Tip for Data Processing

Subset

grade = c("A", "B", "C")
name = c("Joe", "Jane", "Peter")
df = data.frame(name, grade)
df

##    name grade
## 1   Joe     A
## 2  Jane     B
## 3 Peter     C

subset1_df = data.frame(df$name)
subset1_df

##   df.name
## 1     Joe
## 2    Jane
## 3   Peter

subset1_df = data.frame(df$name)
colnames(subset1_df) = c("name")
subset1_df

##    name
## 1   Joe
## 2  Jane
## 3 Peter

subset2_df = data.frame(name = df$name)
subset2_df

##    name
## 1   Joe
## 2  Jane
## 3 Peter

Kmeans

Kmeans<-function(c){
        x <- rbind(matrix(rnorm(100, sd = 0.3), ncol = 2),
                   matrix(rnorm(100, mean = 1, sd = 0.3), ncol = 2))
        colnames(x) <- c("x", "y")
        cl <- kmeans(x, c)
        plot(x, col = cl$cluster)
        points(cl$centers, col = 1:c, pch = 8, cex=2)
}
Kmeans(3)