Logistic Regression Multi-level Independent variables

im trying to study logistic regression, when i did the target variable with all features, i had the summary showing the p-values as usual, but one for the features has 60 level, another feature has 13 level, so how can i proceed with this kind of data, knowing that some of these level has significant low p-values but others dont, so i cant drop the feature completely for example below is a sample of the summary, please your advise

    Coefficients:
                         Estimate Std. Error z value Pr(|z|)    
(Intercept)             3.262e+01  3.241e+00  10.063   2e-16 ***
Perc_PaidCash           1.932e+00  4.887e-02  39.541   2e-16 ***
AgeYear                -1.426e-02  1.363e-03 -10.463   2e-16 ***
Income                 -1.256e-06  1.818e-07  -6.909 4.88e-12 ***
PremLate_3_6_Months1    9.494e-01  3.946e-02  24.063   2e-16 ***
PremLate_3_6_Months2    1.646e+00  5.760e-02  28.566   2e-16 ***
PremLate_3_6_Months3    1.796e+00  8.309e-02  21.612   2e-16 ***
PremLate_3_6_Months4    2.315e+00  1.339e-01  17.294   2e-16 ***
PremLate_3_6_Months5    2.238e+00  2.311e-01   9.688   2e-16 ***
PremLate_3_6_Months6    3.010e+00  3.298e-01   9.128   2e-16 ***
PremLate_3_6_Months7    1.404e+00  5.906e-01   2.378 0.017407 *  
PremLate_3_6_Months8    2.372e+00  6.701e-01   3.539 0.000401 ***
PremLate_3_6_Months9    1.509e+01  3.151e+02   0.048 0.961804    
PremLate_3_6_Months11   1.506e+01  4.414e+02   0.034 0.972778    
PremLate_3_6_Months13   1.507e+01  6.590e+02   0.023 0.981755    
PremLate_6_12_Late1     2.020e+00  5.056e-02  39.951   2e-16 ***
PremLate_6_12_Late2     2.489e+00  8.987e-02  27.699   2e-16 ***
PremLate_6_12_Late3     3.570e+00  1.623e-01  21.999   2e-16 ***
PremLate_6_12_Late4     3.792e+00  2.658e-01  14.269   2e-16 ***
PremLate_6_12_Late5     2.891e+00  4.179e-01   6.919 4.56e-12 ***
PremLate_6_12_Late6    -4.017e-01  6.057e-01  -0.663 0.507230    
PremLate_6_12_Late7     3.267e+00  5.779e-01   5.653 1.57e-08 ***
PremLate_6_12_Late8     1.574e+01  4.959e+02   0.032 0.974680    
PremLate_6_12_Late9     1.471e+01  3.415e+02   0.043 0.965643    
PremLate_6_12_Late10   -1.654e+01  1.455e+03  -0.011 0.990934    

Topic target-encoding feature-engineering logistic-regression predictive-modeling data-cleaning

Category Data Science


Once a Feature is one-Hot encoded, it is as code as an "N" new feature.
You may discard those which has low Feature-importance

About

Geeks Mental is a community that publishes articles and tutorials about Web, Android, Data Science, new techniques and Linux security.