Week 7: Apply it to your data 6

Import Data

# excel file
soccer <- read_excel("../00_data/mydata.xlsx")
soccer

## # A tibble: 380 × 22
##    Date      HomeTeam AwayTeam  FTHG  FTAG FTR    HTHG  HTAG HTR   Referee    HS
##    <chr>     <chr>    <chr>    <dbl> <dbl> <chr> <dbl> <dbl> <chr> <chr>   <dbl>
##  1 13/08/20… Brentfo… Arsenal      2     0 H         1     0 H     M Oliv…     8
##  2 14/08/20… Man Uni… Leeds        5     1 H         1     0 H     P Tier…    16
##  3 14/08/20… Burnley  Brighton     1     2 A         1     0 H     D Coote    14
##  4 14/08/20… Chelsea  Crystal…     3     0 H         2     0 H     J Moss     13
##  5 14/08/20… Everton  Southam…     3     1 H         0     1 A     A Madl…    14
##  6 14/08/20… Leicest… Wolves       1     0 H         1     0 H     C Paws…     9
##  7 14/08/20… Watford  Aston V…     3     2 H         2     0 H     M Dean     13
##  8 14/08/20… Norwich  Liverpo…     0     3 A         0     1 A     A Marr…    14
##  9 15/08/20… Newcast… West Ham     2     4 A         2     1 H     M Atki…    17
## 10 15/08/20… Tottenh… Man City     1     0 H         0     0 D     A Tayl…    13
## # ℹ 370 more rows
## # ℹ 11 more variables: AS <dbl>, HST <dbl>, AST <dbl>, HF <dbl>, AF <dbl>,
## #   HC <dbl>, AC <dbl>, HY <dbl>, AY <dbl>, HR <dbl>, AR <dbl>

Introduction

Questions

Variation

Visualizing distributions

soccer %>%
    ggplot(aes(x = FTR)) +
    geom_bar()

soccer %>%
    ggplot(mapping = aes(x = HS)) +
    geom_histogram(binwidth = 1)

soccer %>%
    filter(HS < 25) %>%
    ggplot(aes(x = HS)) +
    geom_histogram(binwidth = 1)

soccer %>%
    ggplot(aes(x = HS, color = FTR)) +
    geom_freqpoly()

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

Typical values

soccer %>%
    # Filter out high home shot counts
    filter(HS < 25) %>%
    # Plot
    ggplot(aes(x = HS)) +
    geom_histogram(binwidth = 1)

soccer %>%
    ggplot(aes(x = FTHG)) +
    geom_histogram()

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

Unusual values

soccer %>%
    ggplot(aes(x = AS)) +
    geom_histogram()

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

soccer %>%
    ggplot(aes(x = AS)) +
    geom_histogram() +
    coord_cartesian(ylim = c(0, 50))

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

Missing Values

soccer %>%
    # filter(AS < 0 | AS > 30) %>%
    mutate(AS = ifelse(AS < 0 | AS > 30, NA, AS)) %>%
    # Plot
    ggplot(aes(x = HS, y = AS)) +
    geom_point()

## Warning: Removed 1 row containing missing values or values outside the scale range
## (`geom_point()`).

Covariation

A categorical and continuous variable

soccer %>%
    ggplot(aes(x = FTR, y = HS)) +
    geom_boxplot()

Two categorical variables

soccer %>%
    count(HomeTeam, FTR) %>%
    ggplot(aes(x = HomeTeam, y = FTR, fill = n)) +
    geom_tile(na.rm = TRUE)

Two continous variables

library(hexbin)
soccer %>%
    ggplot(aes(x = HS, y = AS)) +
    geom_hex()

soccer %>%
    filter(HS < 25) %>%
    ggplot(aes(x = HS, y = AS)) +
    geom_boxplot(aes(group = cut_width(HS, 5)))

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

Patterns and models

library(modelr)
mod <- lm(log(HS) ~ log(AS), data = soccer)

soccer2 <- soccer %>%
    modelr::add_residuals(mod) %>%
    mutate(resid = exp(resid))

soccer2 %>%
    ggplot(aes(AS, resid)) +
    geom_point()

soccer2 %>%
    ggplot(aes(FTR, resid)) +
    geom_boxplot()