project 2a

Load in libraries

library(tidyverse)
library(kableExtra)
library(knitr)
library(stringr)
library(readr)
library(plyr)
library(dplyr)
library(data.table)
library(readxl)
require(xlsx)
library(rJava)
library(xlsx)
rm (list=ls())

Tidy dataset 1: Movies database

• Posted by Betsy
• link to source

Load in Data from xlsx file

• Dataframe requires tidying
  • Join individual movies into one movies column
  • Separate timestamp by day and time
    • Could perform some interesting time series analysis on the effects of time of day of review
  • Omit NA Values( the file read in 100+ extra rows of NA)
  • Convert 0’s to NA assuming that 0’s meant the person didn’t see the movie
    • This could be a bad assumption and perverse the data
    • Two reviewers didnt review a single movie, so I will filter them out

movies <- as.data.frame(read.xlsx("Movie Ratings.xlsx", header=TRUE,1))
#tail(movies)
#dim(movies)

movies%<>% 
    gather(Movies,Movie_rating,3:12) %>% 
    select(Timestamp,Reviewer=Name,Movies,Movie_rating,Number.of.Movies.Seen) %>%   
    separate('Timestamp',c("day","time")," ") %>% 
    na.omit() %>% 
    arrange(Reviewer) %>% 
  #  mutate(Reviewer==Name) %>% 
    replace(.==0,NA) %>% 
    filter(Movie_rating>0)

    
movies %>% 
    dplyr::group_by(Movies) %>% 
    dplyr::summarise(Movie_rating=round(mean(Movie_rating,na.rm=TRUE),2)) %>% 
    kable(.)

Movies	Movie_rating
Alien..Covenant	2.50
Blade.Runner.2049	4.00
Ghost.in.the.Shell	3.60
Guardians.of.the.Galaxy.2	3.94
Spider.Man..Homecoming	3.73
Star.Wars..The.Last.Jedi	4.22
Thor..Ragnarok	4.50
Valerian.and.the.City.of.a.Thousand.Planets	2.80
War.for.the.Planet.of.the.Apes	4.17
Wonder.Woman	4.26

data Visualization

• Display average rating by user
• Display average rating by movie
• Subset and display active critics(people who have seen over 5 movies) average ratings +Display average rating by movie from active critics

movies %>%  
    dplyr::group_by(Reviewer) %>% 
    dplyr::summarise(Average_Review=round(mean(Movie_rating,na.rm=TRUE),2)) %>% 
    arrange(desc(Average_Review)) %>% 
    ggplot(., aes(x=Reviewer , Average_Review)) + 
    geom_bar(aes(fill = Reviewer), position = "dodge", stat = "identity")+
    coord_flip()+
    labs(title="Average Rating By User")

movies %>%  
    dplyr::group_by(Movies) %>% 
    dplyr::summarise(Average_Review=round(mean(Movie_rating,na.rm=TRUE),2)) %>% 
    arrange(desc(Average_Review)) %>% 
    ggplot(., aes(x=Movies , Average_Review)) + 
    geom_bar(aes(fill = Movies), position = "dodge", stat = "identity")+
    theme(axis.text.x=element_text(angle=45,hjust=1))+
    labs(title="Average Rating By Movie")

 movies %>%  
    dplyr::group_by(Reviewer) %>% 
    filter(Number.of.Movies.Seen>5) %>% 
    dplyr::summarise(Average_Review=round(mean(Movie_rating,na.rm=TRUE),2)) %>% 
    ggplot(., aes(x=Reviewer , Average_Review)) + 
    geom_bar(aes(fill = Reviewer), position = "dodge", stat = "identity")+
    theme(axis.text.x=element_text(angle=45,hjust=1))+
    labs(title="Active Critics")

movies %>%  
    dplyr::group_by(Movies) %>% 
    dplyr::summarise(Average_Review=round(mean(Movie_rating,na.rm=TRUE),2)) %>% 
    arrange(desc(Average_Review)) %>% 
    ggplot(., aes(x=Movies , Average_Review)) + 
    geom_bar(aes(fill = Movies), position = "dodge", stat = "identity")+
    coord_flip()+
    labs(title="Active Critics Average Rating By Movie")