# Create the years and durations lists
years = [2011 + i for i in range(10)]
durations = [103, 101, 99, 100, 100, 95, 95, 96, 93, 90]
# Create a dictionary with the two lists
movie_dict = {'years': years, 'durations': durations}
# Print the dictionary
movie_dict
# Import pandas under its usual alias
import pandas as pd
# Create a DataFrame from the dictionary
durations_df = pd.DataFrame(movie_dict)
# Print the DataFrame
durations_df
yearsint64
2011 - 2020
durationsint64
90 - 103
0
2011
103
1
2012
101
2
2013
99
3
2014
100
4
2015
100
5
2016
95
6
2017
95
7
2018
96
8
2019
93
9
2020
90
# Import matplotlib.pyplot under its usual alias and create a figure
import matplotlib.pyplot as plt
fig = plt.figure()
# Draw a line plot of release_years and durations
plt.plot(durations_df['years'], durations_df['durations'])
# Create a title
plt.title('Netflix Movie Durations 2011-2020')
# Show the plot
plt.show()
# Read in the CSV as a DataFrame
netflix_df = pd.read_csv('/work/netflix_data.csv')
# Print the first five rows of the DataFrame
netflix_df.head(5)
show_idobject
typeobject
0
s1
TV Show
1
s2
Movie
2
s3
Movie
3
s4
Movie
4
s5
Movie
# Subset the DataFrame for type "Movie"
netflix_df_movies_only = netflix_df[netflix_df['type'] == "Movie"]
# Select only the columns of interest
netflix_movies_col_subset = netflix_df_movies_only.loc[:, ['title', 'country', 'genre', 'release_year', 'duration']]
# Print the first five rows of the new DataFrame
netflix_movies_col_subset.head(5)
titleobject
countryobject
1
7:19
Mexico
2
23:59
Singapore
3
9
United States
4
21
United States
6
122
Egypt
# Create a figure and increase the figure size
fig = plt.figure(figsize=(12,8))
# Create a scatter plot of duration versus year
plt.scatter(netflix_movies_col_subset['release_year'], netflix_movies_col_subset['duration'])
# Create a title
plt.title('Movie Duration by Year of Release')
# Show the plot
plt.show()
# Filter for durations shorter than 60 minutes
short_movies = netflix_movies_col_subset[netflix_movies_col_subset['duration'] < 60]
# Print the first 20 rows of short_movies
short_movies.head(20)
titleobject
#Rucker505%
100 Things to do Before High School5%
18 others90%
countryobject
United States55%
4 others25%
Missing20%
35
#Rucker50
United States
55
100 Things to do Before High School
United States
67
13TH: A Conversation with Oprah Winfrey & Ava DuVernay
nan
101
3 Seconds Divorce
Canada
146
A 3 Minute Hug
Mexico
162
A Christmas Special: Miraculous: Tales of Ladybug & Cat Noir
France
171
A Family Reunion Christmas
United States
177
A Go! Go! Cory Carson Christmas
United States
178
A Go! Go! Cory Carson Halloween
nan
179
A Go! Go! Cory Carson Summer Camp
nan
# Define an empty list
colors = []
# Iterate over rows of netflix_movies_col_subset
for lab, row in netflix_movies_col_subset.iterrows() :
if row['genre'] == 'Children' :
colors.append('red')
elif row['genre'] == 'Documentaries' :
colors.append('blue')
elif row['genre'] == 'Stand-Up' :
colors.append('green')
else:
colors.append('black')
# Inspect the first 10 values in your list
colors[:9]
# Set the figure style and initalize a new figure
plt.style.use('fivethirtyeight')
fig = plt.figure(figsize=(12,8))
# Create a scatter plot of duration versus release_year
plt.scatter(netflix_movies_col_subset['release_year'], netflix_movies_col_subset['duration'], c = colors)
# Create a title and axis labels
plt.title('Movie duration by year of release')
plt.xlabel('Release year')
plt.ylabel('Duration (min)')
# Show the plot
plt.show()
# Are we certain that movies are getting shorter?
are_movies_getting_shorter = 'No'