improvements to consistency in visualizations in reg1,2

Author: trevorcampbell

source/regression1.Rmd

@@ -244,13 +244,17 @@ nearest_neighbors <- small_sacramento |>
 nearest_neighbors
 ```
 
-```{r 07-knn3-example, echo = FALSE, fig.height = 3.5, fig.width = 4.5, fig.cap = "Scatter plot of price (USD) versus house size (square feet) with lines to 5 nearest neighbors."}
+```{r 07-knn3-example, echo = FALSE, fig.height = 3.5, fig.width = 4.5, fig.cap = "Scatter plot of price (USD) versus house size (square feet) with lines to 5 nearest neighbors (highlighted in orange)."}
 nearest_neighbors <- mutate(nearest_neighbors, twothou = rep(2000, 5))
 
 nn_plot <- small_plot +
   geom_segment(
     data = nearest_neighbors,
-    aes(x = twothou, xend = sqft, y = price, yend = price), color = "orange"
+    aes(x = twothou, xend = sqft, y = price, yend = price), color = "black"
+  ) +
+  geom_point(
+    data = nearest_neighbors,
+    aes(x = sqft, y = price), color = "darkorange"
   )
 
 nn_plot
@@ -347,13 +351,13 @@ different from the true values, then RMSPE will be quite large. When we
 use cross-validation, we will choose the $K$ that gives
 us the smallest RMSPE.
 
-```{r 07-verticalerrors, echo = FALSE, message = FALSE, warning = FALSE, fig.cap = "Scatter plot of price (USD) versus house size (square feet) with example predictions (blue line) and the error in those predictions compared with true response values for three selected observations (vertical red lines).", fig.height = 3.5, fig.width = 4.5}
+```{r 07-verticalerrors, echo = FALSE, message = FALSE, warning = FALSE, fig.cap = "Scatter plot of price (USD) versus house size (square feet) with example predictions (blue line) and the error in those predictions compared with true response values (vertical lines).", fig.height = 3.5, fig.width = 4.5}
 # save the seed
 seedval <- .Random.seed
 
 # (synthetic) new prediction points
-pts <- tibble(sqft = c(1250, 1850, 2250), price = c(250000, 200000, 500000))
-finegrid <- tibble(sqft = seq(from = 900, to = 3900, by = 10))
+pts <- tibble(sqft = c(1500, 1810, 2200), price = c(300000, 160000, 500000))
+finegrid <- tibble(sqft = seq(from = 500, to = 4100, by = 10))
 
 # fit the model
 sacr_recipe_hid <- recipe(price ~ sqft, data = small_sacramento) |>
@@ -375,8 +379,8 @@ sacr_full_preds_hid <- sacr_fit_hid |>
                            bind_cols(finegrid)
 
 sacr_new_preds_hid <- sacr_fit_hid |>
-                           predict(pts) |>
-                           bind_cols(pts)
+                           predict(small_sacramento) |>
+                           bind_cols(small_sacramento)
 
 # plot the vertical prediction errors
 errors_plot <- ggplot(small_sacramento, aes(x = sqft, y = price)) +
@@ -386,11 +390,11 @@ errors_plot <- ggplot(small_sacramento, aes(x = sqft, y = price)) +
   scale_y_continuous(labels = dollar_format()) +
   geom_line(data = sacr_full_preds_hid,
             aes(x = sqft, y = .pred),
-            color = "blue") +
+            color = "steelblue", linewidth=1) +
   geom_segment(
     data = sacr_new_preds_hid,
     aes(x = sqft, xend = sqft, y = price, yend = .pred),
-    color = "red") +
+    color = "black") +
   geom_point(data = sacr_new_preds_hid,
              aes(x = sqft, y = price),
              color = "black")
@@ -543,7 +547,7 @@ for (i in 1:6) {
         xlab("House size (square feet)") +
         ylab("Price (USD)") +
         scale_y_continuous(labels = dollar_format()) +
-        geom_line(data = sacr_preds, aes(x = sqft, y = .pred), color = "blue") +
+        geom_line(data = sacr_preds, aes(x = sqft, y = .pred), color = "steelblue", linewidth=1) +
         ggtitle(paste0("K = ", gridvals[[i]])) +
         theme(text = element_text(size = 20), axis.title=element_text(size=20))
 }
@@ -676,7 +680,8 @@ plot_final <- ggplot(sacramento, aes(x = sqft, y = price)) +
   geom_point(alpha = 0.4) +
   geom_line(data = sacr_preds,
             mapping = aes(x = sqft, y = .pred),
-            color = "blue") +
+            color = "steelblue",
+            linewidth = 1) +
   xlab("House size (square feet)") +
   ylab("Price (USD)") +
   scale_y_continuous(labels = dollar_format()) +

source/regression2.Rmd

@@ -117,7 +117,7 @@ small_plot <- ggplot(small_sacramento, aes(x = sqft, y = price)) +
   xlab("House size (square feet)") +
   ylab("Price (USD)") +
   scale_y_continuous(labels = dollar_format()) +
-  geom_smooth(method = "lm", se = FALSE)
+  geom_smooth(method = "lm", se = FALSE, color = "steelblue")
 
 small_plot
 ```
@@ -154,10 +154,9 @@ small_model <- lm(price ~ sqft, data = small_sacramento)
 prediction <- predict(small_model, data.frame(sqft = 2000))
 
 small_plot +
-  geom_vline(xintercept = 2000, linetype = "dotted") +
-  geom_point(aes(x = 2000,
-                 y = prediction[[1]],
-                 color = "red", size = 2.5)) +
+  geom_vline(xintercept = 2000, linetype = "dashed") +
+  geom_point(aes(x = 2000, y = prediction[[1]]),
+                 color = "red", size = 2.5) +
   annotate("text",
            x = 2350,
            y = prediction[[1]]-30000,
@@ -179,15 +178,15 @@ Some plausible examples are shown in Figure \@ref(fig:08-several-lines).
 
 ```{r 08-several-lines, echo = FALSE, message = FALSE, warning = FALSE, fig.height = 3.5, fig.width = 4.5,  fig.cap = "Scatter plot of sale price versus size with many possible lines that could be drawn through the data points."}
 small_plot +
-  geom_abline(intercept = -64542.23, slope = 190, color = "green") +
-  geom_abline(intercept = -6900, slope = 175, color = "purple") +
-  geom_abline(intercept = -64542.23, slope = 160, color = "red")
+  geom_abline(intercept = -64542.23, slope = 190, color = "darkorange", linewidth = 1) +
+  geom_abline(intercept = -6900, slope = 175, color = "purple", linewidth = 1) +
+  geom_abline(intercept = -64542.23, slope = 160, color = "firebrick", linewidth = 1)
 ```
 
 Simple linear regression chooses the straight line of best fit by choosing
 the line that minimizes the **average squared vertical distance** between itself and
-each of the observed data points in the training data. Figure \@ref(fig:08-verticalDistToMin) illustrates
-these vertical distances as red lines. Finally, to assess the predictive
+each of the observed data points in the training data (equivalent to minimizing the RMSE).
+Figure \@ref(fig:08-verticalDistToMin) illustrates these vertical distances as red lines. Finally, to assess the predictive
 accuracy of a simple linear regression model,
 we use RMSPE&mdash;the same measure of predictive performance we used with K-NN regression.
 \index{RMSPE}
@@ -199,7 +198,7 @@ small_sacramento <- small_sacramento |>
 small_plot +
   geom_segment(data = small_sacramento,
                aes(xend = sqft, yend = predicted),
-               colour = "red")
+               colour = "black")
 ```
 
 ## Linear regression in R
@@ -317,7 +316,8 @@ lm_plot_final <- ggplot(sacramento, aes(x = sqft, y = price)) +
   geom_point(alpha = 0.4) +
   geom_line(data = sacr_preds,
             mapping = aes(x = sqft, y = .pred),
-            color = "blue") +
+            color = "steelblue",
+            linewidth = 1) +
   xlab("House size (square feet)") +
   ylab("Price (USD)") +
   scale_y_continuous(labels = dollar_format()) +
@@ -390,7 +390,7 @@ knn_plot_final <- ggplot(sacr_preds, aes(x = sqft, y = price)) +
   xlab("House size (square feet)") +
   ylab("Price (USD)") +
   scale_y_continuous(labels = dollar_format()) +
-  geom_line(data = sacr_preds, aes(x = sqft, y = .pred), color = "blue") +
+  geom_line(data = sacr_preds, aes(x = sqft, y = .pred), color = "steelblue", linewidth = 1) +
   ggtitle("K-NN regression") +
   annotate("text", x = 3500, y = 100000, label = paste("RMSPE =", sacr_rmspe)) +
   theme(text = element_text(size = 18), axis.title=element_text(size=18))
@@ -663,7 +663,7 @@ lm_plot_outlier <- ggplot(sacramento_train_small, aes(x = sqft, y = price)) +
   xlab("House size (square feet)") +
   ylab("Price (USD)") +
   scale_y_continuous(labels = dollar_format()) +
-  geom_smooth(method = "lm", se = FALSE) +
+  geom_smooth(method = "lm", se = FALSE, color = "steelblue") +
   geom_smooth(data = sacramento_train_small |>
                 add_row(sqft = 5000, price = 50000),
               method = "lm", se = FALSE, color = "red")
@@ -693,7 +693,7 @@ lm_plot_outlier_large <- ggplot(sacramento_train, aes(x = sqft, y = price)) +
   xlab("House size (square feet)") +
   ylab("Price (USD)") +
   scale_y_continuous(labels = dollar_format()) +
-  geom_smooth(method = "lm", se = FALSE) +
+  geom_smooth(method = "lm", se = FALSE, color = "steelblue") +
   geom_smooth(data = sacramento_train |>
                 add_row(sqft = 5000, price = 50000),
               method = "lm",
@@ -853,7 +853,7 @@ curve_plt <- ggplot(df, aes(x = x, y = y)) +
   geom_point() +
   xlab("x") +
   ylab("y") +
-  geom_smooth(method = "lm", se = FALSE)
+  geom_smooth(method = "lm", se = FALSE, color = "steelblue")
 curve_plt
 ```
 
@@ -880,7 +880,7 @@ curve_plt2 <- ggplot(df, aes(x = z, y = y)) +
   geom_point() +
   xlab(expression(paste("z = x"^"3"))) +
   ylab("y") +
-  geom_smooth(method = "lm", se = FALSE)
+  geom_smooth(method = "lm", se = FALSE, color = "steelblue")
 
 curve_plt2
 ```