12/4/2019 https://cdn.livechat-static.com/api/file/lc/att/6516421/59ac32d0446f743de1a5ced4d86f548d/project.txt
https://cdn.livechat-static.com/api/file/lc/att/6516421/59ac32d0446f743de1a5ced4d86f548d/project.txt 1/1
#Create test and validation sets
# Create edx set, validation set, and submission file
if(!require(tidyverse)) install.packages(“tidyverse”, repos = “http://cran.us.r-project.org”)
if(!require(caret)) install.packages(“caret”, repos = “http://cran.us.r-project.org”)
# MovieLens 10M dataset:
# https://grouplens.org/datasets/movielens/10m/
# http://files.grouplens.org/datasets/movielens/ml-10m.zip
dl <- tempfile()
download.file(“http://files.grouplens.org/datasets/movielens/ml-10m.zip”, dl)
ratings <- read.table(text = gsub(“::”, “\t”, readLines(unzip(dl, “ml-10M100K/ratings.dat”))),
col.names = c(“userId”, “movieId”, “rating”, “timestamp”))
movies <- str_split_fixed(readLines(unzip(dl, “ml-10M100K/movies.dat”)), “\\::”, 3)
colnames(movies) <- c(“movieId”, “title”, “genres”)
movies <- as.data.frame(movies) %>% mutate(movieId = as.numeric(levels(movieId))[movieId],
title = as.character(title),
genres = as.character(genres))
movielens <- left_join(ratings, movies, by = “movieId”)
# Validation set will be 10% of MovieLens data
set.seed(1)
test_index <- createDataPartition(y = movielens$rating, times = 1, p = 0.1, list = FALSE)
edx <- movielens[-test_index,]
temp <- movielens[test_index,]
# Make sure userId and movieId in validation set are also in edx set
validation <- temp %>%
semi_join(edx, by = “movieId”) %>%
semi_join(edx, by = “userId”)
# Add rows removed from validation set back into edx set
removed <- anti_join(temp, validation)
edx <- rbind(edx, removed)
rm(dl, ratings, movies, test_index, temp, movielens, removed)