#kreiranje tabela osnovni na?in
##radimo na WHO
list.files()
## [1] "1.instal-vectori-i-df.html" "1.instal vectori i df.R"
## [3] "2.indeksiranje.html" "2.indeksiranje.R"
## [5] "3.Na.html" "3.Na.R"
## [7] "4.tables-in-R.html" "4.tables-in-R.R"
## [9] "4.tables-in-R.spin.R" "4.tables-in-R.spin.Rmd"
## [11] "4.tables in R.R" "importing big files in.R"
## [13] "indeksiranje - brisati.R" "install-old-package.html"
## [15] "install old package.R" "List of packages-for classes.txt"
## [17] "mydf.csv" "report.xlsx"
## [19] "rsconnect" "startanje-u-R.html"
## [21] "startanje u R.R" "tabels-in-Rmd-5pcgs.docx"
## [23] "tabels-in-Rmd-5pcgs.html" "tabels-in-Rmd-5pcgs.knit.md"
## [25] "tabels in Rmd 5pcgs.Rmd" "Tokyo_updated.xlsx"
## [27] "update R.txt" "Uvod u R i R studio_R-figure"
## [29] "WHO.csv" "WHO_labelled.csv"
## [31] "Zadaci lesson 1.docx" "Zadaci nakon lesson 1.R"
Tokyo_updated <- readxl::read_xlsx("Tokyo_updated.xlsx") #mozemo importovati i na ovaj nacin nismo pozvali library () nego smo prisli funkciji preko dvije tacke
## New names:
## • `` -> `...13`
str(Tokyo_updated)
## tibble [1,884 × 13] (S3: tbl_df/tbl/data.frame)
## $ Store : chr [1:1884] "Tokyo" "Tokyo" "Tokyo" "Tokyo" ...
## $ Brand : chr [1:1884] "Asics" "Asics" "Asics" "Asics" ...
## $ Type : chr [1:1884] "WB1820" "Kayano Single Tab" "WB1820" "WB2585" ...
## $ Gender : chr [1:1884] "Female" "Unisex" "Female" "Female" ...
## $ Size : chr [1:1884] "42" "42-44" "37" "39" ...
## $ Color : chr [1:1884] "Blue" "Blue" "Pink" "Black" ...
## $ Category : chr [1:1884] "Pants" "Socks" "Pants" "Pants" ...
## $ Sales Price: num [1:1884] 89 25 89 99 89 ...
## $ Date : POSIXct[1:1884], format: "2015-07-15" "2015-07-15" ...
## $ Time : POSIXct[1:1884], format: "1899-12-31 07:32:09" "1899-12-31 07:33:36" ...
## $ Loyalty : chr [1:1884] "41842" "46176" "---" "40444" ...
## $ Month : num [1:1884] 7 7 7 7 7 7 7 7 7 7 ...
## $ ...13 : num [1:1884] 29 29 29 29 29 29 29 29 29 29 ...
table (Tokyo_updated$Brand)
##
## Adidas Asics Nike
## 213 1058 613
table (Tokyo_updated$Store)
##
## Tokyo
## 1884
#ako zelimo dva elementa u tabeli onda nam obje varijable moraju biti kategoricke.
table(Tokyo_updated$Brand, Tokyo_updated$Gender)
##
## Female Male Unisex
## Adidas 87 126 0
## Asics 570 288 200
## Nike 253 49 311
tabela <- table (Tokyo_updated$Brand, Tokyo_updated$Gender)
tabela
##
## Female Male Unisex
## Adidas 87 126 0
## Asics 570 288 200
## Nike 253 49 311
prop.table(tabela,1)
##
## Female Male Unisex
## Adidas 0.40845070 0.59154930 0.00000000
## Asics 0.53875236 0.27221172 0.18903592
## Nike 0.41272431 0.07993475 0.50734095
prop.table(tabela,2)
##
## Female Male Unisex
## Adidas 0.0956044 0.2721382 0.0000000
## Asics 0.6263736 0.6220302 0.3913894
## Nike 0.2780220 0.1058315 0.6086106
#install.packages ("tableone")----
#install.packages ("purrr")
#install.packages ("glue")
library(tableone)
CreateTableOne(data=Tokyo_updated, vars = c("Brand","Sales Price" ), strata = c("Gender")) # izbacuje mean i sd u odnosu na stratu
## Stratified by Gender
## Female Male Unisex p
## n 910 463 511
## Brand (%) <0.001
## Adidas 87 ( 9.6) 126 (27.2) 0 ( 0.0)
## Asics 570 (62.6) 288 (62.2) 200 (39.1)
## Nike 253 (27.8) 49 (10.6) 311 (60.9)
## Sales Price (mean (SD)) 100.31 (44.07) 125.89 (39.76) 21.10 (2.10) <0.001
## Stratified by Gender
## test
## n
## Brand (%)
## Adidas
## Asics
## Nike
## Sales Price (mean (SD))
#da ova formula profunkcionise moramo instalirati pakete glue i purrr
#objasnjenje za mean i sd - tzv apply funkcije
tapply(Tokyo_updated$`Sales Price`, Tokyo_updated$Gender, mean)
## Female Male Unisex
## 100.30777 125.89417 21.10162
tapply(Tokyo_updated$`Sales Price`, Tokyo_updated$Gender, sd)
## Female Male Unisex
## 44.065790 39.761840 2.096324
#drugi paket
#install.packages("descr") ----
library(descr)
crosstab(Tokyo_updated$Brand,Tokyo_updated$Category, prop.r=T, plot=T, digits=1)
## Cell Contents
## |-------------------------|
## | Count |
## | Row Percent |
## |-------------------------|
##
## =============================================================
## Tokyo_updated$Category
## Tokyo_updated$Brand Bra Pants Shoe Socks Total
## -------------------------------------------------------------
## Adidas 0 0 213 0 213
## 0.0% 0.0% 100.0% 0.0% 11.3%
## -------------------------------------------------------------
## Asics 0 683 82 293 1058
## 0.0% 64.6% 7.8% 27.7% 56.2%
## -------------------------------------------------------------
## Nike 218 0 84 311 613
## 35.6% 0.0% 13.7% 50.7% 32.5%
## -------------------------------------------------------------
## Total 218 683 379 604 1884
## =============================================================
crosstab(Tokyo_updated$Category,Tokyo_updated$Brand, prop.r=T, plot=T, digits=1) #zamjeniti mjesta za druge proporcije
## Cell Contents
## |-------------------------|
## | Count |
## | Row Percent |
## |-------------------------|
##
## ==========================================================
## Tokyo_updated$Brand
## Tokyo_updated$Category Adidas Asics Nike Total
## ----------------------------------------------------------
## Bra 0 0 218 218
## 0.0% 0.0% 100.0% 11.6%
## ----------------------------------------------------------
## Pants 0 683 0 683
## 0.0% 100.0% 0.0% 36.3%
## ----------------------------------------------------------
## Shoe 213 82 84 379
## 56.2% 21.6% 22.2% 20.1%
## ----------------------------------------------------------
## Socks 0 293 311 604
## 0.0% 48.5% 51.5% 32.1%
## ----------------------------------------------------------
## Total 213 1058 613 1884
## ==========================================================