data-enrichment-linear-regression-with-movies

Activity: Create a Linear Regression Model with Statsmodels for Revenue

  • Today we will be working with JUST the data data from the TMDB API for years 2000-2021.

    • We will prepare the data for modeling
      • Some feature engineering
      • Our usual Preprocessing
      • New steps for statsmodels!
    • We will fit a statsmodels linear regression.
    • We Will inspect the model summary.
    • We will create the visualizations to check assumptions about the residuals.
  • Next class we will continue this activity.

    • We will better check all 4 assumptions.
    • We will discuss tactics for dealing with violations of the assumptions.
    • We will use our coefficients to make stakeholder recommendations.

Concepts Demonstrated

  • Using glob for loading in all final files.
  • Statsmodels OLS
  • QQ-Plot
  • Residual Plot