Homework 4

library(readxl)
library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

district<-read_excel("district.xls")

library(pastecs)

## 
## Attaching package: 'pastecs'

## The following objects are masked from 'package:dplyr':
## 
##     first, last

## The following object is masked from 'package:tidyr':
## 
##     extract

bilingual<-district%>%select(DPETBILP,DPSTBIFP)

summary(district$DPETBILP)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    0.00    2.90    7.30   12.58   16.80  100.00

summary(district$DPSTBIFP)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   0.000   0.000   0.000   2.311   2.100  94.300       3

bilingual_clean<-bilingual%>%na.omit(.)

ggplot(bilingual_clean,aes(DPETBILP,DPSTBIFP))+geom_point()

stat.desc(district$DPFPABILP,norm = T)

##      nbr.val     nbr.null       nbr.na          min          max        range 
## 1.202000e+03 1.840000e+02 5.000000e+00 0.000000e+00 2.600000e+01 2.600000e+01 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
## 9.010000e+02 4.000000e-01 7.495840e-01 3.817826e-02 7.490350e-02 1.752011e+00 
##      std.dev     coef.var     skewness     skew.2SE     kurtosis     kurt.2SE 
## 1.323635e+00 1.765827e+00 9.156793e+00 6.488301e+01 1.414057e+02 5.013990e+02 
##   normtest.W   normtest.p 
## 4.668057e-01 1.004389e-50

hist(district$DPETBILP, breaks = 10, probability = T)
lines(density(district$DPETBILP),col= 'red',lwd=2)

hist(log(district$DPETBILP),breaks = 10, probability = T)
lines(density(log(district$DPETBILP)),col= 'red',lwd=2)

district_DPETBILP_log<-district%>%mutate(log_DPETBILP=log(DPETBILP))%>%select(DPETBILP,log_DPETBILP)

head(district_DPETBILP_log)

## # A tibble: 6 × 2
##   DPETBILP log_DPETBILP
##      <dbl>        <dbl>
## 1      1          0    
## 2      2.7        0.993
## 3      4.1        1.41 
## 4      2          0.693
## 5     16.1        2.78 
## 6      6.8        1.92

sqrt(0)

## [1] 0

log(0)

## [1] -Inf