add funk, ana tut, r

sose2021/r/w04/P04-1.R

@@ -0,0 +1,27 @@
+# Josua Kugler, Christian Merten
+
+library(tidyverse)
+
+`%o%` <- function(f, g) function(...) f(g(...))
+
+# ich bin mal so dreist und lese das gesamte file direkt ein
+# wenn hier unbedingt read_lines verwendet werden soll, dann füge
+# man eben zuerst mit paste alle zeilen wieder zusammen
+lines <- read_file("books.txt")
+
+sort_char <- function(s) paste(sort(unlist(str_split(s, ""))), sep="", collapse="")
+
+cleared <- str_match_all(str_to_upper(str_replace_all(lines,
+                                                      pattern="\\(.*?\\)|[^a-zA-Z0-9]",
+                                                      replacement="")),
+                         "([A-Z]+)([0-9]+)")[[1]]
+
+unsorted_data <- tibble(category = sapply(cleared[,2], sort_char),
+                        count = as.integer(cleared[,3]))
+
+data <- unsorted_data[order(unsorted_data[,1]),]
+
+books_of_category <- function(data, cat_let) {
+    apply(data[str_detect(data$category, cat_let), ], 1,
+          function(x) str_glue("We have {x[2]} books of category {x[1]}"))
+}

sose2021/r/w04/P04-2.R

@@ -0,0 +1,112 @@
+# Josua Kugler, Christian Merten
+
+# install.packages("babynames")
+library(tidyverse)
+
+## Create some data-----------------------------------------------------------
+
+set.seed(1)
+
+baseset <- list()
+baseset$grade <- as.integer(c(5,6,7,8,9,10,11))
+baseset$grade_boost <- c(1,3,5,7,8,9,10)
+baseset$letter <- letters[1:4]
+baseset$letter_boost <- sample(1:5, 4, replace=T)
+babynames::babynames %>%
+  group_by(sex, name) %>% 
+  summarise(n = sum(n)) %>%
+  arrange(desc(n)) %>%
+  mutate(rank = min_rank(-n)) %>% 
+  filter (rank <= 3000) ->
+  ranked_names
+baseset$name <- ranked_names$name
+baseset$distance <- c(100,200,400,1000)
+baseset$distance_boost <- c(14,12,10,8)
+
+sample_observation <- function(n) {
+  res <- list()
+  res$name <- sample(baseset$name, n, replace=T)
+  res$grade <- sample(baseset$grade, n, replace=T)
+  res$letter <- sample(baseset$letter, n, replace=T)
+  boost_base <- 
+    baseset$grade_boost[match(res$grade,baseset$grade)] + 
+    baseset$letter_boost[match(res$letter,baseset$letter)]
+  res$time100 <- sample_time(100, baseset$distance_boost[1] + boost_base)
+  res$time200 <- sample_time(200, baseset$distance_boost[2] + boost_base)
+  res$time400 <- sample_time(400, baseset$distance_boost[3] + boost_base)
+  res$time1000 <- sample_time(1000, baseset$distance_boost[4] + boost_base)
+  as_tibble(res)
+}
+
+sample_time <- function(dist, boost) {
+  (runif(length(boost))/2+2.5)/boost*dist*2
+}
+
+sports <- sample_observation(1000)
+
+requirements <- tibble(
+  level = 1:11,
+  min100 = seq(43,23,len=11),
+  min1000 = seq(500,300,len=11)
+)
+
+
+
+## Exercises -----------------------------------------------------------------
+
+# a) 
+# sort sports by 'name' (alphabetically)
+arrange(sports, name)
+
+# b) 
+# sort sports by 'grade' (11, 10, ..., 5), 
+# in case of ties by 'letter' (a, b, d, e),
+# in case of ties by 'name' (A-Z)
+arrange(sports, grade, letter, name)
+
+# c)
+# count the numbers of students per class
+sports %>% group_by(grade, letter) %>% summarize(student_count = n())
+
+# d)
+# what is the mean, max and min class size
+sports %>%
+    group_by(grade, letter) %>%
+    summarize(student_count = n()) %>%
+    ungroup() %>%
+    summarize(mean_class_size = mean(student_count),
+              max_class_size = max(student_count),
+              min_class_size = min(student_count))
+
+# e)
+# get all students with a non-unqiue name
+sports %>% group_by(name) %>% filter(n()>1)
+
+# f)
+# get the top 10 sprinters (100m)
+sports %>% top_n(10, -time100)
+
+# g)
+# get the slowest 10 sprinters (100m)
+sports %>% top_n(10, time100)
+
+# h)
+# remove 100m, 200m, and 400m, and add velocity in km/h for 1000m
+sports %>% mutate(velocity = 60*60/time1000) %>% select(-(time100:time1000))
+
+# i)
+# rename 'grade' to 'level'
+sports %>% rename(level = grade)
+
+# j)
+# calculate average and min times for 200m in each grade
+sports %>% group_by(grade) %>% summarize(average200 = mean(time200), min200 = min(time200))
+
+# k)
+# select all time-columns
+sports %>% select(time100:time1000)
+
+# l)
+# show the fastest sprinter (100m) in each class 
+# sorted by class (ie by grade and letter)
+sports %>% group_by(grade, letter) %>% top_n(1, -time100) %>% arrange(grade, letter)

sose2021/r/w04/books.txt

@@ -0,0 +1,65 @@
+R S V C E W Y: 25
+vqayl 18 (plus minus25)
+wl: 16; MUST - 16; HCUDM: 14; LBR: 20
+c u g m h: 22
+BLZJ 24; FEJB - 27; xsa: 20; LDECK 15; S,K: 27. WOAC: 18; WORZE - 26. PRK 25
+L G U K E 19; w j x n 26
+XTL: 16; O Y B - 35. XHBWK - 18. AXUPL: 31; YELJ 13; d,r,c,l: 26. QEGX: 21
+RALM 26. G,K,I,W: 12; IJXC: 19. HPZAY: 19; JSPCO: 22; BIXE: 12
+VTG: 26
+dce: 25
+P J W 23
+AMFE: 15; YBA: 12; yxb: 26
+GV 19; SA 23; PTQ: 17; VHIC: 22; K W R A: 22; U V E B Y 23
+LEQZN 17; MJ - 11; MWQ: 24; LFOJKG: 28
+PJWUQ: 20. jqpk 14. FKZN 30
+HKWLDP 21; IVKTFSQ 22. QNA 25; Z X V S: 25. K X 17
+SEJ 18. FRYA: 14
+O H E: 19; WT 24. YJCHDNG: 22. JXAV: 22; XQSAT: 27
+W,M,Z,Y - 20; SVF: 17; IHNU 15
+KPVL: 12
+EMADH 30
+HFSAOJ 26
+LPVK: 21; LEM: 22. RDWCXA: 15; YEAU 16
+JCNW: 22 (nicht24)
+F,B,T,W,I,C: 13; QPMZ: 18; albio 22
+r g - 18; tudnp 13; IEWRBLT: 14; V: 20
+sefmdb: 25. WMFC: 14; k 30. V U E G: 17; nsfz: 23. O E C A: 21. N X V: 27
+REGS: 19; DZ: 22
+K Y - 14
+EH: 25; QVB: 24. B H E O N - 30; CH - 23
+AWXC: 18; VGDFZ: 20. ME: 12; YJBA 30. LYXUTHM: 21; D P M W E R 28; mrkavsj: 23; u p y t: 18
+HEINBFZ: 14; SGDLRK 25. G,M,Y,K,R: 19. UHRJT: 19
+OD: 30. PAJZYFH 24; h,v,r,x,w: 36 (plus minus15); DBNW: 24; ZJQWGSC: 26; M B X: 20
+YBCK: 21
+rclgi: 22. nkzpbg 19 (letztes Jahr15); VXZE: 21
+YHZ: 21
+LGTA: 26. K A G: 23. rvg: 20; UTIV - 19; FMVIPRT: 20 (letztes Jahr22)
+P Q X Y N O - 22
+ZSLHRY 27; KOMEN: 28; vf: 27; F W R 26 (soll:23); Y,X,D: 17; HKDM - 16; QMIGNSY: 16; G S Z - 20 (nicht24); DWUERKH - 24 (soll:20)
+L M E G: 16. ifelp: 28. AKQT: 20; BFQTX: 25; JBVWS 21; R Z 16; FGQCEV - 24; NEOF 19
+L R I: 19; Z H C W R: 27; A,V,W,L,U,E,T: 23; it: 32. o r p 20
+e,h: 14. TJSRHFD 25; MOLCHX: 24
+YAK: 21. m d e b 19
+DTOAMNWC: 14
+WNPSBZ 25; WYBNKD 16; xcosjtg 26
+t,s,z,o,f,w,y,a: 26. X,N,J,D: 22
+tefyk 20; V J B R K: 21
+JPEM: 17
+R: 22; CWGH 24 (soll:15)
+GZPA: 12
+LJSGP: 32
+KZBMNH: 26; ILZWJR - 18; GSUC: 20
+Q I N - 22 (nicht28)
+WUDMG: 18. GQAVW: 15
+w: 26; EDZ: 25
+DIX - 9. x n m k f: 17; L Z R O Y V M: 20; QAGVHB: 21; D A H T Q S: 16
+ZGAOI: 22; LICZM: 20. ZHDBKMLU: 21
+FCJUH: 20. IHJVSWB: 18; D F W G: 22. FKWSRM 30. G,M,O 26
+EKI: 18; unm - 22; CZWA: 18; PZML: 25; FVCUY: 27. Z,B,G,X,J,H - 21
+imvx: 21. cd: 27; YVCZQG 22
+XTVI: 20
+GVCDXBNK: 23
+LFGX: 26. EKMV 25; lhdika: 21; OGHLB 21
+PANDMC: 24
+twb: 20