adjusting size of plots and fonts

Author: leem44

classification1.Rmd

@@ -1061,7 +1061,7 @@ ggplot(unscaled_cancer, aes(x = Area,
    facet_zoom(x = ( Area > 380 & Area < 420) , 
               y = (Smoothness > 0.08 & Smoothness < 0.14), zoom.size = 2) + 
     theme_bw() + 
-    theme(text = element_text(size = 12), legend.position="bottom")
+    theme(text = element_text(size = 18), axis.title=element_text(size=18), legend.position="bottom")
 ```
 
 ### Balancing

classification2.Rmd

@@ -1110,7 +1110,7 @@ plt_irrelevant_accuracies <- ggplot(res) +
               geom_line(mapping = aes(x=ks, y=accs)) +
               labs(x = "Number of Irrelevant Predictors", 
                    y = "Model Accuracy Estimate") + 
-  theme(text = element_text(size = 16), axis.title=element_text(size=16)) 
+  theme(text = element_text(size = 18), axis.title=element_text(size=18)) 
 
 plt_irrelevant_accuracies
 ```
@@ -1131,7 +1131,7 @@ plt_irrelevant_nghbrs <- ggplot(res) +
               geom_line(mapping = aes(x=ks, y=nghbrs)) +
               labs(x = "Number of Irrelevant Predictors", 
                    y = "Number of neighbors") + 
-  theme(text = element_text(size = 16), axis.title=element_text(size=16)) 
+  theme(text = element_text(size = 18), axis.title=element_text(size=18)) 
 
 plt_irrelevant_nghbrs
 ```
@@ -1145,7 +1145,7 @@ plt_irrelevant_nghbrs <- ggplot(res_tmp) +
               geom_line(mapping = aes(x=ks, y=accuracy, color=Type)) +
               labs(x = "Number of Irrelevant Predictors", y = "Accuracy") + 
               scale_color_discrete(labels= c("Tuned K", "K = 3")) + 
-  theme(text = element_text(size = 16), axis.title=element_text(size=16)) 
+  theme(text = element_text(size = 17), axis.title=element_text(size=17)) 
 
 plt_irrelevant_nghbrs
 ```
@@ -1378,7 +1378,7 @@ fwd_sel_accuracies_plot <- accuracies |>
   ggplot(aes(x = size, y = accuracy)) +
   geom_line() +
   labs(x = "Number of Predictors", y = "Estimated Accuracy")  +
-  theme(text = element_text(size = 18), axis.title=element_text(size=18)) 
+  theme(text = element_text(size = 20), axis.title=element_text(size=20)) 
 
 fwd_sel_accuracies_plot
 ```

clustering.Rmd

@@ -473,7 +473,7 @@ for (i in 1:4) {
                color = "black", 
                fill = cbpalette) +
     annotate("text", x = -0.5, y = 1.5, label = paste0("Iteration ", i), size = 5)+ 
-    theme(text = element_text(size = 12))
+    theme(text = element_text(size = 14), axis.title=element_text(size=14)) 
   
   if (i == 1 | i == 2) {
     plt_ctr <- plt_ctr +
@@ -506,8 +506,8 @@ for (i in 1:4) {
                stroke = 1, 
                color = "black", 
                fill = cbpalette) +
-    annotate("text", x = -0.5, y = 1.5, label = paste0("Iteration ", i), size = 5)+ 
-    theme(text = element_text(size = 12))
+    annotate("text", x = -0.5, y = 1.5, label = paste0("Iteration ", i), size = 5) + 
+    theme(text = element_text(size = 14), axis.title=element_text(size=14)) 
 
   if (i == 1 | i ==2) {
     plt_lbl <- plt_lbl +
@@ -646,7 +646,7 @@ for (i in 1:5) {
                color = "black", 
                fill = cbpalette) +
     annotate("text", x = -0.5, y = 1.5, label = paste0("Iteration ", i), size = 5) + 
-    theme(text = element_text(size = 12))
+    theme(text = element_text(size = 14), axis.title=element_text(size=14)) 
 
   if (i == 1 | i == 2) {
     plt_ctr <- plt_ctr +
@@ -679,7 +679,7 @@ for (i in 1:5) {
                color = "black", 
                fill = cbpalette) +
     annotate("text", x = -0.5, y = 1.5, label = paste0("Iteration ", i), size = 5) + 
-    theme(text = element_text(size = 12))
+    theme(text = element_text(size = 14), axis.title=element_text(size=14)) 
 
   if (i == 1 | i == 2) {
     plt_lbl <- plt_lbl +
@@ -729,15 +729,15 @@ ggarrange(iter_plot_list[[1]] +
                theme(axis.text.x = element_blank(),
                      axis.ticks.x = element_blank(),
                      axis.title.x = element_blank(),
-                     plot.margin = margin(r = 2, t = 2, b = 1)),
+                     plot.margin = margin(r = 2, t = 2, b = 2)),
           iter_plot_list[[6]] + 
                theme(axis.text.y = element_blank(),
                      axis.ticks.y = element_blank(),
                      axis.title.y = element_blank(),
                      axis.text.x = element_blank(),
                      axis.ticks.x = element_blank(),
                      axis.title.x = element_blank(),
-                     plot.margin = margin(r = 2, l = 2, t = 2, b = 1) ), 
+                     plot.margin = margin(r = 2, l = 2, t = 2, b = 2) ), 
           iter_plot_list[[7]] + 
                theme(axis.text.y = element_blank(),
                      axis.ticks.y = element_blank(),
@@ -826,7 +826,9 @@ p1 <- ggplot(assignments, aes(flipper_length_standardized,
              size = 5, 
              shape = 21, 
              stroke = 1) + 
-  scale_fill_manual(values = cbbPalette)
+  scale_fill_manual(values = cbbPalette) +     
+  theme(text = element_text(size = 12), axis.title=element_text(size=12)) 
+
 
 p1
 ```

inference.Rmd

@@ -557,7 +557,7 @@ annotated_sampling_dist_20 <- sampling_distribution_20 +
     hjust = 1, 
     vjust = 1,
     label = paste("mean = ", round(mean(sample_estimates$sample_mean), 1))
-  )
+  )+  theme(text = element_text(size = 12), axis.title=element_text(size=12)) 
 #+
 #    annotate("text", x =  max_x(sampling_distribution_20), y = max_count(sampling_distribution_20), hjust = 1, vjust = 3,
 #               label = paste("sd = ", round(sd(sample_estimates$sample_mean), 1)))
@@ -571,7 +571,7 @@ annotated_sampling_dist_50 <- sampling_distribution_50 +
     hjust = 1, 
     vjust = 1,
     label = paste("mean = ", round(mean(sample_estimates_50$sample_mean), 1))
-  ) #+
+  )+  theme(text = element_text(size = 12), axis.title=element_text(size=12))  #+
 # annotate("text", x =  max_x(sampling_distribution_20), y = max_count(sampling_distribution_50), hjust = 1, vjust = 3,
 #                 label = paste("sd = ", round(sd(sample_estimates_50$sample_mean), 1)))
 
@@ -583,7 +583,7 @@ annotated_sampling_dist_100 <- sampling_distribution_100 +
     hjust = 1, 
     vjust = 1,
     label = paste("mean = ", round(mean(sample_estimates_100$sample_mean), 1))
-  ) #+
+  ) +  theme(text = element_text(size = 12), axis.title=element_text(size=12)) #+
 #    annotate("text", x =  max_x(sampling_distribution_20), y = max_count(sampling_distribution_100), hjust = 1, vjust = 3,
 #               label = paste("sd = ", round(sd(sample_estimates_100$sample_mean), 1)))
 
@@ -595,7 +595,8 @@ annotated_sampling_dist_500 <- sampling_distribution_500 +
     hjust = 1, 
     vjust = 1,
     label = paste("mean = ", round(mean(sample_estimates_500$sample_mean), 1))
-  ) #+
+  ) +  theme(text = element_text(size = 12), axis.title=element_text(size=12)) 
+#+
 #    annotate("text", x =  max_x(sampling_distribution_20), y = max_count(sampling_distribution_500), hjust = 1, vjust = 3,
 #               label = paste("sd = ", round(sd(sample_estimates_500$sample_mean), 1)))
 

regression1.Rmd

@@ -497,7 +497,7 @@ For each model, we predict prices for the range of possible home sizes we
 observed in the data set (here 500 to 5,000 square feet) and we plot the
 predicted prices as a blue line.
 
-```{r 07-howK, echo = FALSE, warning = FALSE, fig.height = 12, fig.width = 10,fig.cap = "Predicted values for house price (represented as a blue line) from KNN regression models for six different values for $K$."}
+```{r 07-howK, echo = FALSE, warning = FALSE, fig.height = 13, fig.width = 10,fig.cap = "Predicted values for house price (represented as a blue line) from KNN regression models for six different values for $K$."}
 gridvals <- c(1, 3, kmin, 41, 250, 932)
 
 plots <- list()

regression2.Rmd

@@ -327,7 +327,7 @@ simple linear regression model predictions for the Sacramento real estate data
 (predicting price from house size) and the "best" KNN regression model
 obtained from the same problem, shown in Figure \@ref(fig:08-compareRegression).
 
-```{r 08-compareRegression, echo = FALSE, warning = FALSE, message = FALSE, fig.height = 4, fig.width = 10, fig.cap = "Comparison of simple linear regression and KNN regression."}
+```{r 08-compareRegression, echo = FALSE, warning = FALSE, message = FALSE, fig.height = 4.75, fig.width = 10, fig.cap = "Comparison of simple linear regression and KNN regression."}
 set.seed(1234)
 sacr_spec <- nearest_neighbor(weight_func = "rectangular", neighbors = 30) |>
   set_engine("kknn") |>
@@ -371,8 +371,10 @@ knn_plot_final <- ggplot(sacr_preds, aes(x = sqft, y = price)) +
   geom_line(data = sacr_preds, aes(x = sqft, y = .pred), color = "blue") +
   ggtitle("KNN regression") +
   annotate("text", x = 3500, y = 100000, label = paste("RMSPE =", sacr_rmspe)) +
-  theme(text = element_text(size = 12))
+  theme(text = element_text(size = 18), axis.title=element_text(size=18)) 
+
 
+  
 lm_rmspe <- lm_test_results |>
   filter(.metric == "rmse") |>
   pull(.estimate) |>
@@ -381,7 +383,7 @@ lm_rmspe <- lm_test_results |>
 lm_plot_final <- lm_plot_final +
   annotate("text", x = 3500, y = 100000, label = paste("RMSPE =", lm_rmspe)) +
   ggtitle("linear regression") +
-  theme(text = element_text(size = 12))
+  theme(text = element_text(size = 18), axis.title=element_text(size=18)) 
 
 grid.arrange(lm_plot_final, knn_plot_final, ncol = 2)
 ```

viz.Rmd

@@ -1238,7 +1238,8 @@ morley_hist_default <- ggplot(morley_rel,
        y = "# Measurements", 
        fill = "Experiment ID") +
   theme(legend.position = "none") +
-  ggtitle("Default bin width (bins = 30)")
+  ggtitle("Default (bins = 30)")  + 
+  theme(text = element_text(size = 14), axis.title=element_text(size=14)) 
 
 morley_hist_big <- ggplot(morley_rel, 
                           aes(x = relative_accuracy, 
@@ -1250,7 +1251,8 @@ morley_hist_big <- ggplot(morley_rel,
        y = "# Measurements", 
        fill = "Experiment ID") +
   theme(legend.position = "none") +
-  ggtitle( "binwidth = 0.1")
+  ggtitle( "binwidth = 0.1")  + 
+  theme(text = element_text(size = 14), axis.title=element_text(size=14)) 
 
 morley_hist_med <- ggplot(morley_rel, 
                           aes(x = relative_accuracy, 
@@ -1262,7 +1264,8 @@ morley_hist_med <- ggplot(morley_rel,
        y = "# Measurements", 
        fill = "Experiment ID") +
   theme(legend.position = "none") +
-  ggtitle("binwidth = 0.01")
+  ggtitle("binwidth = 0.01")  + 
+  theme(text = element_text(size = 14), axis.title=element_text(size=14)) 
 
 morley_hist_small <- ggplot(morley_rel, 
                             aes(x = relative_accuracy, 
@@ -1274,7 +1277,8 @@ morley_hist_small <- ggplot(morley_rel,
        y = "# Measurements", 
        fill = "Experiment ID") +
   theme(legend.position = "none") +
-  ggtitle("binwidth = 0.001")
+  ggtitle("binwidth = 0.001")  + 
+  theme(text = element_text(size = 14), axis.title=element_text(size=14)) 
 
 plot_grid(morley_hist_default, 
           morley_hist_small, 
@@ -1433,7 +1437,8 @@ library(svglite) # we need this to save SVG files
 faithful_plot <- ggplot(data = faithful, aes(x = waiting, y = eruptions)) +
   geom_point() +
   labs(x = "Waiting time to next eruption \n (minutes)",
-       y = "Eruption time \n (minutes)")
+       y = "Eruption time \n (minutes)") + 
+  theme(text = element_text(size = 12))
 
 faithful_plot
 ```