-
Perform a EDA explanation for the histograms and Corelation matrix in under 10 lines. What can you conclude from them? marks
-
Do you think data scaling and categorical variables handling is needed in the dataset? Why or Why not?
-
Code and compare results showing at least two classifier models from Logistic regression, GBM(Gradient boosting) or AdaBoost. Compare the accuracy results via a confusion matrix and report. Which model would you recommend here? Why? marks
-
Create a Grid Search for both L1,L2 regularisation using C = [0.001, 0.01, 0.1, 1, 10, 100, 1000] for one of the models you recommended. What is your conclusion?–
-
Code and using Keras fit at least 3 types of Neural network using Keras Sequential model. Use at least 3 models from below options. You can keep batch size as 15 and number of epochs to 100.Why you think your model improved or did not improve?