# Load data.table
library(data.table)
# Import food.csv: food
dt_food<-fread("food.csv")
# Convert food to a data frame
df_food<-data.frame(dt_food)
# View summary of food
summary(food)
# View head of food
head(food)
# View structure of food
str(food)
# Load dplyr
library(dplyr)
# View a glimpse of food
glimpse(food)
# View column names of food
colnames(food)

# Define vector of duplicate cols
duplicates <- c(4, 6, 11, 13, 15, 17, 18, 20, 22,
                24, 25, 28, 32, 34, 36, 38, 40,
                44, 46, 48, 51, 54, 65, 158)
# Remove duplicates from food: food2
food2<-food[-duplicates]

# Define useless vector
useless <- c(1, 2, 3, 32:41)
# Remove useless columns from food2: food3
food3<-food2[-useless]

# Create vector of column indices: nutrition
nutrition<-str_detect(names(food3),"100g")
# View a summary of nutrition columns
summary(food3[,nutrition])

# Find indices of sugar NA values: missing
missing <- is.na(food3$sugars_100g)

# Replace NA values with 0
food3$sugars_100g[missing] <- 0

# Create first histogram

hist(food3$sugars_100g,breaks=100)
# Create food4
i<-which(food3$sugars_100g==0)
food4 <- food3[-i, ]
# Create second histogram
hist(food4$sugars_100g,breaks=100)

# Find entries containing "plasti": plastic
plastic<-str_detect(food3$packaging,"plasti")

# Print the sum of plastic
sum(plastic)