The entire code for the blog post

English Football Blog Post Code

#Grouping the matches by season
df_season <- df %>%  #%>% is a special operator which translates to 'then' in English.
group_by(Season) %>%
summarise(HomeGoals = sum(hgoal), AwayGoals = sum(vgoal), HomeWins = sum(result == 'H'), AwayWins = sum(result =='A'), Draws = sum(result == 'D'))

#Grouping the matches by full time scores 
df_scoreline <- df %>%
  group_by(FT) %>%
  summarise(count=n()) %>%
  arrange(desc(count))

#Calculating the total, home and away goals  
total_goals <- sum(df$totgoal)
home_goals <- sum(df$hgoal)
away_goals <- sum(df$vgoal)

# Making plots for Home,Away win percentage and draw percentage
ggplot(df_season, aes(x=Season, y=(HomeWins*100)/(HomeWins+AwayWins+Draws))) +
  geom_point(size = 3,position="jitter") + 
  geom_smooth(stat = "smooth", position = "identity", color="red", size=1.14) + 
  ggtitle("Home Win Percentage")+ 
  xlab("Year")+ 
  ylab("Win Percentage") + 
  theme_gray()

ggplot(df_season, aes(x=Season, y=(AwayWins*100)/(HomeWins+AwayWins+Draws))) +
  geom_point(size = 3,position="jitter") + 
  geom_smooth(stat = "smooth", position = "identity", color="red", size=1.14) + 
  scale_x_continuous(limits=c(1890,2010)) +
  scale_y_continuous(limits=c(15,35))+
  ggtitle("Away Win Percentage")+
  xlab("Year")+ 
  ylab("Win Percentage") + 
  theme_gray()

ggplot(df_season, aes(x=Season, y=(Draws*100)/(HomeWins+AwayWins+Draws))) +
  geom_point(size = 3,position="jitter", color="black") + 
  geom_smooth(stat = "smooth", position = "identity", color="red", size=1.14) + 
  scale_x_continuous(limits=c(1890,2010)) +
  scale_y_continuous(limits=c(15,35))+
  ggtitle("Draw Percentage")+ 
  xlab("Year")+ 
  ylab("Draw Percentage")

# Calculating home and away goals
df_season$AverageHomeGoalsPerGame = df_season$HomeGoals/(df_season$HomeWins + df_season$AwayWins + df_season$Draws)
df_season$AverageAwayGoalsPerGame = df_season$AwayGoals/(df_season$HomeWins + df_season$AwayWins + df_season$Draws)

# Plotting the average home and away goals
ggplot(df_season, aes(x=Season, y=AverageHomeGoalsPerGame)) +
  ggtitle("Average Home Goals")+ 
  xlab("Year") + 
  ylab("Average Goals Per Game") +
  geom_smooth(stat= "identity", color="orange") + 
  scale_x_continuous(limits=c(1890,2010))

ggplot(df_season, aes(x=Season, y=AverageAwayGoalsPerGame)) +
  ggtitle("Average Away Goals")+ 
  xlab("Year") + 
  ylab("Average Goals Per Game") +
  geom_smooth(stat= "identity", color="orange") + 
  scale_x_continuous(limits=c(1890,2010))

#Average Goals per Game  
ggplot(df_season,aes(x=Season, y=AGPG)) +
  scale_x_continuous(limits=c(1890,2010))+
  geom_line(size=2, color="purple") +
  ggtitle("Average Goals Over The Years")+
  ylab("Average Goals Per Game")+
  xlab("Years")