-
Linear Regression Perform Linear Regression on the given dataset. Also perform K-Fold cross-validation in this exercise. Analysis to be included in your report: (a). Choose an appropriate value of K and justify it in your report along with the preprocessing strategy. (b). Include plots between training loss v/s iterations and validation loss v/s itera- tions. (c). Implement gradient descent using two losses - RMSE loss and MAE loss. Include the best RMSE and MAE value achieved in your report.
-
Use the Real_time_dataset for this. Apply different types of loss functions to predict class ‘gender’ and report their performances.
-
Use Decision Tree(DT) and Gaussian Naive Bayes (GNB) classifier to train Dataset 1. Split the data into 60-20-20 train-val-test splits. Implement K-Fold cross validation for both GNB and DT. (a) Save the best model, load the saved model to predict the results on the test data. (b) Evaluate testing data on the basis of accuracy, precision, recall, F1-Score, plot ROC-curve and confusion matrix . (c) Find optimal depth as a parameter in-case of DT using Grid Search and use K-Fold cross validation to validate it. (d) For DT plot training and validation accuracy plot with respect to tree depth and write your analysis.
sabyasachidatta/Linear-Regression-Decision-Tree-Gaussian-Naive-Bayes
Perform Linear Regression on the given dataset. Also perform K-Fold cross-validation
Jupyter Notebook