Make sure all figures display and references resolve

Author: joelostblom

source/classification1.md

@@ -374,10 +374,10 @@ perim_concav_with_new_point = (
     alt.Chart(perim_concav_with_new_point_df)
     .mark_point(opacity=0.6, filled=True, size=40)
     .encode(
-        x=alt.X("Perimeter").title="Perimeter (standardized)"),
-        y=alt.Y("Concavity").title="Concavity (standardized)"),
+        x=alt.X("Perimeter").title("Perimeter (standardized)"),
+        y=alt.Y("Concavity").title("Concavity (standardized)"),
         color=alt.Color("Class").title("Diagnosis"),
-        shape=alt.Shape("Class").scale((range=["circle", "circle", "diamond"])),
+        shape=alt.Shape("Class").scale(range=["circle", "circle", "diamond"]),
         size=alt.condition("datum.Class == 'Unknown'", alt.value(100), alt.value(30)),
         stroke=alt.condition("datum.Class == 'Unknown'", alt.value('black'), alt.value(None)),
     )

source/classification2.md

@@ -1161,7 +1161,7 @@ large_accuracies_grid = pd.DataFrame(
 large_accuracy_vs_k = alt.Chart(large_accuracies_grid).mark_line(point=True).encode(
     x=alt.X("param_kneighborsclassifier__n_neighbors").title("Neighbors"),
     y=alt.Y("mean_test_score")
-        .scale(domain=(0.60, 0.90)
+        .scale(domain=(0.60, 0.90))
         .title("Accuracy estimate")
 )
 

source/clustering.md

@@ -219,7 +219,7 @@ Scatter plot of standardized bill length versus standardized flipper length.
 Based on the visualization
 in {numref}`scatter_plot`,
 we might suspect there are a few subtypes of penguins within our data set.
-We can see roughly 3 groups of observations in {numref}`scatter`,
+We can see roughly 3 groups of observations in {numref}`scatter_plot`,
 including:
 
 1. a small flipper and bill length group,

source/inference.md

@@ -427,7 +427,7 @@ We can visualize the population distribution of the price per night with a histo
 
 population_distribution = alt.Chart(airbnb).mark_bar().encode(
     x=alt.X("price")
-        .bin()
+        .bin(maxbins=30)
         .title("Price per night (Canadian dollars)"),
     y=alt.Y("count()", title="Count"),
 )
@@ -500,7 +500,7 @@ of our sample.
 
 sample_distribution = alt.Chart(one_sample).mark_bar().encode(
     x=alt.X("price")
-        .bin()
+        .bin(maxbins=30)
         .title("Price per night (Canadian dollars)"),
     y=alt.Y("count()").title("Count"),
 )
@@ -574,9 +574,9 @@ sample_estimates
 
 sampling_distribution = alt.Chart(sample_estimates).mark_bar().encode(
     x=alt.X("sample_mean")
-        .bin()
+        .bin(maxbins=30)
         .title("Sample mean price per night (Canadian dollars)"),
-    y=alt.Y("count()").title("Count"),
+    y=alt.Y("count()").title("Count")
 )
 
 sampling_distribution
@@ -943,7 +943,7 @@ one_sample
 
 one_sample_dist = alt.Chart(one_sample).mark_bar().encode(
     x=alt.X("price")
-        .bin()
+        .bin(maxbins=30)
         .title("Price per night (Canadian dollars)"),
     y=alt.Y("count()").title("Count"),
 )
@@ -983,7 +983,7 @@ we change the `replace` parameter to `True`.
 boot1 = one_sample.sample(frac=1, replace=True)
 boot1_dist = alt.Chart(boot1).mark_bar().encode(
     x=alt.X("price")
-        .bin()
+        .bin(maxbins=30)
         .title("Price per night (Canadian dollars)"),
     y=alt.Y("count()", title="Count"),
 )