NA / 5
We will cover the following tasks in 58 minutes:
Analyzing Movie Release Dates
In Analyze Box Office Data with Seaborn and Python we focused on exploratory data analysis. In this task, we identify the
release_date column as ripe for feature engineering.
Before we can create new features based on
release_date, we need to define a function to process the dates and convert them to a standard
Datetime format. We will perform data imputation to account for missing values, after which we will apply our processing on the training and test sets.
Feature Engineering Release Date
Now that we have standardized the date format, we will define a function to create new columns for the year, weekday, month, week of the year, day, and quarter.
Visualize the Number of Films Per Year with Plotly
We will use Plotly to create an interactive visualization of the number of films released per year in both the training and test sets.
We use the generic
go.Scatter function from
plotly.graph_objects, and specify the
mode argument to choose between markers or lines.
Number of Films and Revenue Per Year
In this task, we will visualize both the number of films and total revenue per year, and the number of films vs the average revenue per year. We will be able to compare and contrast trends we observe to that of the previous task.
Do Release Days Impact Revenue?
Is it reasonable to assume that movies released on weekends will gross higher revenues? Let’s put this assumption to the test in this task by creating a categorical plot of the day of the week on the x-axis and revenue on the y-axis. Are you surprised by the results? Why or why not?
Relationship between Runtime and Revenue
We will create two plots in this task. The first describes the distribution of the duration of films. The second plots revenue against duration. Let’s find out if the data illustrates the optimal duration of a movie to maximize revenue.
About the Host (Snehan Kekre)
Snehan Kekre is a Machine Learning and Data Science Instructor at Coursera. He studied Computer Science and Artificial Intelligence at Minerva Schools at KGI, based in San Francisco. His interests include AI safety, EdTech, and instructional design. He recognizes that building a deep, technical understanding of machine learning and AI among students and engineers is necessary in order to grow the AI safety community. This passion drives him to design hands-on, project-based machine learning courses on Rhyme.