Use tidyverse functions to answer the following questions:

1) Which NBA player scored the most points in 1991?

library(tidyverse)

## -- Attaching packages -------------------------------------------- tidyverse 1.2.1 --

## √ ggplot2 2.2.1     √ purrr   0.2.4
## √ tibble  1.4.2     √ dplyr   0.7.4
## √ tidyr   0.8.0     √ stringr 1.2.0
## √ readr   1.1.1     √ forcats 0.2.0

## -- Conflicts ----------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

data2<-read.csv(file.choose())
data2_tibble<-as_tibble(data2)
new1<-filter(data2_tibble, Year==1991)
new2<-arrange(new1,desc(PTS))
new2[1,2]

## # A tibble: 1 x 1
##   Player         
##   <fct>          
## 1 Michael Jordan*

2) Which player had the best free throw percentage from the year 2000 to the most recent year in the data?

new3<-filter(data2_tibble, Year>=2000)
new4<-arrange(new3,desc(FT.))
new4[1,2]

## # A tibble: 1 x 1
##   Player    
##   <fct>     
## 1 Drew Barry

3) Rename the variable “pos” to “position”

new5<-rename(data2_tibble, Position=Pos)
new5[1:10,]

## # A tibble: 10 x 52
##     Year Player   Position   Age Tm        G    GS    MP   PER   TS. X3PAr
##    <int> <fct>    <fct>    <int> <fct> <int> <int> <int> <dbl> <dbl> <dbl>
##  1  1950 Curly A~ G-F         31 FTW      63    NA    NA    NA 0.368    NA
##  2  1950 Cliff B~ SG          29 INO      49    NA    NA    NA 0.435    NA
##  3  1950 Leo Bar~ SF          25 CHS      67    NA    NA    NA 0.394    NA
##  4  1950 Ed Bart~ F           24 TOT      15    NA    NA    NA 0.312    NA
##  5  1950 Ed Bart~ F           24 DNN      13    NA    NA    NA 0.308    NA
##  6  1950 Ed Bart~ F           24 NYK       2    NA    NA    NA 0.376    NA
##  7  1950 Ralph B~ G           22 INO      60    NA    NA    NA 0.422    NA
##  8  1950 Gene Be~ G-F         23 TRI       3    NA    NA    NA 0.275    NA
##  9  1950 Charlie~ F-C         28 TOT      65    NA    NA    NA 0.346    NA
## 10  1950 Charlie~ F-C         28 FTW      36    NA    NA    NA 0.362    NA
## # ... with 41 more variables: FTr <dbl>, ORB. <dbl>, DRB. <dbl>,
## #   TRB. <dbl>, AST. <dbl>, STL. <dbl>, BLK. <dbl>, TOV. <dbl>,
## #   USG. <dbl>, blanl <lgl>, OWS <dbl>, DWS <dbl>, WS <dbl>, WS.48 <dbl>,
## #   blank2 <lgl>, OBPM <dbl>, DBPM <dbl>, BPM <dbl>, VORP <dbl>, FG <int>,
## #   FGA <int>, FG. <dbl>, X3P <int>, X3PA <int>, X3P. <dbl>, X2P <int>,
## #   X2PA <int>, X2P. <dbl>, eFG. <dbl>, FT <int>, FTA <int>, FT. <dbl>,
## #   ORB <int>, DRB <int>, TRB <int>, AST <int>, STL <int>, BLK <int>,
## #   TOV <int>, PF <int>, PTS <int>

4) Use this variable to create two variables that are called “first_position” and “second_position”. (hint:separate by splitting the position variable in two)

new6<-separate(new5, Position, into=c("first_position","second_position" ))

## Warning: Expected 2 pieces. Missing pieces filled with `NA` in 24212 rows
## [2, 3, 4, 5, 6, 7, 12, 14, 16, 17, 18, 20, 22, 23, 24, 25, 27, 33, 37,
## 38, ...].

new6[1:10,]

## # A tibble: 10 x 53
##     Year Player     first_position second_position   Age Tm        G    GS
##    <int> <fct>      <chr>          <chr>           <int> <fct> <int> <int>
##  1  1950 Curly Arm~ G              F                  31 FTW      63    NA
##  2  1950 Cliff Bar~ SG             <NA>               29 INO      49    NA
##  3  1950 Leo Barnh~ SF             <NA>               25 CHS      67    NA
##  4  1950 Ed Bartels F              <NA>               24 TOT      15    NA
##  5  1950 Ed Bartels F              <NA>               24 DNN      13    NA
##  6  1950 Ed Bartels F              <NA>               24 NYK       2    NA
##  7  1950 Ralph Bea~ G              <NA>               22 INO      60    NA
##  8  1950 Gene Berce G              F                  23 TRI       3    NA
##  9  1950 Charlie B~ F              C                  28 TOT      65    NA
## 10  1950 Charlie B~ F              C                  28 FTW      36    NA
## # ... with 45 more variables: MP <int>, PER <dbl>, TS. <dbl>, X3PAr <dbl>,
## #   FTr <dbl>, ORB. <dbl>, DRB. <dbl>, TRB. <dbl>, AST. <dbl>, STL. <dbl>,
## #   BLK. <dbl>, TOV. <dbl>, USG. <dbl>, blanl <lgl>, OWS <dbl>, DWS <dbl>,
## #   WS <dbl>, WS.48 <dbl>, blank2 <lgl>, OBPM <dbl>, DBPM <dbl>,
## #   BPM <dbl>, VORP <dbl>, FG <int>, FGA <int>, FG. <dbl>, X3P <int>,
## #   X3PA <int>, X3P. <dbl>, X2P <int>, X2PA <int>, X2P. <dbl>, eFG. <dbl>,
## #   FT <int>, FTA <int>, FT. <dbl>, ORB <int>, DRB <int>, TRB <int>,
## #   AST <int>, STL <int>, BLK <int>, TOV <int>, PF <int>, PTS <int>

5) Unite these two variables back into a single variable called “position_united”

new7<-unite(new6, position_united, first_position,second_position,sep="-")
new7[1:10,]

## # A tibble: 10 x 52
##     Year Player  position_united   Age Tm        G    GS    MP   PER   TS.
##    <int> <fct>   <chr>           <int> <fct> <int> <int> <int> <dbl> <dbl>
##  1  1950 Curly ~ G-F                31 FTW      63    NA    NA    NA 0.368
##  2  1950 Cliff ~ SG-NA              29 INO      49    NA    NA    NA 0.435
##  3  1950 Leo Ba~ SF-NA              25 CHS      67    NA    NA    NA 0.394
##  4  1950 Ed Bar~ F-NA               24 TOT      15    NA    NA    NA 0.312
##  5  1950 Ed Bar~ F-NA               24 DNN      13    NA    NA    NA 0.308
##  6  1950 Ed Bar~ F-NA               24 NYK       2    NA    NA    NA 0.376
##  7  1950 Ralph ~ G-NA               22 INO      60    NA    NA    NA 0.422
##  8  1950 Gene B~ G-F                23 TRI       3    NA    NA    NA 0.275
##  9  1950 Charli~ F-C                28 TOT      65    NA    NA    NA 0.346
## 10  1950 Charli~ F-C                28 FTW      36    NA    NA    NA 0.362
## # ... with 42 more variables: X3PAr <dbl>, FTr <dbl>, ORB. <dbl>,
## #   DRB. <dbl>, TRB. <dbl>, AST. <dbl>, STL. <dbl>, BLK. <dbl>,
## #   TOV. <dbl>, USG. <dbl>, blanl <lgl>, OWS <dbl>, DWS <dbl>, WS <dbl>,
## #   WS.48 <dbl>, blank2 <lgl>, OBPM <dbl>, DBPM <dbl>, BPM <dbl>,
## #   VORP <dbl>, FG <int>, FGA <int>, FG. <dbl>, X3P <int>, X3PA <int>,
## #   X3P. <dbl>, X2P <int>, X2PA <int>, X2P. <dbl>, eFG. <dbl>, FT <int>,
## #   FTA <int>, FT. <dbl>, ORB <int>, DRB <int>, TRB <int>, AST <int>,
## #   STL <int>, BLK <int>, TOV <int>, PF <int>, PTS <int>

6) Create two new datasets. 1) a new dataset from the original dataset that includes all data except the age variable (be sure to give this dataset a new name). 2) a new dataset from the original dataset that includes the year, the player name, and age. 3) add a new column to both datasets called “mergeid” that includes a sequence of numbers beginning with a 1 in the first row of the data and ending with the total number of rows in the last row of the data (hint:“df1$mergeid<-seq(1,nrow(df1),1)”)

dataset1<-data2_tibble %>%
  select(Year,Pos,Tm:PTS)
dataset1[1:10,]

## # A tibble: 10 x 50
##     Year Pos   Tm        G    GS    MP   PER   TS. X3PAr   FTr  ORB.  DRB.
##    <int> <fct> <fct> <int> <int> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
##  1  1950 G-F   FTW      63    NA    NA    NA 0.368    NA 0.467    NA    NA
##  2  1950 SG    INO      49    NA    NA    NA 0.435    NA 0.387    NA    NA
##  3  1950 SF    CHS      67    NA    NA    NA 0.394    NA 0.259    NA    NA
##  4  1950 F     TOT      15    NA    NA    NA 0.312    NA 0.395    NA    NA
##  5  1950 F     DNN      13    NA    NA    NA 0.308    NA 0.378    NA    NA
##  6  1950 F     NYK       2    NA    NA    NA 0.376    NA 0.750    NA    NA
##  7  1950 G     INO      60    NA    NA    NA 0.422    NA 0.301    NA    NA
##  8  1950 G-F   TRI       3    NA    NA    NA 0.275    NA 0.313    NA    NA
##  9  1950 F-C   TOT      65    NA    NA    NA 0.346    NA 0.395    NA    NA
## 10  1950 F-C   FTW      36    NA    NA    NA 0.362    NA 0.480    NA    NA
## # ... with 38 more variables: TRB. <dbl>, AST. <dbl>, STL. <dbl>,
## #   BLK. <dbl>, TOV. <dbl>, USG. <dbl>, blanl <lgl>, OWS <dbl>, DWS <dbl>,
## #   WS <dbl>, WS.48 <dbl>, blank2 <lgl>, OBPM <dbl>, DBPM <dbl>,
## #   BPM <dbl>, VORP <dbl>, FG <int>, FGA <int>, FG. <dbl>, X3P <int>,
## #   X3PA <int>, X3P. <dbl>, X2P <int>, X2PA <int>, X2P. <dbl>, eFG. <dbl>,
## #   FT <int>, FTA <int>, FT. <dbl>, ORB <int>, DRB <int>, TRB <int>,
## #   AST <int>, STL <int>, BLK <int>, TOV <int>, PF <int>, PTS <int>

dataset2<-data2_tibble %>%
  select(Year,Player, Age)
dataset2[1:10,]

## # A tibble: 10 x 3
##     Year Player            Age
##    <int> <fct>           <int>
##  1  1950 Curly Armstrong    31
##  2  1950 Cliff Barker       29
##  3  1950 Leo Barnhorst      25
##  4  1950 Ed Bartels         24
##  5  1950 Ed Bartels         24
##  6  1950 Ed Bartels         24
##  7  1950 Ralph Beard        22
##  8  1950 Gene Berce         23
##  9  1950 Charlie Black      28
## 10  1950 Charlie Black      28

meigeid=seq(1,nrow(dataset1),1)
dataset3<-data.frame(meigeid,dataset1)
dataset3[1:10,]

##    meigeid Year Pos  Tm  G GS MP PER   TS. X3PAr   FTr ORB. DRB. TRB. AST.
## 1        1 1950 G-F FTW 63 NA NA  NA 0.368    NA 0.467   NA   NA   NA   NA
## 2        2 1950  SG INO 49 NA NA  NA 0.435    NA 0.387   NA   NA   NA   NA
## 3        3 1950  SF CHS 67 NA NA  NA 0.394    NA 0.259   NA   NA   NA   NA
## 4        4 1950   F TOT 15 NA NA  NA 0.312    NA 0.395   NA   NA   NA   NA
## 5        5 1950   F DNN 13 NA NA  NA 0.308    NA 0.378   NA   NA   NA   NA
## 6        6 1950   F NYK  2 NA NA  NA 0.376    NA 0.750   NA   NA   NA   NA
## 7        7 1950   G INO 60 NA NA  NA 0.422    NA 0.301   NA   NA   NA   NA
## 8        8 1950 G-F TRI  3 NA NA  NA 0.275    NA 0.313   NA   NA   NA   NA
## 9        9 1950 F-C TOT 65 NA NA  NA 0.346    NA 0.395   NA   NA   NA   NA
## 10      10 1950 F-C FTW 36 NA NA  NA 0.362    NA 0.480   NA   NA   NA   NA
##    STL. BLK. TOV. USG. blanl  OWS  DWS   WS WS.48 blank2 OBPM DBPM BPM
## 1    NA   NA   NA   NA    NA -0.1  3.6  3.5    NA     NA   NA   NA  NA
## 2    NA   NA   NA   NA    NA  1.6  0.6  2.2    NA     NA   NA   NA  NA
## 3    NA   NA   NA   NA    NA  0.9  2.8  3.6    NA     NA   NA   NA  NA
## 4    NA   NA   NA   NA    NA -0.5 -0.1 -0.6    NA     NA   NA   NA  NA
## 5    NA   NA   NA   NA    NA -0.5 -0.1 -0.6    NA     NA   NA   NA  NA
## 6    NA   NA   NA   NA    NA  0.0  0.0  0.0    NA     NA   NA   NA  NA
## 7    NA   NA   NA   NA    NA  3.6  1.2  4.8    NA     NA   NA   NA  NA
## 8    NA   NA   NA   NA    NA -0.1  0.0 -0.1    NA     NA   NA   NA  NA
## 9    NA   NA   NA   NA    NA -2.2  5.0  2.8    NA     NA   NA   NA  NA
## 10   NA   NA   NA   NA    NA -0.7  2.2  1.5    NA     NA   NA   NA  NA
##    VORP  FG FGA   FG. X3P X3PA X3P. X2P X2PA  X2P.  eFG.  FT FTA   FT. ORB
## 1    NA 144 516 0.279  NA   NA   NA 144  516 0.279 0.279 170 241 0.705  NA
## 2    NA 102 274 0.372  NA   NA   NA 102  274 0.372 0.372  75 106 0.708  NA
## 3    NA 174 499 0.349  NA   NA   NA 174  499 0.349 0.349  90 129 0.698  NA
## 4    NA  22  86 0.256  NA   NA   NA  22   86 0.256 0.256  19  34 0.559  NA
## 5    NA  21  82 0.256  NA   NA   NA  21   82 0.256 0.256  17  31 0.548  NA
## 6    NA   1   4 0.250  NA   NA   NA   1    4 0.250 0.250   2   3 0.667  NA
## 7    NA 340 936 0.363  NA   NA   NA 340  936 0.363 0.363 215 282 0.762  NA
## 8    NA   5  16 0.313  NA   NA   NA   5   16 0.313 0.313   0   5 0.000  NA
## 9    NA 226 813 0.278  NA   NA   NA 226  813 0.278 0.278 209 321 0.651  NA
## 10   NA 125 435 0.287  NA   NA   NA 125  435 0.287 0.287 132 209 0.632  NA
##    DRB TRB AST STL BLK TOV  PF PTS
## 1   NA  NA 176  NA  NA  NA 217 458
## 2   NA  NA 109  NA  NA  NA  99 279
## 3   NA  NA 140  NA  NA  NA 192 438
## 4   NA  NA  20  NA  NA  NA  29  63
## 5   NA  NA  20  NA  NA  NA  27  59
## 6   NA  NA   0  NA  NA  NA   2   4
## 7   NA  NA 233  NA  NA  NA 132 895
## 8   NA  NA   2  NA  NA  NA   6  10
## 9   NA  NA 163  NA  NA  NA 273 661
## 10  NA  NA  75  NA  NA  NA 140 382

dataset4<-data.frame(meigeid,dataset2)             
dataset4[1:10,]

##    meigeid Year          Player Age
## 1        1 1950 Curly Armstrong  31
## 2        2 1950    Cliff Barker  29
## 3        3 1950   Leo Barnhorst  25
## 4        4 1950      Ed Bartels  24
## 5        5 1950      Ed Bartels  24
## 6        6 1950      Ed Bartels  24
## 7        7 1950     Ralph Beard  22
## 8        8 1950      Gene Berce  23
## 9        9 1950   Charlie Black  28
## 10      10 1950   Charlie Black  28

7) Join the two datasets from question six together to recreate the original dataset plus the new merge id.

datasetjoin<-left_join(dataset3, dataset4, by="meigeid")
datasetjoin[1:10,]

##    meigeid Year.x Pos  Tm  G GS MP PER   TS. X3PAr   FTr ORB. DRB. TRB.
## 1        1   1950 G-F FTW 63 NA NA  NA 0.368    NA 0.467   NA   NA   NA
## 2        2   1950  SG INO 49 NA NA  NA 0.435    NA 0.387   NA   NA   NA
## 3        3   1950  SF CHS 67 NA NA  NA 0.394    NA 0.259   NA   NA   NA
## 4        4   1950   F TOT 15 NA NA  NA 0.312    NA 0.395   NA   NA   NA
## 5        5   1950   F DNN 13 NA NA  NA 0.308    NA 0.378   NA   NA   NA
## 6        6   1950   F NYK  2 NA NA  NA 0.376    NA 0.750   NA   NA   NA
## 7        7   1950   G INO 60 NA NA  NA 0.422    NA 0.301   NA   NA   NA
## 8        8   1950 G-F TRI  3 NA NA  NA 0.275    NA 0.313   NA   NA   NA
## 9        9   1950 F-C TOT 65 NA NA  NA 0.346    NA 0.395   NA   NA   NA
## 10      10   1950 F-C FTW 36 NA NA  NA 0.362    NA 0.480   NA   NA   NA
##    AST. STL. BLK. TOV. USG. blanl  OWS  DWS   WS WS.48 blank2 OBPM DBPM
## 1    NA   NA   NA   NA   NA    NA -0.1  3.6  3.5    NA     NA   NA   NA
## 2    NA   NA   NA   NA   NA    NA  1.6  0.6  2.2    NA     NA   NA   NA
## 3    NA   NA   NA   NA   NA    NA  0.9  2.8  3.6    NA     NA   NA   NA
## 4    NA   NA   NA   NA   NA    NA -0.5 -0.1 -0.6    NA     NA   NA   NA
## 5    NA   NA   NA   NA   NA    NA -0.5 -0.1 -0.6    NA     NA   NA   NA
## 6    NA   NA   NA   NA   NA    NA  0.0  0.0  0.0    NA     NA   NA   NA
## 7    NA   NA   NA   NA   NA    NA  3.6  1.2  4.8    NA     NA   NA   NA
## 8    NA   NA   NA   NA   NA    NA -0.1  0.0 -0.1    NA     NA   NA   NA
## 9    NA   NA   NA   NA   NA    NA -2.2  5.0  2.8    NA     NA   NA   NA
## 10   NA   NA   NA   NA   NA    NA -0.7  2.2  1.5    NA     NA   NA   NA
##    BPM VORP  FG FGA   FG. X3P X3PA X3P. X2P X2PA  X2P.  eFG.  FT FTA   FT.
## 1   NA   NA 144 516 0.279  NA   NA   NA 144  516 0.279 0.279 170 241 0.705
## 2   NA   NA 102 274 0.372  NA   NA   NA 102  274 0.372 0.372  75 106 0.708
## 3   NA   NA 174 499 0.349  NA   NA   NA 174  499 0.349 0.349  90 129 0.698
## 4   NA   NA  22  86 0.256  NA   NA   NA  22   86 0.256 0.256  19  34 0.559
## 5   NA   NA  21  82 0.256  NA   NA   NA  21   82 0.256 0.256  17  31 0.548
## 6   NA   NA   1   4 0.250  NA   NA   NA   1    4 0.250 0.250   2   3 0.667
## 7   NA   NA 340 936 0.363  NA   NA   NA 340  936 0.363 0.363 215 282 0.762
## 8   NA   NA   5  16 0.313  NA   NA   NA   5   16 0.313 0.313   0   5 0.000
## 9   NA   NA 226 813 0.278  NA   NA   NA 226  813 0.278 0.278 209 321 0.651
## 10  NA   NA 125 435 0.287  NA   NA   NA 125  435 0.287 0.287 132 209 0.632
##    ORB DRB TRB AST STL BLK TOV  PF PTS Year.y          Player Age
## 1   NA  NA  NA 176  NA  NA  NA 217 458   1950 Curly Armstrong  31
## 2   NA  NA  NA 109  NA  NA  NA  99 279   1950    Cliff Barker  29
## 3   NA  NA  NA 140  NA  NA  NA 192 438   1950   Leo Barnhorst  25
## 4   NA  NA  NA  20  NA  NA  NA  29  63   1950      Ed Bartels  24
## 5   NA  NA  NA  20  NA  NA  NA  27  59   1950      Ed Bartels  24
## 6   NA  NA  NA   0  NA  NA  NA   2   4   1950      Ed Bartels  24
## 7   NA  NA  NA 233  NA  NA  NA 132 895   1950     Ralph Beard  22
## 8   NA  NA  NA   2  NA  NA  NA   6  10   1950      Gene Berce  23
## 9   NA  NA  NA 163  NA  NA  NA 273 661   1950   Charlie Black  28
## 10  NA  NA  NA  75  NA  NA  NA 140 382   1950   Charlie Black  28

8) Subset the original dataset to 1995. Group the data by year and team name and then summarise the average number of points per team. (arrange from most to least points.)

dataset1995<-filter(data2_tibble,Year==1995)
datasetgroup<-group_by(dataset1995,Year,Tm)
datasetgroup[1:10,]

## # A tibble: 10 x 52
## # Groups:   Year, Tm [9]
##     Year Player   Pos     Age Tm        G    GS    MP   PER    TS.   X3PAr
##    <int> <fct>    <fct> <int> <fct> <int> <int> <int> <dbl>  <dbl>   <dbl>
##  1  1995 Alaa Ab~ PF       26 TOT      54     0   506  12.6 0.519  0.00900
##  2  1995 Alaa Ab~ PF       26 SAC      51     0   476  14.1 0.540  0.00900
##  3  1995 Alaa Ab~ PF       26 PHI       3     0    30 -12.5 0.0910 0      
##  4  1995 Mahmoud~ PG       25 DEN      73    43  2082  17.8 0.543  0.214  
##  5  1995 Michael~ PG       32 CHH      29     0   443  17.7 0.583  0.547  
##  6  1995 Rafael ~ SF       30 DET      79    16  1776  11.3 0.521  0.142  
##  7  1995 Danny A~ SG       35 PHO      74     1  1374  14.3 0.596  0.507  
##  8  1995 Victor ~ C        25 GSW      50    29  1237  12.8 0.530  0.0560 
##  9  1995 Derrick~ C        22 PHI      64     1  1032  11.6 0.481  0.0160 
## 10  1995 Greg An~ PF       30 ATL      51     0   622  12.6 0.547  0      
## # ... with 41 more variables: FTr <dbl>, ORB. <dbl>, DRB. <dbl>,
## #   TRB. <dbl>, AST. <dbl>, STL. <dbl>, BLK. <dbl>, TOV. <dbl>,
## #   USG. <dbl>, blanl <lgl>, OWS <dbl>, DWS <dbl>, WS <dbl>, WS.48 <dbl>,
## #   blank2 <lgl>, OBPM <dbl>, DBPM <dbl>, BPM <dbl>, VORP <dbl>, FG <int>,
## #   FGA <int>, FG. <dbl>, X3P <int>, X3PA <int>, X3P. <dbl>, X2P <int>,
## #   X2PA <int>, X2P. <dbl>, eFG. <dbl>, FT <int>, FTA <int>, FT. <dbl>,
## #   ORB <int>, DRB <int>, TRB <int>, AST <int>, STL <int>, BLK <int>,
## #   TOV <int>, PF <int>, PTS <int>

datasetsum<-summarise(datasetgroup, yearavg=mean(PTS, na.rm=TRUE))
datasetfinal<-arrange(datasetsum,desc(yearavg))
datasetfinal[1:10,]

## # A tibble: 10 x 3
## # Groups:   Year [1]
##     Year Tm    yearavg
##    <int> <fct>   <dbl>
##  1  1995 SEA       647
##  2  1995 ORL       606
##  3  1995 PHO       605
##  4  1995 DAL       604
##  5  1995 MIL       582
##  6  1995 UTA       582
##  7  1995 MIA       553
##  8  1995 SAS       546
##  9  1995 IND       542
## 10  1995 LAL       538

9) Let’s reshape the data in the previous question into a wide format using tidy. Create a wide dataset that keeps year in a single column, but spreads team names to multiple individual columns with each column delineating points per team in 1995. (hint: you should only have one year in the resulting data)

datasetspread<-spread(datasetfinal, Tm,yearavg)
datasetspread

## # A tibble: 1 x 29
## # Groups:   Year [1]
##    Year   ATL   BOS   CHH   CHI   CLE   DAL   DEN   DET   GSW   HOU   IND
##   <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1  1995   440   496   516   520   494   604   489   503   482   499   542
## # ... with 17 more variables: LAC <dbl>, LAL <dbl>, MIA <dbl>, MIL <dbl>,
## #   MIN <dbl>, NJN <dbl>, NYK <dbl>, ORL <dbl>, PHI <dbl>, PHO <dbl>,
## #   POR <dbl>, SAC <dbl>, SAS <dbl>, SEA <dbl>, TOT <dbl>, UTA <dbl>,
## #   WSB <dbl>

10) Now return the data to a long (tidy) format by moving teams back into a single column and points in a single column (data should include three columns: one for year, one for teams, and one for points.)

datasetgather<-datasetspread %>%
  gather(Tm,yearavg,c("ATL","BOS","CHH","CHI","CLE","DAL","DEN","DET","GSW","HOU","IND","LAC","LAL","MIA","MIL","MIN","NJN","NYK", "ORL","PHI","PHO", "POR","SAC","SAS","SEA", "TOT","UTA", "WSB"))
datasetgather[1:10,]

## # A tibble: 10 x 3
## # Groups:   Year [1]
##     Year Tm    yearavg
##    <int> <chr>   <dbl>
##  1  1995 ATL       440
##  2  1995 BOS       496
##  3  1995 CHH       516
##  4  1995 CHI       520
##  5  1995 CLE       494
##  6  1995 DAL       604
##  7  1995 DEN       489
##  8  1995 DET       503
##  9  1995 GSW       482
## 10  1995 HOU       499

link of Rmarkdown: http://rpubs.com/Junyu/357505

Homework2

JunyuMeng-jm4655

February 5,2018

Use tidyverse functions to answer the following questions:

1) Which NBA player scored the most points in 1991?

2) Which player had the best free throw percentage from the year 2000 to the most recent year in the data?

3) Rename the variable “pos” to “position”

4) Use this variable to create two variables that are called “first_position” and “second_position”. (hint:separate by splitting the position variable in two)

5) Unite these two variables back into a single variable called “position_united”

7) Join the two datasets from question six together to recreate the original dataset plus the new merge id.

8) Subset the original dataset to 1995. Group the data by year and team name and then summarise the average number of points per team. (arrange from most to least points.)

10) Now return the data to a long (tidy) format by moving teams back into a single column and points in a single column (data should include three columns: one for year, one for teams, and one for points.)