>
 <div class="cell_output docutils container">
 <div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Intel MKL WARNING: Support of Intel(R) Streaming SIMD Extensions 4.2 (Intel(R) SSE4.2) enabled only processors has been deprecated. Intel oneAPI Math Kernel Library 2025.0 will require Intel(R) Advanced Vector Extensions (Intel(R) AVX) instructions.
-</pre></div>
-</div>
-<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Train-set R^2: 0.87
+Train-set R^2: 0.87
 Test-set R^2: 0.85
 </pre></div>
 </div>
@@ -2326,11 +2324,11 @@ <h2>Lag-based features<a class="headerlink" href="#lag-based-features" title="Pe
 </div>
 </div>
 <div class="cell_output docutils container">
-<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Train-set R^2: 0.94
+<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Train-set R^2: 0.95
 Test-set R^2: 0.69
 </pre></div>
 </div>
-<img alt="../_images/e417bc322c2d5f45c26fef85d8149e47dea18d0086601724795dd4371655590f.png" src="../_images/e417bc322c2d5f45c26fef85d8149e47dea18d0086601724795dd4371655590f.png" />
+<img alt="../_images/5150da95375430c2933d48e4fc388a55452908c508d4d2b6a556e8852f1b5b13.png" src="../_images/5150da95375430c2933d48e4fc388a55452908c508d4d2b6a556e8852f1b5b13.png" />
 </div>
 </div>
 <p>The results are better than <code class="docutils literal notranslate"><span class="pre">Ridge</span></code> with lag features but they are not as good as the results with our previously engineered features. How about combining lag-based features and the previously extracted features?</p>
@@ -2349,11 +2347,11 @@ <h2>Lag-based features<a class="headerlink" href="#lag-based-features" title="Pe
 </div>
 </div>
 <div class="cell_output docutils container">
-<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Train-set R^2: 0.95
-Test-set R^2: 0.77
+<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Train-set R^2: 0.96
+Test-set R^2: 0.79
 </pre></div>
 </div>
-<img alt="../_images/5adcf6f71245dc2af25579426397569bfabc368c6ff2b11bbb55fd3dd9b00575.png" src="../_images/5adcf6f71245dc2af25579426397569bfabc368c6ff2b11bbb55fd3dd9b00575.png" />
+<img alt="../_images/b0a7e1d5a49f4ed2ed8a16cce855565a4b2be320bccefe01777eea067c3e4203.png" src="../_images/b0a7e1d5a49f4ed2ed8a16cce855565a4b2be320bccefe01777eea067c3e4203.png" />
 </div>
 </div>
 <p>Some improvement but we are getting better results without the lag features in this case.</p>
@@ -2453,36 +2451,36 @@ <h3>Cross-validation<a class="headerlink" href="#cross-validation" title="Permal
   <tbody>
     <tr>
       <th>0</th>
-      <td>0.001298</td>
-      <td>0.000331</td>
+      <td>0.001065</td>
+      <td>0.000278</td>
       <td>0.642676</td>
       <td>0.873182</td>
     </tr>
     <tr>
       <th>1</th>
-      <td>0.000765</td>
-      <td>0.000313</td>
+      <td>0.000933</td>
+      <td>0.000739</td>
       <td>0.828405</td>
       <td>0.874305</td>
     </tr>
     <tr>
       <th>2</th>
-      <td>0.000902</td>
-      <td>0.000316</td>
+      <td>0.000750</td>
+      <td>0.000254</td>
       <td>0.773851</td>
       <td>0.901262</td>
     </tr>
     <tr>
       <th>3</th>
-      <td>0.001197</td>
-      <td>0.000282</td>
+      <td>0.000604</td>
+      <td>0.000221</td>
       <td>0.696712</td>
       <td>0.889429</td>
     </tr>
     <tr>
       <th>4</th>
-      <td>0.001477</td>
-      <td>0.000735</td>
+      <td>0.001104</td>
+      <td>0.000630</td>
       <td>0.892733</td>
       <td>0.863889</td>
     </tr>
@@ -3854,18 +3852,10 @@ <h3>Forecasting further into the future on a retail dataset<a class="headerlink"
 </div></div></div>
 </div>
 <ul class="simple">
-<li><p>Ok, that is fine, but what if we want to predict 5 months in the future?</p></li>
-<li><p>Well, we would not have access to our features!! We don’t yet know the previous months sales, or two months prior!</p></li>
-</ul>
-<ul class="simple">
-<li><p>There are a few approaches which could be employed:</p></li>
+<li><p>Now what if we want to predict 5 months in the future?</p></li>
+<li><p>We would not have access to our features!! We don’t yet know the previous months sales, or two months prior!</p></li>
 </ul>
-<ol class="arabic simple">
-<li><p>Train a separate model for each number of months. E.g. one model that predicts sales for next month, another model that predicts sales in two months, etc. We can build these datasets.</p></li>
-<li><p>Use a multi-output model that jointly predicts RainTomorrow, RainIn2Days, etc. However, multi-output models are outside the scope of CPSC 330.</p></li>
-<li><p>Use one model and sequentially predict using a <code class="docutils literal notranslate"><span class="pre">for</span></code> loop. However, this requires predicting <em>all</em> features into a model so may not be that useful here.</p></li>
-</ol>
-<p>If we decide to use approach 3, we would predict these values and then pretend they are true! For example, given that it’s November 2022</p>
+<p>If we decide to use approach 3 from above, we would predict these values and then pretend they are true! For example, given that it’s November 2022</p>
 <ol class="arabic simple">
 <li><p>Predict December 2022 sales</p></li>
 <li><p>Then, to predict for January 2023, we need to know December 2022 sales. Use our <em>prediction</em> for December 2022 as the truth.</p></li>

diff --git a/lectures/class_demos/14_class-demo.html b/lectures/class_demos/14_class-demo.html
@@ -387,7 +387,7 @@ <h2>Let’s cluster images!!<a class="headerlink" href="#let-s-cluster-images" t
 Intel MKL WARNING: Support of Intel(R) Streaming SIMD Extensions 4.2 (Intel(R) SSE4.2) enabled only processors has been deprecated. Intel oneAPI Math Kernel Library 2025.0 will require Intel(R) Advanced Vector Extensions (Intel(R) AVX) instructions.
 </pre></div>
 </div>
-<img alt="../../_images/5b39903db0485a9b21537a0d7b86bb2f9c84024f110548905eb790e2738a6846.png" src="../../_images/5b39903db0485a9b21537a0d7b86bb2f9c84024f110548905eb790e2738a6846.png" />
+<img alt="../../_images/48a5080bcd9cf4d13f1f354843c4d6d714c8339431fd608db9bb9626fc527b5b.png" src="../../_images/48a5080bcd9cf4d13f1f354843c4d6d714c8339431fd608db9bb9626fc527b5b.png" />
 </div>
 </div>
 <div class="cell docutils container">

diff --git a/lectures/class_demos/15_class-demo.html b/lectures/class_demos/15_class-demo.html
@@ -380,7 +380,7 @@ <h1>Lecture 15: Class demo<a class="headerlink" href="#lecture-15-class-demo" ti
 Intel MKL WARNING: Support of Intel(R) Streaming SIMD Extensions 4.2 (Intel(R) SSE4.2) enabled only processors has been deprecated. Intel oneAPI Math Kernel Library 2025.0 will require Intel(R) Advanced Vector Extensions (Intel(R) AVX) instructions.
 </pre></div>
 </div>
-<img alt="../../_images/772fe5fc68484659778e0c3c1e983081dd53124d48f9db48e5ee38933a13389b.png" src="../../_images/772fe5fc68484659778e0c3c1e983081dd53124d48f9db48e5ee38933a13389b.png" />
+<img alt="../../_images/ba18b18b02c464f14da9f2d87f368ccb74c4c44097fa00d79994060a21cf0b86.png" src="../../_images/ba18b18b02c464f14da9f2d87f368ccb74c4c44097fa00d79994060a21cf0b86.png" />
 </div>
 </div>
 <div class="cell docutils container">

diff --git a/searchindex.js b/searchindex.js