# Import the numpy and pandas packages
import numpy as np
import pandas as pd
from notebook import notebookapp
The "Movies" dataset is a tabular dataset containing information about movies. Each row of the dataset represents a single movie and each column contains a different attribute of the movie. Some of the attributes include the movie title, the director's name, the actors, the movie genres, the duration, the budget, the gross revenue, and the IMDb rating.
-> By analyzing this dataset, you can answer various questions related to movies, such as which movie has the highest gross revenue, which director has directed the most number of movies, which genre is the most popular among the audience, and so on.
# Unzip the zip file containing the data. Be sure to specify the correct path to the zip file
# The path below is specific to my own Google Drive.
#!unzip /content/drive/Othercomputers/My\ Mac/Documents/WSU/movies_data.zip
#!unzip /content/drive/Othercomputers/My\/work/movies_data.zip
#severs = list(notebookapp.list_running_servers())
#if severs:
# url = severs[0]['url']
# print(f"Jupyter server running at {url}")
#else:
# print("No running servers found")
!unzip movies_data.zip hw3_file
Archive: movies_data.zip
caution: filename not matched: hw3_file
# list the contents of the Present Working Directory (also called pwd)
!ls
hw3_file MovieAssignmentData.csv movies_data.zip newFolder
movies = pd.DataFrame(pd.read_csv("./MovieAssignmentData.csv")) # pd.read_csv function is used to read the data
movies.head() # notice the use of the .head() function for quickly displaying the data to get a feel
colorobject
director_nameobject
0
Color
James Cameron
1
Color
Gore Verbinski
2
Color
Sam Mendes
3
Color
Christopher Nolan
4
nan
Doug Walker
# Row, columns in the Data
movies.shape
# Concise summary of the Dataframe.
movies.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5043 entries, 0 to 5042
Data columns (total 28 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 color 5024 non-null object
1 director_name 4939 non-null object
2 num_critic_for_reviews 4993 non-null float64
3 duration 5028 non-null float64
4 director_facebook_likes 4939 non-null float64
5 actor_3_facebook_likes 5020 non-null float64
6 actor_2_name 5030 non-null object
7 actor_1_facebook_likes 5036 non-null float64
8 gross 4159 non-null float64
9 genres 5043 non-null object
10 actor_1_name 5036 non-null object
11 movie_title 5043 non-null object
12 num_voted_users 5043 non-null int64
13 cast_total_facebook_likes 5043 non-null int64
14 actor_3_name 5020 non-null object
15 facenumber_in_poster 5030 non-null float64
16 plot_keywords 4890 non-null object
17 movie_imdb_link 5043 non-null object
18 num_user_for_reviews 5022 non-null float64
19 language 5031 non-null object
20 country 5038 non-null object
21 content_rating 4740 non-null object
22 budget 4551 non-null float64
23 title_year 4935 non-null float64
24 actor_2_facebook_likes 5030 non-null float64
25 imdb_score 5043 non-null float64
26 aspect_ratio 4714 non-null float64
27 movie_facebook_likes 5043 non-null int64
dtypes: float64(13), int64(3), object(12)
memory usage: 1.1+ MB
# Generate descriptive statistics that summarize the central tendency, dispersion and shape of a dataset’s distribution,
# excluding NaN values
movies.describe()
num_nans = movies['gross'].isna().sum()
print("Number of NaN values in column 'gross':", num_nans)
#movies.dropna()
Number of NaN values in column 'gross': 884
movies.director_name.describe()
longest_duration = movies['duration'].max()
print("The longest duration of any movie in the dataset is:", longest_duration)
The longest duration of any movie in the dataset is: 511.0
# TODO [1 line]: Write code to find how many different movie genres there are [10]
num_directors = movies['director_name'].nunique()
print("The sum of the directors in the dataset without repetitions: ",num_directors)
# count the number of unique directors
# print the result
The sum of the directors in the dataset without repetitions: 2398
# TODO [1 line]: Write code to find number of languages across all the movies in the dataset [10]
num_genres = movies['director_name'].nunique()
print("There are ", num_genres)
There are 2398
# Code for column-wise null count here
movies.isnull().sum()
# TODO [1 line]: Write your code for row-wise null count here;
# Use the .sum() function, paying attention to the axis argument [10]
#Count the number of null values in each row
null_counts = movies.isnull().sum(axis = 1)
print("Number of null values in each row:", null_counts)
Number of null values in each row: 0 0
1 0
2 0
3 0
4 14
..
5038 4
5039 5
5040 4
5041 2
5042 0
Length: 5043, dtype: int64
# TODO [1-2 lines]: Write your code for column-wise null percentages here rounded to 2 decimal places [10]
temp = round(null_counts.mean() *100, 2)
print("Column-wise null percentage which is rounded to 2 decimal places is: ", temp)
Column-wise null percentage which is rounded to 2 decimal places is: 53.5
temp = movies['language'].fillna('English')
movies['language'] = temp
print(movies['language'])
0 English
1 English
2 English
3 English
4 English
...
5038 English
5039 English
5040 English
5041 English
5042 English
Name: language, Length: 5043, dtype: object
movies.language.isnull().sum() # this should print 0 if your code above is correct
# TODO [1 line]: Write your code for dropping these rows here that have > 5 NaN values [10]
movies_dropped = movies.dropna(thresh=5)
#The thresh parameter is set to 5, which means that only rows with 5 or more NaN values will be dropped.
print(movies_dropped)
color director_name num_critic_for_reviews duration \
0 Color James Cameron 723.0 178.0
1 Color Gore Verbinski 302.0 169.0
2 Color Sam Mendes 602.0 148.0
3 Color Christopher Nolan 813.0 164.0
4 NaN Doug Walker NaN NaN
... ... ... ... ...
5038 Color Scott Smith 1.0 87.0
5039 Color NaN 43.0 43.0
5040 Color Benjamin Roberds 13.0 76.0
5041 Color Daniel Hsia 14.0 100.0
5042 Color Jon Gunn 43.0 90.0
director_facebook_likes actor_3_facebook_likes actor_2_name \
0 0.0 855.0 Joel David Moore
1 563.0 1000.0 Orlando Bloom
2 0.0 161.0 Rory Kinnear
3 22000.0 23000.0 Christian Bale
4 131.0 NaN Rob Walker
... ... ... ...
5038 2.0 318.0 Daphne Zuniga
5039 NaN 319.0 Valorie Curry
5040 0.0 0.0 Maxwell Moody
5041 0.0 489.0 Daniel Henney
5042 16.0 16.0 Brian Herzlinger
actor_1_facebook_likes gross genres \
0 1000.0 760505847.0 Action|Adventure|Fantasy|Sci-Fi
1 40000.0 309404152.0 Action|Adventure|Fantasy
2 11000.0 200074175.0 Action|Adventure|Thriller
3 27000.0 448130642.0 Action|Thriller
4 131.0 NaN Documentary
... ... ... ...
5038 637.0 NaN Comedy|Drama
5039 841.0 NaN Crime|Drama|Mystery|Thriller
5040 0.0 NaN Drama|Horror|Thriller
5041 946.0 10443.0 Comedy|Drama|Romance
5042 86.0 85222.0 Documentary
... num_user_for_reviews language country content_rating budget \
0 ... 3054.0 English USA PG-13 237000000.0
1 ... 1238.0 English USA PG-13 300000000.0
2 ... 994.0 English UK PG-13 245000000.0
3 ... 2701.0 English USA PG-13 250000000.0
4 ... NaN English NaN NaN NaN
... ... ... ... ... ... ...
5038 ... 6.0 English Canada NaN NaN
5039 ... 359.0 English USA TV-14 NaN
5040 ... 3.0 English USA NaN 1400.0
5041 ... 9.0 English USA PG-13 NaN
5042 ... 84.0 English USA PG 1100.0
title_year actor_2_facebook_likes imdb_score aspect_ratio \
0 2009.0 936.0 7.9 1.78
1 2007.0 5000.0 7.1 2.35
2 2015.0 393.0 6.8 2.35
3 2012.0 23000.0 8.5 2.35
4 NaN 12.0 7.1 NaN
... ... ... ... ...
5038 2013.0 470.0 7.7 NaN
5039 NaN 593.0 7.5 16.00
5040 2013.0 0.0 6.3 NaN
5041 2012.0 719.0 6.3 2.35
5042 2004.0 23.0 6.6 1.85
movie_facebook_likes
0 33000
1 0
2 85000
3 164000
4 0
... ...
5038 84
5039 32000
5040 16
5041 660
5042 456
[5043 rows x 28 columns]
# TODO [1 line]: Write your code for checking the fraction of retained rows here [10]
fraction_retained = len(movies.dropna(subset=['title_year'])) / len(movies)
print('Fraction of retained rows:', fraction_retained)
Fraction of retained rows: 0.9785841760856633
len(movies)-len(movies.drop_duplicates())
# TODO [1 line]: Write your code for dropping duplicate values here [10]
movies.drop_duplicates(inplace=True)
# TODO [1 line]: Write your code for creating the profit column here [10]
movies['profit'] = movies['gross'] - movies['budget']
# TODO [1 line]: Write your code for sorting the dataframe here [10]
movies_by_profit = movies.sort_values(by='profit', ascending=False)
print(movies_by_profit)
color director_name num_critic_for_reviews duration \
0 Color James Cameron 723.0 178.0
29 Color Colin Trevorrow 644.0 124.0
26 Color James Cameron 315.0 194.0
3024 Color George Lucas 282.0 125.0
3080 Color Steven Spielberg 215.0 120.0
... ... ... ... ...
5036 Color Anthony Vallone NaN 84.0
5038 Color Scott Smith 1.0 87.0
5039 Color NaN 43.0 43.0
5040 Color Benjamin Roberds 13.0 76.0
5041 Color Daniel Hsia 14.0 100.0
director_facebook_likes actor_3_facebook_likes actor_2_name \
0 0.0 855.0 Joel David Moore
29 365.0 1000.0 Judy Greer
26 0.0 794.0 Kate Winslet
3024 0.0 504.0 Peter Cushing
3080 14000.0 548.0 Dee Wallace
... ... ... ...
5036 2.0 2.0 John Considine
5038 2.0 318.0 Daphne Zuniga
5039 NaN 319.0 Valorie Curry
5040 0.0 0.0 Maxwell Moody
5041 0.0 489.0 Daniel Henney
actor_1_facebook_likes gross genres \
0 1000.0 760505847.0 Action|Adventure|Fantasy|Sci-Fi
29 3000.0 652177271.0 Action|Adventure|Sci-Fi|Thriller
26 29000.0 658672302.0 Drama|Romance
3024 11000.0 460935665.0 Action|Adventure|Fantasy|Sci-Fi
3080 861.0 434949459.0 Family|Sci-Fi
... ... ... ...
5036 45.0 NaN Crime|Drama
5038 637.0 NaN Comedy|Drama
5039 841.0 NaN Crime|Drama|Mystery|Thriller
5040 0.0 NaN Drama|Horror|Thriller
5041 946.0 10443.0 Comedy|Drama|Romance
... language country content_rating budget title_year \
0 ... English USA PG-13 237000000.0 2009.0
29 ... English USA PG-13 150000000.0 2015.0
26 ... English USA PG-13 200000000.0 1997.0
3024 ... English USA PG 11000000.0 1977.0
3080 ... English USA PG 10500000.0 1982.0
... ... ... ... ... ... ...
5036 ... English USA PG-13 3250.0 2005.0
5038 ... English Canada NaN NaN 2013.0
5039 ... English USA TV-14 NaN NaN
5040 ... English USA NaN 1400.0 2013.0
5041 ... English USA PG-13 NaN 2012.0
actor_2_facebook_likes imdb_score aspect_ratio movie_facebook_likes \
0 936.0 7.9 1.78 33000
29 2000.0 7.0 2.00 150000
26 14000.0 7.7 2.35 26000
3024 1000.0 8.7 2.35 33000
3080 725.0 7.9 1.85 34000
... ... ... ... ...
5036 44.0 7.8 NaN 4
5038 470.0 7.7 NaN 84
5039 593.0 7.5 16.00 32000
5040 0.0 6.3 NaN 16
5041 719.0 6.3 2.35 660
profit
0 523505847.0
29 502177271.0
26 458672302.0
3024 449935665.0
3080 424449459.0
... ...
5036 NaN
5038 NaN
5039 NaN
5040 NaN
5041 NaN
[4998 rows x 29 columns]
# print the top 10 movies data
top10 = movies_by_profit.head(10)
top10
colorobject
Color100%
director_nameobject
James Cameron20%
George Lucas20%
6 others60%
0
Color
James Cameron
29
Color
Colin Trevorrow
26
Color
James Cameron
3024
Color
George Lucas
3080
Color
Steven Spielberg
17
Color
Joss Whedon
509
Color
Roger Allers
240
Color
George Lucas
66
Color
Christopher Nolan
439
Color
Gary Ross
# TODO [3 lines]: Write your code for extracting the top 250 movies as per the IMDb score here. Make sure that you store it in a new dataframe
# and name that dataframe as 'IMDb_Top_250' [30]
IMDb_Top_250 = movies[movies.num_voted_users > 25000].sort_values(by=['imdb_score'], ascending=False)[:250]
#add 'Rank' column with the values 1~250
IMDb_Top_250['Rank'] = range(1,251)
# print a sample of the dataset
IMDb_Top_250
colorobject
Color84.8%
Black and White14.8%
Missing0.4%
director_nameobject
Christopher Nolan2.8%
157 others90.8%
Missing6.4%
1937
Color
Frank Darabont
3466
Color
Francis Ford Coppola
66
Color
Christopher Nolan
3481
Color
nan
2837
Color
Francis Ford Coppola
339
Color
Peter Jackson
4822
Black and White
Sidney Lumet
4498
Color
Sergio Leone
1874
Black and White
Steven Spielberg
3355
Color
Quentin Tarantino
# print the top 5
IMDb_Top_250.head()
colorobject
director_nameobject
1937
Color
Frank Darabont
3466
Color
Francis Ford Coppola
66
Color
Christopher Nolan
3481
Color
nan
2837
Color
Francis Ford Coppola
# TODO [1 line]: Write code to do the above [20]
Top_Foreign_Lang_Film = IMDb_Top_250[IMDb_Top_250['language'] != 'English']
print(Top_Foreign_Lang_Film)
color director_name \
4498 Color Sergio Leone
4747 Black and White Akira Kurosawa
4029 Color Fernando Meirelles
2373 Color Hayao Miyazaki
3870 Color Raja Menon
4921 Color Majid Majidi
4259 Color Florian Henckel von Donnersmarck
3685 Color Rakeysh Omprakash Mehra
2323 Color Hayao Miyazaki
4105 Color Chan-wook Park
2970 Color Wolfgang Petersen
1298 Black and White Jean-Pierre Jeunet
1329 Color S.S. Rajamouli
4659 Color Asghar Farhadi
4033 Color Thomas Vinterberg
2829 Color Oliver Hirschbiegel
2734 Black and White Fritz Lang
2551 Color Guillermo del Toro
2047 Color Hayao Miyazaki
3550 Color Denis Villeneuve
4000 Color Juan José Campanella
4160 Color Rajkumar Hirani
4267 Color Alejandro G. Iñárritu
2830 Color Alejandro Amenábar
4461 Color Thomas Vinterberg
1061 Black and White Andrei Tarkovsky
2914 Color Je-kyu Kang
3423 Color Katsuhiro Ôtomo
3553 Color José Padilha
3456 Color Vincent Paronnaud
2739 Color Andrey Zvyagintsev
2802 Color Julian Schnabel
4897 Color Sergio Leone
3344 Color Karan Johar
4284 Color Ari Folman
4144 Color Walter Salles
num_critic_for_reviews duration director_facebook_likes \
4498 181.0 142.0 0.0
4747 153.0 202.0 0.0
4029 214.0 135.0 353.0
2373 246.0 125.0 6000.0
3870 39.0 130.0 6.0
4921 46.0 89.0 373.0
4259 215.0 137.0 207.0
3685 33.0 157.0 85.0
2323 174.0 134.0 6000.0
4105 305.0 120.0 0.0
2970 96.0 293.0 249.0
1298 242.0 122.0 0.0
1329 44.0 159.0 50.0
4659 354.0 123.0 0.0
4033 349.0 115.0 346.0
2829 192.0 178.0 101.0
2734 260.0 145.0 756.0
2551 406.0 112.0 0.0
2047 212.0 119.0 6000.0
3550 226.0 139.0 777.0
4000 262.0 129.0 195.0
4160 15.0 144.0 124.0
4267 157.0 115.0 0.0
2830 157.0 125.0 448.0
4461 98.0 105.0 346.0
1061 144.0 115.0 0.0
2914 86.0 148.0 16.0
3423 150.0 124.0 78.0
3553 142.0 115.0 294.0
3456 242.0 89.0 10.0
2739 103.0 99.0 445.0
2802 259.0 112.0 232.0
4897 122.0 99.0 0.0
3344 210.0 128.0 160.0
4284 231.0 90.0 56.0
4144 71.0 113.0 179.0
actor_3_facebook_likes actor_2_name \
4498 24.0 Luigi Pistilli
4747 4.0 Minoru Chiaki
4029 40.0 Seu Jorge
2373 7.0 Ryûnosuke Kamiki
3870 12.0 Sameer Ali Khan
4921 27.0 Amir Farrokh Hashemian
4259 155.0 Ulrich Mühe
3685 199.0 Steven Mackintosh
2323 745.0 Jada Pinkett Smith
4105 38.0 Ji-tae Yu
2970 18.0 Martin Semmelrogge
1298 54.0 Jamel Debbouze
1329 72.0 Anushka Shetty
4659 620.0 Leila Hatami
4033 26.0 Alexandra Rapaport
2829 471.0 Bruno Ganz
2734 18.0 Gustav Fröhlich
2551 250.0 Maribel Verdú
2047 422.0 Blythe Danner
3550 58.0 Mélissa Désormeaux-Poulin
4000 50.0 Soledad Villamil
4160 327.0 Sanjay Dutt
4267 35.0 Jorge Salinas
2830 93.0 Lola Dueñas
4461 141.0 Paprika Steen
1061 12.0 Anatoliy Solonitsyn
2914 489.0 Bin Won
3423 4.0 Takeshi Kusao
3553 15.0 Fernanda Machado
3456 106.0 Gena Rowlands
2739 9.0 Vladimir Garin
2802 177.0 Mathieu Amalric
4897 93.0 Gian Maria Volontè
3344 81.0 Jimmy Shergill
4284 0.0 Ronny Dayag
4144 11.0 Matheus Nachtergaele
actor_1_facebook_likes gross \
4498 16000.0 6100000.0
4747 304.0 269061.0
4029 1000.0 7563397.0
2373 17.0 10049886.0
3870 85.0 NaN
4921 36.0 925402.0
4259 380.0 11284657.0
3685 397.0 2197331.0
2323 893.0 2298191.0
4105 717.0 2181290.0
2970 362.0 11433134.0
1298 326.0 33201661.0
1329 218.0 6498000.0
4659 786.0 7098492.0
4033 74.0 610968.0
2829 918.0 5501940.0
2734 136.0 26435.0
2551 634.0 37623143.0
2047 23000.0 4710455.0
3550 131.0 6857096.0
4000 827.0 20167424.0
4160 464.0 NaN
4267 85.0 5383834.0
2830 273.0 2086345.0
4461 280.0 1647780.0
1061 29.0 NaN
2914 717.0 1110186.0
3423 6.0 439162.0
3553 585.0 8060.0
3456 963.0 4443403.0
2739 20.0 502028.0
2802 413.0 5990075.0
4897 16000.0 3500000.0
3344 8000.0 4018695.0
4284 56.0 2283276.0
4144 119.0 5595428.0
genres ... country \
4498 Western ... Italy
4747 Action|Adventure|Drama ... Japan
4029 Crime|Drama ... Brazil
2373 Adventure|Animation|Family|Fantasy ... Japan
3870 Action|Drama|History|Thriller|War ... India
4921 Drama|Family ... Iran
4259 Drama|Thriller ... Germany
3685 Comedy|Drama|History|Romance ... India
2323 Adventure|Animation|Fantasy ... Japan
4105 Drama|Mystery|Thriller ... South Korea
2970 Adventure|Drama|Thriller|War ... West Germany
1298 Comedy|Romance ... France
1329 Action|Adventure|Drama|Fantasy|War ... India
4659 Drama|Mystery ... Iran
4033 Drama ... Denmark
2829 Biography|Drama|History|War ... Germany
2734 Drama|Sci-Fi ... Germany
2551 Drama|Fantasy|War ... Spain
2047 Adventure|Animation|Family|Fantasy ... Japan
3550 Drama|Mystery|War ... Canada
4000 Drama|Mystery|Thriller ... Argentina
4160 Comedy|Drama|Romance ... India
4267 Drama|Thriller ... Mexico
2830 Biography|Drama|Romance ... Spain
4461 Drama ... Denmark
1061 Drama|Mystery|Sci-Fi ... Soviet Union
2914 Action|Drama|War ... South Korea
3423 Action|Animation|Sci-Fi ... Japan
3553 Action|Crime|Drama|Thriller ... Brazil
3456 Animation|Biography|Drama|War ... France
2739 Drama|Mystery|Thriller ... Russia
2802 Biography|Drama ... France
4897 Action|Drama|Western ... Italy
3344 Adventure|Drama|Thriller ... India
4284 Animation|Biography|Documentary|Drama|History|War ... Israel
4144 Drama ... Brazil
content_rating budget title_year actor_2_facebook_likes \
4498 Approved 1.200000e+06 1966.0 34.0
4747 Unrated 2.000000e+06 1954.0 8.0
4029 R 3.300000e+06 2002.0 69.0
2373 PG 1.900000e+07 2001.0 10.0
3870 NaN 4.400000e+06 2016.0 26.0
4921 PG 1.800000e+05 1997.0 35.0
4259 R 2.000000e+06 2006.0 284.0
3685 Not Rated NaN 2006.0 227.0
2323 PG-13 2.400000e+09 1997.0 851.0
4105 R 3.000000e+06 2003.0 78.0
2970 R 1.400000e+07 1981.0 21.0
1298 R 7.700000e+07 2001.0 326.0
1329 NaN 1.802615e+07 2015.0 133.0
4659 PG-13 5.000000e+05 2011.0 712.0
4033 R 3.800000e+06 2012.0 69.0
2829 R 1.350000e+07 2004.0 653.0
2734 Not Rated 6.000000e+06 1927.0 23.0
2551 R 1.350000e+07 2006.0 269.0
2047 PG 2.400000e+07 2004.0 713.0
3550 R 6.800000e+06 2010.0 66.0
4000 R 2.000000e+06 2009.0 88.0
4160 PG-13 1.200000e+08 2006.0 426.0
4267 R 2.000000e+06 2000.0 79.0
2830 PG-13 1.000000e+07 2004.0 114.0
4461 R 1.300000e+06 1998.0 278.0
1061 PG 1.000000e+06 1972.0 29.0
2914 R 1.280000e+07 2004.0 517.0
3423 R 1.100000e+09 1988.0 5.0
3553 R 4.000000e+06 2007.0 39.0
3456 PG-13 7.300000e+06 2007.0 545.0
2739 Unrated NaN 2003.0 13.0
2802 PG-13 NaN 2007.0 412.0
4897 R 2.000000e+05 1964.0 360.0
3344 PG-13 1.200000e+07 2010.0 327.0
4284 R 1.500000e+06 2008.0 0.0
4144 R 2.900000e+06 1998.0 14.0
imdb_score aspect_ratio movie_facebook_likes profit Rank
4498 8.9 2.35 20000 4.900000e+06 8
4747 8.7 1.37 11000 -1.730939e+06 23
4029 8.7 1.85 28000 4.263397e+06 24
2373 8.6 1.85 28000 -8.950114e+06 36
3870 8.5 2.35 10000 NaN 42
4921 8.5 1.85 0 7.454020e+05 52
4259 8.5 2.35 39000 9.284657e+06 60
3685 8.4 2.35 0 NaN 63
2323 8.4 1.85 11000 -2.397702e+09 65
4105 8.4 2.35 43000 -8.187100e+05 74
2970 8.4 1.85 11000 -2.566866e+06 75
1298 8.4 2.35 39000 -4.379834e+07 82
1329 8.4 1.85 21000 -1.152815e+07 83
4659 8.4 1.85 48000 6.598492e+06 85
4033 8.3 2.35 60000 -3.189032e+06 88
2829 8.3 1.85 14000 -7.998060e+06 102
2734 8.3 1.33 12000 -5.973565e+06 104
2551 8.2 1.85 27000 2.412314e+07 120
2047 8.2 1.85 13000 -1.928954e+07 123
3550 8.2 1.85 37000 5.709600e+04 127
4000 8.2 2.35 33000 1.816742e+07 130
4160 8.2 2.35 349 NaN 139
4267 8.1 1.85 11000 3.383834e+06 162
2830 8.1 2.35 0 -7.913655e+06 166
4461 8.1 1.33 5000 3.477800e+05 185
1061 8.1 2.35 0 NaN 186
2914 8.1 2.35 0 -1.168981e+07 188
3423 8.1 1.85 0 -1.099561e+09 196
3553 8.1 1.85 11000 -3.991940e+06 199
3456 8.0 1.85 14000 -2.856597e+06 202
2739 8.0 1.85 0 NaN 205
2802 8.0 1.85 13000 NaN 208
4897 8.0 2.35 0 3.300000e+06 211
3344 8.0 2.35 27000 -7.981305e+06 226
4284 8.0 1.85 0 7.832760e+05 243
4144 8.0 2.35 0 2.695428e+06 248
[36 rows x 30 columns]
# print the top 5 foreign language films
Top_Foreign_Lang_Film.head()['movie_title']