--- title: "andmed" output: html_document --- ```r rnorm(10, 170, 10) #Kogus, keskväärtus, standardhälve ``` ``` ## [1] 183.6060 167.3414 165.6200 171.1106 183.9981 179.2919 166.1464 ## [8] 186.7021 174.6433 179.6424 ``` ```r round(rnorm(10, 170, 10)) ``` ``` ## [1] 161 170 172 162 163 172 165 158 187 162 ``` ```r sort(round(rnorm(10, 170, 10))) ``` ``` ## [1] 156 156 158 164 166 167 171 173 174 183 ``` ```r rev(sort(round(rnorm(10, 170, 10)))) ``` ``` ## [1] 184 181 178 175 175 174 172 170 155 147 ``` ```r set.seed(258) #Juhuarvugeneraatori algväärtus round(rnorm(10, 170, 10)) ``` ``` ## [1] 179 169 179 181 170 173 172 183 180 178 ``` ```r round(rnorm(10, 170, 10)) ``` ``` ## [1] 162 172 171 148 166 170 158 152 170 179 ``` ```r eesnimed=c("Juku" ,"Kati", "Mati", "Madis", "Mari", "Martin") sample(eesnimed, 3) ``` ``` ## [1] "Martin" "Mari" "Juku" ``` ```r sample(eesnimed, 3) ``` ``` ## [1] "Mari" "Mati" "Kati" ``` ```r head(mtcars) #näitandmed 70ndate autodega ``` ``` ## mpg cyl disp hp drat wt qsec vs am gear carb ## Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4 ## Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4 ## Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1 ## Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1 ## Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2 ## Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1 ``` ```r mtcars[1:3, ] #Kolm esimest rida ``` ``` ## mpg cyl disp hp drat wt qsec vs am gear carb ## Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4 ## Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4 ## Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1 ``` ```r mtcars[sample(1:nrow(mtcars), 5),] #5 juhuslikku autot, nrows- ridade arv ``` ``` ## mpg cyl disp hp drat wt qsec vs am gear carb ## Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4 ## Merc 450SLC 15.2 8 275.8 180 3.07 3.780 18.00 0 0 3 3 ## Ford Pantera L 15.8 8 351.0 264 4.22 3.170 14.50 0 1 5 4 ## Toyota Corolla 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1 ## Chrysler Imperial 14.7 8 440.0 230 3.23 5.345 17.42 0 0 3 4 ``` ```r #Harjutus - arvutage kümne juhusliku auto keskmine mpg (miles per gallon) mean(mtcars[sample(1:nrow(mtcars), 10),"mpg"]) ``` ``` ## [1] 20.64 ``` ```r #mtcars$mpg 1:nrow(mtcars) ``` ``` ## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 ## [24] 24 25 26 27 28 29 30 31 32 ``` ```r sample(5:32, 10) #esimest nelja ei vali ``` ``` ## [1] 9 7 24 16 30 6 12 10 29 28 ``` ```r #Viiel korral käivitatakse käsklust, kus valitakse kümne juhusliku auto keskmine sapply(1:5, function(i){ mean(mtcars[sample(1:nrow(mtcars), 10),"mpg"])}) ``` ``` ## [1] 21.03 19.85 19.84 21.45 18.54 ``` ```r hist(sapply(1:100, function(i){ mean(mtcars[sample(1:nrow(mtcars), 10),"mpg"])})) ```

```r summary(sapply(1:100, function(i){ mean(mtcars[sample(1:nrow(mtcars), 5),"mpg"])})) ``` ``` ## Min. 1st Qu. Median Mean 3rd Qu. Max. ## 14.68 18.86 20.06 19.99 21.24 26.06 ``` ```r sample(eesnimed, 10, replace=TRUE) #Kordused lubatud ``` ``` ## [1] "Mati" "Mati" "Madis" "Juku" "Madis" "Juku" "Juku" ## [8] "Martin" "Kati" "Mari" ``` ```r #bussiooteaeg ühtlase jaotuse järgi 0-7 min runif(1, 0, 7) #üks väärtus random uniform ``` ``` ## [1] 5.42535 ``` ```r runif(20, 0, 7) ``` ``` ## [1] 5.77247319 2.58999152 3.32226904 1.96473961 1.40787691 4.17666601 ## [7] 0.06701862 5.62912596 2.80423478 6.32425679 5.70144005 4.04969707 ## [13] 1.86213824 1.03944634 2.05853889 1.02489841 1.69111271 5.80053457 ## [19] 6.91361361 4.49201933 ``` ```r #Püüdke modelleerida bussiga kohale jõudmise aega: #ooteaeg 0-7 minutit ühtlase jaotuse järgi, #Sõiduaeg normaaljaotusega keskväärtusega 20 minutit, standardhälve 3 minutit #Tekitage käsuga üks tulemus, korrake käsku, jälgige tulemusi runif(1, 0, 7)+rnorm(1, 20, 3) ``` ``` ## [1] 17.41337 ``` ```r #Leidke, mitmel juhul sajast oli kohale jõudmise aeg üle 25 minuti sapply(1:100, function(i){runif(1, 0, 7)+rnorm(1, 20, 3)}) ``` ``` ## [1] 29.11322 21.71840 23.58097 22.28106 21.55456 29.75523 30.11284 ## [8] 25.97437 17.09062 21.58720 27.89258 21.43209 25.41527 23.74427 ## [15] 23.77225 21.69429 26.31299 17.92246 23.95913 16.93469 27.83307 ## [22] 27.20376 20.66867 25.91598 24.23704 19.07705 26.09275 26.32807 ## [29] 24.99013 18.36085 30.50155 25.70791 22.94316 28.39643 17.02537 ## [36] 23.19889 31.10508 22.74684 23.16333 23.34466 29.59527 26.95016 ## [43] 23.59573 25.47840 20.42723 26.41380 28.75433 27.31718 27.33992 ## [50] 18.74272 24.60766 25.18463 21.65846 19.98717 23.19538 25.04167 ## [57] 22.07836 23.99556 26.93769 16.51895 22.90385 26.42548 23.47269 ## [64] 13.44981 28.14308 23.05273 20.14640 20.24029 27.01863 23.32243 ## [71] 15.86142 24.20807 24.67220 20.39500 23.07053 24.87616 21.16198 ## [78] 25.37083 23.35999 24.35513 28.08235 25.32993 17.42529 21.65088 ## [85] 27.35891 27.30793 27.40201 24.25352 27.82874 24.35449 25.80345 ## [92] 24.13197 25.70148 21.69222 23.83253 22.42461 24.18690 29.16936 ## [99] 23.85800 26.43971 ``` ```r sapply(1:100, function(i){runif(1, 0, 7)+rnorm(1, 20, 3)})>25 ``` ``` ## [1] TRUE TRUE FALSE FALSE TRUE FALSE FALSE TRUE TRUE TRUE FALSE ## [12] FALSE FALSE TRUE FALSE FALSE FALSE FALSE TRUE FALSE FALSE TRUE ## [23] FALSE TRUE FALSE FALSE TRUE TRUE FALSE FALSE FALSE FALSE TRUE ## [34] TRUE TRUE FALSE FALSE FALSE FALSE FALSE FALSE TRUE TRUE FALSE ## [45] TRUE FALSE FALSE TRUE FALSE FALSE FALSE TRUE FALSE TRUE TRUE ## [56] FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE TRUE FALSE TRUE ## [67] FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE ## [78] TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE ## [89] FALSE TRUE TRUE FALSE FALSE FALSE FALSE TRUE FALSE TRUE FALSE ## [100] TRUE ``` ```r ajad=sapply(1:100, function(i){runif(1, 0, 7)+rnorm(1, 20, 3)}) length(ajad[ajad>25]) ``` ``` ## [1] 37 ``` ```r #ajad[ajad>25] ajad=sapply(1:100, function(i){runif(1, 0, 7)+rnorm(1, 20, 3)}) length(ajad[ajad>30]) #veidi pikem minekuaeg ``` ``` ## [1] 2 ``` ```r #http://www.tlu.ee/~jaagup/andmed/muu/ounad/ounad3_100.txt ounad3_100=read.table("http://www.tlu.ee/~jaagup/andmed/muu/ounad/ounad3_100.txt", header=TRUE, sep=",") ounad2=edit(ounad3_100) antoonovkad=ounad3_100[ounad3_100$ounasort=="Antoonovka", "diameeter"] antoonovkad ``` ``` ## [1] 7.57 6.06 10.63 5.72 7.47 10.16 7.73 7.75 4.76 6.90 8.48 ## [12] 7.28 3.87 7.46 7.78 8.01 6.05 6.92 8.13 7.71 2.26 7.91 ## [23] 6.29 7.21 8.21 5.35 6.72 9.51 5.16 6.14 3.61 3.87 ``` ```r (antoonovkad=ounad3_100[ounad3_100$ounasort=="Antoonovka", "diameeter"]) ``` ``` ## [1] 7.57 6.06 10.63 5.72 7.47 10.16 7.73 7.75 4.76 6.90 8.48 ## [12] 7.28 3.87 7.46 7.78 8.01 6.05 6.92 8.13 7.71 2.26 7.91 ## [23] 6.29 7.21 8.21 5.35 6.72 9.51 5.16 6.14 3.61 3.87 ``` ```r t.test(antoonovkad) ``` ``` ## ## One Sample t-test ## ## data: antoonovkad ## t = 20.722, df = 31, p-value < 2.2e-16 ## alternative hypothesis: true mean is not equal to 0 ## 95 percent confidence interval: ## 6.16115 7.50635 ## sample estimates: ## mean of x ## 6.83375 ``` ```r t.test(antoonovkad, conf.level=0.9) ``` ``` ## ## One Sample t-test ## ## data: antoonovkad ## t = 20.722, df = 31, p-value < 2.2e-16 ## alternative hypothesis: true mean is not equal to 0 ## 90 percent confidence interval: ## 6.274594 7.392906 ## sample estimates: ## mean of x ## 6.83375 ``` ```r #Leidke Kuldrenettide keskmise diameetri usaldusvahemik 99% täpsusega t.test(antoonovkad, mu=7.5, alternative="less") ``` ``` ## ## One Sample t-test ## ## data: antoonovkad ## t = -2.0203, df = 31, p-value = 0.02603 ## alternative hypothesis: true mean is less than 7.5 ## 95 percent confidence interval: ## -Inf 7.392906 ## sample estimates: ## mean of x ## 6.83375 ``` ```r mean(antoonovkad) ``` ``` ## [1] 6.83375 ``` ```r sd(antoonovkad) ``` ``` ## [1] 1.865543 ``` ```r x=seq(3, 10, 0.1) y=dnorm(x, mean(antoonovkad), sd(antoonovkad)) plot(x, y, type="l") # l nagu line qnorm(0.95, mean(antoonovkad), sd(antoonovkad)) ``` ``` ## [1] 9.902295 ``` ```r abline(v=qnorm(0.95, mean(antoonovkad), sd(antoonovkad))) ```

```r #95% antoonovkate valimi jaotusega üldkogumist võiksid olla #väiksemad kui 9,9 #Näidake diameeter, millest nende parameetritega normaaljaotuse puhul #on õuntest väiksemad 25%, tõmmake vastav joon kuldrenetid=ounad3_100[ounad3_100$ounasort=="Kuldrenett", "diameeter"] kuldrenetid ``` ``` ## [1] 4.47 5.73 2.52 0.36 3.10 0.83 2.96 5.86 5.02 1.93 6.48 3.10 1.76 4.58 ## [15] 1.96 3.43 6.66 8.75 2.55 2.73 5.80 4.96 5.74 2.18 2.09 2.41 5.10 0.87 ## [29] 6.31 5.35 2.25 3.13 3.51 3.51 0.90 5.45 ``` ```r t.test(antoonovkad, kuldrenetid) ``` ``` ## ## Welch Two Sample t-test ## ## data: antoonovkad and kuldrenetid ## t = 6.6421, df = 65.779, p-value = 7.069e-09 ## alternative hypothesis: true difference in means is not equal to 0 ## 95 percent confidence interval: ## 2.169562 4.034605 ## sample estimates: ## mean of x mean of y ## 6.833750 3.731667 ``` ```r #95 percent confidence interval: # 2.169562 4.034605 attributes(t.test(antoonovkad, kuldrenetid)) ``` ``` ## $names ## [1] "statistic" "parameter" "p.value" "conf.int" "estimate" ## [6] "null.value" "alternative" "method" "data.name" ## ## $class ## [1] "htest" ``` ```r t.test(antoonovkad, kuldrenetid)[["conf.int"]] ``` ``` ## [1] 2.169562 4.034605 ## attr(,"conf.level") ## [1] 0.95 ``` ```r t.test(antoonovkad, kuldrenetid)[["conf.int"]][1] ``` ``` ## [1] 2.169562 ``` ```r piirid=round(t.test(antoonovkad, kuldrenetid)[["conf.int"]], 2) paste('Antoonovkad on 95% tõenäosusega suuremad ', piirid[1], 'kuni', piirid[2], "cm") ``` ``` ## [1] "Antoonovkad on 95% tõenäosusega suuremad 2.17 kuni 4.03 cm" ``` ```r #Kuvage Antoonovkate ja Liivi sibulõunte keskmise diameetri erinevus #välja 90% tõenäosusega ```