Session Ready
Exercise

Comparing R-squared and coefficients

During the analysis of imputed DataFrames on a linear model, the R-squared score which explains the accuracy and the coefficients which explains the model itself can act as some of the important characteristics to check for the quality of imputation.

In this exercise, you will compare the adjusted R-squared and the coefficients of the linear regressions belonging to the mean, KNN and MICE imputed DataFrames against the baseline linear model diabetes_cc respectively. Their linear models have already been loaded for you as lm, lm_mean, lm_KNN and lm_MICE for making the comparisons.

Instructions 1/3
undefined XP
  • 1
    • Create the r_squared DataFrame by mapping each model's adjusted R-squared to the imputation name.
    • 2
      • Create the coeff DataFrame by mapping each model's coefficients to the imputation name.
    • 3
      • Select the best imputation based on the R-squared score.