Clase 5

## Leer datasets
##Archivos .csv txt tsv 

library(readr)

#read.csv()  #Archivos.csv "separados por comas"
#read.table() #Archivos. txt "separado por espacios"
#read.csv2()  #Archivos que estan separados por ;
#read_tsv()   # cuando los archivos estan dilimitados por el TAB

# Archivo excel
#install.packages("readxl")
library(readxl)
#read_excel()
#read_xls()
#read_xlsx()

url <- "https://raw.githubusercontent.com/rafalab/dslabs/master/inst/extdata/murders.csv"
murders <- read.csv(url)
download.file(url,"murders.csv")

# resumen 
library(dplyr)

## 
## Adjuntando el paquete: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(dslabs)

## 
## Adjuntando el paquete: 'dslabs'

## The following object is masked _by_ '.GlobalEnv':
## 
##     murders

data("heights")

# Calcular el promedio y la desviacion estandar por genero 

sm<-heights %>% filter(sex=="Male") %>%
  summarise(mean=mean(height), sd=sd(height))

## Interpretar los resultados
sm$mean

## [1] 69.31475

sm$sd

## [1] 3.611024

sf<-heights %>% filter(sex=="Female") %>%
  summarise(mean=mean(height), sd=sd(height))

data("murders")

head(murders)

##        state abb region population total
## 1    Alabama  AL  South    4779736   135
## 2     Alaska  AK   West     710231    19
## 3    Arizona  AZ   West    6392017   232
## 4   Arkansas  AR  South    2915918    93
## 5 California  CA   West   37253956  1257
## 6   Colorado  CO   West    5029196    65

max_total<- murders$state[which.max(murders$total)]

max_total2<- murders$state[which.max(murders$population)]

murders<- murders %>% mutate(rate=total*100000/population)

head(murders) 

##        state abb region population total     rate
## 1    Alabama  AL  South    4779736   135 2.824424
## 2     Alaska  AK   West     710231    19 2.675186
## 3    Arizona  AZ   West    6392017   232 3.629527
## 4   Arkansas  AR  South    2915918    93 3.189390
## 5 California  CA   West   37253956  1257 3.374138
## 6   Colorado  CO   West    5029196    65 1.292453

meanrate<- murders %>% select(rate) %>% summarise(mean(rate))
meanrate

##   mean(rate)
## 1   2.779125

murders<- murders%>%mutate(dif=meanrate$`mean(rate)`-rate)
head(murders)

##        state abb region population total     rate         dif
## 1    Alabama  AL  South    4779736   135 2.824424 -0.04529833
## 2     Alaska  AK   West     710231    19 2.675186  0.10393949
## 3    Arizona  AZ   West    6392017   232 3.629527 -0.85040182
## 4   Arkansas  AR  South    2915918    93 3.189390 -0.41026465
## 5 California  CA   West   37253956  1257 3.374138 -0.59501286
## 6   Colorado  CO   West    5029196    65 1.292453  1.48667234

quantile(murders$rate,c(0.5,0,1))

##        50%         0%       100% 
##  2.6871225  0.3196211 16.4527532