Working with R language Day 01

1. List of built-in data sets
   
   data()
   
   
2. The R Datasets Package
   
   help(package = "datasets")
3. List the data sets in all *available* packages
   
   data(package = .packages(all.available = TRUE))
4. List data sets including in ggplot2 package
   
   data(package = "ggplot2")
5. Describe data set "movies" which is included in the "psych" package
   
   library(psych)
   describe(movies)
6. Draw a pie chart using different colours schemes
   
   library(ggplot2)
   par(mfrow =  c(2,2)) # plot 4 pie charts in one diagram
   pie(rep(1,8), col = FALSE, main = "Blank Pie") # no colours shown
   pie(rep(1,8), main = "Default Colours")
   pie(c(1,2,3,4,5,6,7,8), col = heat.colors(7), main = "Heat Colours")
   pie(rep(1,8), col = rainbow(8), main = "Rainbow Colours")
7. EDA
   
   library(ggplot2)
   library(ggplot2movies)
   library(psych)
   
   data("movies") # using movies data
   dim(movies)
   summary(movies)
   str(movies)
   head(movies)
   describe(movies)
   movies$rating #list values of rating column (variable)
8. Plot a histogram of ratings and length for a random sample of 1000 movies
   
   library(ggplot2)
   library(ggplot2movies)
   library(ggpubr) # for ggrange()
   
   movies_1000_rows <- movies[sample(nrow(movies),1000),]
   
   rating_htg <- qplot(rating, data = movies_1000_rows, geom = "histogram", main = "Movie Ratings")
   
   lenth_htg <- qplot(length, data = movies_1000_rows, geom = "histogram", main = "Movie Length")
   
   # Display two histograms in the same figure
   
   ggarrange(rating_htg, lenth_htg, labels = c("A", "B"), ncol = 2, nrow = 1)
9. Working with Data frames
   
   movies$unused_column <- NULL #remove column unused_column
   
   medianRating <- median(movies$rating)
   movies$median_rating_col <- ifelse(movies$rating > medianRating, "Larger", "Smaller")
   
   OR to replacing rating column with "Larger" or "Smaller" values
   
   movies$rating <- with(movies, ifelse(rating > medianRating, "Larger", "Smaller")
10. # Summarise a data frame by groups in R using dplyr package
    
    library(ggplot2movies)
    library(dplyr) # for group_by(), select(), summarise()
    
    # List number of movies produced by each year
    
    mymovies <- movies %>%
    select(year, length, title) %>%
    group_by(year) %>%
    summarise(avg_length=mean(length), number_of_titles=n())
11. Using apply function
    
    apply(movies, 2, mean)
12. #Find all functions that has apply in the end
    apropos(".apply")