data(cars)

Question 1

median(cars$speed)

## [1] 15

Question 2

library(jsonlite)

url <- "https://min-api.cryptocompare.com/data/v2/histoday?fsym=BTC&tsym=USD&limit=100"

btc_data <- fromJSON(url)

btc_df <- btc_data$Data$Data 

max_close <- max(btc_df$close, na.rm = TRUE)

max_close

## [1] 124723

Question 3 (Mini Project)

Title: Comparing NFL NFC 2020 Pro Football Reference Team Statistics

Research Qs:

1. Which NFC teams had the highest win percentages in 2020?

2. Is there a relationship between points scored per game and total wins?

3. Which NFC teams allowed the fewest points per game?

Data Extraction

pacman::p_load(robotstxt, rvest)


nfl_html <- read_html("https://www.pro-football-reference.com/years/2020/")
nfl_html

## {html_document}
## <html data-version="klecko-" data-root="/home/pfr/build" lang="en" class="no-js">
## [1] <head>\n<meta http-equiv="Content-Type" content="text/html; charset=UTF-8 ...
## [2] <body class="pfr">\n<div id="wrap">\n  <div id="header" role="banner">\n  ...

table_html <- html_elements(nfl_html, "table")
table_html

## {xml_nodeset (2)}
## [1] <table class="sortable stats_table" id="AFC" data-cols-to-freeze=",1">\n< ...
## [2] <table class="sortable stats_table" id="NFC" data-cols-to-freeze=",1">\n< ...

#Table for NFC Teams
tibble_list <- html_table(table_html[2], fill = TRUE)
tibble_list

## [[1]]
## # A tibble: 20 × 13
##    Tm         W     L     T     `W-L%` PF    PA    PD    MoV   SoS   SRS   OSRS 
##    <chr>      <chr> <chr> <chr> <chr>  <chr> <chr> <chr> <chr> <chr> <chr> <chr>
##  1 NFC East   NFC … NFC … NFC … NFC E… NFC … NFC … NFC … NFC … NFC … NFC … NFC …
##  2 Washingto… 7     9     0     .438   335   329   6     0.4   -1.2  -0.8  -4.1 
##  3 New York … 6     10    0     .375   280   357   -77   -4.8  0.4   -4.4  -6.7 
##  4 Dallas Co… 6     10    0     .375   395   473   -78   -4.9  -0.2  -5.1  1.0  
##  5 Philadelp… 4     11    1     .281   334   418   -84   -5.3  0.8   -4.4  -2.8 
##  6 NFC North  NFC … NFC … NFC … NFC N… NFC … NFC … NFC … NFC … NFC … NFC … NFC …
##  7 Green Bay… 13    3     0     .813   509   369   140   8.8   -1.1  7.7   5.9  
##  8 Chicago B… 8     8     0     .500   372   370   2     0.1   0.1   0.2   -2.2 
##  9 Minnesota… 7     9     0     .438   430   475   -45   -2.8  0.4   -2.4  1.3  
## 10 Detroit L… 5     11    0     .313   377   519   -142  -8.9  1.2   -7.7  -1.0 
## 11 NFC South  NFC … NFC … NFC … NFC S… NFC … NFC … NFC … NFC … NFC … NFC … NFC …
## 12 New Orlea… 12    4     0     .750   482   337   145   9.1   0.5   9.6   5.1  
## 13 Tampa Bay… 11    5     0     .688   492   355   137   8.6   0.8   9.4   6.5  
## 14 Carolina … 5     11    0     .313   350   402   -52   -3.3  2.2   -1.1  -2.4 
## 15 Atlanta F… 4     12    0     .250   396   414   -18   -1.1  1.9   0.7   -0.1 
## 16 NFC West   NFC … NFC … NFC … NFC W… NFC … NFC … NFC … NFC … NFC … NFC … NFC …
## 17 Seattle S… 12    4     0     .750   459   371   88    5.5   0.0   5.5   4.8  
## 18 Los Angel… 10    6     0     .625   372   296   76    4.8   0.7   5.4   -0.8 
## 19 Arizona C… 8     8     0     .500   410   367   43    2.7   -0.1  2.6   1.5  
## 20 San Franc… 6     10    0     .375   376   390   -14   -0.9  1.7   0.8   0.2  
## # ℹ 1 more variable: DSRS <chr>

team_stats <- tibble_list[[1]]
head(team_stats)

## # A tibble: 6 × 13
##   Tm    W     L     T     `W-L%` PF    PA    PD    MoV   SoS   SRS   OSRS  DSRS 
##   <chr> <chr> <chr> <chr> <chr>  <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
## 1 NFC … NFC … NFC … NFC … NFC E… NFC … NFC … NFC … NFC … NFC … NFC … NFC … NFC …
## 2 Wash… 7     9     0     .438   335   329   6     0.4   -1.2  -0.8  -4.1  3.2  
## 3 New … 6     10    0     .375   280   357   -77   -4.8  0.4   -4.4  -6.7  2.3  
## 4 Dall… 6     10    0     .375   395   473   -78   -4.9  -0.2  -5.1  1.0   -6.1 
## 5 Phil… 4     11    1     .281   334   418   -84   -5.3  0.8   -4.4  -2.8  -1.6 
## 6 NFC … NFC … NFC … NFC … NFC N… NFC … NFC … NFC … NFC … NFC … NFC … NFC … NFC …

Data Cleaning

str(team_stats)

## tibble [20 × 13] (S3: tbl_df/tbl/data.frame)
##  $ Tm  : chr [1:20] "NFC East" "Washington Football Team*" "New York Giants" "Dallas Cowboys" ...
##  $ W   : chr [1:20] "NFC East" "7" "6" "6" ...
##  $ L   : chr [1:20] "NFC East" "9" "10" "10" ...
##  $ T   : chr [1:20] "NFC East" "0" "0" "0" ...
##  $ W-L%: chr [1:20] "NFC East" ".438" ".375" ".375" ...
##  $ PF  : chr [1:20] "NFC East" "335" "280" "395" ...
##  $ PA  : chr [1:20] "NFC East" "329" "357" "473" ...
##  $ PD  : chr [1:20] "NFC East" "6" "-77" "-78" ...
##  $ MoV : chr [1:20] "NFC East" "0.4" "-4.8" "-4.9" ...
##  $ SoS : chr [1:20] "NFC East" "-1.2" "0.4" "-0.2" ...
##  $ SRS : chr [1:20] "NFC East" "-0.8" "-4.4" "-5.1" ...
##  $ OSRS: chr [1:20] "NFC East" "-4.1" "-6.7" "1.0" ...
##  $ DSRS: chr [1:20] "NFC East" "3.2" "2.3" "-6.1" ...

names(team_stats) <- make.names(names(team_stats))
head(team_stats)

## # A tibble: 6 × 13
##   Tm     W     L     T     W.L.  PF    PA    PD    MoV   SoS   SRS   OSRS  DSRS 
##   <chr>  <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
## 1 NFC E… NFC … NFC … NFC … NFC … NFC … NFC … NFC … NFC … NFC … NFC … NFC … NFC …
## 2 Washi… 7     9     0     .438  335   329   6     0.4   -1.2  -0.8  -4.1  3.2  
## 3 New Y… 6     10    0     .375  280   357   -77   -4.8  0.4   -4.4  -6.7  2.3  
## 4 Dalla… 6     10    0     .375  395   473   -78   -4.9  -0.2  -5.1  1.0   -6.1 
## 5 Phila… 4     11    1     .281  334   418   -84   -5.3  0.8   -4.4  -2.8  -1.6 
## 6 NFC N… NFC … NFC … NFC … NFC … NFC … NFC … NFC … NFC … NFC … NFC … NFC … NFC …

team_stats$W <- as.numeric(team_stats$W)

## Warning: NAs introduced by coercion

team_stats_clean <- team_stats[!is.na(team_stats$W), ]
head(team_stats_clean)

## # A tibble: 6 × 13
##   Tm         W L     T     W.L.  PF    PA    PD    MoV   SoS   SRS   OSRS  DSRS 
##   <chr>  <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
## 1 Washi…     7 9     0     .438  335   329   6     0.4   -1.2  -0.8  -4.1  3.2  
## 2 New Y…     6 10    0     .375  280   357   -77   -4.8  0.4   -4.4  -6.7  2.3  
## 3 Dalla…     6 10    0     .375  395   473   -78   -4.9  -0.2  -5.1  1.0   -6.1 
## 4 Phila…     4 11    1     .281  334   418   -84   -5.3  0.8   -4.4  -2.8  -1.6 
## 5 Green…    13 3     0     .813  509   369   140   8.8   -1.1  7.7   5.9   1.8  
## 6 Chica…     8 8     0     .500  372   370   2     0.1   0.1   0.2   -2.2  2.4

Research Qs

1. Which NFC teams had the highest win percentages in 2020?

top_win_pct <- team_stats_clean[order(team_stats_clean$W.L., decreasing = TRUE), ]
head(top_win_pct)

## # A tibble: 6 × 13
##   Tm         W L     T     W.L.  PF    PA    PD    MoV   SoS   SRS   OSRS  DSRS 
##   <chr>  <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
## 1 Green…    13 3     0     .813  509   369   140   8.8   -1.1  7.7   5.9   1.8  
## 2 New O…    12 4     0     .750  482   337   145   9.1   0.5   9.6   5.1   4.5  
## 3 Seatt…    12 4     0     .750  459   371   88    5.5   0.0   5.5   4.8   0.7  
## 4 Tampa…    11 5     0     .688  492   355   137   8.6   0.8   9.4   6.5   2.8  
## 5 Los A…    10 6     0     .625  372   296   76    4.8   0.7   5.4   -0.8  6.2  
## 6 Chica…     8 8     0     .500  372   370   2     0.1   0.1   0.2   -2.2  2.4

2. Is there a relationship between points scored per game and total wins?

team_stats_clean$PF <- as.numeric(team_stats_clean$PF)

plot(team_stats_clean$PF, team_stats_clean$W,
     xlab = "Points Scored (PF)",
     ylab = "Wins",
     main = "Points Scored vs Wins",
     pch = 19, col = "darkgreen")

abline(lm(W ~ PF, data = team_stats_clean), col = "red")

cor(team_stats_clean$PF, team_stats_clean$W)

## [1] 0.7642514

Yes there is a strong postive correlation and relationship between ppg and total wins

3. Which NFC teams allowed the fewest points per game?

team_stats_clean$PA <- as.numeric(team_stats_clean$PA)
best_defense <- team_stats_clean[order(team_stats_clean$PA), ]
best_defense[, c("Tm", "PA", "W", "L")][1:5, ]

## # A tibble: 5 × 4
##   Tm                           PA     W L    
##   <chr>                     <dbl> <dbl> <chr>
## 1 Los Angeles Rams+           296    10 6    
## 2 Washington Football Team*   329     7 9    
## 3 New Orleans Saints*         337    12 4    
## 4 Tampa Bay Buccaneers+       355    11 5    
## 5 New York Giants             357     6 10

Business Intelligence Mini_Project1

Calvin Thomas

2025-10-16

Question 1

Question 2

Question 3 (Mini Project)

Title: Comparing NFL NFC 2020 Pro Football Reference Team Statistics

Research Qs:

1. Which NFC teams had the highest win percentages in 2020?

2. Is there a relationship between points scored per game and total wins?

3. Which NFC teams allowed the fewest points per game?

Data Extraction

Data Cleaning

Research Qs

1. Which NFC teams had the highest win percentages in 2020?

2. Is there a relationship between points scored per game and total wins?

Yes there is a strong postive correlation and relationship between ppg and total wins

3. Which NFC teams allowed the fewest points per game?