R Data Analysis/Rを使った人事データ分析入門
3 likes3,650 views
1. This document introduces R and R Studio, which are popular tools for statistical analysis and visualization. 2. It demonstrates how to import data, perform basic operations and analyses like linear regression, and visualize results with plots. 3. Examples include loading data from Excel, correlating variables, fitting linear models, and conducting principal component analysis.
R Data Analysis/Rを使った人事データ分析入門
- 1. R
- 2. 3 R R Studio
- 3. 2 1 2
- 5. R
- 6. R (Mac Widows Mac OS
- 7. R (Win Widows Mac OS USB
- 9. R studio R
- 10. R studio R
- 13. R
- 14. ” # ” #
- 15. R R script ctrl + enter R enter console 5 + 5 10 * 3 plot(1:10) plot(1:100) ?summary
- 16. read.csv error install.packages("readxl") library(readxl) x <- read_excel("/Users/omotetakanori/Desktop/test_mac/class Data.xlsx") readxl install (library x excel
- 19. tests %>% select(Japanese, Mathematics) %>% cor() tests %>% select(Japanese:Mathematics) %>% cor()
- 20. #Data tests <- read_excel("rhrData.xlsx") library(dplyr) #Data tests %>% head(3) # library(ggplot2) tests %>% ggplot(aes(x=Expense,y=Sales)) + geom_point() + geom_smooth(method = "lm")
- 21. # lm.Sales.Expense <- lm(Sales~Expense,data = tests) # summary(lm.Sales.Expense) Call: lm(formula = Sales ~ Expense, data = tests) Residuals: Min 1Q Median 3Q Max -1558.1 -514.3 163.8 366.9 1300.4 Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 1260.693 418.680 3.011 0.00750 ** Expense 7.073 2.117 3.340 0.00364 ** --- Signif. codes: 0 *** 0.001 ** 0.01 * 0.05 . 0.1 1 Residual standard error: 709.3 on 18 degrees of freedom Multiple R-squared: 0.3827, Adjusted R-squared: 0.3484 F-statistic: 11.16 on 1 and 18 DF, p-value: 0.003642
- 22. 0 0 0
- 23. ( ) # library(readxl) tokei <- read_excel("TokeiSeminar.xlsx") lm.tokeiseminar <- lm(FutureSales ~ Sex+ Academic + Interview + IQ + MBTI + Abroad + Leadership + Athelete, data = tokei) summary(lm.tokeiseminar)
- 24. 1. Data 2. 2000 1 3. 4. 2000 mutate Environment #Data tests <- read_excel("rhrData.xlsx") #if sales 2000>= #1. tests <- tests %>% mutate(IsSalesOver2000= Sales >= 2000)
- 25. predict xlab ylab 1. Data 2. 2000 1 3. 4. 2000 # 2000 pred.Salesover2000 <- predict (glm.Sales.NoCl.Ex,data = tests.over2000) plot(pred.Salesover2000, xlab = "SalesName", ylab = "2000overProb")
- 26. 1 2
- 28. 0 0 50 100 150 200 250 0 5 10 15 20 Sales 58V N 96 3 N 1 S N S 9 5 4 2
- 29. (p) p -1.5 -1 -0.5 0 0.5 1 1.5 2 -2.5 -2 -1.5 -1 -0.5 0 0.5 1 1.5 2
- 30. # (PrincipalComponentAnalysis) library(dplyr) # tests<- read_excel('classData.xlsx') testsPr <- tests %>% select(English:Mathematics) rownames(testsPr) <-tests$Name testsPr <- prcomp(testsPr) testsPr %>% biplot()