Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add info from outlier reason 2 and clean up graphs #69

Merged
merged 4 commits into from
Dec 17, 2024
+28 −23
Merged

Add info from outlier reason 2 and clean up graphs #69

Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e6c8805
Add maing changes
wagnerlmichael Dec 17, 2024
4326291
Remove hard coded triad refs
wagnerlmichael Dec 17, 2024
9bddac9
Remove quotes
wagnerlmichael Dec 17, 2024
a385af5
Incorporate feedback
wagnerlmichael Dec 17, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
53 changes: 30 additions & 23 deletions reports/performance/_outliers.qmd
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,27 +18,29 @@ exclusively on these price-based factors that determine outlier status.
### Count by Type

```{r _outliers_type_breakdown}
# Make new column for a few cells of the outliers section
# Subset important outlier information
training_data <- training_data %>%
mutate(price_outlier_reason = case_when(
# Also grabs outlier reason Non-livable computed in 00-ingest.R
str_detect(sv_outlier_reason1, regex("price|Non-livable", ignore_case = TRUE)) ~ sv_outlier_reason1,
str_detect(sv_outlier_reason2, regex("price", ignore_case = TRUE)) ~ sv_outlier_reason2,
str_detect(sv_outlier_reason3, regex("price", ignore_case = TRUE)) ~ sv_outlier_reason3,
TRUE ~ NA_character_
))
mutate(
outlier_reasons_to_graph = if_else(
sv_is_outlier,
paste0(sv_outlier_reason1, " (", sv_outlier_reason2, ")"),
NA_character_
)
) %>%
# Yank NA string values to make output cleaner
mutate(outlier_reasons_to_graph = str_remove_all(outlier_reasons_to_graph, " \\(NA\\)"))
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

suggestion (blocking): Use a case_when() here. Creating a string and then manipulating it is fragile and error-prone.


# Determine the axis limit
y_lim_axis_outlier_breakdown <- training_data %>%
filter(sv_is_outlier) %>%
count(price_outlier_reason) %>%
count(outlier_reasons_to_graph) %>%
summarise(max_value = max(n)) %>%
pull(max_value)

training_data %>%
filter(sv_is_outlier) %>%
count(price_outlier_reason) %>%
ggplot(aes(x = reorder(price_outlier_reason, -n), y = n)) +
count(outlier_reasons_to_graph) %>%
ggplot(aes(x = reorder(outlier_reasons_to_graph, -n), y = n)) +
geom_bar(stat = "identity") +
geom_text(aes(label = comma(n)), vjust = -0.5) +
ylim(0, 1.03 * y_lim_axis_outlier_breakdown) +
Expand All @@ -57,19 +59,19 @@ training_data %>%
```{r _outliers_type_breakdown_table}
training_data %>%
filter(sv_is_outlier) %>%
group_by(meta_year, price_outlier_reason) %>%
group_by(meta_year, outlier_reasons_to_graph) %>%
summarise(n = n()) %>%
rename(Year = meta_year) %>%
pivot_wider(id_cols = Year, names_from = price_outlier_reason, values_from = n) %>%
pivot_wider(id_cols = Year, names_from = outlier_reasons_to_graph, values_from = n) %>%
kable() %>%
kable_styling("striped")

training_data %>%
filter(sv_is_outlier) %>%
group_by(meta_year, price_outlier_reason) %>%
group_by(meta_year, outlier_reasons_to_graph) %>%
summarise(n = n(), .groups = "drop") %>%
rename(Year = meta_year) %>%
pivot_wider(id_cols = Year, names_from = price_outlier_reason, values_from = n) %>%
pivot_wider(id_cols = Year, names_from = outlier_reasons_to_graph, values_from = n) %>%
kable() %>%
kable_styling("striped")
```
Expand Down Expand Up @@ -262,6 +264,11 @@ outliers_ratio_comparison <- training_data %>%
) %>%
distinct(meta_township_name, percent, above_below, triad)

axis_limit_outlier_ratio_comparison <- outliers_ratio_comparison %>%
arrange(desc(percent)) %>%
Matrix::head(1) %>%
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

suggestion (blocking): Replace this with slice_max().

pull(percent)

outliers_ratio_comparison %>%
ggplot(aes(x = reorder(meta_township_name, percent), y = percent)) +
labs(
Expand All @@ -270,7 +277,7 @@ outliers_ratio_comparison %>%
geom_bar(stat = "identity", aes(fill = above_below)) +
coord_flip() +
geom_text(aes(label = round(percent, 2)), size = 3.2, hjust = -0.2) +
scale_y_continuous(limits = c(0, 1.5)) +
scale_y_continuous(limits = c(0, 1.1 * axis_limit_outlier_ratio_comparison)) +
theme_minimal() +
theme(
axis.title.y = element_blank(),
Expand Down Expand Up @@ -301,7 +308,7 @@ outliers_table_township_summary <- outliers_table_township_summary %>%
`Med. Sale Price` = median(meta_sale_price, na.rm = TRUE),
`Max. Sale Price` = max(meta_sale_price, na.rm = TRUE),
Count = n(),
.by = c(price_outlier_reason, meta_township_name)
.by = c(outlier_reasons_to_graph, meta_township_name)
) %>%
left_join(
outliers_table_township_summary %>%
Expand All @@ -315,7 +322,7 @@ outliers_table_township_summary <- outliers_table_township_summary %>%
mutate(across(contains("Sale"), dollar)) %>%
relocate(meta_township_name) %>%
dplyr::rename(
"Outlier Type" = price_outlier_reason,
"Outlier Type" = outlier_reasons_to_graph,
"Township Name" = meta_township_name
) %>%
arrange(`Township Name`, desc(Count))
Expand Down Expand Up @@ -346,7 +353,7 @@ outliers_table_class_summary <- outliers_table_class_summary %>%
`Med. Sale Price` = median(meta_sale_price, na.rm = TRUE),
`Max. Sale Price` = max(meta_sale_price, na.rm = TRUE),
Count = n(),
.by = c(price_outlier_reason, meta_class)
.by = c(outlier_reasons_to_graph, meta_class)
) %>%
left_join(
outliers_table_class_summary %>%
Expand All @@ -360,7 +367,7 @@ outliers_table_class_summary <- outliers_table_class_summary %>%
mutate(across(contains("Sale"), dollar)) %>%
relocate(meta_class) %>%
dplyr::rename(
"Outlier Type" = price_outlier_reason,
"Outlier Type" = outlier_reasons_to_graph,
"Class" = meta_class
) %>%
arrange(`Class`, desc(Count))
Expand Down Expand Up @@ -431,7 +438,7 @@ outlier_decile_breakout <- function(data, dec) {
arrange(meta_sale_price) %>%
mutate(decile = ntile(meta_sale_price, 10)) %>%
filter(decile == dec & sv_is_outlier) %>%
group_by(price_outlier_reason) %>%
group_by(outlier_reasons_to_graph) %>%
summarise(count = n()) %>%
ungroup() %>%
slice_max(count, n = 1) %>%
Expand All @@ -441,8 +448,8 @@ outlier_decile_breakout <- function(data, dec) {
arrange(meta_sale_price) %>%
mutate(decile = ntile(meta_sale_price, 10)) %>%
filter(decile == dec & sv_is_outlier) %>%
summarise(count = n(), .by = price_outlier_reason) %>%
ggplot(aes(x = reorder(price_outlier_reason, -count), y = count)) +
summarise(count = n(), .by = outlier_reasons_to_graph) %>%
ggplot(aes(x = reorder(outlier_reasons_to_graph, -count), y = count)) +
labs(
y = "Number of Sales",
x = "Outlier Types"
Expand Down
Loading