R Notebook

### Install Packages

install.packages("rvest") #package for harvesting data

install.packages("tidyverse") #packages for cleansing data

install.packages("tm")  # package for text mining

### Load Packages
library(rvest)
library(tidyverse)
library(tm)

largest_companies <- read_html("https://www.investing.com/indices/us-spx-500-components")   
companies<-largest_companies%>%
html_nodes("#cr1")%>%
html_table(header=1) -> sp500

sp500 <- sp500[[1]]

sp500

ncol(sp500)

[1] 10

names(sp500)

 [1] ""       "Name"   "Last"   "High"   "Low"    "Chg."   "Chg. %" "Vol."   "Time"   ""      

sp500Clean<-sp500[c(2:8)]
sp500Clean

Percent_Change<-((sp500Clean$Last-sp500Clean$Low)/sp500Clean$Low)*100

Error in sp500Clean$Last - sp500Clean$Low : 
  non-numeric argument to binary operator

Last<-as.numeric(sp500Clean$Last)

Warning: NAs introduced by coercion

Low<-as.numeric(sp500Clean$Low)

Warning: NAs introduced by coercion

Percent_Change<-((Last-Low)/Low)*100

hist(Percent_Change, main="S&P500 Stock Price Low >> Last", xlab="% Change",col = "blue")