Week 7: Apply it to your data 6

Import Data

data <- read_excel("../00_data/Raw data Roundabout.xlsx")

# Display the actual column names
names(data)

##  [1] "name"                  "address"               "town_city"            
##  [4] "county_area"           "state_region"          "country"              
##  [7] "lat"                   "long"                  "type"                 
## [10] "status"                "year_completed"        "approaches"           
## [13] "driveways"             "lane_type"             "functional_class"     
## [16] "control_type"          "other_control_type"    "previous_control_type"

# Display the first few rows
glimpse(data)

## Rows: 27,887
## Columns: 18
## $ name                  <chr> "Arapahoe Ave. / 4th St.", "Arapahoe Ave. / 5th …
## $ address               <chr> "Boulder, Boulder Co., CO (United States)", "Bou…
## $ town_city             <chr> "Boulder", "Boulder", "Belmar", "Belmar", "Seatt…
## $ county_area           <chr> "Boulder Co.", "Boulder Co.", "Monmouth Co.", "M…
## $ state_region          <chr> "CO", "CO", "NJ", "NJ", "WA", "WA", "WA", "WA", …
## $ country               <chr> "United States", "United States", "United States…
## $ lat                   <dbl> -105.29160, -105.28920, -74.01782, -74.02169, -1…
## $ long                  <dbl> 40.01294, 40.01295, 40.17772, 40.17855, 47.65796…
## $ type                  <chr> "Traffic Calming Circle", "Traffic Calming Circl…
## $ status                <chr> "Existing", "Existing", "Existing", "Existing", …
## $ year_completed        <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 1997, 0, 0, 0, 0, 2012, …
## $ approaches            <dbl> 3, 3, 4, 4, 0, 0, 0, 0, 4, 0, 0, 0, 0, 4, 0, 0, …
## $ driveways             <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, …
## $ lane_type             <chr> "Single-Lane", "Single-Lane", "Single-Lane", "Si…
## $ functional_class      <chr> "Other (At-Grade)", "Other (At-Grade)", "Other (…
## $ control_type          <chr> "One-Way/Two-Way Stop", "One-Way/Two-Way Stop", …
## $ other_control_type    <chr> "None", "None", "Unknown", "Unknown", "Unknown",…
## $ previous_control_type <chr> "Unknown", "Unknown", "Unknown", "Unknown", "Unk…

Introduction

Questions

Variation

Visualizing distributions

data %>%
    filter(year_completed > 0) %>%
    ggplot(aes(x = year_completed)) +
    geom_histogram(binwidth = 5)

data %>%
    filter(year_completed > 0, year_completed < 2020) %>%
    ggplot(aes(x = year_completed)) +
    geom_histogram(binwidth = 5)

data %>%
    ggplot(aes(x = approaches, color = type)) +
    geom_freqpoly()

## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.

Typical values

data %>%
    filter(year_completed > 0) %>%
    ggplot(aes(x = year_completed)) +
    geom_histogram(binwidth = 1)

data %>%
    ggplot(aes(x = approaches)) +
    geom_histogram(binwidth = 1)

Unusual values

data %>%
    ggplot(aes(x = approaches)) +
    geom_histogram()

## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.

data %>%
    ggplot(aes(x = approaches)) +
    geom_histogram() +
    coord_cartesian(xlim = c(0, 10))

## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.

Missing Values

data %>%
    mutate(year_completed = ifelse(year_completed == 0, NA, year_completed)) %>%
    ggplot(aes(x = year_completed, y = approaches)) +
    geom_point()

## Warning: Removed 16367 rows containing missing values or values outside the scale range
## (`geom_point()`).

Covariation

A categorical and continuous variable

data %>%
    ggplot(aes(x = type, y = approaches)) +
    geom_boxplot()

Two categorical variables

data %>%
    count(type, approaches) %>%
    ggplot(aes(x = type, y = factor(approaches), fill = n)) +
    geom_tile()

Two continous variables

data %>%
    filter(year_completed > 0) %>%
    ggplot(aes(x = year_completed, y = approaches)) +
    geom_point()

data %>%
    filter(year_completed > 0) %>%
    ggplot(aes(x = year_completed, y = approaches)) +
    geom_boxplot(aes(group = cut_width(year_completed, 5)))

## Warning: Orientation is not uniquely specified when both the x and y aesthetics are
## continuous. Picking default orientation 'x'.

Patterns and models

mod <- lm(approaches ~ year_completed,
          data = data %>% filter(year_completed > 0))

roundabouts4 <- data %>%
    filter(year_completed > 0) %>%
    modelr::add_residuals(mod)

roundabouts4 %>%
    ggplot(aes(year_completed, resid)) +
    geom_point()

roundabouts4 %>%
    ggplot(aes(type, resid)) +
    geom_boxplot()