|
|
|
|
|
|
Traceback
| Data | ||
| avg_payroll | 30 obs. of 2 variables | |
| avg_stats_per_year | 148 obs. of 4 variables | |
| avg_std_stats_per_year | 148 obs. of 4 variables | |
| payroll_tab | 858 obs. of 15 variables | |
| result | 30 obs. of 2 variables | |
| spread_payrolls | 30 obs. of 3 variables | |
| standard_payrolls | 30 obs. of 3 variables | |
| Values | ||
| lahman_con | List of 2 | |
| payroll_query | "with total_payroll as\n (SELECT teamID, yearID, sum(salary) as payroll\n FROM Salaries \n GROUP BY teamID, yearID)\n SELECT Teams.teamID, \n Teams.yearID, \n Teams.lgID, \n payroll, \n franchID, \n rank, W,G, ((W*1.0/G)*100) as win_percentage\n FROM total_payroll, Teams\n WHERE total_payroll.yearID = Teams.yearID and\n total_payroll.teamID = Teams.teamID" | |
| query_object | Formal class SQLiteResult | |
| query_result | List of 2 | |
| salary_query | "SELECT yearID, sum(salary) as total_payroll \n FROM Salaries \n WHERE lgID == 'AL'\n GROUP BY yearID" | |
|
|
|
|
|
129:1 |  | Chunk 6: problem2  | R Markdown |
Title
Baseball and the Power of Money
Install some packages
install_packages
Load the Data
load_data
SQL
sql
sql2
Wrangling
Problem 1
p1
Notes on missing data
Exploratory data analysis
Payroll Distribution
Problem 2.
problem2
Problem 3.
question1
question1.1
Correlation Between Payroll and Winning Percentage
Problem 4.
problem4
Question 2.
oakA
Data Transformations
Standardization across years
Problem 5.
problem5
Problem 6.
problem6
Question 3.
Expected wins
Problem 7.
problem7
Spending Efficiency
Problem 8
problem8
Question 4.
Conclusion
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
# yearID >=1990 & yearID <= 2014
payroll_tab %>%
filter(yearID >=1990 & yearID <= 2014) %>%
ggplot(aes(x=yearID, y=payroll)) +
geom_line() +
facet_wrap(~teamID) +
xlab("Year") +
ylab("Total Payroll") +
ggtitle("Team Payrolls Over Time for Teams") +
theme(text = element_text(size = 7.5),
axis.text.x = element_text(angle=90, vjust=1))
# Put all of these on one large plot
payroll_tab %>%
filter(yearID >=1990 & yearID <= 2014) %>%
ggplot(aes(x=yearID, y=payroll)) +
geom_point() +
geom_smooth() +
xlab("Year") +
ylab("Total Payroll") +
ggtitle("Payrolls of Teams Over Time")
```
This first table produced many plots for each team. In each plot, we have the **year** in the x-axis
and we show **total payroll** in the y-axis. The first plot is difficult to visualize and make a
statement about the overall trend of all teams across many years so we try to combine all of the
teams and their payrolls in one plot (the second plot above). As you can see from the first plot,
some teams only have payroll information for some later (more recent) years. In the second plot,
their are many points that appear in vertical lines because our dataset has data about payrolls of
teams in discrete years.
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
Source |
Console
~/russia_tea/
|
|
> payroll_tab %>% + filter(teamID %in% c("OAK", "BOS", "NYA", "ATL", "TBA")) %>% + ggplot(aes(x=yearID, y=efficiency)) + + geom_smooth() + + geom_point(aes(colour=teamID)) + + xlab("Year") + + ylab("Winning Efficiency") + + ggtitle("Efficiency of Teams Over Time") + + labs(colour="Team") > payroll_tab %>% + filter(teamID %in% c("OAK", "BOS", "NYA", "ATL", "TBA")) %>% + ggplot(aes(x=yearID, y=efficiency, color = teamID)) + + geom_smooth() + + #geom_point(aes(colour=teamID)) + + xlab("Year") + + ylab("Winning Efficiency") + + ggtitle("Efficiency of Teams Over Time") + + labs(colour="Team") > save.image("~/project2/project2_env.RData") > install.packages("UScensus2010") Installing package into ‘/usr/local/lib/R/site-library’ (as ‘lib’ is unspecified) trying URL 'https://cran.rstudio.com/src/contrib/UScensus2010_0.11.tar.gz' Content type 'application/x-gzip' length 63114 bytes (61 KB) ================================================== downloaded 61 KB * installing *source* package ‘UScensus2010’ ... ** package ‘UScensus2010’ successfully unpacked and MD5 sums checked ** R ** data ** inst ** preparing package for lazy loading ** help *** installing help indices ** building package indices ** testing if installed package can be loaded * DONE (UScensus2010) The downloaded source packages are in ‘/tmp/Rtmp9uHv2u/downloaded_packages’ > library(UScensus2010) Loading required package: maptools Loading required package: sp Checking rgeos availability: TRUE Loading required package: foreign Package UScensus2010: US Census 2010 Suite of R Packages Version 0.11 created on 2011-11-18. Zack Almquist, University of California-Irvine ne For citation information, type citation("UScensus2010"). Type help(package=UScensus2010) to get started. > help(package="UScensus2010") > data(maryland) Warning message: In data(maryland) : data set ‘maryland’ not found > data("maryland") Warning message: In data("maryland") : data set ‘maryland’ not found > ?UScensus2010::county > ?UScensus2010::state No documentation for ‘state’ in specified packages and libraries: you could try ‘??state’ > ?UScensus2010::city > md <- UScensus2010::city("Maryland") Error in if (!statefips & nchar(state) == 2) { : argument is of length zero > md <- UScensus2010::city(",aryland") Error in if (!statefips & nchar(state) == 2) { : argument is of length zero > md <- UScensus2010::city(state="maryland") Error in get(paste(state, ".cdp10", sep = "")) : object 'maryland.cdp10' not found In addition: Warning message: In data(list = paste(state, ".cdp10", sep = ""), envir = parent.frame()) : data set ‘maryland.cdp10’ not found > md <- UScensus2010::city(state="montgomery") Error in city.aux(name, state, statefips, sp.object, proj) : Not a State! > md <- UScensus2010::city("montgomery", state="maryland") Error in get(paste(state, ".cdp10", sep = "")) : object 'maryland.cdp10' not found In addition: Warning message: In data(list = paste(state, ".cdp10", sep = ""), envir = parent.frame()) : data set ‘maryland.cdp10’ not found 02 Nov 2016 15:07:22 [rsession-rstudio] ERROR session hadabend; LOGGED FROM: rstudio::core::Error {anonymous}::rInit(const rstudio::r::session::RInitInfo&) /home/ubuntu/rstudio/src/cpp/session/SessionMain.cpp:1862 Checking rgeos availability: TRUE Error in library(packageName, lib.loc = lib, character.only = TRUE) : there is no package called ‘UScensus2010’ 02 Nov 2016 15:07:24 [rsession-rstudio] ERROR r error 4 (R code execution error) [errormsg=Error in library(packageName, lib.loc = lib, character.only = TRUE) : there is no package called ‘UScensus2010’ , context=Error restoring session data (loading package UScensus2010)]; OCCURRED AT: rstudio::core::Error rstudio::r::exec::{anonymous}::evaluateExpressionsUnsafe(SEXP, SEXP, SEXPREC**, rstudio::r::sexp::Protect*) /home/ubuntu/rstudio/src/cpp/r/RExec.cpp:147; LOGGED FROM: void rstudio::r::session::search_path::{anonymous}::loadPackage(const string&, const string&) /home/ubuntu/rstudio/src/cpp/r/session/RSearchPath.cpp:198 Error restoring session data (loading package UScensus2010): R code execution error > payroll_tab %>% + filter(yearID >=1990 & yearID <= 2014) %>% + ggplot(aes(x=yearID, y=payroll)) + + geom_line() + + facet_wrap(~teamID) + + xlab("Year") + + ylab("Total Payroll") + + ggtitle("Team Payrolls Over Time for Teams") + + theme(text = element_text(size=20), + axis.text.x = element_text(angle=90, vjust=1)) > payroll_tab %>% + filter(yearID >=1990 & yearID <= 2014) %>% + ggplot(aes(x=yearID, y=payroll)) + + geom_point() + + geom_smooth() + + xlab("Year") + + ylab("Total Payroll") + + ggtitle("Payrolls of Teams Over Time") > payroll_tab %>% + group_by(yearID) %>% + summarise(avg_payroll = mean(payroll)) %>% + ggplot(aes(x=yearID, y=avg_payroll)) + + geom_bar(stat = "identity") + + xlab("Year") + + ylab("Average Payroll of Baseball Teams") + + ggtitle("Average Payroll of Baseball Teams over Time") + + geom_smooth() > payroll_tab %>% + filter(yearID >=1990 & yearID <= 2014) %>% + ggplot(aes(x=yearID, y=payroll)) + + geom_line() + + facet_wrap(~teamID) + + xlab("Year") + + ylab("Total Payroll") + + ggtitle("Team Payrolls Over Time for Teams") + + theme(text = element_text(size=10), + axis.text.x = element_text(angle=90, vjust=1)) > payroll_tab %>% + filter(yearID >=1990 & yearID <= 2014) %>% + ggplot(aes(x=yearID, y=payroll)) + + geom_line() + + facet_wrap(~teamID) + + xlab("Year") + + ylab("Total Payroll") + + ggtitle("Team Payrolls Over Time for Teams") + + theme(text = element_text(), + axis.text.x = element_text(angle=90, vjust=1)) > payroll_tab %>% + filter(yearID >=1990 & yearID <= 2014) %>% + ggplot(aes(x=yearID, y=payroll)) + + geom_point() + + geom_smooth() + + xlab("Year") + + ylab("Total Payroll") + + ggtitle("Payrolls of Teams Over Time") > ?theme > payroll_tab %>% + group_by(yearID) %>% + summarise(avg_payroll = mean(payroll)) %>% + ggplot(aes(x=yearID, y=avg_payroll)) + + geom_bar(stat = "identity") + + xlab("Year") + + ylab("Average Payroll of Baseball Teams") + + ggtitle("Average Payroll of Baseball Teams over Time") + + geom_smooth() > payroll_tab %>% + group_by(yearID) %>% + summarise(max_payroll = max(payroll), min_payroll = min(payroll)) %>% + ggplot(aes(x = yearID, y = (max_payroll-min_payroll))) + + geom_bar(stat = "identity") + + xlab("Year") + + ylab("Payroll Spread") + + ggtitle("Difference in Payroll Between Wealthy and Poor Teams Over Time") + + geom_smooth() > payroll_tab %>% + group_by(yearID) %>% + summarise(max_payroll = max(payroll), min_payroll = min(payroll)) %>% + ggplot(aes(x = yearID, y = (max_payroll-min_payroll))) + + geom_bar(stat = "identity") + + xlab("Year") + + ylab("Payroll Spread") + + ggtitle("Difference in Payroll Between Wealthy and Poor Teams Over Time") + + geom_smooth() + + scale_x_continuous(breaks = (max(payroll_tab$yearID) - min(payroll_tab$yearID))) > payroll_tab %>% + group_by(yearID) %>% + summarise(max_payroll = max(payroll), min_payroll = min(payroll)) %>% + ggplot(aes(x = yearID, y = (max_payroll-min_payroll))) + + geom_bar(stat = "identity") + + xlab("Year") + + ylab("Payroll Spread") + + ggtitle("Difference in Payroll Between Wealthy and Poor Teams Over Time") + + geom_smooth() + + scale_x_continuous(breaks = 10) > payroll_tab %>% + group_by(yearID) %>% + summarise(max_payroll = max(payroll), min_payroll = min(payroll)) %>% + ggplot(aes(x = yearID, y = (max_payroll-min_payroll))) + + geom_bar(stat = "identity") + + xlab("Year") + + ylab("Payroll Spread") + + ggtitle("Difference in Payroll Between Wealthy and Poor Teams Over Time") + + geom_smooth() + + scale_x_continuous(breaks = 10) > payroll_tab %>% + group_by(yearID) %>% + summarise(max_payroll = max(payroll), min_payroll = min(payroll)) %>% + ggplot(aes(x = yearID, y = (max_payroll-min_payroll))) + + geom_bar(stat = "identity") + + xlab("Year") + + ylab("Payroll Spread") + + ggtitle("Difference in Payroll Between Wealthy and Poor Teams Over Time") + + geom_smooth() > payroll_tab %>% + group_by(yearID) %>% + summarise(max_payroll = max(payroll), min_payroll = min(payroll)) %>% + ggplot(aes(x = yearID, y = (max_payroll-min_payroll))) + + geom_bar(stat = "identity") + + xlab("Year") + + ylab("Payroll Spread") + + ggtitle("Difference in Payroll Between Wealthy and Poor Teams Over Time") + + geom_smooth() + + scale_x_continuous(breaks = number_ticks(10)) Error in check_breaks_labels(breaks, labels) : could not find function "number_ticks" > ?pretty > pretty(10,n) Error in n%/%3 : non-numeric argument to binary operator > pretty(10,1) [1] 10 > pretty(10,2) [1] 10 > pretty(10,3) [1] 0 10 > pretty(limits,10) Error in pretty(limits, 10) : object 'limits' not found > ?pretty_breaks > pretty_breaks(3) Error: could not find function "pretty_breaks" > payroll_tab %>% + group_by(yearID) %>% + summarise(max_payroll = max(payroll), min_payroll = min(payroll)) %>% + ggplot(aes(x = yearID, y = (max_payroll-min_payroll))) + + geom_bar(stat = "identity") + + xlab("Year") + + ylab("Payroll Spread") + + ggtitle("Difference in Payroll Between Wealthy and Poor Teams Over Time") + + geom_smooth() + + scale_x_continuous(breaks = pretty_breaks(10)) Error in check_breaks_labels(breaks, labels) : could not find function "pretty_breaks" > payroll_tab %>% + group_by(yearID) %>% + summarise(max_payroll = max(payroll), min_payroll = min(payroll)) %>% + ggplot(aes(x = yearID, y = (max_payroll-min_payroll))) + + geom_bar(stat = "identity") + + xlab("Year") + + ylab("Payroll Spread") + + ggtitle("Difference in Payroll Between Wealthy and Poor Teams Over Time") + + geom_smooth() + + scale_x_continuous(breaks = scales::pretty_breaks(10)) > payroll_tab %>% + group_by(yearID) %>% + summarise(max_payroll = max(payroll), min_payroll = min(payroll)) %>% + ggplot(aes(x = yearID, y = (max_payroll-min_payroll))) + + geom_bar(stat = "identity") + + xlab("Year") + + ylab("Payroll Spread") + + ggtitle("Difference in Payroll Between Wealthy and Poor Teams Over Time") + + geom_smooth() + + scale_x_continuous(breaks = scales::pretty_breaks(15)) > ?range > range(payroll$yearID) Error: object 'payroll' not found > range(payroll_tab$yearID) [1] 1985 2014 > diff(range(payroll_tab$yearID)) [1] 29 > payroll_tab %>% + group_by(yearID) %>% + summarise(max_payroll = max(payroll), min_payroll = min(payroll)) %>% + ggplot(aes(x = yearID, y = (max_payroll-min_payroll))) + + geom_bar(stat = "identity") + + xlab("Year") + + ylab("Payroll Spread") + + ggtitle("Difference in Payroll Between Wealthy and Poor Teams Over Time") + + geom_smooth() + + scale_x_continuous(breaks = scales::pretty_breaks(diff(range(payroll_tab$yearID)))) > payroll_tab %>% + group_by(yearID) %>% + summarise(max_payroll = max(payroll), min_payroll = min(payroll)) %>% + ggplot(aes(x = yearID, y = (max_payroll-min_payroll))) + + geom_bar(stat = "identity") + + xlab("Year") + + ylab("Payroll Spread") + + ggtitle("Difference in Payroll Between Wealthy and Poor Teams Over Time") + + geom_smooth() + + scale_x_continuous(breaks = scales::pretty_breaks(diff(range(payroll_tab$yearID)))) + + theme(text = element_text(), + axis.text.x = element_text(angle=90, vjust=1)) > payroll_tab %>% + group_by(yearID) %>% + summarise(max_payroll = max(payroll), min_payroll = min(payroll)) %>% + ggplot(aes(x = yearID, y = (max_payroll-min_payroll))) + + geom_bar(stat = "identity") + + xlab("Year") + + ylab("Payroll Spread") + + ggtitle("Difference in Payroll Between Wealthy and Poor Teams Over Time") + + geom_smooth() + + scale_x_continuous(breaks = scales::pretty_breaks(diff(range(payroll_tab$yearID)))/2) + + theme(text = element_text(), + axis.text.x = element_text(angle=90, vjust=1)) Error in scales::pretty_breaks(diff(range(payroll_tab$yearID)))/2 : non-numeric argument to binary operator > payroll_tab %>% + group_by(yearID) %>% + summarise(max_payroll = max(payroll), min_payroll = min(payroll)) %>% + ggplot(aes(x = yearID, y = (max_payroll-min_payroll))) + + geom_bar(stat = "identity") + + xlab("Year") + + ylab("Payroll Spread") + + ggtitle("Difference in Payroll Between Wealthy and Poor Teams Over Time") + + geom_smooth() + + scale_x_continuous(breaks = scales::pretty_breaks(diff(range(payroll_tab$yearID)))) + + theme(text = element_text(), + axis.text.x = element_text(angle=90, vjust=1)) > payroll_tab %>% + group_by(yearID) %>% + summarise(max_payroll = max(payroll), min_payroll = min(payroll)) %>% + ggplot(aes(x = yearID, y = (max_payroll-min_payroll))) + + geom_bar(stat = "identity") + + xlab("Year") + + ylab("Payroll Spread") + + ggtitle("Difference in Payroll Between Wealthy and Poor Teams Over Time") + + geom_smooth() + + scale_x_continuous(breaks = scales::pretty_breaks(20)) + + theme(text = element_text(), + axis.text.x = element_text(angle=90, vjust=1)) > payroll_tab %>% sample_n(10) %>% select(teamID, yearID,year_range) # A tibble: 10 × 3 teamID yearID year_range <chr> <int> <fctr> 1 CAL 1991 (1991,1997] 2 CHN 2006 (2002,2008] 3 DET 2001 (1997,2002] 4 NYA 1993 (1991,1997] 5 SEA 1986 (1985,1991] 6 CHN 1988 (1985,1991] 7 ARI 2009 (2008,2014] 8 HOU 1999 (1997,2002] 9 SFN 1985 (1985,1991] 10 SEA 2010 (2008,2014] > avg_stats_per_year %>% sample_n(1) %>% select(teamID,average_pay_in_years,average_win_percent_in_years,year_range) Source: local data frame [0 x 4] Groups: year_range [0] # ... with 4 variables: teamID <chr>, average_pay_in_years <dbl>, average_win_percent_in_years <dbl>, # year_range <fctr> > avg_stats_per_year %>% select(teamID,average_pay_in_years,average_win_percent_in_years,year_range) Source: local data frame [148 x 4] Groups: year_range [5] teamID average_pay_in_years average_win_percent_in_years year_range <chr> <dbl> <dbl> <fctr> 1 ATL 14475059 40.22038 (1985,1991] 2 BAL 11658262 45.40360 (1985,1991] 3 BOS 14563356 52.89024 (1985,1991] 4 CAL 15077312 51.74897 (1985,1991] 5 CHA 9008958 48.18396 (1985,1991] 6 CHN 13605046 48.44389 (1985,1991] 7 CIN 10646369 52.73049 (1985,1991] 8 CLE 9232153 44.49431 (1985,1991] 9 DET 13402658 50.97960 (1985,1991] 10 HOU 13020061 51.23457 (1985,1991] # ... with 138 more rows > avg_stats_per_year Source: local data frame [148 x 4] Groups: year_range [5] year_range teamID average_pay_in_years average_win_percent_in_years <fctr> <chr> <dbl> <dbl> 1 (1985,1991] ATL 14475059 40.22038 2 (1985,1991] BAL 11658262 45.40360 3 (1985,1991] BOS 14563356 52.89024 4 (1985,1991] CAL 15077312 51.74897 5 (1985,1991] CHA 9008958 48.18396 6 (1985,1991] CHN 13605046 48.44389 7 (1985,1991] CIN 10646369 52.73049 8 (1985,1991] CLE 9232153 44.49431 9 (1985,1991] DET 13402658 50.97960 10 (1985,1991] HOU 13020061 51.23457 # ... with 138 more rows > avg_stats_per_year %>% sample_n(10) Source: local data frame [50 x 4] Groups: year_range [5] year_range teamID average_pay_in_years average_win_percent_in_years <fctr> <chr> <dbl> <dbl> 1 (1985,1991] BOS 14563356 52.89024 2 (1985,1991] PHI 11807505 46.30896 3 (1985,1991] TOR 13027137 55.87318 4 (1985,1991] SEA 7085071 45.00230 5 (1985,1991] CLE 9232153 44.49431 6 (1985,1991] CHA 9008958 48.18396 7 (1985,1991] OAK 12618240 55.55556 8 (1985,1991] LAN 16466313 51.33359 9 (1985,1991] CAL 15077312 51.74897 10 (1985,1991] SFN 11856147 50.92593 # ... with 40 more rows > avg_stats_per_year %>% sample_n(10) Source: local data frame [50 x 4] Groups: year_range [5] year_range teamID average_pay_in_years average_win_percent_in_years <fctr> <chr> <dbl> <dbl> 1 (1985,1991] DET 13402658 50.97960 2 (1985,1991] HOU 13020061 51.23457 3 (1985,1991] NYA 17883336 51.80968 4 (1985,1991] ATL 14475059 40.22038 5 (1985,1991] TOR 13027137 55.87318 6 (1985,1991] TEX 7901650 47.40945 7 (1985,1991] BOS 14563356 52.89024 8 (1985,1991] MON 11252155 51.49272 9 (1985,1991] CLE 9232153 44.49431 10 (1985,1991] PHI 11807505 46.30896 # ... with 40 more rows > avg_stats_per_year %>% + ggplot( + aes(x=average_pay_in_years, y=average_win_percent_in_years, label=teamID)) + + geom_point() + + geom_text() + + facet_wrap(~year_range) + + xlab("Average Team Payroll") + + ylab("Average Winning Percentage") + + ggtitle("Average Winning Percentage vs. Average Payroll across Time") + + geom_smooth(method = 'lm') > avg_stats_per_year %>% + ggplot( + aes(x=average_pay_in_years, y=average_win_percent_in_years, label=teamID)) + + geom_text() + + facet_wrap(~year_range) + + xlab("Average Team Payroll") + + ylab("Average Winning Percentage") + + ggtitle("Average Winning Percentage vs. Average Payroll across Time") + + geom_smooth(method = 'lm') > avg_stats_per_year %>% + ggplot(aes(x=average_pay_in_years, y=average_win_percent_in_years)) + + geom_point(aes(colour=ifelse(teamID=="OAK", 'Oakland As', "Other Team"))) + + facet_wrap(~year_range) + + xlab("Average Team Payroll") + + ylab("Average Winning Percentage") + + ggtitle("Oakland A's Spending Efficency Over Time") + + geom_smooth(method = 'lm') + + labs(colour="Team") > head(standard_payrolls) # A tibble: 6 × 3 yearID average_payroll_year st_dev_payroll_year <int> <dbl> <dbl> 1 1985 10075565 2470845 2 1986 11840558 3186956 3 1987 10483668 3848337 4 1988 11555862 3386331 5 1989 13845989 3568844 6 1990 17072354 3771834 > avg_std_stats_per_year %>% + ggplot( + aes(x=average_pay_in_years, y=average_win_percent_in_years, label=teamID)) + + geom_point() + + geom_text() + + facet_wrap(~year_range) + + xlab("Average Standard Team Payroll") + + ylab("Average Winning Percentage") + + ggtitle("Average Winning Percentage vs. Average Standard Payroll across Time") + + geom_smooth(method = 'lm') > payroll_tab %>% + ggplot( + aes(x=standard_payroll, y=win_percentage, label=teamID)) + + geom_point(aes(colour=yearID)) + + #geom_text() + + xlab("Standard Team Payroll") + + ylab("Winning Percentage") + + ggtitle("Winning Percentage vs. Standard Payroll across Time") + + geom_smooth(method = 'lm') + + labs(colour = "Year") > payroll_tab %>% + ggplot(aes(x=standard_payroll, y=win_percentage, label=teamID)) + + geom_point(aes(colour=yearID)) + + xlab("Standard Team Payroll") + + ylab("Winning Percentage") + + ggtitle("Winning Percentage vs. Standard Payroll across Time") + + geom_smooth(method = 'lm') + + labs(colour = "Year") > head(payroll_tab %>% select(teamID, yearID,win_percentage, expected_win_pct)) # A tibble: 6 × 4 teamID yearID win_percentage expected_win_pct <chr> <int> <dbl> <dbl> 1 ATL 1985 40.74074 54.78726 2 BAL 1985 51.55280 51.50267 3 BOS 1985 49.69325 50.83169 4 CAL 1985 55.55556 54.40368 5 CHA 1985 52.14724 49.76791 6 CHN 1985 47.53086 52.65835 > payroll_tab <- payroll_tab %>% mutate(efficiency = win_percentage-expected_win_pct) > payroll_tab %>% + filter(teamID %in% c("OAK", "BOS", "NYA", "ATL", "TBA")) %>% + ggplot(aes(x=yearID, y=efficiency)) + + geom_smooth() + + geom_point(aes(colour=teamID)) + + xlab("Year") + + ylab("Winning Efficiency") + + ggtitle("Efficiency of Teams (Overall) Over Time") + + labs(colour="Team") > payroll_tab %>% + filter(teamID %in% c("OAK", "BOS", "NYA", "ATL", "TBA")) %>% + ggplot(aes(x=yearID, y=efficiency, color = teamID)) + + geom_smooth() + + #geom_point(aes(colour=teamID)) + + xlab("Year") + + ylab("Winning Efficiency") + + ggtitle("Efficiency of Specific Teams Over Time") + + labs(colour="Team") > avg_stats_per_year %>% sample_n(10) Source: local data frame [50 x 4] Groups: year_range [5] year_range teamID average_pay_in_years average_win_percent_in_years <fctr> <chr> <dbl> <dbl> 1 (1985,1991] DET 13402658 50.97960 2 (1985,1991] NYA 17883336 51.80968 3 (1985,1991] MIN 10584470 49.17695 4 (1985,1991] CLE 9232153 44.49431 5 (1985,1991] CHN 13605046 48.44389 6 (1985,1991] KCA 15132358 51.64481 7 (1985,1991] NYN 16158735 59.38786 8 (1985,1991] LAN 16466313 51.33359 9 (1985,1991] ML4 11362523 49.58017 10 (1985,1991] OAK 12618240 55.55556 # ... with 40 more rows > avg_stats_per_year <- payroll_tab %>% + group_by(year_range,teamID) %>% + summarise(average_pay_in_years = mean(payroll), + average_win_percent_in_years = mean(win_percentage, na.rm=TRUE)) > avg_stats_per_year %>% sample_n(10) Source: local data frame [0 x 4] Groups: year_range [0] # ... with 4 variables: year_range <fctr>, teamID <chr>, average_pay_in_years <dbl>, # average_win_percent_in_years <dbl> > avg_stats_per_year Source: local data frame [148 x 4] Groups: year_range [?] year_range teamID average_pay_in_years average_win_percent_in_years <fctr> <chr> <dbl> <dbl> 1 (1985,1991] ATL 14475059 40.22038 2 (1985,1991] BAL 11658262 45.40360 3 (1985,1991] BOS 14563356 52.89024 4 (1985,1991] CAL 15077312 51.74897 5 (1985,1991] CHA 9008958 48.18396 6 (1985,1991] CHN 13605046 48.44389 7 (1985,1991] CIN 10646369 52.73049 8 (1985,1991] CLE 9232153 44.49431 9 (1985,1991] DET 13402658 50.97960 10 (1985,1991] HOU 13020061 51.23457 # ... with 138 more rows > head(avg_stats_per_year) Source: local data frame [6 x 4] Groups: year_range [1] year_range teamID average_pay_in_years average_win_percent_in_years <fctr> <chr> <dbl> <dbl> 1 (1985,1991] ATL 14475059 40.22038 2 (1985,1991] BAL 11658262 45.40360 3 (1985,1991] BOS 14563356 52.89024 4 (1985,1991] CAL 15077312 51.74897 5 (1985,1991] CHA 9008958 48.18396 6 (1985,1991] CHN 13605046 48.44389 > avg_stats_per_year %>% + ggplot( + aes(x=average_pay_in_years, y=average_win_percent_in_years, label=teamID)) + + geom_point() + + geom_text() + + facet_wrap(~year_range) + + xlab("Average Team Payroll") + + ylab("Average Winning Percentage") + + ggtitle("Average Winning Percentage vs. Average Payroll across Time") + + geom_smooth(method = 'lm') > avg_stats_per_year %>% + ggplot(aes(x=average_pay_in_years, y=average_win_percent_in_years, label=teamID)) + + geom_point() + + geom_text() + + facet_wrap(~year_range) + + xlab("Average Team Payroll") + + ylab("Average Winning Percentage") + + ggtitle("Average Winning Percentage vs. Average Payroll across Time") + + geom_smooth(method = 'lm') + + theme(text = element_text(), + axis.text.x = element_text(angle=90, vjust=1)) > avg_stats_per_year %>% + ggplot(aes(x=average_pay_in_years, y=average_win_percent_in_years)) + + geom_point(aes(colour=ifelse(teamID=="OAK", 'Oakland As', "Other Teams"))) + + facet_wrap(~year_range) + + xlab("Average Team Payroll") + + ylab("Average Winning Percentage") + + ggtitle("Oakland A's Spending Efficency Over Time") + + geom_smooth(method = 'lm') + + labs(colour="Team") + + theme(text = element_text(), + axis.text.x = element_text(angle=90, vjust=1)) > payroll_tab %>% + ggplot(aes(x=standard_payroll, y=win_percentage, label=teamID)) + + geom_point(aes(colour=Rank)) + + xlab("Standard Team Payroll") + + ylab("Winning Percentage") + + ggtitle("Winning Percentage vs. Standard Payroll across Time") + + geom_smooth(method = 'lm') + + labs(colour = "Year") > payroll_tab %>% + ggplot(aes(x=standard_payroll, y=win_percentage, label=teamID)) + + geom_point(aes(colour=Rank)) + + xlab("Standard Team Payroll") + + ylab("Winning Percentage") + + ggtitle("Winning Percentage vs. Standard Payroll across Time") + + geom_smooth(method = 'lm') + + labs(colour = "Rank") + + scale_colour_gradient(low="red", high="blue") > payroll_tab %>% + ggplot(aes(x=standard_payroll, y=win_percentage, label=teamID)) + + geom_point(aes(colour=Rank)) + + xlab("Standard Team Payroll") + + ylab("Winning Percentage") + + ggtitle("Winning Percentage vs. Standard Payroll across Time") + + geom_smooth(method = 'lm') + + labs(colour = "Rank") + + scale_colour_gradient(low="green", high="red") > payroll_tab %>% + filter(yearID >=1990 & yearID <= 2014) %>% + ggplot(aes(x=yearID, y=payroll)) + + geom_line() + + facet_wrap(~teamID) + + xlab("Year") + + ylab("Total Payroll") + + ggtitle("Team Payrolls Over Time for Teams") + + theme(text = element_text(size = 10), + axis.text.x = element_text(angle=90, vjust=1)) > ?rvest No documentation for ‘rvest’ in specified packages and libraries: you could try ‘??rvest’ > ??rvest > payroll_tab %>% select(teamID, yearID, payroll_tab, average_payroll_year, st_dev_payroll_year) Error: All select() inputs must resolve to integer column positions. The following do not: * payroll_tab > payroll_tab %>% select(teamID, yearID, payroll_tab, average_payroll_year, st_dev_payroll_year) Error: All select() inputs must resolve to integer column positions. The following do not: * payroll_tab > payroll_tab %>% select(teamID, yearID, average_payroll_year, st_dev_payroll_year) # A tibble: 858 × 4 teamID yearID average_payroll_year st_dev_payroll_year <chr> <int> <dbl> <dbl> 1 ATL 1985 10075565 2470845 2 BAL 1985 10075565 2470845 3 BOS 1985 10075565 2470845 4 CAL 1985 10075565 2470845 5 CHA 1985 10075565 2470845 6 CHN 1985 10075565 2470845 7 CIN 1985 10075565 2470845 8 CLE 1985 10075565 2470845 9 DET 1985 10075565 2470845 10 HOU 1985 10075565 2470845 # ... with 848 more rows > payroll_tab %>% select(teamID, yearID, average_payroll_year, st_dev_payroll_year) %>% sample_n(5) # A tibble: 5 × 4 teamID yearID average_payroll_year st_dev_payroll_year <chr> <int> <dbl> <dbl> 1 SEA 2013 101150855 48830287 2 ATL 1997 40260210 13060728 3 DET 2002 67469251 24692193 4 TEX 1995 33981049 9447998 5 TOR 2009 88824233 33857093 > head(standard_payrolls) # A tibble: 6 × 3 yearID average_payroll_year st_dev_payroll_year <int> <dbl> <dbl> 1 1985 10075565 2470845 2 1986 11840558 3186956 3 1987 10483668 3848337 4 1988 11555862 3386331 5 1989 13845989 3568844 6 1990 17072354 3771834 > payroll_tab %>% select(teamID, yearID, average_payroll_year, st_dev_payroll_year) %>% head() # A tibble: 6 × 4 teamID yearID average_payroll_year st_dev_payroll_year <chr> <int> <dbl> <dbl> 1 ATL 1985 10075565 2470845 2 BAL 1985 10075565 2470845 3 BOS 1985 10075565 2470845 4 CAL 1985 10075565 2470845 5 CHA 1985 10075565 2470845 6 CHN 1985 10075565 2470845 > payroll_tab %>% + select(teamID, yearID, average_payroll_year, st_dev_payroll_year) %>% + sample_n(5) # A tibble: 5 × 4 teamID yearID average_payroll_year st_dev_payroll_year <chr> <int> <dbl> <dbl> 1 MON 1991 23578785 6894669 2 CHN 2014 99800016 45705053 3 BAL 2000 55537837 21416220 4 TOR 1996 34177984 10688535 5 ML4 1994 33137010 8528749 Checking rgeos availability: TRUE > payroll_tab %>% + filter(yearID >=1990 & yearID <= 2014) %>% + ggplot(aes(x=yearID, y=payroll)) + + geom_line() + + facet_wrap(~teamID) + + xlab("Year") + + ylab("Total Payroll") + + ggtitle("Team Payrolls Over Time for Teams") + + theme(text = element_text(size = 7.5), + axis.text.x = element_text(angle=90, vjust=1)) | ||
|
Console |