Final Presentation: Video and PDF Slides
Project Logs and Files:
The project files can be downloaded here
Screenshots of work:
Figure 1: visualization of missing values in the dataset.
Figure 2: Visualization after the missing values have been replaced.
Figure 3: URL-Type Frequency Count
Figure 3: Importance of features from all 79 features in the dataset.
Figure 4: To avoid overfitting in model training, the top 15 features are selected after applying the data dimensionality reduction technique.
Table 1: Average accuracy comparison of different ML Algorithms trained using the Cross-Validation Technique.
Table 2: Result Matrices on Testing Extra Tree Classifier on Unseen Data
Further to view work in PDF format click here.
