figure sizes

docs/sitemap.xml

@@ -110,11 +110,11 @@
   </url>
   <url>
     <loc>https://iml.numbat.space/week10/tutorialsol.html</loc>
-    <lastmod>2024-05-03T00:04:26.272Z</lastmod>
+    <lastmod>2024-05-03T00:12:27.655Z</lastmod>
   </url>
   <url>
     <loc>https://iml.numbat.space/week10/tutorial.html</loc>
-    <lastmod>2024-05-03T00:04:26.272Z</lastmod>
+    <lastmod>2024-05-03T00:12:27.655Z</lastmod>
   </url>
   <url>
     <loc>https://iml.numbat.space/week12/index.html</loc>

docs/week10/tutorial.html

@@ -339,7 +339,7 @@ <h4 class="anchored" data-anchor-id="how-would-you-cluster-this-data">1. How wou
 <div class="cell-output-display">
 <div class="quarto-figure quarto-figure-center">
 <figure class="figure">
-<p><img src="tutorial_files/figure-html/unnamed-chunk-4-1.png" class="img-fluid quarto-figure quarto-figure-center figure-img" style="width:100.0%"></p>
+<p><img src="tutorial_files/figure-html/unnamed-chunk-4-1.png" class="img-fluid quarto-figure quarto-figure-center figure-img" style="width:60.0%"></p>
 </figure>
 </div>
 </div>
@@ -388,7 +388,7 @@ <h4 class="anchored" data-anchor-id="clustering-spotify-data-with-k-means">2. Cl
 <div class="cell-output-display">
 <div class="quarto-figure quarto-figure-center">
 <figure class="figure">
-<p><img src="tutorial_files/figure-html/unnamed-chunk-8-1.png" class="img-fluid quarto-figure quarto-figure-center figure-img" style="width:100.0%"></p>
+<p><img src="tutorial_files/figure-html/unnamed-chunk-8-1.png" class="img-fluid quarto-figure quarto-figure-center figure-img" style="width:60.0%"></p>
 </figure>
 </div>
 </div>
@@ -400,8 +400,8 @@ <h4 class="anchored" data-anchor-id="clustering-spotify-data-with-k-means">2. Cl
 <li>Divide the data into 11 clusters, and examine the number of songs in each. Using plotly, mouse over the resulting plot and explore songs belonging to a cluster. (I don’t know much about these songs, but if you are a music fan maybe discussing with other class members and your tutor about the groupings, like which ones are grouped in clusters with high <code>liveness</code>, high <code>tempo</code> or <code>danceability</code> could be fun.)</li>
 </ol>
 </section>
-<section id="clustering-several-simulated-data-sets-with-know-cluster-structure" class="level4">
-<h4 class="anchored" data-anchor-id="clustering-several-simulated-data-sets-with-know-cluster-structure">3. Clustering several simulated data sets with know cluster structure</h4>
+<section id="clustering-several-simulated-data-sets-with-known-cluster-structure" class="level4">
+<h4 class="anchored" data-anchor-id="clustering-several-simulated-data-sets-with-known-cluster-structure">3. Clustering several simulated data sets with known cluster structure</h4>
 <ol type="a">
 <li>In tutorial of week 3 you used the tour to visualise the data sets <code>c1</code> and <code>c3</code> provided with the <code>mulgar</code> package. Review what you said about the structure in these data sets, and write down your expectations for how a cluster analysis would divide the data.</li>
 </ol>

docs/week10/tutorial.qmd

@@ -90,6 +90,7 @@ a. How would you cluster this data?
 
 ```{r}
 #| echo: false
+#| out-width: 60%
 set.seed(840)
 challenge <- sphere.hollow(p=2, n=200)$points |> as_tibble()
 challenge[1:100, ] <- challenge[1:100, ] * 2.2
@@ -110,6 +111,7 @@ My distance will use the radial distance from $(0, 0)$. You first convert each p
 
 
 ```{r}
+#| out-width: 60%
 mydist <- function(x1, x2) {
   d <- abs(sqrt(sum(x1^2)) - sqrt(sum(x2^2)))
   return(d)
@@ -154,6 +156,7 @@ Many of the variables have skewed distributions. For cluster analysis, why might
 ::: unilur-solution
 
 ```{r}
+#| out-width: 60%
 p <- spotify_std |>
   pivot_longer(danceability:artist_popularity,
                names_to="var", values_to="value") |>
@@ -173,6 +176,7 @@ Yes, for example "Free Bird" and "Sparkle" could be found by simply examining a
 b. Transform the skewed variables to be as symmetric as possible, and then fit a $k=3$-means clustering. Extract and report these metrics: `totss`, `tot.withinss`, `betweenss`. What is the ratio of within to between SS?
 
 ```{r}
+#| out-width: 60%
 # Transforming some variables: imperfect
 spotify_tf <- spotify |>
   mutate(speechiness = log10(speechiness),
@@ -196,6 +200,7 @@ spotify_tf |>
 ::: unilur-solution
 
 ```{r}
+#| out-width: 60%
 # Check that it clusters
 set.seed(131)
 spotify_km3 <- kmeans(spotify_tf[,5:15], 3)
@@ -220,6 +225,7 @@ c. Now the algorithm $k=1, ..., 20$. Extract the metrics, and plot the ratio of
 ::: unilur-solution
 
 ```{r}
+#| out-width: 60%
 # Run many k
 spotify_km <- 
   tibble(k = 1:20) %>%
@@ -267,7 +273,7 @@ spotify_assign_df |>
 ```
 :::
 
-#### 3. Clustering several simulated data sets with know cluster structure
+#### 3. Clustering several simulated data sets with known cluster structure
 
 a. In tutorial of week 3 you used the tour to visualise the data sets `c1` and `c3` provided with the `mulgar` package. Review what you said about the structure in these data sets, and write down your expectations for how a cluster analysis would divide the data.
 

week10/tutorial.qmd

@@ -90,6 +90,7 @@ a. How would you cluster this data?
 
 ```{r}
 #| echo: false
+#| out-width: 60%
 set.seed(840)
 challenge <- sphere.hollow(p=2, n=200)$points |> as_tibble()
 challenge[1:100, ] <- challenge[1:100, ] * 2.2
@@ -110,6 +111,7 @@ My distance will use the radial distance from $(0, 0)$. You first convert each p
 
 
 ```{r}
+#| out-width: 60%
 mydist <- function(x1, x2) {
   d <- abs(sqrt(sum(x1^2)) - sqrt(sum(x2^2)))
   return(d)
@@ -154,6 +156,7 @@ Many of the variables have skewed distributions. For cluster analysis, why might
 ::: unilur-solution
 
 ```{r}
+#| out-width: 60%
 p <- spotify_std |>
   pivot_longer(danceability:artist_popularity,
                names_to="var", values_to="value") |>
@@ -173,6 +176,7 @@ Yes, for example "Free Bird" and "Sparkle" could be found by simply examining a
 b. Transform the skewed variables to be as symmetric as possible, and then fit a $k=3$-means clustering. Extract and report these metrics: `totss`, `tot.withinss`, `betweenss`. What is the ratio of within to between SS?
 
 ```{r}
+#| out-width: 60%
 # Transforming some variables: imperfect
 spotify_tf <- spotify |>
   mutate(speechiness = log10(speechiness),
@@ -196,6 +200,7 @@ spotify_tf |>
 ::: unilur-solution
 
 ```{r}
+#| out-width: 60%
 # Check that it clusters
 set.seed(131)
 spotify_km3 <- kmeans(spotify_tf[,5:15], 3)
@@ -220,6 +225,7 @@ c. Now the algorithm $k=1, ..., 20$. Extract the metrics, and plot the ratio of
 ::: unilur-solution
 
 ```{r}
+#| out-width: 60%
 # Run many k
 spotify_km <- 
   tibble(k = 1:20) %>%
@@ -267,7 +273,7 @@ spotify_assign_df |>
 ```
 :::
 
-#### 3. Clustering several simulated data sets with know cluster structure
+#### 3. Clustering several simulated data sets with known cluster structure
 
 a. In tutorial of week 3 you used the tour to visualise the data sets `c1` and `c3` provided with the `mulgar` package. Review what you said about the structure in these data sets, and write down your expectations for how a cluster analysis would divide the data.