setwd("C:/Users/cmiller2/Desktop/movies")
df <- read.csv(file="movies_data_clean.csv", header=TRUE)
df <- read.csv(file="movies_data_clean.csv", header=TRUE)
times <- df$Runtime
times
summary(times)
sd(times)
hist(times)
lowsd <- 122.9 - sd(times)
lowsd
hisd <- 122.9 + sd(times)
hisd
times[times < lowsd]
length(times[times < lowsd]) / length(times)
times[times > hisd]  # retrieves times more than hisd
length(times[times > hisd]) / length(times)
times[lowsd < times & times < hisd]
length(times[lowsd < times & times < hisd]) / length(times)
times[times < 122.9 - 2*sd(times)]
times < 122.9 - 2*sd(times)
122.9 - 2*sd(times)
length(times[times < 122.9 - 2*sd(times)]) / length(times)
source("C:/Users/cmiller2/Desktop/movies/movies.R")
times[times > 122.9 + 2*sd(times)]
length(times[times > 122.9 + 2*sd(times)]) / length(times)
times[times > 122.9 - 2*sd(times) & times < 122.9 + 2*sd(times)] # within 2 sd
length(times[times > 122.9 - 2*sd(times) & times < 122.9 + 2*sd(times)]) / length(1000)
length(times[times > 122.9 - 2*sd(times) & times < 122.9 + 2*sd(times)]) / length(1000)
times[times > 122.9 - 2*sd(times) & times < 122.9 + 2*sd(times)]
length(times[times > 122.9 - 2*sd(times) & times < 122.9 + 2*sd(times)])
length(times[times > 122.9 - 2*sd(times) & times < 122.9 + 2*sd(times)]) / length(times)
source("C:/Users/cmiller2/Desktop/movies/movies.R")
(122.9 - time) / sd(time)
(122.9 - comedy_time) / sd(times)
comedy_time <- 90
(122.9 - comedy_time) / sd(times)
(comedy_time - 122.9) / sd(times)
source("C:/Users/cmiller2/Desktop/movies/movies.R")
source("C:/Users/cmiller2/Desktop/movies/movies.R")
epic_time <- 170
zscore170 <- (epic_time - 122.9) / sd(times)  # z score of 170 minutes
zscore170
source("C:/Users/cmiller2/Desktop/movies/movies.R")
