Week 7: Apply it to your data 6

Import data

cats <- read_csv("../00_data/MKmyData1.csv")

## Rows: 101 Columns: 17
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (8): id.on.tag, animal.name, scientific.name, tag.deployment.start, tag....
## dbl (5): Column1, prey.per.month, hours.indoor.per.day, cats.in.house, age
## lgl (4): hunt, dry.food, wet.food, other.food
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

cats

## # A tibble: 101 × 17
##    Column1 id.on.tag    animal.name scientific.name tag.deployment.start
##      <dbl> <chr>        <chr>       <chr>           <chr>               
##  1       1 Tommy-Tag    Tommy       Felis catus     6/3/17 1:02         
##  2       2 Athena       Athena      Felis catus     6/24/17 1:02        
##  3       3 Ares         Ares        Felis catus     6/24/17 1:03        
##  4       4 Lola         Lola        Felis catus     6/24/17 1:18        
##  5       5 Maverick     Maverick    Felis catus     6/25/17 1:04        
##  6       6 Coco         Coco        Felis catus     6/28/17 1:02        
##  7       7 Charlie      Charlie     Felis catus     6/28/17 1:03        
##  8       8 Jago         Jago        Felis catus     6/28/17 4:10        
##  9       9 Morpheus-Tag Morpheus    Felis catus     7/1/17 1:02         
## 10      10 Nettle-Tag   Nettle      Felis catus     7/1/17 1:05         
## # ℹ 91 more rows
## # ℹ 12 more variables: tag.deployment.end <chr>, hunt <lgl>,
## #   prey.per.month <dbl>, reproductive.condition <chr>, sex <chr>,
## #   hours.indoor.per.day <dbl>, cats.in.house <dbl>, dry.food <lgl>,
## #   wet.food <lgl>, other.food <lgl>, study.location <chr>, age <dbl>

Introduction

Variation

Visualizing distributions

ggplot(data = cats) +
    geom_bar(mapping = aes(x = reproductive.condition))

cats %>% count(reproductive.condition)

## # A tibble: 4 × 2
##   reproductive.condition     n
##   <chr>                  <int>
## 1 Neutered                  55
## 2 Not fixed                  2
## 3 Spayed                    41
## 4 <NA>                       3

ggplot(data = cats) +
  geom_histogram(mapping = aes(x = age))

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

## Warning: Removed 1 rows containing non-finite values (`stat_bin()`).

ggplot(data = cats, mapping = aes(x = age, colour = reproductive.condition)) +
  geom_freqpoly()

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

## Warning: Removed 1 rows containing non-finite values (`stat_bin()`).

Typical values

ggplot(data = cats, mapping = aes(x = cats.in.house)) +
  geom_histogram()

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

Unusual values

ggplot(cats) + 
  geom_histogram(mapping = aes(x = prey.per.month), binwidth = 6)

Missing Values

cats2 <- cats %>% 
  mutate(y = ifelse(age < 3 | age > 15, NA, age))

ggplot(data = cats2, mapping = aes(x = age, y = reproductive.condition)) + 
  geom_point(na.rm = TRUE)

Covariation

A categorical and continuous variable

ggplot(data = cats, mapping = aes(x = age)) + 
  geom_freqpoly(mapping = aes(colour = reproductive.condition), binwidth = 0.75)

## Warning: Removed 1 rows containing non-finite values (`stat_bin()`).

ggplot(cats) + 
  geom_bar(mapping = aes(x = reproductive.condition))

ggplot(data = cats, mapping = aes(x = reproductive.condition, y = age)) +
  geom_boxplot()

## Warning: Removed 1 rows containing non-finite values (`stat_boxplot()`).

Two categorical variables

ggplot(data = cats) +
  geom_count(mapping = aes(x = reproductive.condition, y = sex))

cats %>% 
  count(reproductive.condition, sex) %>%  
  ggplot(mapping = aes(x = reproductive.condition, y = sex)) +
    geom_tile(mapping = aes(fill = n))

Two continous variables

ggplot(data = cats) +
  geom_point(mapping = aes(x = age, y = prey.per.month))

## Warning: Removed 1 rows containing missing values (`geom_point()`).

ggplot(data = cats) +
  geom_point(mapping = aes(x = age, y = prey.per.month), alpha = 1/5)

## Warning: Removed 1 rows containing missing values (`geom_point()`).

ggplot(data = cats) +
  geom_bin2d(mapping = aes(x = age, y = prey.per.month))

## Warning: Removed 1 rows containing non-finite values (`stat_bin2d()`).

ggplot(data = cats) +
  geom_hex(mapping = aes(x = age, y = prey.per.month))

## Warning: Removed 1 rows containing non-finite values (`stat_binhex()`).

ggplot(data = cats, mapping = aes(x = age, y = prey.per.month)) + 
  geom_boxplot(mapping = aes(group = cut_width(age, 0.1)))

## Warning: Removed 1 rows containing missing values (`stat_boxplot()`).

Patterns and models

ggplot(data = cats) + 
  geom_point(mapping = aes(x = age, y = hours.indoor.per.day))

## Warning: Removed 1 rows containing missing values (`geom_point()`).

Comment

There is no true patterns or relationships with the numerical variables