cflint12

#In order for the Shiny app and part of this code to run, you must have installed ggvis and shiny on your computer.
#This will require R Base 3.1.0 or higher.
#If you are using Ubuntu trusty, this may require you to add an additional line to your /etc/apt/sources.list file
#You can do this by following the instructions below:

#First, type the following into your terminal: sudo gedit /etc/apt/sources.list
# 
#Then, paste "deb http://cran.wustl.edu/bin/linux/ubuntu trusty/" on a new line at end of current sources.list 
# text file in Text Editor.
#

cflint12

"","Short_Key","Long_Name","Year","Country_GDP","Country_Population","Country_Pop_Dens","Region","Income","Income_Group_GDP","Income_Group_Population","Income_Group_Pop_Dens","Region_GDP","Region_Population","Region_Pop_Dens"
"1","AF","Afghanistan",2001,2461666314.78366,21347782,32.6988665257482,"South Asia","Low income",168320464483.076,651625175,43.8567060376896,638745671205.06,1405746086,294.504402860938
"2","AF","Afghanistan",2002,4128818042.61749,22202806,34.0413749750855,"South Asia","Low income",176332502923.58,666831547,44.3116864018666,672494121092.634,1429513552,299.505846646499
"3","AF","Afghanistan",2003,4583648921.74369,23116142,35.4417030802018,"South Asia","Low income",193372966826.881,682231310,45.3350175141828,784882714578.081,1453111368,304.449964769898
"4","AF","Afghanistan",2004,5285461998.97866,24018682,36.8254787421615,"South Asia","Low income",216569844116.367,697754397,46.3669133771839,911124327836.882,1476314527,309.420502370042
"5","AF","Afghanistan",2005,6275076015.72254,24860855,38

cflint12

"","Title","Earnings_in_Mil","Released","Year","Month","Month_Num","Qtr_Num","Rated","Runtime_Minutes","Metascore","imdbRating","imdbVotes","Language_1","Language_2","Language_3","Language_4","Language_5","Language_6","Language_7","Language_8","Language_9","Country_1","Country_2","Country_3","Country_4","Country_5","Country_6","Country_7","Country_8","Country_9","Country_10","Country_11","Country_12","Country_13","Writer_1","Writer_2","Writer_3","Writer_4","Writer_5","Writer_6","Writer_7","Writer_8","Writer_9","Writer_10","Writer_11","Writer_12","Writer_13","Writer_14","Writer_15","Writer_16","Writer_17","Writer_18","Writer_19","Writer_20","Writer_21","Writer_22","Writer_23","Writer_24","Writer_25","Writer_26","Writer_27","Writer_28","Writer_29","Writer_30","Writer_31","Director_1","Director_2","Director_3","Director_4","Director_5","Director_6","Director_7","Director_8","Director_9","Director_10","Director_11","Director_12","Director_13","Director_14","Director_15","Director_16","Director_17","Director_18","

cflint12

#First load the data and libraries

#setwd('Set working directory here.')

library(Hmisc)
library(ggvis)
library(dplyr)
library(car)

movie_df = read.csv('Movie_DF_wBusinessData.csv')

cflint12

import os
import pandas as pd

#os.chdir('Change your directory here ...')

'''
Take the output from IMDB_Initial_WebScraping.py and use Excel to separate out the 
languages, countries, writers, genres, directors, actors, and genres into separate 
cells by using the "Text to Columns" feature with commas as the delimiter, making sure

cflint12

'''
This program was generated to scrape movie data from the IMDB website
in conjunction with omdbapi.com
'''

#Import the necessary libraries
import urllib2
from bs4 import BeautifulSoup as bs
import pandas as pd
import os