Recommendation system for movies

What Are Recommendation Systems in Machine

Learning?

Today, we are facing a very rapid growth in the volume and structure of the Internet. Users are more often found to be lost
in this complex and messy environment of websites due to their complex structure and large amounts of information. So
personalizing and simplifying the web is more important than ever before for users and owners of e-commerce websites.

Machine learning-based recommendation systems are powerful engines using machine learning algorithms to segment
customers based on their user data and behavioral patterns (such as purchase and browsing history, likes, or reviews) and
target them with personalized product and content suggestions

Who is using them?

Today, it plays a very important role in sites that have a lot of hits, users or products, in the fields of entertainment, content-
based, e-commerce, advertising and social networks, etc., such as Netflix, youtube, amazon,lastfm, imdb, Yahoo, Spotify
and so on.
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline

import warnings
warnings.filterwarnings("ignore")

movies = pd.read_csv('../input/movies-recomandation/tmdb_5000_movies.csv')
movies.head()

budget genres homepage id keywords original_language original_title overview popularity prod

[{"id": In the
[{"id": 28,
1463, 22nd
"name":
"name": century, a
0 237000000 "Action"}, http://www.avatarmovie.com/ 19995 en Avatar 150.437577
"culture paraplegic
{"id": 12,
clash"}, Marine is
"nam...
{"id":... di...

Captain
[{"id": 270, Barbossa,
[{"id": 12, Pirates of the
"name": long
"name": Caribbean:
1 300000000 http://disney.go.com/disneypictures/pirates/ 285 "ocean"}, en believed 139.082615
"Adventure"}, At World's
{"id": 726, to be
{"id": 14, "... End
"na... dead,
ha...

A cryptic
[{"id": 28, [{"id": 470, message
"name": "name": from
2 245000000 "Action"}, http://www.sonypictures.com/movies/spectre/ 206647 "spy"}, en Spectre Bond’s 107.376788
{"id": 12, {"id": 818, past
"nam... "name... sends him
o...

[{"id": 849,
[{"id": 28, Following
"name":
"name": the death
"dc The Dark
3 250000000 "Action"}, http://www.thedarkknightrises.com/ 49026 en of District 112.312950
comics"}, Knight Rises Pictu
{"id": 80, Attorney
{"id":
"nam... Harve...
853,...

John
[{"id": 28, [{"id": 818, Carter is a
"name": "name": war-
4 260000000 "Action"}, http://movies.disney.com/john-carter 49529 "based on en John Carter weary, 43.926995
{"id": 12, novel"}, former
"nam... {"id":... military
ca...

print(f'\033[94m')
movies.shape

(4803, 20)

credits = pd.read_csv('../input/movies-recomandation/tmdb_5000_credits.csv')
credits.head()

movie_id title cast crew

0 19995 Avatar [{"cast_id": 242, "character": "Jake Sully", "... [{"credit_id": "52fe48009251416c750aca23", "de...

1 285 Pirates of the Caribbean: At World's End [{"cast_id": 4, "character": "Captain Jack Spa... [{"credit_id": "52fe4232c3a36847f800b579", "de...

2 206647 Spectre [{"cast_id": 1, "character": "James Bond", "cr... [{"credit_id": "54805967c3a36829b5002c41", "de...

3 49026 The Dark Knight Rises [{"cast_id": 2, "character": "Bruce Wayne / Ba... [{"credit_id": "52fe4781c3a36847f81398c3", "de...

4 49529 John Carter [{"cast_id": 5, "character": "John Carter", "c... [{"credit_id": "52fe479ac3a36847f813eaa3", "de...

print(f'\033[94m')
credits.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 4803 entries, 0 to 4802
Data columns (total 4 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 movie_id 4803 non-null int64
1 title 4803 non-null object
2 cast 4803 non-null object
3 crew 4803 non-null object
dtypes: int64(1), object(3)
memory usage: 150.2+ KB

movies.shape
(4803, 20)

print(f'\033[94m')
movies.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 4803 entries, 0 to 4802
Data columns (total 20 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 budget 4803 non-null int64
1 genres 4803 non-null object
2 homepage 1712 non-null object
3 id 4803 non-null int64
4 keywords 4803 non-null object
5 original_language 4803 non-null object
6 original_title 4803 non-null object
7 overview 4800 non-null object
8 popularity 4803 non-null float64
9 production_companies 4803 non-null object
10 production_countries 4803 non-null object
11 release_date 4802 non-null object
12 revenue 4803 non-null int64
13 runtime 4801 non-null float64
14 spoken_languages 4803 non-null object
15 status 4803 non-null object
16 tagline 3959 non-null object
17 title 4803 non-null object
18 vote_average 4803 non-null float64
19 vote_count 4803 non-null int64
dtypes: float64(3), int64(4), object(13)
memory usage: 750.6+ KB

import missingno
missingno.bar(movies, color="dodgerblue", sort="ascending", figsize=(10,5), fontsize=12);

import missingno as msno

missingno.matrix(movies, figsize=(10,5), fontsize=12, color=(1, 0.38, 0.27));
movies.head()['budget']

0 237000000
1 300000000
2 245000000
3 250000000
4 260000000
Name: budget, dtype: int64

movies = movies.merge(credits,on='title')
movies.head(1)

budget genres homepage id keywords original_language original_title overview popularity production_companies

[{"id": In the
[{"id": 28,
1463, 22nd
"name": [{"name": "Ingenious
"name": century, a
0 237000000 "Action"}, http://www.avatarmovie.com/ 19995 en Avatar 150.437577 Film Partners", "id":
"culture paraplegic
{"id": 12, 289...
clash"}, Marine is
"nam...
{"id":... di...

1 rows × 23 columns

movies.shape

(4809, 23)

movies = movies[['movie_id','title','overview','genres','keywords','cast','crew']]
movies.head(2)

movie_id title overview genres keywords cast crew

In the 22nd century, [{"id": 28, "name": [{"id": 1463, [{"cast_id": 242, [{"credit_id":
0 19995 Avatar a paraplegic Marine "Action"}, {"id": 12, "name": "culture "character": "Jake "52fe48009251416c750aca23",
is di... "nam... clash"}, {"id":... Sully", "... "de...

Pirates of the Captain Barbossa, [{"id": 12, "name": [{"id": 270, "name": [{"cast_id": 4, [{"credit_id":
1 285 Caribbean: At long believed to be "Adventure"}, {"id": "ocean"}, {"id": 726, "character": "52fe4232c3a36847f800b579",
World's End dead, ha... 14, "... "na... "Captain Jack Spa... "de...

movies.isnull().sum()

movie_id 0
title 0
overview 3
genres 0
keywords 0
cast 0
crew 0
dtype: int64

movies.dropna(inplace=True)

movies.iloc[0]['genres']

'[{"id": 28, "name": "Action"}, {"id": 12, "name": "Adventure"}, {"id": 14, "name": "Fantasy"}, {"id": 878, "na
me": "Science Fiction"}]'

movies.iloc[0:3]['genres']
0 [{"id": 28, "name": "Action"}, {"id": 12, "nam...
1 [{"id": 12, "name": "Adventure"}, {"id": 14, "...
2 [{"id": 28, "name": "Action"}, {"id": 12, "nam...
Name: genres, dtype: object

movies.loc[0:3]['genres']

0 [{"id": 28, "name": "Action"}, {"id": 12, "nam...

1 [{"id": 12, "name": "Adventure"}, {"id": 14, "...
2 [{"id": 28, "name": "Action"}, {"id": 12, "nam...
3 [{"id": 28, "name": "Action"}, {"id": 80, "nam...
Name: genres, dtype: object

movies.iloc[2:7,0:3] # [Rows , Columns]

movie_id title overview

2 206647 Spectre A cryptic message from Bond’s past sends him o...

3 49026 The Dark Knight Rises Following the death of District Attorney Harve...

4 49529 John Carter John Carter is a war-weary, former military ca...

5 559 Spider-Man 3 The seemingly invincible Spider-Man goes up ag...

6 38757 Tangled When the kingdom's most wanted-and most charmi...

Movie Recommender System Building

Recommender System

Recommender Systems simply put, are AI algorithms that utilize Big Data to suggest additional products to consumers
based on a variety of features. These recommendations can be based on factors such as past purchases, demographic
info, their search history, time spent reviewing the product or a like, dislike or a comment left behind by these
consumers.The idea of Recommender Systems is that if you can narrow down the pool of selection options for your
customers to a few meaningful and relevant choices, they are more likely to make a purchase now, as well as come back
for more down the road.

Different Types of Recommender Systems

 Collaborative Filtering

The Collaborative filtering method for recommender systems is a method that is solely based on the past interactions that
have been recorded between users and items, in order to produce new recommendations.

Collaborative Filtering tends to find what similar users would like and the recommendations to be provided and in order to
classify the users into clusters of similar types and recommend each user according to the preference of its cluster.

The main idea that governs the collaborative methods is that through past user-item interactions when processed through
the system, it becomes sufficient to detect similar users or similar items to make predictions based on these estimated
facts and insights.

Content Based Filtering

The content-based approach uses additional information about users and/or items. This filtering method uses item features
to recommend other items similar to what the user likes and also based on their previous actions or explicit feedback.

The main idea of content-based methods is to try to build a model, based on the available “features”, that explain the
observed user-item interactions.

Such a model helps us in making new predictions for a user pretty easily, with just a look at the profile of this user and
based on its information, to determine relevant movies to suggest.

We will be using Content Based Filtering for this

dataset

def convert(obj):
 L = []
for i in obj:
L.append(i['name'])
return L

# This code convert string into list

import ast
ast.literal_eval('[{"id": 28, "name": "Action"}, {"id": 12, "name": "Adventure"}, {"id": 14, "name": "Fantasy"}, {"id

[{'id': 28, 'name': 'Action'},

{'id': 12, 'name': 'Adventure'},
{'id': 14, 'name': 'Fantasy'},
{'id': 878, 'name': 'Science Fiction'}]

def convert(obj):
L = []
for i in ast.literal_eval(obj):
L.append(i['name'])
return L

movies['genres'].apply(convert)

0 [Action, Adventure, Fantasy, Science Fiction]

1 [Adventure, Fantasy, Action]
2 [Action, Adventure, Crime]
3 [Action, Crime, Drama, Thriller]
4 [Action, Adventure, Science Fiction]
...
4804 [Action, Crime, Thriller]
4805 [Comedy, Romance]
4806 [Comedy, Drama, Romance, TV Movie]
4807 []
4808 [Documentary]
Name: genres, Length: 4806, dtype: object

movies["genres"] = movies['genres'].apply(convert)

movies.head(1)

movie_id title overview genres keywords cast crew

In the 22nd century, a [Action, Adventure, [{"id": 1463, "name": [{"cast_id": 242, [{"credit_id":
0 19995 Avatar paraplegic Marine is Fantasy, Science "culture clash"}, "character": "Jake "52fe48009251416c750aca23",
di... Fiction] {"id":... Sully", "... "de...

movies["keywords"] = movies['keywords'].apply(convert)

movies.head(1)

movie_id title overview genres keywords cast crew

In the 22nd century, a [Action, Adventure, [culture clash, future, [{"cast_id": 242, [{"credit_id":
0 19995 Avatar paraplegic Marine is Fantasy, Science space war, space "character": "Jake "52fe48009251416c750aca23",
di... Fiction] colon... Sully", "... "de...

movies['cast'][0]

'[{"cast_id": 242, "character": "Jake Sully", "credit_id": "5602a8a7c3a3685532001c9a", "gender": 2, "id": 65731
, "name": "Sam Worthington", "order": 0}, {"cast_id": 3, "character": "Neytiri", "credit_id": "52fe48009251416c
750ac9cb", "gender": 1, "id": 8691, "name": "Zoe Saldana", "order": 1}, {"cast_id": 25, "character": "Dr. Grace
Augustine", "credit_id": "52fe48009251416c750aca39", "gender": 1, "id": 10205, "name": "Sigourney Weaver", "ord
er": 2}, {"cast_id": 4, "character": "Col. Quaritch", "credit_id": "52fe48009251416c750ac9cf", "gender": 2, "id
": 32747, "name": "Stephen Lang", "order": 3}, {"cast_id": 5, "character": "Trudy Chacon", "credit_id": "52fe48
009251416c750ac9d3", "gender": 1, "id": 17647, "name": "Michelle Rodriguez", "order": 4}, {"cast_id": 8, "chara
cter": "Selfridge", "credit_id": "52fe48009251416c750ac9e1", "gender": 2, "id": 1771, "name": "Giovanni Ribisi"
, "order": 5}, {"cast_id": 7, "character": "Norm Spellman", "credit_id": "52fe48009251416c750ac9dd", "gender":
2, "id": 59231, "name": "Joel David Moore", "order": 6}, {"cast_id": 9, "character": "Moat", "credit_id": "52fe
48009251416c750ac9e5", "gender": 1, "id": 30485, "name": "CCH Pounder", "order": 7}, {"cast_id": 11, "character
": "Eytukan", "credit_id": "52fe48009251416c750ac9ed", "gender": 2, "id": 15853, "name": "Wes Studi", "order":
8}, {"cast_id": 10, "character": "Tsu\'Tey", "credit_id": "52fe48009251416c750ac9e9", "gender": 2, "id": 10964,
"name": "Laz Alonso", "order": 9}, {"cast_id": 12, "character": "Dr. Max Patel", "credit_id": "52fe48009251416c
750ac9f1", "gender": 2, "id": 95697, "name": "Dileep Rao", "order": 10}, {"cast_id": 13, "character": "Lyle Wai
nfleet", "credit_id": "52fe48009251416c750ac9f5", "gender": 2, "id": 98215, "name": "Matt Gerald", "order": 11}
, {"cast_id": 32, "character": "Private Fike", "credit_id": "52fe48009251416c750aca5b", "gender": 2, "id": 1541
53, "name": "Sean Anthony Moran", "order": 12}, {"cast_id": 33, "character": "Cryo Vault Med Tech", "credit_id"
: "52fe48009251416c750aca5f", "gender": 2, "id": 397312, "name": "Jason Whyte", "order": 13}, {"cast_id": 34, "
character": "Venture Star Crew Chief", "credit_id": "52fe48009251416c750aca63", "gender": 2, "id": 42317, "name
": "Scott Lawrence", "order": 14}, {"cast_id": 35, "character": "Lock Up Trooper", "credit_id": "52fe4800925141
6c750aca67", "gender": 2, "id": 986734, "name": "Kelly Kilgour", "order": 15}, {"cast_id": 36, "character": "Sh
uttle Pilot", "credit_id": "52fe48009251416c750aca6b", "gender": 0, "id": 1207227, "name": "James Patrick Pitt"
, "order": 16}, {"cast_id": 37, "character": "Shuttle Co-Pilot", "credit_id": "52fe48009251416c750aca6f", "gend
er": 0, "id": 1180936, "name": "Sean Patrick Murphy", "order": 17}, {"cast_id": 38, "character": "Shuttle Crew
Chief", "credit_id": "52fe48009251416c750aca73", "gender": 2, "id": 1019578, "name": "Peter Dillon", "order": 1
8}, {"cast_id": 39, "character": "Tractor Operator / Troupe", "credit_id": "52fe48009251416c750aca77", "gender"
: 0, "id": 91443, "name": "Kevin Dorman", "order": 19}, {"cast_id": 40, "character": "Dragon Gunship Pilot", "c
redit_id": "52fe48009251416c750aca7b", "gender": 2, "id": 173391, "name": "Kelson Henderson", "order": 20}, {"c
ast_id": 41, "character": "Dragon Gunship Gunner", "credit_id": "52fe48009251416c750aca7f", "gender": 0, "id":
1207236, "name": "David Van Horn", "order": 21}, {"cast_id": 42, "character": "Dragon Gunship Navigator", "cred
it_id": "52fe48009251416c750aca83", "gender": 0, "id": 215913, "name": "Jacob Tomuri", "order": 22}, {"cast_id"
: 43, "character": "Suit #1", "credit_id": "52fe48009251416c750aca87", "gender": 0, "id": 143206, "name": "Mich
ael Blain-Rozgay", "order": 23}, {"cast_id": 44, "character": "Suit #2", "credit_id": "52fe48009251416c750aca8b
", "gender": 2, "id": 169676, "name": "Jon Curry", "order": 24}, {"cast_id": 46, "character": "Ambient Room Tec
h", "credit_id": "52fe48009251416c750aca8f", "gender": 0, "id": 1048610, "name": "Luke Hawker", "order": 25}, {
"cast_id": 47, "character": "Ambient Room Tech / Troupe", "credit_id": "52fe48009251416c750aca93", "gender": 0,
"id": 42288, "name": "Woody Schultz", "order": 26}, {"cast_id": 48, "character": "Horse Clan Leader", "credit_i
d": "52fe48009251416c750aca97", "gender": 2, "id": 68278, "name": "Peter Mensah", "order": 27}, {"cast_id": 49,
"character": "Link Room Tech", "credit_id": "52fe48009251416c750aca9b", "gender": 0, "id": 1207247, "name": "So
nia Yee", "order": 28}, {"cast_id": 50, "character": "Basketball Avatar / Troupe", "credit_id": "52fe4800925141
6c750aca9f", "gender": 1, "id": 1207248, "name": "Jahnel Curfman", "order": 29}, {"cast_id": 51, "character": "
Basketball Avatar", "credit_id": "52fe48009251416c750acaa3", "gender": 0, "id": 89714, "name": "Ilram Choi", "o
rder": 30}, {"cast_id": 52, "character": "Na\'vi Child", "credit_id": "52fe48009251416c750acaa7", "gender": 0,
"id": 1207249, "name": "Kyla Warren", "order": 31}, {"cast_id": 53, "character": "Troupe", "credit_id": "52fe48
009251416c750acaab", "gender": 0, "id": 1207250, "name": "Lisa Roumain", "order": 32}, {"cast_id": 54, "charact
er": "Troupe", "credit_id": "52fe48009251416c750acaaf", "gender": 1, "id": 83105, "name": "Debra Wilson", "orde
r": 33}, {"cast_id": 57, "character": "Troupe", "credit_id": "52fe48009251416c750acabb", "gender": 0, "id": 120
7253, "name": "Chris Mala", "order": 34}, {"cast_id": 55, "character": "Troupe", "credit_id": "52fe48009251416c
750acab3", "gender": 0, "id": 1207251, "name": "Taylor Kibby", "order": 35}, {"cast_id": 56, "character": "Trou
pe", "credit_id": "52fe48009251416c750acab7", "gender": 0, "id": 1207252, "name": "Jodie Landau", "order": 36},
{"cast_id": 58, "character": "Troupe", "credit_id": "52fe48009251416c750acabf", "gender": 0, "id": 1207254, "na
me": "Julie Lamm", "order": 37}, {"cast_id": 59, "character": "Troupe", "credit_id": "52fe48009251416c750acac3"
, "gender": 0, "id": 1207257, "name": "Cullen B. Madden", "order": 38}, {"cast_id": 60, "character": "Troupe",
"credit_id": "52fe48009251416c750acac7", "gender": 0, "id": 1207259, "name": "Joseph Brady Madden", "order": 39
}, {"cast_id": 61, "character": "Troupe", "credit_id": "52fe48009251416c750acacb", "gender": 0, "id": 1207262,
"name": "Frankie Torres", "order": 40}, {"cast_id": 62, "character": "Troupe", "credit_id": "52fe48009251416c75
0acacf", "gender": 1, "id": 1158600, "name": "Austin Wilson", "order": 41}, {"cast_id": 63, "character": "Troup
e", "credit_id": "52fe48019251416c750acad3", "gender": 1, "id": 983705, "name": "Sara Wilson", "order": 42}, {"
cast_id": 64, "character": "Troupe", "credit_id": "52fe48019251416c750acad7", "gender": 0, "id": 1207263, "name
": "Tamica Washington-Miller", "order": 43}, {"cast_id": 65, "character": "Op Center Staff", "credit_id": "52fe
48019251416c750acadb", "gender": 1, "id": 1145098, "name": "Lucy Briant", "order": 44}, {"cast_id": 66, "charac
ter": "Op Center Staff", "credit_id": "52fe48019251416c750acadf", "gender": 2, "id": 33305, "name": "Nathan Mei
ster", "order": 45}, {"cast_id": 67, "character": "Op Center Staff", "credit_id": "52fe48019251416c750acae3", "
gender": 0, "id": 1207264, "name": "Gerry Blair", "order": 46}, {"cast_id": 68, "character": "Op Center Staff",
"credit_id": "52fe48019251416c750acae7", "gender": 2, "id": 33311, "name": "Matthew Chamberlain", "order": 47},
{"cast_id": 69, "character": "Op Center Staff", "credit_id": "52fe48019251416c750acaeb", "gender": 0, "id": 120
7265, "name": "Paul Yates", "order": 48}, {"cast_id": 70, "character": "Op Center Duty Officer", "credit_id": "
52fe48019251416c750acaef", "gender": 0, "id": 1207266, "name": "Wray Wilson", "order": 49}, {"cast_id": 71, "ch
aracter": "Op Center Staff", "credit_id": "52fe48019251416c750acaf3", "gender": 2, "id": 54492, "name": "James
Gaylyn", "order": 50}, {"cast_id": 72, "character": "Dancer", "credit_id": "52fe48019251416c750acaf7", "gender"
: 0, "id": 1207267, "name": "Melvin Leno Clark III", "order": 51}, {"cast_id": 73, "character": "Dancer", "cred
it_id": "52fe48019251416c750acafb", "gender": 0, "id": 1207268, "name": "Carvon Futrell", "order": 52}, {"cast_
id": 74, "character": "Dancer", "credit_id": "52fe48019251416c750acaff", "gender": 0, "id": 1207269, "name": "B
randon Jelkes", "order": 53}, {"cast_id": 75, "character": "Dancer", "credit_id": "52fe48019251416c750acb03", "
gender": 0, "id": 1207270, "name": "Micah Moch", "order": 54}, {"cast_id": 76, "character": "Dancer", "credit_i
d": "52fe48019251416c750acb07", "gender": 0, "id": 1207271, "name": "Hanniyah Muhammad", "order": 55}, {"cast_i
d": 77, "character": "Dancer", "credit_id": "52fe48019251416c750acb0b", "gender": 0, "id": 1207272, "name": "Ch
ristopher Nolen", "order": 56}, {"cast_id": 78, "character": "Dancer", "credit_id": "52fe48019251416c750acb0f",
"gender": 0, "id": 1207273, "name": "Christa Oliver", "order": 57}, {"cast_id": 79, "character": "Dancer", "cre
dit_id": "52fe48019251416c750acb13", "gender": 0, "id": 1207274, "name": "April Marie Thomas", "order": 58}, {"
cast_id": 80, "character": "Dancer", "credit_id": "52fe48019251416c750acb17", "gender": 0, "id": 1207275, "name
": "Bravita A. Threatt", "order": 59}, {"cast_id": 81, "character": "Mining Chief (uncredited)", "credit_id": "
52fe48019251416c750acb1b", "gender": 0, "id": 1207276, "name": "Colin Bleasdale", "order": 60}, {"cast_id": 82,
"character": "Veteran Miner (uncredited)", "credit_id": "52fe48019251416c750acb1f", "gender": 0, "id": 107969,
"name": "Mike Bodnar", "order": 61}, {"cast_id": 83, "character": "Richard (uncredited)", "credit_id": "52fe480
19251416c750acb23", "gender": 0, "id": 1207278, "name": "Matt Clayton", "order": 62}, {"cast_id": 84, "characte
r": "Nav\'i (uncredited)", "credit_id": "52fe48019251416c750acb27", "gender": 1, "id": 147898, "name": "Nicole
Dionne", "order": 63}, {"cast_id": 85, "character": "Trooper (uncredited)", "credit_id": "52fe48019251416c750ac
b2b", "gender": 0, "id": 1207280, "name": "Jamie Harrison", "order": 64}, {"cast_id": 86, "character": "Trooper
(uncredited)", "credit_id": "52fe48019251416c750acb2f", "gender": 0, "id": 1207281, "name": "Allan Henry", "ord
er": 65}, {"cast_id": 87, "character": "Ground Technician (uncredited)", "credit_id": "52fe48019251416c750acb33
", "gender": 2, "id": 1207282, "name": "Anthony Ingruber", "order": 66}, {"cast_id": 88, "character": "Flight C
rew Mechanic (uncredited)", "credit_id": "52fe48019251416c750acb37", "gender": 0, "id": 1207283, "name": "Ashle
y Jeffery", "order": 67}, {"cast_id": 14, "character": "Samson Pilot", "credit_id": "52fe48009251416c750ac9f9",
"gender": 0, "id": 98216, "name": "Dean Knowsley", "order": 68}, {"cast_id": 89, "character": "Trooper (uncredi
ted)", "credit_id": "52fe48019251416c750acb3b", "gender": 0, "id": 1201399, "name": "Joseph Mika-Hunt", "order"
: 69}, {"cast_id": 90, "character": "Banshee (uncredited)", "credit_id": "52fe48019251416c750acb3f", "gender":
0, "id": 236696, "name": "Terry Notary", "order": 70}, {"cast_id": 91, "character": "Soldier (uncredited)", "cr
edit_id": "52fe48019251416c750acb43", "gender": 0, "id": 1207287, "name": "Kai Pantano", "order": 71}, {"cast_i
d": 92, "character": "Blast Technician (uncredited)", "credit_id": "52fe48019251416c750acb47", "gender": 0, "id
": 1207288, "name": "Logan Pithyou", "order": 72}, {"cast_id": 93, "character": "Vindum Raah (uncredited)", "cr
edit_id": "52fe48019251416c750acb4b", "gender": 0, "id": 1207289, "name": "Stuart Pollock", "order": 73}, {"cas
t_id": 94, "character": "Hero (uncredited)", "credit_id": "52fe48019251416c750acb4f", "gender": 0, "id": 584868
, "name": "Raja", "order": 74}, {"cast_id": 95, "character": "Ops Centreworker (uncredited)", "credit_id": "52f
e48019251416c750acb53", "gender": 0, "id": 1207290, "name": "Gareth Ruck", "order": 75}, {"cast_id": 96, "chara
cter": "Engineer (uncredited)", "credit_id": "52fe48019251416c750acb57", "gender": 0, "id": 1062463, "name": "R
hian Sheehan", "order": 76}, {"cast_id": 97, "character": "Col. Quaritch\'s Mech Suit (uncredited)", "credit_id
": "52fe48019251416c750acb5b", "gender": 0, "id": 60656, "name": "T. J. Storm", "order": 77}, {"cast_id": 98, "
character": "Female Marine (uncredited)", "credit_id": "52fe48019251416c750acb5f", "gender": 0, "id": 1207291,
"name": "Jodie Taylor", "order": 78}, {"cast_id": 99, "character": "Ikran Clan Leader (uncredited)", "credit_id
": "52fe48019251416c750acb63", "gender": 1, "id": 1186027, "name": "Alicia Vela-Bailey", "order": 79}, {"cast_i
d": 100, "character": "Geologist (uncredited)", "credit_id": "52fe48019251416c750acb67", "gender": 0, "id": 120
7292, "name": "Richard Whiteside", "order": 80}, {"cast_id": 101, "character": "Na\'vi (uncredited)", "credit_i
d": "52fe48019251416c750acb6b", "gender": 0, "id": 103259, "name": "Nikie Zambo", "order": 81}, {"cast_id": 102
, "character": "Ambient Room Tech / Troupe", "credit_id": "52fe48019251416c750acb6f", "gender": 1, "id": 42286,
"name": "Julene Renee", "order": 82}]'

def convert3(obj):
def convert3(obj):
L = []
counter = 0
for i in ast.literal_eval(obj):
if counter !=3:
L.append(i['name'])
counter += 1
else:
break
return L

movies['cast'].apply(convert3)

0 [Sam Worthington, Zoe Saldana, Sigourney Weaver]

1 [Johnny Depp, Orlando Bloom, Keira Knightley]
2 [Daniel Craig, Christoph Waltz, Léa Seydoux]
3 [Christian Bale, Michael Caine, Gary Oldman]
4 [Taylor Kitsch, Lynn Collins, Samantha Morton]
...
4804 [Carlos Gallardo, Jaime de Hoyos, Peter Marqua...
4805 [Edward Burns, Kerry Bishé, Marsha Dietlein]
4806 [Eric Mabius, Kristin Booth, Crystal Lowe]
4807 [Daniel Henney, Eliza Coupe, Bill Paxton]
4808 [Drew Barrymore, Brian Herzlinger, Corey Feldman]
Name: cast, Length: 4806, dtype: object

movies['cast'] = movies['cast'].apply(convert3)
movies.head(1)

movie_id title overview genres keywords cast crew

In the 22nd century, a [Action, Adventure, [culture clash, future, [Sam Worthington, Zoe [{"credit_id":
0 19995 Avatar paraplegic Marine is Fantasy, Science space war, space Saldana, Sigourney "52fe48009251416c750aca23",
di... Fiction] colon... Weaver] "de...

movies['crew'][0]

'[{"credit_id": "52fe48009251416c750aca23", "department": "Editing", "gender": 0, "id": 1721, "job": "Editor",

"name": "Stephen E. Rivkin"}, {"credit_id": "539c47ecc3a36810e3001f87", "department": "Art", "gender": 2, "id":
496, "job": "Production Design", "name": "Rick Carter"}, {"credit_id": "54491c89c3a3680fb4001cf7", "department"
: "Sound", "gender": 0, "id": 900, "job": "Sound Designer", "name": "Christopher Boyes"}, {"credit_id": "54491c
b70e0a267480001bd0", "department": "Sound", "gender": 0, "id": 900, "job": "Supervising Sound Editor", "name":
"Christopher Boyes"}, {"credit_id": "539c4a4cc3a36810c9002101", "department": "Production", "gender": 1, "id":
1262, "job": "Casting", "name": "Mali Finn"}, {"credit_id": "5544ee3b925141499f0008fc", "department": "Sound",
"gender": 2, "id": 1729, "job": "Original Music Composer", "name": "James Horner"}, {"credit_id": "52fe48009251
416c750ac9c3", "department": "Directing", "gender": 2, "id": 2710, "job": "Director", "name": "James Cameron"},
{"credit_id": "52fe48009251416c750ac9d9", "department": "Writing", "gender": 2, "id": 2710, "job": "Writer", "n
ame": "James Cameron"}, {"credit_id": "52fe48009251416c750aca17", "department": "Editing", "gender": 2, "id": 2
710, "job": "Editor", "name": "James Cameron"}, {"credit_id": "52fe48009251416c750aca29", "department": "Produc
tion", "gender": 2, "id": 2710, "job": "Producer", "name": "James Cameron"}, {"credit_id": "52fe48009251416c750
aca3f", "department": "Writing", "gender": 2, "id": 2710, "job": "Screenplay", "name": "James Cameron"}, {"cred
it_id": "539c4987c3a36810ba0021a4", "department": "Art", "gender": 2, "id": 7236, "job": "Art Direction", "name
": "Andrew Menzies"}, {"credit_id": "549598c3c3a3686ae9004383", "department": "Visual Effects", "gender": 0, "i
d": 6690, "job": "Visual Effects Producer", "name": "Jill Brooks"}, {"credit_id": "52fe48009251416c750aca4b", "
department": "Production", "gender": 1, "id": 6347, "job": "Casting", "name": "Margery Simkin"}, {"credit_id":
"570b6f419251417da70032fe", "department": "Art", "gender": 2, "id": 6878, "job": "Supervising Art Director", "n
ame": "Kevin Ishioka"}, {"credit_id": "5495a0fac3a3686ae9004468", "department": "Sound", "gender": 0, "id": 688
3, "job": "Music Editor", "name": "Dick Bernstein"}, {"credit_id": "54959706c3a3686af3003e81", "department": "S
ound", "gender": 0, "id": 8159, "job": "Sound Effects Editor", "name": "Shannon Mills"}, {"credit_id": "54491d5
8c3a3680fb1001ccb", "department": "Sound", "gender": 0, "id": 8160, "job": "Foley", "name": "Dennie Thorpe"}, {
"credit_id": "54491d6cc3a3680fa5001b2c", "department": "Sound", "gender": 0, "id": 8163, "job": "Foley", "name"
: "Jana Vance"}, {"credit_id": "52fe48009251416c750aca57", "department": "Costume & Make-Up", "gender": 1, "id"
: 8527, "job": "Costume Design", "name": "Deborah Lynn Scott"}, {"credit_id": "52fe48009251416c750aca2f", "depa
rtment": "Production", "gender": 2, "id": 8529, "job": "Producer", "name": "Jon Landau"}, {"credit_id": "539c49
37c3a36810ba002194", "department": "Art", "gender": 0, "id": 9618, "job": "Art Direction", "name": "Sean Hawort
h"}, {"credit_id": "539c49b6c3a36810c10020e6", "department": "Art", "gender": 1, "id": 12653, "job": "Set Decor
ation", "name": "Kim Sinclair"}, {"credit_id": "570b6f2f9251413a0e00020d", "department": "Art", "gender": 1, "i
d": 12653, "job": "Supervising Art Director", "name": "Kim Sinclair"}, {"credit_id": "54491a6c0e0a26748c001b19"
, "department": "Art", "gender": 2, "id": 14350, "job": "Set Designer", "name": "Richard F. Mays"}, {"credit_id
": "56928cf4c3a3684cff0025c4", "department": "Production", "gender": 1, "id": 20294, "job": "Executive Producer
", "name": "Laeta Kalogridis"}, {"credit_id": "52fe48009251416c750aca51", "department": "Costume & Make-Up", "g
ender": 0, "id": 17675, "job": "Costume Design", "name": "Mayes C. Rubeo"}, {"credit_id": "52fe48009251416c750a
ca11", "department": "Camera", "gender": 2, "id": 18265, "job": "Director of Photography", "name": "Mauro Fiore
"}, {"credit_id": "5449194d0e0a26748f001b39", "department": "Art", "gender": 0, "id": 42281, "job": "Set Design
er", "name": "Scott Herbertson"}, {"credit_id": "52fe48009251416c750aca05", "department": "Crew", "gender": 0,
"id": 42288, "job": "Stunts", "name": "Woody Schultz"}, {"credit_id": "5592aefb92514152de0010f5", "department":
"Costume & Make-Up", "gender": 0, "id": 29067, "job": "Makeup Artist", "name": "Linda DeVetta"}, {"credit_id":
"5592afa492514152de00112c", "department": "Costume & Make-Up", "gender": 0, "id": 29067, "job": "Hairstylist",
"name": "Linda DeVetta"}, {"credit_id": "54959ed592514130fc002e5d", "department": "Camera", "gender": 2, "id":
33302, "job": "Camera Operator", "name": "Richard Bluck"}, {"credit_id": "539c4891c3a36810ba002147", "departmen
t": "Art", "gender": 2, "id": 33303, "job": "Art Direction", "name": "Simon Bright"}, {"credit_id": "54959c0692
51417a81001f3a", "department": "Visual Effects", "gender": 0, "id": 113145, "job": "Visual Effects Supervisor",
"name": "Richard Martin"}, {"credit_id": "54959a0dc3a3680ff5002c8d", "department": "Crew", "gender": 2, "id": 5
8188, "job": "Visual Effects Editor", "name": "Steve R. Moore"}, {"credit_id": "52fe48009251416c750aca1d", "dep
artment": "Editing", "gender": 2, "id": 58871, "job": "Editor", "name": "John Refoua"}, {"credit_id": "54491a4d
c3a3680fc30018ca", "department": "Art", "gender": 0, "id": 92359, "job": "Set Designer", "name": "Karl J. Marti
n"}, {"credit_id": "52fe48009251416c750aca35", "department": "Camera", "gender": 1, "id": 72201, "job": "Direct
or of Photography", "name": "Chiling Lin"}, {"credit_id": "52fe48009251416c750ac9ff", "department": "Crew", "ge
nder": 0, "id": 89714, "job": "Stunts", "name": "Ilram Choi"}, {"credit_id": "54959c529251416e2b004394", "depar
tment": "Visual Effects", "gender": 2, "id": 93214, "job": "Visual Effects Supervisor", "name": "Steven Quale"}
, {"credit_id": "54491edf0e0a267489001c37", "department": "Crew", "gender": 1, "id": 122607, "job": "Dialect Co
ach", "name": "Carla Meyer"}, {"credit_id": "539c485bc3a368653d001a3a", "department": "Art", "gender": 2, "id":
132585, "job": "Art Direction", "name": "Nick Bassett"}, {"credit_id": "539c4903c3a368653d001a74", "department"
: "Art", "gender": 0, "id": 132596, "job": "Art Direction", "name": "Jill Cormack"}, {"credit_id": "539c4967c3a
368653d001a94", "department": "Art", "gender": 0, "id": 132604, "job": "Art Direction", "name": "Andy McLaren"}
, {"credit_id": "52fe48009251416c750aca45", "department": "Crew", "gender": 0, "id": 236696, "job": "Motion Cap
ture Artist", "name": "Terry Notary"}, {"credit_id": "54959e02c3a3680fc60027d2", "department": "Crew", "gender"
: 2, "id": 956198, "job": "Stunt Coordinator", "name": "Garrett Warren"}, {"credit_id": "54959ca3c3a3686ae30043
8c", "department": "Visual Effects", "gender": 2, "id": 957874, "job": "Visual Effects Supervisor", "name": "Jo
nathan Rothbart"}, {"credit_id": "570b6f519251412c74001b2f", "department": "Art", "gender": 0, "id": 957889, "j
ob": "Supervising Art Director", "name": "Stefan Dechant"}, {"credit_id": "570b6f62c3a3680b77007460", "departme
nt": "Art", "gender": 2, "id": 959555, "job": "Supervising Art Director", "name": "Todd Cherniawsky"}, {"credit
_id": "539c4a3ac3a36810da0021cc", "department": "Production", "gender": 0, "id": 1016177, "job": "Casting", "na
me": "Miranda Rivers"}, {"credit_id": "539c482cc3a36810c1002062", "department": "Art", "gender": 0, "id": 10325
36, "job": "Production Design", "name": "Robert Stromberg"}, {"credit_id": "539c4b65c3a36810c9002125", "departm
ent": "Costume & Make-Up", "gender": 2, "id": 1071680, "job": "Costume Design", "name": "John Harding"}, {"cred
it_id": "54959e6692514130fc002e4e", "department": "Camera", "gender": 0, "id": 1177364, "job": "Steadicam Opera
tor", "name": "Roberto De Angelis"}, {"credit_id": "539c49f1c3a368653d001aac", "department": "Costume & Make-Up
", "gender": 2, "id": 1202850, "job": "Makeup Department Head", "name": "Mike Smithson"}, {"credit_id": "549599
9ec3a3686ae100460c", "department": "Visual Effects", "gender": 0, "id": 1204668, "job": "Visual Effects Produce
r", "name": "Alain Lalanne"}, {"credit_id": "54959cdfc3a3681153002729", "department": "Visual Effects", "gender
": 0, "id": 1206410, "job": "Visual Effects Supervisor", "name": "Lucas Salton"}, {"credit_id": "54959623925141
7a81001eae", "department": "Crew", "gender": 0, "id": 1234266, "job": "Post Production Supervisor", "name": "Ja
nace Tashjian"}, {"credit_id": "54959c859251416e1e003efe", "department": "Visual Effects", "gender": 0, "id": 1
271932, "job": "Visual Effects Supervisor", "name": "Stephen Rosenbaum"}, {"credit_id": "5592af28c3a368775a0010
5f", "department": "Costume & Make-Up", "gender": 0, "id": 1310064, "job": "Makeup Artist", "name": "Frankie Ka
rena"}, {"credit_id": "539c4adfc3a36810e300203b", "department": "Costume & Make-Up", "gender": 1, "id": 1319844
, "job": "Costume Supervisor", "name": "Lisa Lovaas"}, {"credit_id": "54959b579251416e2b004371", "department":
"Visual Effects", "gender": 0, "id": 1327028, "job": "Visual Effects Supervisor", "name": "Jonathan Fawkner"},
{"credit_id": "539c48a7c3a36810b5001fa7", "department": "Art", "gender": 0, "id": 1330561, "job": "Art Directio
n", "name": "Robert Bavin"}, {"credit_id": "539c4a71c3a36810da0021e0", "department": "Costume & Make-Up", "gend
er": 0, "id": 1330567, "job": "Costume Supervisor", "name": "Anthony Almaraz"}, {"credit_id": "539c4a8ac3a36810
ba0021e4", "department": "Costume & Make-Up", "gender": 0, "id": 1330570, "job": "Costume Supervisor", "name":
"Carolyn M. Fenton"}, {"credit_id": "539c4ab6c3a36810da0021f0", "department": "Costume & Make-Up", "gender": 0,
"id": 1330574, "job": "Costume Supervisor", "name": "Beth Koenigsberg"}, {"credit_id": "54491ab70e0a267480001ba
2", "department": "Art", "gender": 0, "id": 1336191, "job": "Set Designer", "name": "Sam Page"}, {"credit_id":
"544919d9c3a3680fc30018bd", "department": "Art", "gender": 0, "id": 1339441, "job": "Set Designer", "name": "Te
x Kadonaga"}, {"credit_id": "54491cf50e0a267483001b0c", "department": "Editing", "gender": 0, "id": 1352422, "j
ob": "Dialogue Editor", "name": "Kim Foscato"}, {"credit_id": "544919f40e0a26748c001b09", "department": "Art",
"gender": 0, "id": 1352962, "job": "Set Designer", "name": "Tammy S. Lee"}, {"credit_id": "5495a115c3a3680ff500
2d71", "department": "Crew", "gender": 0, "id": 1357070, "job": "Transportation Coordinator", "name": "Denny Ca
ira"}, {"credit_id": "5495a12f92514130fc002e94", "department": "Crew", "gender": 0, "id": 1357071, "job": "Tran
sportation Coordinator", "name": "James Waitkus"}, {"credit_id": "5495976fc3a36811530026b0", "department": "Sou
nd", "gender": 0, "id": 1360103, "job": "Supervising Sound Editor", "name": "Addison Teague"}, {"credit_id": "5
4491837c3a3680fb1001c5a", "department": "Art", "gender": 2, "id": 1376887, "job": "Set Designer", "name": "C. S
cott Baker"}, {"credit_id": "54491878c3a3680fb4001c9d", "department": "Art", "gender": 0, "id": 1376888, "job":
"Set Designer", "name": "Luke Caska"}, {"credit_id": "544918dac3a3680fa5001ae0", "department": "Art", "gender":
0, "id": 1376889, "job": "Set Designer", "name": "David Chow"}, {"credit_id": "544919110e0a267486001b68", "depa
rtment": "Art", "gender": 0, "id": 1376890, "job": "Set Designer", "name": "Jonathan Dyer"}, {"credit_id": "544
91967c3a3680faa001b5e", "department": "Art", "gender": 0, "id": 1376891, "job": "Set Designer", "name": "Joseph
Hiura"}, {"credit_id": "54491997c3a3680fb1001c8a", "department": "Art", "gender": 0, "id": 1376892, "job": "Art
Department Coordinator", "name": "Rebecca Jellie"}, {"credit_id": "544919ba0e0a26748f001b42", "department": "Ar
t", "gender": 0, "id": 1376893, "job": "Set Designer", "name": "Robert Andrew Johnson"}, {"credit_id": "54491b1
dc3a3680faa001b8c", "department": "Art", "gender": 0, "id": 1376895, "job": "Assistant Art Director", "name": "
Mike Stassi"}, {"credit_id": "54491b79c3a3680fbb001826", "department": "Art", "gender": 0, "id": 1376897, "job"
: "Construction Coordinator", "name": "John Villarino"}, {"credit_id": "54491baec3a3680fb4001ce6", "department"
: "Art", "gender": 2, "id": 1376898, "job": "Assistant Art Director", "name": "Jeffrey Wisniewski"}, {"credit_i
d": "54491d2fc3a3680fb4001d07", "department": "Editing", "gender": 0, "id": 1376899, "job": "Dialogue Editor",
"name": "Cheryl Nardi"}, {"credit_id": "54491d86c3a3680fa5001b2f", "department": "Editing", "gender": 0, "id":
1376901, "job": "Dialogue Editor", "name": "Marshall Winn"}, {"credit_id": "54491d9dc3a3680faa001bb0", "departm
ent": "Sound", "gender": 0, "id": 1376902, "job": "Supervising Sound Editor", "name": "Gwendolyn Yates Whittle"
}, {"credit_id": "54491dc10e0a267486001bce", "department": "Sound", "gender": 0, "id": 1376903, "job": "Sound R
e-Recording Mixer", "name": "William Stein"}, {"credit_id": "54491f500e0a26747c001c07", "department": "Crew", "
gender": 0, "id": 1376909, "job": "Choreographer", "name": "Lula Washington"}, {"credit_id": "549599239251412c4
e002a2e", "department": "Visual Effects", "gender": 0, "id": 1391692, "job": "Visual Effects Producer", "name":
"Chris Del Conte"}, {"credit_id": "54959d54c3a36831b8001d9a", "department": "Visual Effects", "gender": 2, "id"
: 1391695, "job": "Visual Effects Supervisor", "name": "R. Christopher White"}, {"credit_id": "54959bdf9251412c
4e002a66", "department": "Visual Effects", "gender": 0, "id": 1394070, "job": "Visual Effects Supervisor", "nam
e": "Dan Lemmon"}, {"credit_id": "5495971d92514132ed002922", "department": "Sound", "gender": 0, "id": 1394129,
"job": "Sound Effects Editor", "name": "Tim Nielsen"}, {"credit_id": "5592b25792514152cc0011aa", "department":
"Crew", "gender": 0, "id": 1394286, "job": "CG Supervisor", "name": "Michael Mulholland"}, {"credit_id": "54959
a329251416e2b004355", "department": "Crew", "gender": 0, "id": 1394750, "job": "Visual Effects Editor", "name":
"Thomas Nittmann"}, {"credit_id": "54959d6dc3a3686ae9004401", "department": "Visual Effects", "gender": 0, "id"
: 1394755, "job": "Visual Effects Supervisor", "name": "Edson Williams"}, {"credit_id": "5495a08fc3a3686ae30044
1c", "department": "Editing", "gender": 0, "id": 1394953, "job": "Digital Intermediate", "name": "Christine Car
r"}, {"credit_id": "55402d659251413d6d000249", "department": "Visual Effects", "gender": 0, "id": 1395269, "job
": "Visual Effects Supervisor", "name": "John Bruno"}, {"credit_id": "54959e7b9251416e1e003f3e", "department":
"Camera", "gender": 0, "id": 1398970, "job": "Steadicam Operator", "name": "David Emmerichs"}, {"credit_id": "5
4959734c3a3686ae10045e0", "department": "Sound", "gender": 0, "id": 1400906, "job": "Sound Effects Editor", "na
me": "Christopher Scarabosio"}, {"credit_id": "549595dd92514130fc002d79", "department": "Production", "gender":
0, "id": 1401784, "job": "Production Supervisor", "name": "Jennifer Teves"}, {"credit_id": "549596009251413af70
028cc", "department": "Production", "gender": 0, "id": 1401785, "job": "Production Manager", "name": "Brigitte
Yorke"}, {"credit_id": "549596e892514130fc002d99", "department": "Sound", "gender": 0, "id": 1401786, "job": "S
ound Effects Editor", "name": "Ken Fischer"}, {"credit_id": "549598229251412c4e002a1c", "department": "Crew", "
gender": 0, "id": 1401787, "job": "Special Effects Coordinator", "name": "Iain Hutton"}, {"credit_id": "5495983
49251416e2b00432b", "department": "Crew", "gender": 0, "id": 1401788, "job": "Special Effects Coordinator", "na
me": "Steve Ingram"}, {"credit_id": "54959905c3a3686ae3004324", "department": "Visual Effects", "gender": 0, "i
d": 1401789, "job": "Visual Effects Producer", "name": "Joyce Cox"}, {"credit_id": "5495994b92514132ed002951",
"department": "Visual Effects", "gender": 0, "id": 1401790, "job": "Visual Effects Producer", "name": "Jenny Fo
ster"}, {"credit_id": "549599cbc3a3686ae1004613", "department": "Crew", "gender": 0, "id": 1401791, "job": "Vis
ual Effects Editor", "name": "Christopher Marino"}, {"credit_id": "549599f2c3a3686ae100461e", "department": "Cr
ew", "gender": 0, "id": 1401792, "job": "Visual Effects Editor", "name": "Jim Milton"}, {"credit_id": "54959a51
c3a3686af3003eb5", "department": "Visual Effects", "gender": 0, "id": 1401793, "job": "Visual Effects Producer"
, "name": "Cyndi Ochs"}, {"credit_id": "54959a7cc3a36811530026f4", "department": "Crew", "gender": 0, "id": 140
1794, "job": "Visual Effects Editor", "name": "Lucas Putnam"}, {"credit_id": "54959b91c3a3680ff5002cb4", "depar
tment": "Visual Effects", "gender": 0, "id": 1401795, "job": "Visual Effects Supervisor", "name": "Anthony \'Ma
x\' Ivins"}, {"credit_id": "54959bb69251412c4e002a5f", "department": "Visual Effects", "gender": 0, "id": 14017
96, "job": "Visual Effects Supervisor", "name": "John Knoll"}, {"credit_id": "54959cbbc3a3686ae3004391", "depar
tment": "Visual Effects", "gender": 2, "id": 1401799, "job": "Visual Effects Supervisor", "name": "Eric Saindon
"}, {"credit_id": "54959d06c3a3686ae90043f6", "department": "Visual Effects", "gender": 0, "id": 1401800, "job"
: "Visual Effects Supervisor", "name": "Wayne Stables"}, {"credit_id": "54959d259251416e1e003f11", "department"
: "Visual Effects", "gender": 0, "id": 1401801, "job": "Visual Effects Supervisor", "name": "David Stinnett"},
{"credit_id": "54959db49251413af7002975", "department": "Visual Effects", "gender": 0, "id": 1401803, "job": "V
isual Effects Supervisor", "name": "Guy Williams"}, {"credit_id": "54959de4c3a3681153002750", "department": "Cr
ew", "gender": 0, "id": 1401804, "job": "Stunt Coordinator", "name": "Stuart Thorp"}, {"credit_id": "54959ef2c3
a3680fc60027f2", "department": "Lighting", "gender": 0, "id": 1401805, "job": "Best Boy Electric", "name": "Gil
es Coburn"}, {"credit_id": "54959f07c3a3680fc60027f9", "department": "Camera", "gender": 2, "id": 1401806, "job
": "Still Photographer", "name": "Mark Fellman"}, {"credit_id": "54959f47c3a3681153002774", "department": "Ligh
ting", "gender": 0, "id": 1401807, "job": "Lighting Technician", "name": "Scott Sprague"}, {"credit_id": "54959
f8cc3a36831b8001df2", "department": "Visual Effects", "gender": 0, "id": 1401808, "job": "Animation Director",
"name": "Jeremy Hollobon"}, {"credit_id": "54959fa0c3a36831b8001dfb", "department": "Visual Effects", "gender":
0, "id": 1401809, "job": "Animation Director", "name": "Orlando Meunier"}, {"credit_id": "54959fb6c3a3686af3003
f54", "department": "Visual Effects", "gender": 0, "id": 1401810, "job": "Animation Director", "name": "Taisuke
Tanimura"}, {"credit_id": "54959fd2c3a36831b8001e02", "department": "Costume & Make-Up", "gender": 0, "id": 140
1812, "job": "Set Costumer", "name": "Lilia Mishel Acevedo"}, {"credit_id": "54959ff9c3a3686ae300440c", "depart
ment": "Costume & Make-Up", "gender": 0, "id": 1401814, "job": "Set Costumer", "name": "Alejandro M. Hernandez"
}, {"credit_id": "5495a0ddc3a3686ae10046fe", "department": "Editing", "gender": 0, "id": 1401815, "job": "Digit
al Intermediate", "name": "Marvin Hall"}, {"credit_id": "5495a1f7c3a3686ae3004443", "department": "Production",
"gender": 0, "id": 1401816, "job": "Publicist", "name": "Judy Alley"}, {"credit_id": "5592b29fc3a36869d100002f"
, "department": "Crew", "gender": 0, "id": 1418381, "job": "CG Supervisor", "name": "Mike Perry"}, {"credit_id"
: "5592b23a9251415df8001081", "department": "Crew", "gender": 0, "id": 1426854, "job": "CG Supervisor", "name":
"Andrew Morley"}, {"credit_id": "55491e1192514104c40002d8", "department": "Art", "gender": 0, "id": 1438901, "j
ob": "Conceptual Design", "name": "Seth Engstrom"}, {"credit_id": "5525d5809251417276002b06", "department": "Cr
ew", "gender": 0, "id": 1447362, "job": "Visual Effects Art Director", "name": "Eric Oliver"}, {"credit_id": "5
54427ca925141586500312a", "department": "Visual Effects", "gender": 0, "id": 1447503, "job": "Modeling", "name"
: "Matsune Suzuki"}, {"credit_id": "551906889251415aab001c88", "department": "Art", "gender": 0, "id": 1447524,
"job": "Art Department Manager", "name": "Paul Tobin"}, {"credit_id": "5592af8492514152cc0010de", "department":
"Costume & Make-Up", "gender": 0, "id": 1452643, "job": "Hairstylist", "name": "Roxane Griffin"}, {"credit_id":
"553d3c109251415852001318", "department": "Lighting", "gender": 0, "id": 1453938, "job": "Lighting Artist", "na
me": "Arun Ram-Mohan"}, {"credit_id": "5592af4692514152d5001355", "department": "Costume & Make-Up", "gender":
0, "id": 1457305, "job": "Makeup Artist", "name": "Georgia Lockhart-Adams"}, {"credit_id": "5592b2eac3a36877470
012a5", "department": "Crew", "gender": 0, "id": 1466035, "job": "CG Supervisor", "name": "Thrain Shadbolt"}, {
"credit_id": "5592b032c3a36877450015f1", "department": "Crew", "gender": 0, "id": 1483220, "job": "CG Superviso
r", "name": "Brad Alexander"}, {"credit_id": "5592b05592514152d80012f6", "department": "Crew", "gender": 0, "id
": 1483221, "job": "CG Supervisor", "name": "Shadi Almassizadeh"}, {"credit_id": "5592b090c3a36877570010b5", "d
epartment": "Crew", "gender": 0, "id": 1483222, "job": "CG Supervisor", "name": "Simon Clutterbuck"}, {"credit_
id": "5592b0dbc3a368774b00112c", "department": "Crew", "gender": 0, "id": 1483223, "job": "CG Supervisor", "nam
e": "Graeme Demmocks"}, {"credit_id": "5592b0fe92514152db0010c1", "department": "Crew", "gender": 0, "id": 1483
224, "job": "CG Supervisor", "name": "Adrian Fernandes"}, {"credit_id": "5592b11f9251415df8001059", "department
": "Crew", "gender": 0, "id": 1483225, "job": "CG Supervisor", "name": "Mitch Gates"}, {"credit_id": "5592b15dc
3a3687745001645", "department": "Crew", "gender": 0, "id": 1483226, "job": "CG Supervisor", "name": "Jerry Kung
"}, {"credit_id": "5592b18e925141645a0004ae", "department": "Crew", "gender": 0, "id": 1483227, "job": "CG Supe
rvisor", "name": "Andy Lomas"}, {"credit_id": "5592b1bfc3a368775d0010e7", "department": "Crew", "gender": 0, "i
d": 1483228, "job": "CG Supervisor", "name": "Sebastian Marino"}, {"credit_id": "5592b2049251415df8001078", "de
partment": "Crew", "gender": 0, "id": 1483229, "job": "CG Supervisor", "name": "Matthias Menz"}, {"credit_id":
"5592b27b92514152d800136a", "department": "Crew", "gender": 0, "id": 1483230, "job": "CG Supervisor", "name": "
Sergei Nevshupov"}, {"credit_id": "5592b2c3c3a36869e800003c", "department": "Crew", "gender": 0, "id": 1483231,
"job": "CG Supervisor", "name": "Philippe Rebours"}, {"credit_id": "5592b317c3a36877470012af", "department": "C
rew", "gender": 0, "id": 1483232, "job": "CG Supervisor", "name": "Michael Takarangi"}, {"credit_id": "5592b345
c3a36877470012bb", "department": "Crew", "gender": 0, "id": 1483233, "job": "CG Supervisor", "name": "David Wei
tzberg"}, {"credit_id": "5592b37cc3a368775100113b", "department": "Crew", "gender": 0, "id": 1483234, "job": "C
G Supervisor", "name": "Ben White"}, {"credit_id": "573c8e2f9251413f5d000094", "department": "Crew", "gender":
1, "id": 1621932, "job": "Stunts", "name": "Min Windle"}]'

def fetch_director(obj):
L = []
for i in ast.literal_eval(obj):
if i ['job'] == "Director":

L.append(i['name'])
return L

movies['crew'].apply(fetch_director)
0 [James Cameron]
1 [Gore Verbinski]
2 [Sam Mendes]
3 [Christopher Nolan]
4 [Andrew Stanton]
...
4804 [Robert Rodriguez]
4805 [Edward Burns]
4806 [Scott Smith]
4807 [Daniel Hsia]
4808 [Brian Herzlinger, Jon Gunn, Brett Winn]
Name: crew, Length: 4806, dtype: object

movies['crew'] = movies['crew'].apply(fetch_director)
movies.head(1)

movie_id title overview genres keywords cast crew

In the 22nd century, a [Action, Adventure, [culture clash, future, space [Sam Worthington, Zoe [James
0 19995 Avatar
paraplegic Marine is di... Fantasy, Science Fiction] war, space colon... Saldana, Sigourney Weaver] Cameron]

movies['overview'][0]

'In the 22nd century, a paraplegic Marine is dispatched to the moon Pandora on a unique mission, but becomes to
rn between following orders and protecting an alien civilization.'

movies['overview'].apply(lambda x:x.split())

0 [In, the, 22nd, century,, a, paraplegic, Marin...

1 [Captain, Barbossa,, long, believed, to, be, d...
2 [A, cryptic, message, from, Bond’s, past, send...
3 [Following, the, death, of, District, Attorney...
4 [John, Carter, is, a, war-weary,, former, mili...
...
4804 [El, Mariachi, just, wants, to, play, his, gui...
4805 [A, newlywed, couple's, honeymoon, is, upended...
4806 ["Signed,, Sealed,, Delivered", introduces, a,...
4807 [When, ambitious, New, York, attorney, Sam, is...
4808 [Ever, since, the, second, grade, when, he, fi...
Name: overview, Length: 4806, dtype: object

movies['overview'] = movies['overview'].apply(lambda x:x.split())

movies.head(1)

movie_id title overview genres keywords cast crew

[In, the, 22nd, century,, a, [Action, Adventure, [culture clash, future, space [Sam Worthington, Zoe [James
0 19995 Avatar
paraplegic, Marin... Fantasy, Science Fiction] war, space colon... Saldana, Sigourney Weaver] Cameron]

# Sam Worthington

# Convert

# SamWorthington

movies['genres'].apply(lambda x:[i.replace(" ", "") for i in x])

0 [Action, Adventure, Fantasy, ScienceFiction]

1 [Adventure, Fantasy, Action]
2 [Action, Adventure, Crime]
3 [Action, Crime, Drama, Thriller]
4 [Action, Adventure, ScienceFiction]
...
4804 [Action, Crime, Thriller]
4805 [Comedy, Romance]
4806 [Comedy, Drama, Romance, TVMovie]
4807 []
4808 [Documentary]
Name: genres, Length: 4806, dtype: object

movies['genres'] = movies['genres'].apply(lambda x:[i.replace(" ", "") for i in x])

movies['keywords'] = movies['keywords'].apply(lambda x:[i.replace(" ", "") for i in x])

movies['cast'] = movies['cast'].apply(lambda x:[i.replace(" ", "") for i in x])

movies['crew'] = movies['crew'].apply(lambda x:[i.replace(" ", "") for i in x])

movies.head()
 movie_id title overview genres keywords cast crew

[In, the, 22nd, [Action, Adventure, [cultureclash, future, [SamWorthington,

0 19995 Avatar century,, a, Fantasy, spacewar, ZoeSaldana, [JamesCameron]
paraplegic, Marin... ScienceFiction] spacecolony, ... SigourneyWeaver]

Pirates of the [Captain, Barbossa,, [ocean, drugabuse, [JohnnyDepp,

[Adventure, Fantasy,
1 285 Caribbean: At long, believed, to, be, exoticisland, OrlandoBloom, [GoreVerbinski]
Action]
World's End d... eastindiatrad... KeiraKnightley]

[A, cryptic, message, [spy, basedonnovel, [DanielCraig,

[Action, Adventure,
2 206647 Spectre from, Bond’s, past, secretagent, sequel, ChristophWaltz, [SamMendes]
Crime]
send... mi6, ... LéaSeydoux]

[ChristianBale,
The Dark Knight [Following, the, death, [Action, Crime, [dccomics, crimefighter,
3 49026 MichaelCaine, [ChristopherNolan]
Rises of, District, Attorney... Drama, Thriller] terrorist, secretiden...
GaryOldman]

[John, Carter, is, a, [basedonnovel, mars, [TaylorKitsch,

[Action, Adventure,
4 49529 John Carter war-weary,, former, medallion, spacetravel, LynnCollins, [AndrewStanton]
ScienceFiction]
mili... p... SamanthaMorton]

movies['tags'] = movies['overview'] + movies['genres'] + movies['keywords'] + movies['cast'] + movies['crew']

movies.head(1)

movie_id title overview genres keywords cast crew tags

[In, the,
[In, the, 22nd, [Action, Adventure, [cultureclash, future, [SamWorthington, 22nd,
0 19995 Avatar century,, a, Fantasy, spacewar, ZoeSaldana, [JamesCameron] century,, a,
paraplegic, Marin... ScienceFiction] spacecolony, ... SigourneyWeaver] paraplegic,
Marin...

new_df = movies[["movie_id","title","tags"]]
new_df.head(2)

movie_id title tags

0 19995 Avatar [In, the, 22nd, century,, a, paraplegic, Marin...

1 285 Pirates of the Caribbean: At World's End [Captain, Barbossa,, long, believed, to, be, d...

# This is called steaming

["loved","loving","love"]

["love","love","love"]

['love', 'love', 'love']

import nltk

from nltk.stem.porter import PorterStemmer

ps = PorterStemmer()

# Example

def stem1(text):
y = []

for i in text.split():
ps.stem()

def stem(text):
y = []

for i in text.split():
y.append(ps.stem(i))

return " ".join(y)

new_df['tags'][0]
['In',
'the',
'22nd',
'century,',
'a',
'paraplegic',
'Marine',
'is',
'dispatched',
'to',
'the',
'moon',
'Pandora',
'on',
'a',
'unique',
'mission,',
'but',
'becomes',
'torn',
'between',
'following',
'orders',
'and',
'protecting',
'an',
'alien',
'civilization.',
'Action',
'Adventure',
'Fantasy',
'ScienceFiction',
'cultureclash',
'future',
'spacewar',
'spacecolony',
'society',
'spacetravel',
'futuristic',
'romance',
'space',
'alien',
'tribe',
'alienplanet',
'cgi',
'marine',
'soldier',
'battle',
'loveaffair',
'antiwar',
'powerrelations',
'mindandsoul',
'3d',
'SamWorthington',
'ZoeSaldana',
'SigourneyWeaver',
'JamesCameron']

new_df['tags'] = new_df["tags"].apply(lambda x:" ".join(x))

new_df.head(1)

movie_id title tags

0 19995 Avatar In the 22nd century, a paraplegic Marine is di...

new_df['tags'][0]

'In the 22nd century, a paraplegic Marine is dispatched to the moon Pandora on a unique mission, but becomes to
rn between following orders and protecting an alien civilization. Action Adventure Fantasy ScienceFiction cultu
reclash future spacewar spacecolony society spacetravel futuristic romance space alien tribe alienplanet cgi ma
rine soldier battle loveaffair antiwar powerrelations mindandsoul 3d SamWorthington ZoeSaldana SigourneyWeaver
JamesCameron'

new_df['tags'].apply(lambda x:x.lower())

0 in the 22nd century, a paraplegic marine is di...

1 captain barbossa, long believed to be dead, ha...
2 a cryptic message from bond’s past sends him o...
3 following the death of district attorney harve...
4 john carter is a war-weary, former military ca...
...
4804 el mariachi just wants to play his guitar and ...
4805 a newlywed couple's honeymoon is upended by th...
4806 "signed, sealed, delivered" introduces a dedic...
4807 when ambitious new york attorney sam is sent t...
4808 ever since the second grade when he first saw ...
Name: tags, Length: 4806, dtype: object
# Convert all in lover case
new_df['tags'] = new_df['tags'].apply(lambda x:x.lower())

new_df.head(1)

movie_id title tags

0 19995 Avatar in the 22nd century, a paraplegic marine is di...

new_df['tags'][0]

'in the 22nd century, a paraplegic marine is dispatched to the moon pandora on a unique mission, but becomes to
rn between following orders and protecting an alien civilization. action adventure fantasy sciencefiction cultu
reclash future spacewar spacecolony society spacetravel futuristic romance space alien tribe alienplanet cgi ma
rine soldier battle loveaffair antiwar powerrelations mindandsoul 3d samworthington zoesaldana sigourneyweaver
jamescameron'

new_df['tags'][1]

"captain barbossa, long believed to be dead, has come back to life and is headed to the edge of the earth with
will turner and elizabeth swann. but nothing is quite as it seems. adventure fantasy action ocean drugabuse exo
ticisland eastindiatradingcompany loveofone'slife traitor shipwreck strongwoman ship alliance calypso afterlife
fighter pirate swashbuckler aftercreditsstinger johnnydepp orlandobloom keiraknightley goreverbinski"

Ranking vs. Recommendation

People sometimes confuse between ranking (or search ranking) system and recommender system, and some may even
think they are interchangeable. While both algorithms are trying to present items in a sorted way, there are some key
differences between these two:

Ranking algorithms normally put more relevant items closer to the top of the showing list whereas recommender systems
sometimes try to avoid overspecialization. A good recommender system should not recommend items that are too similar
to what users have seen before, and should diversify its recommendations.

Ranking algorithms rely on search query provided by users, who know what they are looking for. Recommender systems,
on the other hand, without any explicit inputs from users, aim to discovering things they might not have found otherwise.

Matrix Factorization

Latent factor models compress user-item matrix into a low-dimensional representation in terms of latent factors. One
advantage of using this approach is that instead of having a high dimensional matrix containing abundant number of
missing values we will be dealing with a much smaller matrix in lower-dimensional space.

A reduced presentation could be utilized for either user-based or item-based neighborhood algorithms that are presented
in the previous section. There are several advantages with this paradigm. It handles the sparsity of the original matrix
better than memory based ones. Also comparing similarity on the resulting matrix is much more scalable especially in
dealing with large sparse datasets.
 An important decision is the number of factors to factor the user-item matrix. The higher the number of factors, the more
precise is the factorization in the original matrix reconstructions. Therefore, if the model is allowed to memorize too much
details of the original matrix, it may not generalize well for data it was not trained on. Reducing the number of factors
increases the model generalization.

from sklearn.feature_extraction.text import CountVectorizer

cv = CountVectorizer(max_features=5000,stop_words='english')

vector = cv.fit_transform(new_df['tags']).toarray()

vector

array([[0, 0, 0, ..., 0, 0, 0],

[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0],
...,
[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0]])

vector[0]

array([0, 0, 0, ..., 0, 0, 0])

vector.shape

(4806, 5000)

cv.get_feature_names()

['000',
'007',
'10',
'100',
'11',
'12',
'13',
'14',
'15',
'16',
'17',
'18',
'18th',
'19',
'1930s',
'1940s',
'1944',
'1950',
'1950s',
'1960s',
'1970s',
'1971',
'1974',
'1976',
'1980',
'1980s',
'1985',
'1990s',
'1999',
'19th',
'19thcentury',
'20',
'200',
'2003',
'2009',
'20th',
'24',
'25',
'30',
'300',
'3d',
'40',
'50',
'500',
'60',
'60s',
'70',
'aaron',
'aaroneckhart',
'abandoned',
'abducted',
'abigailbreslin',
'abilities',
'ability',
'able',
'aboard',
'abuse',
'abusive',
'academic',
'academy',
'accept',
'accepted',
'accepts',
'access',
'accident',
'accidental',
'accidentally',
'accompanied',
'accomplish',
'account',
'accountant',
'accused',
'ace',
'achieve',
'act',
'acting',
'action',
'actionhero',
'actions',
'activist',
'activities',
'activity',
'actor',
'actors',
'actress',
'acts',
'actual',
'actually',
'adam',
'adams',
'adamsandler',
'adamshankman',
'adaptation',
'adapted',
'addict',
'addicted',
'addiction',
'adolescence',
'adopt',
'adopted',
'adoption',
'adopts',
'adrienbrody',
'adult',
'adultery',
'adulthood',
'adults',
'advantage',
'adventure',
'adventures',
'advertising',
'advice',
'affair',
'affairs',
'affection',
'affections',
'afghanistan',
'africa',
'african',
'africanamerican',
'aftercreditsstinger',
'afterlife',
'aftermath',
'age',
'aged',
'agedifference',
'agency',
'agenda',
'agent',
'agents',
'aggressive',
'aging',
'ago',
'agree',
'agrees',
'ahead',
'aid',
'aided',
'aids',
'ailing',
'air',
'airplane',
'airplanecrash',
'airport',
'aka',
'al',
'alabama',
'alan',
'alaska',
'albert',
'alcohol',
'alcoholic',
'alcoholism',
'alecbaldwin',
'alex',
'alfredhitchcock',
'ali',
'alice',
'alien',
'alieninvasion',
'alienlife',
'aliens',
'alike',
'alive',
'allen',
'alliance',
'allied',
'allies',
'allow',
'allows',
'ally',
'alongside',
'alpacino',
'alter',
'alternate',
'alternative',
'alzheimer',
'amanda',
'amandapeet',
'amandaseyfried',
'amateur',
'amazing',
'ambassador',
'ambition',
'ambitious',
'ambulance',
'ambush',
'america',
'american',
'americanabroad',
'americanfootball',
'americans',
'amid',
'amidst',
'amnesia',
'amp',
'amsterdam',
'amusementpark',
'amy',
'amyadams',
'amysmart',
'analyst',
'anarchiccomedy',
'ancient',
'ancientrome',
'ancientworld',
'anderson',
'andiemacdowell',
'andrew',
'android',
'andy',
'andygarcía',
'angel',
'angelabassett',
'angeles',
'angelinajolie',
'angels',
'anger',
'anglee',
'angry',
'animal',
'animalattack',
'animalhorror',
'animals',
'animated',
'animation',
'ann',
'anna',
'annabelle',
'annafaris',
'annakendrick',
'anne',
'annehathaway',
'annemoss',
'annettebening',
'annie',
'anniversary',
'announces',
'annual',
'anonymity',
'anonymous',
'answer',
'answers',
'ant',
'antarctic',
'anthology',
'anthony',
'anthonyanderson',
'anthonyhopkins',
'anthonymackie',
'anthropomorphism',
'anti',
'antics',
'antihero',
'antoinefuqua',
'antoniobanderas',
'antonyelchin',
'apart',
'apartheid',
'apartment',
'ape',
'apes',
'apocalypse',
'apocalyptic',
'apparent',
'apparently',
'appear',
'appears',
'apple',
'appointed',
'apprentice',
'approach',
'approaches',
'approaching',
'april',
'aquarium',
'arab',
'arch',
'archaeologist',
'archeology',
'archer',
'architect',
'arctic',
'area',
'aren',
'arena',
'argument',
'arise',
'aristocrat',
'armed',
'arms',
'army',
'arnold',
'arnoldschwarzenegger',
'arrangedmarriage',
'arrangement',
'arrest',
'arrested',
'arrival',
'arrive',
'arrives',
'arriving',
'arrogant',
'art',
'arthur',
'artificialintelligence',
'artist',
'artistic',
'artists',
'arts',
'ashley',
'ashleyjudd',
'ashtonkutcher',
'asia',
'aside',
'ask',
'asked',
'asking',
'asks',
'aspirations',
'aspiring',
'assassin',
'assassinate',
'assassination',
'assassins',
'assault',
'assigned',
'assignment',
'assistant',
'assumes',
'asteroid',
'astronaut',
'astronauts',
'asylum',
'atheist',
'athlete',
'atlantic',
'atomicbomb',
'attack',
'attacked',
'attacks',
'attempt',
'attempting',
'attempts',
'attending',
'attends',
'attention',
'attic',
'attitude',
'attorney',
'attracted',
'attraction',
'attractive',
'audience',
'audiences',
'audition',
'august',
'aunt',
'austin',
'australia',
'australian',
'author',
'authorities',
'authority',
'autism',
'auto',
'avenge',
'average',
'avoid',
'awaits',
'awakens',
'award',
'away',
'awry',
'ax',
'babe',
'baby',
'bachelor',
'backdrop',
'background',
'backgrounds',
'bad',
'bag',
'bahamas',
'bail',
'balance',
'ball',
'ballet',
'baltimore',
'band',
'bandits',
'bangkok',
'banished',
'bank',
'banker',
'bankrobber',
'bankrobbery',
'bar',
'barely',
'bargained',
'barn',
'barney',
'barry',
'barrylevinson',
'barrysonnenfeld',
'bars',
'base',
'baseball',
'based',
'basedoncomicbook',
'basedongraphicnovel',
'basedonnovel',
'basedonplay',
'basedonstagemusical',
'basedontrueevents',
'basedontruestory',
'basedontvseries',
'basedonvideogame',
'basedonyoungadultnovel',
'basement',
'basketball',
'batman',
'battle',
'battlefield',
'battles',
'battling',
'bay',
'beach',
'bear',
'bears',
'beast',
'beasts',
'beat',
'beating',
'beautiful',
'beautifulwoman',
'beauty',
'becky',
'becominganadult',
'bed',
'bedroom',
'beer',
'befriends',
'began',
'begin',
'beginning',
'begins',
'behavior',
'beings',
'beliefs',
'believe',
'believed',
'believes',
'believing',
'beloved',
'ben',
'benaffleck',
'beneath',
'benfoster',
'beniciodeltoro',
'benjamin',
'benjaminbratt',
'benkingsley',
'bennett',
'benstiller',
'bent',
'berlin',
'best',
'bestfriend',
'bet',
'beth',
'betrayal',
'betrayed',
'bettemidler',
'better',
'betty',
'beverly',
'bible',
'big',
'bigger',
'biggest',
'biker',
'bikini',
'billhader',
'billionaire',
'billmurray',
'billnighy',
'billpaxton',
'billpullman',
'billy',
'billybobthornton',
'billycrudup',
'billycrystal',
'biography',
'bird',
'birth',
'birthday',
'bisexual',
'bishop',
'bit',
'bite',
'bitter',
'bizarre',
'black',
'blackmagic',
'blackmail',
'blackpeople',
'blade',
'blame',
'blind',
'bliss',
'block',
'blonde',
'blood',
'bloodsplatter',
'bloodthirsty',
'bloody',
'blow',
'blue',
'board',
'boarding',
'boardingschool',
'boat',
'bob',
'bobby',
'bobbyfarrelly',
'bobhoskins',
'bodies',
'body',
'bodyguard',
'bold',
'bollywood',
'bomb',
'bombing',
'bond',
'bonds',
'bone',
'book',
'books',
'border',
'bored',
'boredom',
'boring',
'born',
'boss',
'boston',
'botched',
'bound',
'boundaries',
'bounty',
'bountyhunter',
'box',
'boxer',
'boxing',
'boy',
'boyfriend',
'boys',
'bradleycooper',
'bradpitt',
'brain',
'brand',
'brandon',
'brave',
'bravery',
'brazil',
'brazilian',
'break',
'breakdown',
'breaking',
'breaks',
'breast',
'brendanfraser',
'brendangleeson',
'brent',
'brettratner',
'brian',
'briandepalma',
'bride',
'bridge',
'brief',
'brien',
'bright',
'brilliant',
'bring',
'bringing',
'brings',
'brink',
'britain',
'british',
'britishsecretservice',
'brittanymurphy',
'broadway',
'broke',
'broken',
'broker',
'brooklyn',
'brooks',
'brothel',
'brother',
'brotherbrotherrelationship',
'brothers',
'brothersisterrelationship',
'brought',
'brown',
'bruce',
'brucewillis',
'brutal',
'brutality',
'brutally',
'bryansinger',
'buck',
'buddies',
'buddy',
'buddycomedy',
'budget',
'build',
'building',
'built',
'bully',
'bullying',
'bumbling',
'bunny',
'burglar',
'buried',
'bus',
'bush',
'business',
'businessman',
'bust',
'busy',
'butler',
'buy',
'cabin',
'caesar',
'cage',
'cairo',
'cal',
'california',
'called',
'calls',
'calvin',
'camcorder',
'came',
'camera',
'cameraman',
'cameras',
'camerondiaz',
'camp',
'campaign',
'campbell',
'camping',
'campus',
'canada',
'canadian',
'cancer',
'candidate',
'candy',
'cannibal',
'capable',
'capital',
'capitalism',
'capt',
'captain',
'captive',
'capture',
'captured',
'captures',
'car',
'caraccident',
'carchase',
'carcrash',
'card',
'care',
'career',
'carefree',
'caretaker',
'caribbean',
'carjourney',
'carl',
'carlagugino',
'carmen',
'carol',
'carolina',
'carrace',
'carrie',
'carry',
'carrying',
'cars',
'cartel',
'carter',
'cartoon',
'caryelwes',
'case',
'caseyaffleck',
'cash',
'casino',
'cast',
'castle',
'cat',
'cataclysm',
'catastrophe',
'catch',
'catches',
'cateblanchett',
'catherinedeneuve',
'catherinekeener',
'catherinezeta',
'catholic',
'catholicism',
'cattle',
'caught',
'cause',
'caused',
'causes',
'causing',
'cavalry',
'cave',
'cavemen',
'celebrate',
'celebrated',
'celebration',
'celebrity',
'cell',
'cellphone',
'cemetery',
'center',
'centered',
'centers',
'central',
'centuries',
'century',
'ceo',
'ceremony',
'certain',
'chad',
'chain',
'chainsaw',
'challenge',
'challenged',
'challenges',
'champion',
'championship',
'chance',
'change',
'changed',
'changes',
'changing',
'channingtatum',
'chaos',
'chaotic',
'chapter',
'character',
'characters',
'charge',
'charged',
'charismatic',
'charles',
'charlie',
'charliesheen',
'charlizetheron',
'charlotte',
'charm',
'charming',
'chase',
'chased',
'chauffeur',
'cheating',
'cheerleader',
'chef',
'chemical',
'cher',
'chicago',
'chicken',
'chief',
'child',
'childabuse',
'childhero',
'childhood',
'children',
'chilling',
'china',
'chinese',
'chip',
'chiwetelejiofor',
'chloëgracemoretz',
'chloësevigny',
'chocolate',
'choice',
'choices',
'choose',
'chosen',
'chris',
'chriscolumbus',
'chriscooper',
'chrisevans',
'chrishemsworth',
'chrisklein',
'chrispine',
'chrisrock',
'christ',
'christian',
'christianbale',
'christianity',
'christianslater',
'christinaapplegate',
'christinaricci',
'christine',
'christmas',
'christmasparty',
'christmastree',
'christopher',
'christopherlambert',
'christopherlloyd',
'christophernolan',
'christopherplummer',
'christopherwalken',
'christophwaltz',
'chronicle',
'chronicles',
'chuck',
'church',
'cia',
'cigarettesmoking',
'cillianmurphy',
'cinema',
'circle',
'circuit',
'circumstances',
'circus',
'cities',
'citizens',
'city',
'civil',
'civilization',
'civilwar',
'claim',
'claims',
'claire',
'clairedanes',
'clan',
'clark',
'clash',
'class',
'classes',
'classic',
'classmate',
'classmates',
'classroom',
'claudevandamme',
'clay',
'clean',
'clear',
'clerk',
'client',
'clients',
'climate',
'climbing',
'clinteastwood',
'cliveowen',
'clock',
'clone',
'cloning',
'close',
'closer',
'club',
'clubs',
'clues',
'clutches',
'coach',
'coast',
'cocaine',
'code',
'cody',
'coffin',
'cohen',
'col',
'cold',
'coldwar',
'cole',
'colin',
'colinfarrell',
'colinfirth',
'collapse',
'colleague',
'colleagues',
'collect',
'collection',
'collector',
'college',
'collide',
'collins',
'collision',
'colombia',
'colonel',
'colony',
'color',
'colorado',
'colorful',
'coma',
'combat',
'combination',
'combined',
'come',
'comeback',
'comedian',
'comedic',
'comedy',
'comes',
'comet',
'comfort',
'comic',
'comics',
'coming',
'comingofage',
'comingout',
'command',
'commander',
'commercial',
'commit',
'commitment',
'committed',
'common',
'communication',
'communist',
'community',
'companion',
'company',
'compete',
'competing',
'competition',
'competitive',
'complete',
'completely',
'complex',
'complicated',
'complications',
'composer',
'computer',
'computervirus',
'conan',
'concert',
'conclusion',
'condition',
'conditions',
'confession',
'confidence',
'confident',
'conflict',
'confront',
'confronted',
'confused',
'congress',
'conman',
'connected',
'connection',
'connell',
'connor',
'conquer',
'conscience',
'consequences',
'conservative',
'considered',
'conspiracy',
'constant',
'constantly',
'construction',
'contact',
'contain',
'contemporary',
'contend',
'contest',
'continue',
'continues',
'continuing',
'contract',
'control',
'controlled',
'controlling',
'controversial',
'convention',
'converge',
'convict',
'convicted',
'convince',
'convinced',
'convinces',
'cook',
'cooking',
'cool',
'cooper',
'cop',
'cope',
'cops',
'core',
'corner',
'corners',
'corporate',
'corporation',
'corpse',
'corrupt',
...]

# Steaming

["loved","loving","love"]
["love","love","love"]

['love', 'love', 'love']

ps.stem('loved')

'love'

ps.stem('loving')

'love'

ps.stem('love')

'love'

stem('in the 22nd century, a paraplegic marine is dispatched to the moon pandora on a unique mission, but becomes tor

'in the 22nd century, a parapleg marin is dispatch to the moon pandora on a uniqu mission, but becom torn betwe
en follow order and protect an alien civilization. action adventur fantasi sciencefict cultureclash futur space
war spacecoloni societi spacetravel futurist romanc space alien tribe alienplanet cgi marin soldier battl lovea
ffair antiwar powerrel mindandsoul 3d samworthington zoesaldana sigourneyweav jamescameron'

from sklearn.metrics.pairwise import cosine_similarity

similarity = cosine_similarity(vector)

similarity

array([[1. , 0.08964215, 0.06071767, ..., 0.02519763, 0.0277885 ,

0. ],
[0.08964215, 1. , 0.06350006, ..., 0.02635231, 0. ,
0. ],
[0.06071767, 0.06350006, 1. , ..., 0.02677398, 0. ,
0. ],
...,
[0.02519763, 0.02635231, 0.02677398, ..., 1. , 0.07352146,
0.04774099],
[0.0277885 , 0. , 0. , ..., 0.07352146, 1. ,
0.05264981],
[0. , 0. , 0. , ..., 0.04774099, 0.05264981,
1. ]])

similarity[0]

array([1. , 0.08964215, 0.06071767, ..., 0.02519763, 0.0277885 ,

0. ])

new_df[new_df['title'] == 'The Lego Movie'].index[0]

744

sorted(list(enumerate(similarity[0])),reverse=True,key= lambda x:x[1])[1:6]

[(539, 0.26089696604360174),
(1194, 0.2581988897471611),
(260, 0.25110592822973776),
(1216, 0.24944382578492943),
(507, 0.24846467329894412)]

def recommend(movie):
index = new_df[new_df['title'] == movie].index[0]
distances = sorted(list(enumerate(similarity[index])),reverse=True,key = lambda x: x[1])
for i in distances[1:6]:
print(new_df.iloc[i[0]].title)

Movies recommended according to similarity

print(f'\033[94m')
recommend('Spectre')

Quantum of Solace
Never Say Never Again
Skyfall
Thunderball
From Russia with Love

print(f'\033[94m')
recommend('John Carter')

Star Trek: Insurrection

Mission to Mars
Captain America: The First Avenger
Escape from Planet Earth
Ghosts of Mars

References
https://www.zeolearn.com/magazine/recommendation-systems-in-machine-learning

https://www.analyticssteps.com/blogs/what-are-recommendation-systems-machine-learning

https://medium.com/@zeolearn/recommendation-systems-in-machine-learning-96444fd90702

https://www.itransition.com/machine-learning/recommendation-systems

https://muitnoida.edu.in/recommendation-system-in-machine-learning/

https://www.researchgate.net/figure/Types-of-recommendation-algorithms_fig5_322360704