Merge pull request #55 from UBC-DSCI/tidymodels

Tidymodels

Author: trevorcampbell

05-classification.Rmd

@@ -27,6 +27,9 @@ RUN conda install -y pip && \
     pip install rpy2
 ENV LD_LIBRARY_PATH /usr/local/lib/R/lib/:${LD_LIBRARY_PATH}
 
+# install libGLPK
+RUN apt-get install libglpk-dev
+
 # install R packages
 RUN apt-get update -qq && install2.r --error \
     --deps TRUE \
@@ -39,4 +42,5 @@ RUN apt-get update -qq && install2.r --error \
     cowplot \
     svglite \
     tidymodels \
-    reticulate
+    reticulate \ 
+    kknn

06-classification_continued.Rmd

@@ -26,7 +26,7 @@
 <meta name="author" content="Melissa Lee" />
 
 
-<meta name="date" content="2020-07-08" />
+<meta name="date" content="2020-09-03" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1" />
   <meta name="apple-mobile-web-app-capable" content="yes" />
@@ -142,7 +142,7 @@
 <li><a href="./">Introduction to Data Science</a></li>
 
 <li class="divider"></li>
-<li class="chapter" data-level="1" data-path="index.html"><a href="index.html"><i class="fa fa-check"></i><b>1</b> Introduction to Data Science</a><ul>
+<li class="chapter" data-level="1" data-path="index.html"><a href="index.html"><i class="fa fa-check"></i><b>1</b> R, Jupyter, and the tidyverse</a><ul>
 <li class="chapter" data-level="1.1" data-path="index.html"><a href="index.html#chapter-learning-objectives"><i class="fa fa-check"></i><b>1.1</b> Chapter learning objectives</a></li>
 <li class="chapter" data-level="1.2" data-path="index.html"><a href="index.html#jupyter-notebooks"><i class="fa fa-check"></i><b>1.2</b> Jupyter notebooks</a></li>
 <li class="chapter" data-level="1.3" data-path="index.html"><a href="index.html#loading-a-spreadsheet-like-dataset"><i class="fa fa-check"></i><b>1.3</b> Loading a spreadsheet-like dataset</a></li>
@@ -159,7 +159,6 @@
 <li class="chapter" data-level="1.6.3" data-path="index.html"><a href="index.html#formatting-ggplot-objects"><i class="fa fa-check"></i><b>1.6.3</b> Formatting ggplot objects</a></li>
 <li class="chapter" data-level="1.6.4" data-path="index.html"><a href="index.html#coloring-points-by-group"><i class="fa fa-check"></i><b>1.6.4</b> Coloring points by group</a></li>
 <li class="chapter" data-level="1.6.5" data-path="index.html"><a href="index.html#putting-it-all-together"><i class="fa fa-check"></i><b>1.6.5</b> Putting it all together</a></li>
-<li class="chapter" data-level="1.6.6" data-path="index.html"><a href="index.html#whats-next"><i class="fa fa-check"></i><b>1.6.6</b> What’s next?</a></li>
 </ul></li>
 </ul></li>
 <li class="chapter" data-level="2" data-path="reading.html"><a href="reading.html"><i class="fa fa-check"></i><b>2</b> Reading in data locally and from the web</a><ul>
@@ -249,19 +248,20 @@
 <li class="chapter" data-level="5.4.3" data-path="GitHub.html"><a href="GitHub.html#move-to-a-different-directory"><i class="fa fa-check"></i><b>5.4.3</b> Move to a different directory</a></li>
 </ul></li>
 </ul></li>
-<li class="chapter" data-level="6" data-path="classification.html"><a href="classification.html"><i class="fa fa-check"></i><b>6</b> Classification I: Training &amp; predicting</a><ul>
+<li class="chapter" data-level="6" data-path="classification.html"><a href="classification.html"><i class="fa fa-check"></i><b>6</b> Classification I: training &amp; predicting</a><ul>
 <li class="chapter" data-level="6.1" data-path="classification.html"><a href="classification.html#overview-4"><i class="fa fa-check"></i><b>6.1</b> Overview</a></li>
 <li class="chapter" data-level="6.2" data-path="classification.html"><a href="classification.html#chapter-learning-objectives-4"><i class="fa fa-check"></i><b>6.2</b> Chapter learning objectives</a></li>
 <li class="chapter" data-level="6.3" data-path="classification.html"><a href="classification.html#the-classification-problem"><i class="fa fa-check"></i><b>6.3</b> The classification problem</a></li>
 <li class="chapter" data-level="6.4" data-path="classification.html"><a href="classification.html#exploring-a-labelled-data-set"><i class="fa fa-check"></i><b>6.4</b> Exploring a labelled data set</a></li>
 <li class="chapter" data-level="6.5" data-path="classification.html"><a href="classification.html#classification-with-k-nearest-neighbours"><i class="fa fa-check"></i><b>6.5</b> Classification with K-nearest neighbours</a></li>
-<li class="chapter" data-level="6.6" data-path="classification.html"><a href="classification.html#k-nearest-neighbours-in-r"><i class="fa fa-check"></i><b>6.6</b> K-nearest neighbours in R</a></li>
-<li class="chapter" data-level="6.7" data-path="classification.html"><a href="classification.html#data-preprocessing"><i class="fa fa-check"></i><b>6.7</b> Data preprocessing</a><ul>
-<li class="chapter" data-level="6.7.1" data-path="classification.html"><a href="classification.html#shifting-and-scaling"><i class="fa fa-check"></i><b>6.7.1</b> Shifting and scaling</a></li>
+<li class="chapter" data-level="6.6" data-path="classification.html"><a href="classification.html#k-nearest-neighbours-with-tidymodels"><i class="fa fa-check"></i><b>6.6</b> K-nearest neighbours with <code>tidymodels</code></a></li>
+<li class="chapter" data-level="6.7" data-path="classification.html"><a href="classification.html#data-preprocessing-with-tidymodels"><i class="fa fa-check"></i><b>6.7</b> Data preprocessing with <code>tidymodels</code></a><ul>
+<li class="chapter" data-level="6.7.1" data-path="classification.html"><a href="classification.html#centering-and-scaling"><i class="fa fa-check"></i><b>6.7.1</b> Centering and scaling</a></li>
 <li class="chapter" data-level="6.7.2" data-path="classification.html"><a href="classification.html#balancing"><i class="fa fa-check"></i><b>6.7.2</b> Balancing</a></li>
 </ul></li>
+<li class="chapter" data-level="6.8" data-path="classification.html"><a href="classification.html#putting-it-together-in-a-workflow"><i class="fa fa-check"></i><b>6.8</b> Putting it together in a <code>workflow</code></a></li>
 </ul></li>
-<li class="chapter" data-level="7" data-path="classification-continued.html"><a href="classification-continued.html"><i class="fa fa-check"></i><b>7</b> Classification II: Evaluation &amp; tuning</a><ul>
+<li class="chapter" data-level="7" data-path="classification-continued.html"><a href="classification-continued.html"><i class="fa fa-check"></i><b>7</b> Classification II: evaluation &amp; tuning</a><ul>
 <li class="chapter" data-level="7.1" data-path="classification-continued.html"><a href="classification-continued.html#overview-5"><i class="fa fa-check"></i><b>7.1</b> Overview</a></li>
 <li class="chapter" data-level="7.2" data-path="classification-continued.html"><a href="classification-continued.html#chapter-learning-objectives-5"><i class="fa fa-check"></i><b>7.2</b> Chapter learning objectives</a></li>
 <li class="chapter" data-level="7.3" data-path="classification-continued.html"><a href="classification-continued.html#evaluating-accuracy"><i class="fa fa-check"></i><b>7.3</b> Evaluating accuracy</a></li>
@@ -279,20 +279,18 @@
 <li class="chapter" data-level="8.3" data-path="regression1.html"><a href="regression1.html#regression"><i class="fa fa-check"></i><b>8.3</b> Regression</a></li>
 <li class="chapter" data-level="8.4" data-path="regression1.html"><a href="regression1.html#sacremento-real-estate-example"><i class="fa fa-check"></i><b>8.4</b> Sacremento real estate example</a></li>
 <li class="chapter" data-level="8.5" data-path="regression1.html"><a href="regression1.html#k-nearest-neighbours-regression"><i class="fa fa-check"></i><b>8.5</b> K-nearest neighbours regression</a></li>
-<li class="chapter" data-level="8.6" data-path="regression1.html"><a href="regression1.html#assessing-a-nearest-neighbours-regression-model"><i class="fa fa-check"></i><b>8.6</b> Assessing a nearest neighbours regression model</a><ul>
-<li class="chapter" data-level="8.6.1" data-path="regression1.html"><a href="regression1.html#rmspe-versus-rmse"><i class="fa fa-check"></i><b>8.6.1</b> RMSPE versus RMSE</a></li>
+<li class="chapter" data-level="8.6" data-path="regression1.html"><a href="regression1.html#training-evaluating-and-tuning-the-model"><i class="fa fa-check"></i><b>8.6</b> Training, evaluating, and tuning the model</a></li>
+<li class="chapter" data-level="8.7" data-path="regression1.html"><a href="regression1.html#underfitting-and-overfitting"><i class="fa fa-check"></i><b>8.7</b> Underfitting and overfitting</a></li>
+<li class="chapter" data-level="8.8" data-path="regression1.html"><a href="regression1.html#evaluating-on-the-test-set"><i class="fa fa-check"></i><b>8.8</b> Evaluating on the test set</a></li>
+<li class="chapter" data-level="8.9" data-path="regression1.html"><a href="regression1.html#strengths-and-limitations-of-k-nn-regression"><i class="fa fa-check"></i><b>8.9</b> Strengths and limitations of K-NN regression</a></li>
+<li class="chapter" data-level="8.10" data-path="regression1.html"><a href="regression1.html#multivariate-k-nn-regression"><i class="fa fa-check"></i><b>8.10</b> Multivariate K-NN regression</a></li>
 </ul></li>
-<li class="chapter" data-level="8.7" data-path="regression1.html"><a href="regression1.html#how-do-different-ks-affect-k-nn-regression-predictions"><i class="fa fa-check"></i><b>8.7</b> How do different k’s affect k-nn regression predictions</a></li>
-<li class="chapter" data-level="8.8" data-path="regression1.html"><a href="regression1.html#assessing-how-well-the-model-predicts-on-unseen-data-with-the-test-set"><i class="fa fa-check"></i><b>8.8</b> Assessing how well the model predicts on unseen data with the test set</a></li>
-<li class="chapter" data-level="8.9" data-path="regression1.html"><a href="regression1.html#strengths-and-limitations-of-k-nn-regression"><i class="fa fa-check"></i><b>8.9</b> Strengths and limitations of k-nn regression</a></li>
-<li class="chapter" data-level="8.10" data-path="regression1.html"><a href="regression1.html#multivariate-k-nn-regression"><i class="fa fa-check"></i><b>8.10</b> Multivariate k-nn regression</a></li>
-</ul></li>
-<li class="chapter" data-level="9" data-path="regression2.html"><a href="regression2.html"><i class="fa fa-check"></i><b>9</b> Regression II: Linear regression</a><ul>
+<li class="chapter" data-level="9" data-path="regression2.html"><a href="regression2.html"><i class="fa fa-check"></i><b>9</b> Regression II: linear regression</a><ul>
 <li class="chapter" data-level="9.1" data-path="regression2.html"><a href="regression2.html#overview-7"><i class="fa fa-check"></i><b>9.1</b> Overview</a></li>
 <li class="chapter" data-level="9.2" data-path="regression2.html"><a href="regression2.html#chapter-learning-objectives-7"><i class="fa fa-check"></i><b>9.2</b> Chapter learning objectives</a></li>
 <li class="chapter" data-level="9.3" data-path="regression2.html"><a href="regression2.html#simple-linear-regression"><i class="fa fa-check"></i><b>9.3</b> Simple linear regression</a></li>
-<li class="chapter" data-level="9.4" data-path="regression2.html"><a href="regression2.html#linear-regression-in-r-using-caret"><i class="fa fa-check"></i><b>9.4</b> Linear regression in R using <code>caret</code></a></li>
-<li class="chapter" data-level="9.5" data-path="regression2.html"><a href="regression2.html#comparing-simple-linear-and-k-nn-regression"><i class="fa fa-check"></i><b>9.5</b> Comparing simple linear and k-nn regression</a></li>
+<li class="chapter" data-level="9.4" data-path="regression2.html"><a href="regression2.html#linear-regression-in-r"><i class="fa fa-check"></i><b>9.4</b> Linear regression in R</a></li>
+<li class="chapter" data-level="9.5" data-path="regression2.html"><a href="regression2.html#comparing-simple-linear-and-k-nn-regression"><i class="fa fa-check"></i><b>9.5</b> Comparing simple linear and K-NN regression</a></li>
 <li class="chapter" data-level="9.6" data-path="regression2.html"><a href="regression2.html#multivariate-linear-regression"><i class="fa fa-check"></i><b>9.6</b> Multivariate linear regression</a></li>
 <li class="chapter" data-level="9.7" data-path="regression2.html"><a href="regression2.html#the-other-side-of-regression"><i class="fa fa-check"></i><b>9.7</b> The other side of regression</a></li>
 <li class="chapter" data-level="9.8" data-path="regression2.html"><a href="regression2.html#additional-readingsresources-2"><i class="fa fa-check"></i><b>9.8</b> Additional readings/resources</a></li>