Skip to content

Commit

Permalink
newer updates
Browse files Browse the repository at this point in the history
  • Loading branch information
SaniyaKhullar committed Oct 23, 2023
1 parent 5fd9dfb commit 56b76ce
Showing 1 changed file with 1 addition and 2 deletions.
3 changes: 1 addition & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -199,8 +199,7 @@ We can retrieve our model coefficients and other attributes by calling these out
| mse_train | Mean Square Error (MSE): predicted `predY_train` versus actual training values for the response variable Y. |
| sorted_coef_df | [Pandas](https://pandas.pydata.org/) dataframe that sorts the final model coefficients (including the y-intercept) based on their absolute values. The rank is provided from least (most important: highest absolute value coefficient) to highest (least important in model). |
| final_corr_vs_coef_df | [Pandas](https://pandas.pydata.org/) dataframe with 3 rows. <br> • NetREm regression coefficient for predictor <br> • correlation of each predictor with y based on the training data <br> • absolute value ranking of the coefficients for the predictors |
| combined_df | [Pandas](https://pandas.pydata.org/) dataframe with a row for each predictor and several columns detailing:<br> • general NetREm model information: `y_intercept`, train MSE, `beta_net`, `alpha_lasso`, original number of predictors in $X$, filtered number of predictors input to NetREm (based on pre-processing by user), final number of non-zero predictors selected <br>
• predictor-specific results: NetREm coefficient for predictor, absolute value of NetREm coefficient, rank of the absolute value of the coefficient (low ranks imply higher | NetREm coefficient | ) |
| combined_df | [Pandas](https://pandas.pydata.org/) dataframe with a row for each predictor and several columns detailing:<br> • general NetREm model information: `y_intercept`, train MSE, `beta_net`, `alpha_lasso`, original number of predictors in $X$, filtered number of predictors input to NetREm (based on pre-processing by user), final number of non-zero predictors selected <br>• predictor-specific results: NetREm coefficient for predictor, absolute value of NetREm coefficient, rank of the absolute value of the coefficient (low ranks imply higher | NetREm coefficient | ) |


<!-- | all_params_list | List of lists of the parameters used for NetREm model (defensive programming) |
Expand Down

0 comments on commit 56b76ce

Please sign in to comment.