Netflix! What started in 1997 as a DVD rental service has since exploded into one of the largest entertainment and media companies.
Given the large number of movies and series available on the platform, it is a perfect opportunity to flex your exploratory data analysis skills and dive into the entertainment industry. Our friend has also been brushing up on their Python skills and has taken a first crack at a CSV file containing Netflix data. They believe that the average duration of movies has been declining. Using your friends initial research, you'll delve into the Netflix data to see if you can determine whether movie lengths are actually getting shorter and explain some of the contributing factors, if any.
You have been supplied with the dataset netflix_data.csv , along with the following table detailing the column names and descriptions:
The data
netflix_data.csv
| Column | Description |
|---|---|
show_id | The ID of the show |
type | Type of show |
title | Title of the show |
director | Director of the show |
cast | Cast of the show |
country | Country of origin |
date_added | Date added to Netflix |
release_year | Year of Netflix release |
duration | Duration of the show in minutes |
description | Description of the show |
genre | Show genre |
# Importing pandas and matplotlib
import pandas as pd
import matplotlib.pyplot as plt
#load a csv file with data
netflix_df=pd.read_csv('netflix_data.csv')
print(netflix_df.info())
# filter data to be only Movies not TV-Shows
netflix_subset=netflix_df[netflix_df['type']=='Movie']
print(netflix_subset.info())
netflix_movies=pd.DataFrame(netflix_subset[['title','country','genre','release_year',
'duration']])
print(netflix_movies.info())
print(netflix_movies.head())# Filter DataFrame by Movie duration
short_movies=netflix_movies[netflix_movies['duration']<60]
print(short_movies.info())
print(short_movies.head())netflix_movies_year=netflix_movies[netflix_movies['release_year']>=2000].groupby('release_year').count()['title']
#Production of short movies through time
short_movies_year=short_movies[short_movies['release_year']>=2000].groupby('release_year').count()['title']
# I deaside to check what is ratio between total amoun of movies and short movies
percent_of_short_movies=short_movies_year/netflix_movies_year
# I drop two rows where we didnt have any value in data set, to make better visualisation
percent_of_short_movies=percent_of_short_movies.drop(labels=[2002,2007],axis=0).reset_index()
print(percent_of_short_movies)plt.plot(percent_of_short_movies.release_year,percent_of_short_movies.title)
plt.title("Change in Production of Short Movies Netflix")
plt.ylabel('Percent of Short Movies')
plt.xlabel("Year")
plt.show()How you can see we getting increase in production of short movies on Netflix
# Let's look in what genres we get increas after 2015
netflix_movies_2000=netflix_movies[netflix_movies['release_year']>=2015]
table_total=pd.pivot_table(netflix_movies_2000,values='duration',index='genre',
columns='release_year',aggfunc='count',fill_value=0)
short_movies_2000=short_movies[short_movies['release_year']>=2015]
table_short=pd.pivot_table(short_movies_2000,values='duration',index='genre',
columns='release_year',aggfunc='count',fill_value=0)
table_ratio=(table_short/table_total).round(3).fillna(0)
table_ratio=table_ratio.drop(labels='Uncategorized',axis=0)
print(table_ratio)We have stable increase in genres like: Children , Documentaries, Stand-up also we get and increas in Dramas for last few years
ax = table_ratio.T.plot(kind='bar', ylabel='Year',xlabel='Percent from total by genre', figsize=(15,10))colors=[]
for color,row in netflix_movies.iterrows():
if row['genre']== "Children":
colors.append('pink')
elif row['genre'] == "Documentaries":
colors.append('blue')
elif row['genre']=="Stand-Up":
colors.append('orange')
else:
colors.append('green')
print(colors[:5])
fig=plt.figure(figsize=(12,8))
plt.scatter(netflix_movies.release_year,netflix_movies.duration,c=colors)
plt.title("Movie Duration by Year of Release")
plt.xlabel("Release year")
plt.ylabel("Duration (min)")
plt.show()answer='maybe'