eda

knitr::opts_chunk$set(warning = FALSE, message = FALSE)
list.files()

[1] "~$部数据分析师笔试题目_180412.docx"  
[2] "eda.nb.html"                         
[3] "eda.Rmd"                             
[4] "spam.csv"                            
[5] "数据部数据分析师笔试题目_180412.docx"

spam <- read_csv('spam.csv')

Parsed with column specification:
cols(
  .default = col_double(),
  cs = col_integer(),
  capitalLong = col_integer(),
  capitalTotal = col_integer(),
  type = col_character()
)
See spec(...) for full column specifications.
number of columns of result is not a multiple of vector length (arg 1)145 parsing failures.
row # A tibble: 5 x 5 col     row col   expected               actual file       expected   <int> <chr> <chr>                  <chr>  <chr>      actual 1  1449 cs    no trailing characters .1     'spam.csv' file 2  1833 cs    no trailing characters .32    'spam.csv' row 3  1845 cs    no trailing characters .54    'spam.csv' col 4  1847 cs    no trailing characters .39    'spam.csv' expected 5  1860 cs    no trailing characters .14    'spam.csv'
... ................................. ... ...................................................... ........ ................................................................................................................................................................................... ...... ............................................................................... .... ............................................................................... ... ............................................................................... ... ............................................................................... ........ ...............................................................................
See problems(...) for more details.

spam_edited <- 
spam %>% 
    na.omit() # 自己处理下缺失值
pca_model <- 
    prcomp(spam_edited %>% select(-type),
           center = TRUE,scale. = TRUE)
eda_data <- 
predict(pca_model) %>% 
    as_tibble() %>% 
    select(1:2) %>% 
    bind_cols(spam_edited %>% select(type))

• r - Error in svd(x, nu = 0) : 0 extent dimensions - Stack Overflow

eda_data %>% 
    mutate(type = as.factor(type)) %>% 
    ggplot(aes(x = PC1, y = PC2, col = type)) + 
        geom_point()