> tekstid <- read_csv("http://www.tlu.ee/~kais/Kvant_digihum/keeletasemed200.csv")
Parsed with column specification:
cols(
  kood = col_character(),
  eksam = col_character(),
  keeletase = col_character(),
  sonad = col_double(),
  spikkus = col_double(),
  lpikkus = col_double(),
  lemmad = col_double(),
  yld_kaanded = col_double()
)


> arrange(tekstid, sonad)
# A tibble: 220 x 8
   kood          eksam    keeletase sonad spikkus lpikkus lemmad yld_kaanded
   <chr>         <chr>    <chr>     <dbl>   <dbl>   <dbl>  <dbl>       <dbl>
 1 A2III_001-007 2018_III A2           28    4.89    5.6      22           6
 2 A2II_001-010  2018_II  A2           31    5.10    5.17     26           7
 3 A2III_003-031 2018_III A2           32    4.5     5.33     23           5
 4 A2I_001-071   2018_I   A2           33    5.46    4.71     22           7
 5 A2III_001-006 2018_III A2           34    4.35    4.86     28           4
 6 A2IV_002-007  2018_IV  A2           34    6.12    6.8      26           6
 7 A2II_002-066  2018_II  A2           34    4.56    5.67     27           5
 8 A2III_002-033 2018_III A2           34    4.44    6.8      24           6
 9 A2IV_003-031  2018_IV  A2           34    5.74    5.67     26           6
10 A2III_003-002 2018_III A2           35    4.63    3.5      27           5
# … with 210 more rows


> arrange(tekstid, desc(sonad))
# A tibble: 220 x 8
   kood               eksam    keeletase sonad spikkus lpikkus lemmad yld_kaanded
   <chr>              <chr>    <chr>     <dbl>   <dbl>   <dbl>  <dbl>       <dbl>
 1 C1_2017III_001-002 2017_III C1          351    6.02    13      199          11
 2 C1_2017IV_001-028  2017_IV  C1          345    5.65    14.4    157          10
 3 C1_2017I_001-039   2017_I   C1          312    6.31    14.9    193          10
 4 C1_2018I_001-038   2018_I   C1          309    5.82    16.3    161          11
 5 C1_2017II_001-068  2017_II  C1          297    5.38    12.9    154          12
 6 B2IV_002-031       2018_IV  B2          290    5.38    20.7    123          10
 7 C1_2017III_001-007 2017_III C1          289    6.69    15.2    172           9
 8 C1_2017II_001-129  2017_II  C1          285    6.45    14.2    159          13
 9 C1_2018IV_002-036  2018_IV  C1          284    6.34    14.9    158          12
10 C1_2018III_003-052 2018_III C1          283    5.93    15.7    150          11
# … with 210 more rows


> tekstid %>% filter(keeletase=="A2") %>% arrange(desc(yld_kaanded))
# A tibble: 60 x 8
   kood          eksam    keeletase sonad spikkus lpikkus lemmad yld_kaanded
   <chr>         <chr>    <chr>     <dbl>   <dbl>   <dbl>  <dbl>       <dbl>
 1 A2I_001-027   2018_I   A2           75    4.77    6.25     45          10
 2 A2II_004-050  2018_II  A2           54    4.35    6.75     39           9
 3 A2I_001-023   2018_I   A2           38    5.74    6.33     26           8
 4 A2II_002-026  2018_II  A2           43    5       6.14     33           8
 5 A2I_001-065   2018_I   A2           47    5.11    5.22     41           8
 6 A2II_004-051  2018_II  A2           58    4.28    9.67     38           8
 7 A2III_003-012 2018_III A2           56    4.46    8        46           8
 8 A2I_001-015   2018_I   A2           72    4.19    6        43           7
 9 A2I_001-025   2018_I   A2           61    5.46    7.62     43           7
10 A2II_001-010  2018_II  A2           31    5.10    5.17     26           7
# … with 50 more rows


> tekstid %>% group_by(keeletase) %>% summarise(keskpikkus=mean(sonad), minpikkus=min(sonad), makspikkus=max(sonad))
# A tibble: 4 x 4
  keeletase keskpikkus minpikkus makspikkus
  <chr>          <dbl>     <dbl>      <dbl>
1 A2              46.7        28         87
2 B1             107.         72        180
3 B2             166.        111        290
4 C1             258.        201        351


> tekstid %>% group_by(keeletase) %>% summarise(kesklause=mean(lpikkus), minlause=min(lpikkus), makslause=max(lpikkus))
# A tibble: 4 x 4
  keeletase kesklause minlause makslause
  <chr>         <dbl>    <dbl>     <dbl>
1 A2             5.78     3.5       9.67
2 B1             8.05     4.54     14   
3 B2            11.5      7.12     20.7 
4 C1            13.3      9.54     18.9


> tekstid %>% group_by(keeletase) %>% summarise_if(is.numeric, c(kesk=mean, med=median, min=min, maks=max))
# A tibble: 4 x 21
  keeletase sonad_kesk spikkus_kesk lpikkus_kesk lemmad_kesk yld_kaanded_kesk sonad_med
  <chr>          <dbl>        <dbl>        <dbl>       <dbl>            <dbl>     <dbl>
1 A2              46.7         4.88         5.78        33.1             6.35       44 
2 B1             107.          5.12         8.05        61.7             8.18      106.
3 B2             166.          5.29        11.5         94.0             9.08      160.
4 C1             258.          6.28        13.3        147.             10.8       254 
# … with 14 more variables: spikkus_med <dbl>, lpikkus_med <dbl>, lemmad_med <dbl>,
#   yld_kaanded_med <dbl>, sonad_min <dbl>, spikkus_min <dbl>, lpikkus_min <dbl>,
#   lemmad_min <dbl>, yld_kaanded_min <dbl>, sonad_maks <dbl>, spikkus_maks <dbl>,
#   lpikkus_maks <dbl>, lemmad_maks <dbl>, yld_kaanded_maks <dbl>


> View(tekstid %>% group_by(keeletase) %>% summarise_if(is.numeric, c(kesk=mean, med=median, min=min, maks=max)))



> tekstid %>% filter(keeletase=="B1") %>% group_by(eksam) %>% summarise_if(is.numeric, c(keskm=mean))
# A tibble: 4 x 6
  eksam    sonad_keskm spikkus_keskm lpikkus_keskm lemmad_keskm yld_kaanded_keskm
  <chr>          <dbl>         <dbl>         <dbl>        <dbl>             <dbl>
1 2018_I         123.           4.65          9.17         64.7              8.67
2 2018_II        103.           4.82          6.91         62.9              7.8 
3 2018_III        99.2          5.57          7.51         59.5              8.6 
4 2018_IV        105.           5.43          8.62         59.7              7.67