Introduction

Exploratory data analysis and data visualization on the club goal records of Neymar,Lewndowski, Messi and Ronaldo.

[Source : https://www.kaggle.com/datasets/33a8bd46dd5a788c8aba345d665801614155e6232cb0bf53727c3c6955ea9aaf]

NEYMAR

Interesting Facts :

1. He played for Santos FC, FC Barcelona and Paris Saint-Germain.

2. His highest total goals were against Celtic FC, Stade Rennais FC and Villarreal CF.

3. His best club performances came in the year 2015.

4. Almost 70% of his best performances were on his Home ground.

5. He has a very good chance of scoring between the 65th and 70th minutes of the game.

6. Almost 40% of his goals came from the Right foot while playing on Home ground.

7. He got a maximum goal assist from “Lionel Messi” in the club matches.

Goals by Tournament and Club

#Bar Chart - Goals by Tournament and Club
ggplot(data = Matches_Club_neymar, aes(x=reorder(`Tournament`, -`Total_Goal`) ,
                                       y=`Total_Goal`, 
                                        fill=`Club`))+
   theme_bw()+
   theme(legend.position = "bottom", plot.title = element_text(hjust = 0.5, 
                                                               size = 12))+
   geom_bar(stat = "identity")+
   labs(x = "Tournaments", y = "Total Goals", 
        title = "Goals by Tournament and Club")+
   scale_y_continuous(limits = c(0, 100), breaks = seq(0, 100, by = 10))+
   geom_text(aes(label = `Total_Goal`), size = 4, hjust = 0.5, vjust = -.8, 
             position = "stack", col="black")

Goals by Year and Venue

#Bar Chart - Goals by Year and Venue
ggplot(data = Venue_Goal_neymar, aes(x=`Year` , y=`Total_Goal`, 
                                       ))+
   theme_bw()+
   facet_wrap(~`Venue`)+
   theme(legend.position = "bottom", plot.title = element_text(hjust = 0.5, size = 12))+
   geom_line(stat = "identity", size=.8, color="coral", linetype = "dashed")+
   geom_point()+
   labs(x = "Year", y = "Total Goals", 
        title = "Goals by Year and Venue")+
   scale_y_continuous(limits = c(0, 25), breaks = seq(0, 25, by = 5))+
   scale_x_continuous(breaks = Venue_Goal_neymar$Year)+
   geom_text(aes(label = `Total_Goal`), size = 4, hjust = 0.5, vjust = -.9, 
             position = "stack", col="black")

Goals by Minute

#Histogram
neymar_m <- hist(neymar_ttg1$Time_To_Goal, col = "#0099F8",border = "black", 
          xlim = c(0,100), ylim = c(0,30),breaks = 20,
          xlab = "Time to Goal", ylab = "Count", main = " ")
text(neymar_m$mids, neymar_m$counts, labels = neymar_m$counts,
     adj = c(0.6, -0.6))

Goal by Goal Type

ggplot(data = neymar_Goal_Venue,aes(x=reorder(`Goal Type`,`Total Goal`) , y=`Total Goal`, 
                                 fill=`Goal Type`))+
   facet_wrap(~`Venue`)+
   theme_bw()+
   theme(legend.position = " ", plot.title = element_text(hjust = 0.5, size = 12))+
   geom_bar(stat = "identity", position = "dodge", col="black")+
   labs(x = "Goal Type", y = "Total Goals", 
        title = "Goals by Goal Type")+
   scale_y_continuous(limits = c(0, 80), breaks = seq(0, 80, by = 10))+
   geom_text(aes(label = `Total Goal`), size = 4, hjust = -0.5, vjust = .25, 
             position = "identity", col="black")+
   coord_flip()

Top 10 Assist

ggplot(data = neymar_Goal_Assist, aes(x=reorder(`Assist`, -`Total Goal`) ,
                                       y=`Total Goal`, 
                                       fill=`Venue`))+
   theme_bw()+
   theme(legend.position = "right", plot.title = element_text(hjust = 0.5, 
                                                               size = 12))+
   geom_bar(stat = "identity", position = "dodge")+
   labs(x = "Assist", y = "Total Goals", 
        title = "Top 10 Assists")+
   scale_y_continuous(limits = c(0, 100), breaks = seq(0, 100, by = 10))+
   geom_text(aes(label = `Total Goal`), size = 4, hjust = 0.5, vjust = -.8, 
             position = position_dodge(0.9), col="black")

Top 20 Goals by Opponent

ggplot(data = neymar_Max_Goals, aes(x=reorder(`Opponent`, -`Total Goal`) ,
                                      y=`Total Goal`, 
                                      fill=`Venue`))+
   facet_wrap(~`Venue`)+
   theme_bw()+
   theme(legend.position = "right", plot.title = element_text(hjust = 0.5, 
                                                              size = 12))+
   geom_bar(stat = "identity", position = "dodge")+
   labs(x = "Opponent", y = "Total Goals", 
        title = "Top 20 Goals By Opponent")+
   scale_y_continuous(limits = c(0, 10), breaks = seq(0, 10, by = 5))+
   geom_text(aes(label = `Total Goal`), size = 4, hjust = -0.5, vjust = .25, 
             position = position_dodge(0.9), col="black")+
   coord_flip()

LEWANDOWSKI

Interesting Facts :

1. He played for Bayern Munich, Borussia Dortmund, FC Barcelona, Lech Poznan and Znicz Pruszkow.

2. His highest total goals were against Borussia Dortmund.

3. His best club performances came in the year 2021.

4. Almost 65% of his best performances were on the Home ground.

5. He has a very high probability of scoring between the 50th to 55th minutes of the match.

6. While playing on home turf, he scored most of his goals with right foot shots followed by headers.

7. He holds the record of scoring goals even between the 95th and 100th minutes of the match (during additional time).

Goals by Tournament and Club

#Bar Chart - Goals by Tournament and Club
ggplot(data = Matches_Club_lewan, aes(x=reorder(`Tournament`, -`Total_Goal`) ,
                                       y=`Total_Goal`, 
                                       fill=`Club`))+
  theme_bw()+
  theme(legend.position = "bottom", plot.title = element_text(hjust = 0.5, 
                                                              size = 12))+
  geom_bar(stat = "identity")+
  labs(x = "Tournaments", y = "Total Goals", 
       title = "Goals by Tournament and Club")+
  scale_y_continuous(limits = c(0, 100), breaks = seq(0, 100, by = 10))+
  geom_text(aes(label = `Total_Goal`), size = 4, hjust = 0.5, vjust = -.8, 
            position = "stack", col="black")

Goals by Year and Venue

#Bar Chart - Goals by lewan_Year and Venue
ggplot(data = Venue_Goal_lewan, aes(x=`lewan_Year` , y=`Total_Goal`, 
))+
  theme_bw()+
  facet_wrap(~`Venue`)+
  theme(legend.position = "bottom", plot.title = element_text(hjust = 0.5, size = 12))+
  geom_line(stat = "identity", size=.8, color="coral", linetype = "dashed")+
  geom_point()+
  labs(x = "Year", y = "Total Goals", 
       title = "Goals by Year and Venue")+
  scale_y_continuous(limits = c(0, 35), breaks = seq(0, 35, by = 5))+
  scale_x_continuous(breaks = Venue_Goal_lewan$lewan_Year)+
  geom_text(aes(label = `Total_Goal`), size = 4, hjust = 0.5, vjust = -.9, 
            position = "stack", col="black")

Goals by Minute

lewan_m <- hist(lewan_ttg1$Time_To_Goal, col = "#0099F8",border = "black", 
                 xlim = c(0,100), ylim = c(0,40),breaks = 20,
                 xlab = "Time to Goal", ylab = "Count", main = " ")

text(lewan_m$mids, lewan_m$counts, labels = lewan_m$counts,
     adj = c(0.6, -0.6))

Goal by Goal Type

ggplot(data = lewan__Goal_Venue,aes(x=reorder(`Goal Type`,`Total Goal`) , y=`Total Goal`, 
                                    fill=`Goal Type`))+
  facet_wrap(~`Venue`)+
  theme_bw()+
  theme(legend.position = " ", plot.title = element_text(hjust = 0.5, size = 12))+
  geom_bar(stat = "identity", position = "dodge", col="black")+
  labs(x = "Goal Type", y = "Total Goals", 
       title = "Goals by Goal Type")+
  scale_y_continuous(limits = c(0, 150), breaks = seq(0, 150, by = 10))+
  geom_text(aes(label = `Total Goal`), size = 4, hjust = -0.5, vjust = .25, 
            position = "identity", col="black")+
  coord_flip()

Top 10 Assist

#Chart - Top 10 Assist
ggplot(data = lewan_Goal_Assist, aes(x=reorder(`Assist`, -`Total Goal`) ,
                                      y=`Total Goal`, 
                                      fill=`Venue`))+
  theme_bw()+
  theme(legend.position = "right", plot.title = element_text(hjust = 0.5, 
                                                             size = 12))+
  geom_bar(stat = "identity", position = "dodge")+
  labs(x = "Assist", y = "Total Goals", 
       title = "Top 10 Assists")+
  scale_y_continuous(limits = c(0, 100), breaks = seq(0, 100, by = 10))+
  geom_text(aes(label = `Total Goal`), size = 4, hjust = 0.5, vjust = -.8, 
            position = position_dodge(0.9), col="black")

Top 20 Goals by Opponent

ggplot(data = lewan_Max_Goals, aes(x=reorder(`Opponent`, -`Total Goal`) ,
                                    y=`Total Goal`, 
                                    fill=`Venue`))+
  facet_wrap(~`Venue`)+
  theme_bw()+
  theme(legend.position = "right", plot.title = element_text(hjust = 0.5, 
                                                             size = 12))+
  geom_bar(stat = "identity", position = "dodge")+
  labs(x = "Opponent", y = "Total Goals", 
       title = "Top 20 Goals By Opponent")+
  scale_y_continuous(limits = c(0, 20), breaks = seq(0, 20, by = 5))+
  geom_text(aes(label = `Total Goal`), size = 4, hjust = -0.5, vjust = .25, 
            position = position_dodge(0.9), col="black")+
  coord_flip()

MESSI

Interesting Facts :

1. He played for FC Barcelona and Paris Saint-Germain.

2. His highest total goal was against Sevilla FC.

3. His best club performances came in the year 2012.

4. More than 90% of his goals came while playing in the ‘Center Forward’ or ‘Right Wing’ position.

5. He has a very good chance of scoring between the 85th and 90th minutes of the game.

6. He scored nearly 60% of his home goals with his left foot.

7. He never scored a direct free-kick goal while playing for Paris Saint-Germain..

Goals by Tournament and Club

#Bar Chart - Goals by Tournament and Club
ggplot(data = Matches_Club_messi, aes(x=reorder(`Tournament`, -`Total_Goal`) ,
                                      y=`Total_Goal`, 
                                      fill=`Club`))+
  theme_bw()+
  theme(legend.position = "bottom", plot.title = element_text(hjust = 0.5, 
                                                              size = 12))+
  geom_bar(stat = "identity")+
  labs(x = "Tournaments", y = "Total Goals", 
       title = "Goals by Tournament and Club")+
  scale_y_continuous(limits = c(0, 100), breaks = seq(0, 100, by = 10))+
  geom_text(aes(label = `Total_Goal`), size = 4, hjust = 0.5, vjust = -.8, 
            position = "stack", col="black")

Goals by Year and Venue

#Bar Chart - Goals by messi_Year and Venue
ggplot(data = Venue_Goal_messi, aes(x=`messi_Year` , y=`Total_Goal`, 
))+
  theme_bw()+
  facet_wrap(~`Venue`)+
  theme(legend.position = "bottom", plot.title = element_text(hjust = 0.5, size = 12))+
  geom_line(stat = "identity", size=.8, color="coral", linetype = "dashed")+
  geom_point()+
  labs(x = "Year", y = "Total Goals", 
       title = "Goals by Year and Venue")+
  scale_y_continuous(limits = c(0, 50), breaks = seq(0, 50, by = 5))+
  scale_x_continuous(breaks = Venue_Goal_messi$messi_Year)+
  geom_text(aes(label = `Total_Goal`), size = 4, hjust = 0.5, vjust = -.9, 
            position = "stack", col="black")

Goals by Minute

#Histogram
messi_m <- hist(messi_ttg1$Time_To_Goal, col = "#0099F8",border = "black", 
                xlim = c(0,100), ylim = c(0,80),breaks = 20,
                xlab = "Time to Goal", ylab = "Count", main = " ")

text(messi_m$mids, messi_m$counts, labels = messi_m$counts,
     adj = c(0.6, -0.6))

Goal by Goal Type

ggplot(data = messi_goal_Venue,aes(x=reorder(`Goal Type`,`Total Goal`) , y=`Total Goal`, 
                                    fill=`Goal Type`))+
  facet_wrap(~`Venue`)+
  theme_bw()+
  theme(legend.position = " ", plot.title = element_text(hjust = 0.5, size = 12))+
  geom_bar(stat = "identity", position = "dodge", col="black")+
  labs(x = "Goal Type", y = "Total Goals", 
       title = "Goals by Goal Type")+
  scale_y_continuous(limits = c(0, 300), breaks = seq(0, 300, by = 25))+
  geom_text(aes(label = `Total Goal`), size = 4, hjust = -0.5, vjust = .25, 
            position = "identity", col="black")+
  coord_flip()

Top 10 Assist

#Chart - Top 10 Assist
ggplot(data = messi_goal_Assist, aes(x=reorder(`Assist`, -`Total Goal`) ,
                                     y=`Total Goal`, 
                                     fill=`Venue`))+
  theme_bw()+
  theme(legend.position = "right", plot.title = element_text(hjust = 0.5, 
                                                             size = 12))+
  geom_bar(stat = "identity", position = "dodge")+
  labs(x = "Assist", y = "Total Goals", 
       title = "Top 10 Assists")+
  scale_y_continuous(limits = c(0, 150), breaks = seq(0, 150, by = 20))+
  geom_text(aes(label = `Total Goal`), size = 4, hjust = 0.5, vjust = -.8, 
            position = position_dodge(0.9), col="black")

Top 20 Goals by Opponent

ggplot(data = messi_Max_Goals, aes(x=reorder(`Opponent`, -`Total Goal`) ,
                                   y=`Total Goal`, 
                                   fill=`Venue`))+
  facet_wrap(~`Venue`)+
  theme_bw()+
  theme(legend.position = "right", plot.title = element_text(hjust = 0.5, 
                                                             size = 12))+
  geom_bar(stat = "identity", position = "dodge")+
  labs(x = "Opponent", y = "Total Goals", 
       title = "Top 20 Goals By Opponent")+
  scale_y_continuous(limits = c(0, 30), breaks = seq(0, 30, by = 5))+
  geom_text(aes(label = `Total Goal`), size = 4, hjust = -0.5, vjust = .25, 
            position = position_dodge(0.9), col="black")+
  coord_flip()

RONALDO

Interesting Facts:

1. He played for Juventus FC, Manchester United, Real Madrid and Sporting CP.

3. His club performances were in peak between the year 2012 and year 2015.

2. His highest total goal was against Sevilla FC.

3. More than 90% of his goals came while playing in the ‘Center Forward’ or ‘Left Wing’ position. ’

4. He has a very highest probability of scoring between the 85th and 90th Minute of the match.

5. Almost half of his home goals were scored with his right foot or through penalties.

6. He holds the record of scoring goals even between the 100th and 110th minutes of the match (during additional time).

Goals by Tournament and Club

#Bar Chart - Goals by Tournament and Club
ggplot(data = Matches_Club_ronaldo, aes(x=reorder(`Tournament`, -`Total_Goal`) ,
                                      y=`Total_Goal`, 
                                      fill=`Club`))+
  theme_bw()+
  theme(legend.position = "bottom", plot.title = element_text(hjust = 0.5, 
                                                              size = 12))+
  geom_bar(stat = "identity")+
  labs(x = "Tournaments", y = "Total Goals", 
       title = "Goals by Tournament and Club")+
  scale_y_continuous(limits = c(0, 350), breaks = seq(0, 350, by = 50))+
  geom_text(aes(label = `Total_Goal`), size = 4, hjust = 0.5, vjust = -.8, 
            position = "stack", col="black")

Goals by Year and Venue

#Bar Chart - Goals by ronaldo_Year and Venue
ggplot(data = Venue_Goal_ronaldo, aes(x=`ronaldo_Year` , y=`Total_Goal`, 
))+
  theme_bw()+
  facet_wrap(~`Venue`)+
  theme(legend.position = "bottom", plot.title = element_text(hjust = 0.5, size = 12))+
  geom_line(stat = "identity", size=.8, color="coral", linetype = "dashed")+
  geom_point()+
  labs(x = "Year", y = "Total Goals", 
       title = "Goals by Year and Venue")+
  scale_y_continuous(limits = c(0, 40), breaks = seq(0, 40, by = 5))+
  scale_x_continuous(breaks = Venue_Goal_ronaldo$ronaldo_Year)+
  geom_text(aes(label = `Total_Goal`), size = 4, hjust = 0.5, vjust = -.9, 
            position = "stack", col="black")

Goals by Minute

#Histogram
ronaldo_m <- hist(ronaldo_ttg1$Time_To_Goal, col = "#0099F8",border = "black", 
                xlim = c(0,120), ylim = c(0,80),breaks = 20,
                xlab = "Time to Goal", ylab = "Count", main = " ")

text(ronaldo_m$mids, ronaldo_m$counts, labels = ronaldo_m$counts,
     adj = c(0.6, -0.6))

Goal by Goal Type

ggplot(data = ronaldo_goal_Venue,aes(x=reorder(`Goal Type`,`Total Goal`) , y=`Total Goal`, 
                                   fill=`Goal Type`))+
  facet_wrap(~`Venue`)+
  theme_bw()+
  theme(legend.position = " ", plot.title = element_text(hjust = 0.5, size = 12))+
  geom_bar(stat = "identity", position = "dodge", col="black")+
  labs(x = "Goal Type", y = "Total Goals", 
       title = "Goals by Goal Type")+
  scale_y_continuous(limits = c(0, 150), breaks = seq(0, 150, by = 10))+
  geom_text(aes(label = `Total Goal`), size = 4, hjust = -0.5, vjust = .25, 
            position = "identity", col="black")+
  coord_flip()

Top 10 Assist

#Chart - Top 10 Assist
ggplot(data = ronaldo_Goal_Assist, aes(x=reorder(`Assist`, -`Total Goal`) ,
                                     y=`Total Goal`, 
                                     fill=`Venue`))+
  theme_bw()+
  theme(legend.position = "right", plot.title = element_text(hjust = 0.5, 
                                                             size = 12))+
  geom_bar(stat = "identity", position = "dodge")+
  labs(x = "Assist", y = "Total Goals", 
       title = "Top 10 Assists")+
  scale_y_continuous(limits = c(0, 160), breaks = seq(0, 160, by = 20))+
  geom_text(aes(label = `Total Goal`), size = 4, hjust = 0.5, vjust = -.8, 
            position = position_dodge(0.9), col="black")

Top 20 Goals by Opponent

ggplot(data = ronaldo_Max_Goals, aes(x=reorder(`Opponent`, -`Total Goal`) ,
                                   y=`Total Goal`, 
                                   fill=`Venue`))+
  facet_wrap(~`Venue`)+
  theme_bw()+
  theme(legend.position = "right", plot.title = element_text(hjust = 0.5, 
                                                             size = 12))+
  geom_bar(stat = "identity", position = "dodge")+
  labs(x = "Opponent", y = "Total Goals", 
       title = "Top 20 Goals By Opponent")+
  scale_y_continuous(limits = c(0, 20), breaks = seq(0, 20, by = 5))+
  geom_text(aes(label = `Total Goal`), size = 4, hjust = -0.5, vjust = .25, 
            position = position_dodge(0.9), col="black")+
  coord_flip()