Baseball Data Sources

• 2015 Lahman Baseball data (1871 - 2014) is available at - http://www.seanlahman.com/baseball-archive/statistics/
• library(lahman) (? - 2013)

# Loading data
batting_df = tbl_df(Batting)
person_df = tbl_df(Master)
series_df = tbl_df(SeriesPost)
teams_df = tbl_df(Teams)
pitching_df = tbl_df(Pitching)

about Home Runs …

# Top 5 all-time players in MLB history who have hit most home runs
batting_df %>%  
  count(playerID, wt = HR, sort = TRUE) %>%
  head(5) %>%
  left_join(
    person_df %>%
      select(playerID, nameFirst, nameLast), 
    by='playerID') %>%
  select('First Name'=nameFirst, 'Last Name'=nameLast, 
         'Total HRs'=n) %>%
  kable(row.names=FALSE, 
      padding = 2, align='c')

about Home Runs with Seasons …

# Top 5 all-time players in MLB history who have hit most home runs
# add season information
batting_df %>%
  select(playerID, HR, stint) %>%
  group_by(playerID) %>%
  summarise(Total_HR = sum(HR), Seasons = sum(stint==1L)) %>% 
  arrange(desc(Total_HR)) %>%
  head(5) %>%
  left_join(
    person_df %>%
      select(playerID, nameFirst, nameLast), 
    by='playerID') %>%
  select('First Name'=nameFirst, 'Last Name'=nameLast, 
         'Total HRs'=Total_HR, 'Seasons'=Seasons) %>% 
  kable(row.names=FALSE, 
      padding = 2, align='c')

about Scored Runs …

# Top 5 all-time players in MLB history who have most scored runs
batting_df %>%  
  count(playerID, wt = R, sort = TRUE) %>%
  head(5) %>%
  left_join(
    person_df %>%
      select(playerID, nameFirst, nameLast), 
    by='playerID') %>%
  select('First Name'=nameFirst, 'Last Name'=nameLast, 
         'Total Runs'=n) %>%
  kable(row.names=FALSE, 
      padding = 2, align='c')

about Batting Average …

# Top 5 all-time players in MLB history who have highest batting average
# under the conditions - show up more than 1000 games and 1000 at bats
batting_df %>% 
  select(playerID, H, AB, G) %>%
  group_by(playerID) %>%
  summarise(
    Games = sum(G, na.rm=TRUE),
    AtBats = sum(AB, na.rm=TRUE),
    BA = round((sum(H, na.rm=TRUE) / sum(AB, na.rm=TRUE)), 3)
  ) %>%
  filter(Games > 1000, AtBats > 1000) %>% 
  select(playerID, BA) %>%
  arrange(desc(BA)) %>%
  head(5) %>%
  left_join(
    person_df %>%
      select(playerID, nameFirst, nameLast), 
    by='playerID') %>%
  select('First Name'=nameFirst, 'Last Name'=nameLast, 
         'Batting Average'=BA) %>% 
  kable(row.names=FALSE, 
      padding = 2, align='c')

about Consecutive Seasons …

# Top 5 all-time players in MLB history who have played most consecutive seasons
batting_df %>%  
  count(playerID, wt = (stint==1L), sort = TRUE) %>%
  #  filter(rank(desc(n),ties.method='first') <= 5) %>% # same as row_number()
  filter(row_number(desc(n)) <= 5) %>%
  left_join(
    person_df %>%
      select(playerID, nameFirst, nameLast), 
    by='playerID') %>%
  select('First Name'=nameFirst, 'Last Name'=nameLast, 
         'Consecutive Seasons'=n) %>%
  kable(row.names=FALSE, 
        padding = 2, align='c')

about Strikeouts …

# Top 5 all-time players in MLB history who have most strikeouts
pitching_df %>%
  count(playerID, wt=SO, sort=T) %>%
  head(5) %>%
  left_join(
    person_df %>%
      select(playerID, nameFirst, nameLast), 
    by='playerID') %>%
  select('First Name'=nameFirst, 'Last Name'=nameLast, 
         'Total Strikeouts'=n) %>%
  kable(row.names=FALSE, 
        padding = 2, align='c')  

about Strikeouts with Seasons …

# Top 5 all-time players in MLB history who have most strikeouts
# add seasons information
pitching_df %>%
  select(playerID, SO, stint) %>%
  group_by(playerID) %>%
  summarise(Total_Strikeouts = sum(SO), Seasons = sum(stint==1L)) %>%
  arrange(desc(Total_Strikeouts)) %>%
  head(5) %>%
  left_join(
    person_df %>%
      select(playerID, nameFirst, nameLast), 
    by='playerID') %>%
  select('First Name'=nameFirst, 'Last Name'=nameLast, 
         'Total Strikeouts'=Total_Strikeouts, Seasons) %>%
  kable(row.names=FALSE, 
        padding = 2, align='c')  

about Teams in 2014 …

# How many teams are in MLB in 2014?
teams_df %>%
  filter(yearID==2014) %>%
  select(teamID) %>%
  distinct() %>%
  summarize('Total Teams'=n()) %>%
  kable(row.names=FALSE, 
        padding = 2, align='c') 

about Champions with Leagues …

# How many World Series Titles have been won by each League?
series_df %>%
  filter(round=='WS') %>%
  group_by(League=lgIDwinner) %>%
  summarize('Champions'=n()) %>%
  kable(row.names=FALSE, 
        padding = 2, align='c')  

about Champions with Teams …

# Top 15 Teams in MLB history have won the most World Series Titles
series_df %>%
  filter(round=='WS') %>%
  group_by(teamIDwinner) %>%
  summarize(Champs=n(), FirstYear=min(yearID), 
            LastYear=max(yearID)) %>%
  arrange(desc(Champs)) %>%
  head(15) %>%
  left_join (
    teams_df %>%
      select(yearID, teamID, name),
    by = c("teamIDwinner"="teamID", "LastYear"="yearID")
  ) %>%
  select('Team Name'=name, 'Champions'=Champs, 
         'First Year'=FirstYear, 'Last Year'=LastYear) %>%
  kable(row.names=FALSE, 
        padding = 2, align='c')