Import data
# excel file
data <- read_excel("../00_data/myData_charts.xlsx", sheet = "myData", skip = 1)
## New names:
## • `` -> `...1`
data
## # A tibble: 195 × 18
## ...1 Breed Affec…¹ Good …² Good …³ Shedd…⁴ Coat …⁵ Drool…⁶ Coat …⁷ Coat …⁸
## <dbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr> <chr>
## 1 167 Plott … 0 0 0 0 0 0 Plott … Plott …
## 2 6 Poodles 5 5 3 1 NA 1 Curly Long
## 3 13 Yorksh… 5 5 3 1 5 1 Silky Long
## 4 20 Shih T… 5 5 5 1 4 1 Double Long
## 5 38 Maltese 5 3 3 1 4 1 Silky Long
## 6 45 Bichon… 5 5 5 1 5 1 Double Long
## 7 58 Soft C… 5 5 3 1 4 2 Wavy Medium
## 8 62 Aireda… 3 3 3 1 3 1 Wiry Short
## 9 78 Lhasa … 5 3 3 1 3 1 Silky Long
## 10 79 Chines… 4 3 3 1 2 1 Hairle… Short
## # … with 185 more rows, 8 more variables: `Openness To Strangers` <dbl>,
## # `Playfulness Level` <dbl>, `Watchdog/Protective Nature` <dbl>,
## # `Adaptability Level` <dbl>, `Trainability Level` <dbl>,
## # `Energy Level` <dbl>, `Barking Level` <dbl>,
## # `Mental Stimulation Needs` <dbl>, and abbreviated variable names
## # ¹`Affectionate With Family`, ²`Good With Young Children`,
## # ³`Good With Other Dogs`, ⁴`Shedding Level`, ⁵`Coat Grooming Frequency`, …
data <- data %>%
janitor::clean_names()
Introduction
Questions
Variation
Visualizing distributions
data %>%
ggplot(aes(x = shedding_level)) +
geom_histogram(binwidth = 0.5)
Typical values
data %>%
# Filter out shedding level > 2
filter(shedding_level > 2) %>%
# Plot
ggplot(aes(x = shedding_level)) +
geom_histogram(binwidth = 0.4)
Unusual values
Missing Values
Covariation
data %>%
ggplot (aes(x = shedding_level, y = coat_grooming_frequency))
A categorical and continuous variable
data %>%
count(shedding_level, coat_grooming_frequency) %>%
ggplot(aes(x = shedding_level, y = coat_grooming_frequency, fill = n)) +
geom_tile()
## Warning: Removed 1 rows containing missing values (geom_tile).
Two categorical variables
Two continous variables
Patterns and models