notebook.community

Edit and run



In [5]:

    
!ls ../









    



LICENSE            notebooks          sample-files
data               parsed-movie-files



In [7]:

    
from pandas import DataFrame, read_csv
import pandas as pd
df = read_csv(r'/Users/seanreed1/AnacondaProjects/scrapy-projects/movie-project/box-office-data/data/final-box-office-data.csv')



In [9]:

    
df.head()









    Out[9]:






  
    
      
      Rank
      Title
      Release_Year
      Domestic Box Office
      International Box Office
      Total Box Office
    
  
  
    
      0
      1
      Star Wars Ep. VII: The Force Awakens
      2015
      $936,662,225
      $1,122,000,000
      $2,058,662,225
    
    
      1
      2
      Avatar
      2009
      $760,507,625
      $2,023,411,357
      $2,783,918,982
    
    
      2
      3
      Titanic
      1997
      $658,672,302
      $1,548,943,366
      $2,207,615,668
    
    
      3
      4
      Jurassic World
      2015
      $652,198,010
      $1,019,442,583
      $1,671,640,593
    
    
      4
      5
      The Avengers
      2012
      $623,279,547
      $896,200,000
      $1,519,479,547



In [10]:

    
df.ix[:10,:]









    Out[10]:






  
    
      
      Rank
      Title
      Release_Year
      Domestic Box Office
      International Box Office
      Total Box Office
    
  
  
    
      0
      1
      Star Wars Ep. VII: The Force Awakens
      2015
      $936,662,225
      $1,122,000,000
      $2,058,662,225
    
    
      1
      2
      Avatar
      2009
      $760,507,625
      $2,023,411,357
      $2,783,918,982
    
    
      2
      3
      Titanic
      1997
      $658,672,302
      $1,548,943,366
      $2,207,615,668
    
    
      3
      4
      Jurassic World
      2015
      $652,198,010
      $1,019,442,583
      $1,671,640,593
    
    
      4
      5
      The Avengers
      2012
      $623,279,547
      $896,200,000
      $1,519,479,547
    
    
      5
      6
      The Dark Knight
      2008
      $533,345,358
      $469,451,702
      $1,002,797,060
    
    
      6
      7
      Rogue One: A Star Wars Story
      2016
      $532,177,324
      $518,811,164
      $1,050,988,488
    
    
      7
      8
      Beauty and the Beast
      2017
      $504,014,165
      $756,108,198
      $1,260,122,363
    
    
      8
      9
      Finding Dory
      2016
      $486,295,561
      $536,321,815
      $1,022,617,376
    
    
      9
      10
      Star Wars Ep. I: The Phantom Menace
      1999
      $474,544,677
      $552,500,000
      $1,027,044,677
    
    
      10
      11
      Star Wars Ep. IV: A New Hope
      1977
      $460,998,007
      $325,600,000
      $786,598,007



In [17]:

    
# extract title and release year to feed into OBMD process chain
title_plus_year = df[['Title', 'Release_Year']]
title_plus_year.head()









    Out[17]:






  
    
      
      Title
      Release_Year
    
  
  
    
      0
      Star Wars Ep. VII: The Force Awakens
      2015
    
    
      1
      Avatar
      2009
    
    
      2
      Titanic
      1997
    
    
      3
      Jurassic World
      2015
    
    
      4
      The Avengers
      2012



In [25]:

    
title_plus_year.to_csv(r'/Users/seanreed1/AnacondaProjects/scrapy-projects/movie-project/box-office-data/data/title_plus_year.csv', index=False)



In [30]:

    
#check to make sure the file actually saved correctly
title_plus_year2= read_csv(r'/Users/seanreed1/AnacondaProjects/scrapy-projects/movie-project/box-office-data/data/title_plus_year.csv')



In [31]:

    
title_plus_year2.head()









    Out[31]:






  
    
      
      Title
      Release_Year
    
  
  
    
      0
      Star Wars Ep. VII: The Force Awakens
      2015
    
    
      1
      Avatar
      2009
    
    
      2
      Titanic
      1997
    
    
      3
      Jurassic World
      2015
    
    
      4
      The Avengers
      2012



In [32]:

    
title_plus_year2.tail()









    Out[32]:






  
    
      
      Title
      Release_Year
    
  
  
    
      6095
      Heart Condition
      1990
    
    
      6096
      Venom
      1982
    
    
      6097
      Partners
      1982
    
    
      6098
      Kama Sutra
      1997
    
    
      6099
      Serbuan maut
      2012



In [33]:

    
#ok, data has been saved. Now, on to the OMDB data downloader



In [ ]:

	Rank	Title	Release_Year	Domestic Box Office	International Box Office	Total Box Office
0	1	Star Wars Ep. VII: The Force Awakens	2015	$936,662,225	$1,122,000,000	$2,058,662,225
1	2	Avatar	2009	$760,507,625	$2,023,411,357	$2,783,918,982
2	3	Titanic	1997	$658,672,302	$1,548,943,366	$2,207,615,668
3	4	Jurassic World	2015	$652,198,010	$1,019,442,583	$1,671,640,593
4	5	The Avengers	2012	$623,279,547	$896,200,000	$1,519,479,547

	Title	Release_Year
6095	Heart Condition	1990
6096	Venom	1982
6097	Partners	1982
6098	Kama Sutra	1997
6099	Serbuan maut	2012