In [1]:
import pandas as pd
In [ ]:
%%time
cast = pd.DataFrame.from_csv('../data/intro/cast.csv.gz', index_col=None)
In [ ]:
In [ ]:
cast.head()
In [ ]:
In [ ]:
# Create a new `DataFrame` with title and year.
In [ ]:
In [ ]:
# What is the name and year of the very first movie ever made?
In [ ]:
In [ ]:
# How many years into the future does the IMDB database list movie titles?
In [ ]:
In [ ]:
# How many movies listed in `titles` came out in 1950?
In [ ]:
In [ ]:
# What are the 15 most common movie titles in film history?
In [ ]:
In [ ]:
# How many movies has Leonardo DiCaprio acted in?
In [ ]:
In [ ]:
# What movies has Leo acted in major roles (1-3)?
In [ ]:
In [ ]:
# And only in recent (>=2010) years?
In [ ]:
In [ ]:
In [ ]:
# What are the 5 longest movie titles ever?
pd.set_option('max_colwidth', 300)
In [ ]:
In [ ]:
# Plot the number of films that have been released each decade over the history of cinema.
%matplotlib inline
In [ ]:
In [ ]: