https://github.com/jeffreywijaya100/exercise-ml

solving case and answer question given about machine learning
https://github.com/jeffreywijaya100/exercise-ml

bagging-ensemble dbscan-clustering decision-tree heart-failure hierarchical-clustering kmeans-clustering linear machine-learning metrics rbf svm

Last synced: 9 months ago
JSON representation

solving case and answer question given about machine learning

• Host: GitHub
• URL: https://github.com/jeffreywijaya100/exercise-ml
• Owner: jeffreywijaya100
• Created: 2024-10-29T13:42:44.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-10-29T20:08:47.000Z (over 1 year ago)
• Last Synced: 2025-06-17T12:45:56.868Z (12 months ago)
• Topics: bagging-ensemble, dbscan-clustering, decision-tree, heart-failure, hierarchical-clustering, kmeans-clustering, linear, machine-learning, metrics, rbf, svm
• Language: Jupyter Notebook
• Homepage:
• Size: 390 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
![image](https://github.com/user-attachments/assets/5373f2d6-6b13-4ce2-8f14-7c3daf9d77ce)

![image](https://github.com/user-attachments/assets/447567bd-fc36-44ed-91c1-d769824f564c)

![image](https://github.com/user-attachments/assets/3e55e758-74ec-4e03-a2e5-34700c5c3364)

2. Super Vector Machine(SVM) is a set of supervised learning methods used for classification, regression, and other detection.

   a) What makes SVM different with other machine learning models?

   

   b) Perform dataset creation as instructed in the code below:

   ![image](https://github.com/user-attachments/assets/a2899078-7e2b-42ed-b546-451fcb0b7af8)

   c) Using the dataset you created before, perform training and testing using two different tuning sets of **linear** kernel SVM model. Train and test ratio is 80:20.

   d)Using the dataset you created before, perform training and testing using two different tuning sets of **Radial Basis Function (RBF)** SVM model. Train and test ratio is 80:20.

   e) Based on experiments 2c and 2d complete the following table:

   ![image](https://github.com/user-attachments/assets/92e99419-8f6b-407c-bb7d-5a6ffbeb36f2)

   f) Perform analysis based on obtained results in Table 2.2. (Sugesstion: discuss which one is the best, then why, which one is the worst, then why.)

3. The idea of **ensemble learning** is to build a prediction model by combining the strengths of a collection of simpler base models, called weak learners. Bagging is one of ensemble learning. In this question, we will compare a single decision tree model with a bagging model containing 100 decision trees. The **HeartFailurePredictionDataset.csv** dataset used can be seen below:

   a) Perform feature engineering into our dataset.

   

   b) Using the HeartFailurePredictionDataset dataset, perform training and testing using a single decision tree model. Train and test ratio is 80:20.

   

   c) Using the HeartFailurePredictionDataset.csv dataset, perform training and testing using the Bagging model which contain 100 decision tree models. Train and test ratio is 80:20.

   d) Based on experiments 3b and 3c, complete the following table:

   

   ![image](https://github.com/user-attachments/assets/68d48861-6406-4ed4-ace0-e6bdb0a3e091)

   e) Perform analysis based on obtained results in Table 3.1. (Sugesstion: discuss which one is the best, then why, which one is the worst, then why.)