Data Analysis work required statistics in R-Studio
Budget: $8 – $15 AUD
The dataset has a series of parameters of the patient like Sex, Drug Type, etc. You will work on developing a classification tree-based AI technique to predict the drug type that should be given to a particular patient based on their characteristics.
Tasks
1. Read the dataset into a data frame called “drug data”. [Hints: Make sure you set strings As Factors = TRUE while reading the data into the data frame.]
2. Create two sets: training (80% observations of the drug dataset) and test (20% observations of the drug dataset) sets.
3. Create a classification tree using the training set and calculate the classification accuracy of the tree using the test set.
4. Use cross-validation to prune the tree (tree from Step 3) optimally. You can use the misclassification error as the basis for pruning. Calculate the classification accuracy of the pruned tree using the test set.
5. Write each of the paths (root to a leaf node) as a classification rule in human-interpretable form for your stakeholders.
Tasks
1. Read the dataset into a data frame called “drug data”. [Hints: Make sure you set strings As Factors = TRUE while reading the data into the data frame.]
2. Create two sets: training (80% observations of the drug dataset) and test (20% observations of the drug dataset) sets.
3. Create a classification tree using the training set and calculate the classification accuracy of the tree using the test set.
4. Use cross-validation to prune the tree (tree from Step 3) optimally. You can use the misclassification error as the basis for pruning. Calculate the classification accuracy of the pruned tree using the test set.
5. Write each of the paths (root to a leaf node) as a classification rule in human-interpretable form for your stakeholders.