Data analytics FIT3152

my wechat:_0206girl

Don't hesitate to contact me

Instructions and data

The objective of this assignment is to gain familiarity with classification models using R. We want to create models that may be used to predict whether or not a website will be legitimate or designed for phishing -- that is, stealing personal data from users.
You will be using a modified version of the PhiUSIIL Phishing data, hosted by the UCI Machine Learning Archive https://archive.ics.uci.edu/dataset/967/phiusiil+phishing+url+dataset . A research paper based on this data is available here https://doi.org/10.1016/j.cose.2023.103545 .
There are two options for compiling your written report:
(1) You can create your report using any word processor with your R code pasted in as machine readable text as an appendix, and save as a pdf, or
(2) As an R Markdown document that contains the R code with the discussion/text interleaved.
Render this as an HTML file and save as a pdf.
Your video report should be less than 100MB in size. You may need to reduce the resolution of your original recording to achieve this. Use a standard file format such as .mp4, or mov for submission.
Creating your data set
Clear your workspace, set the number of significant digits to a sensible value, and use ' Phish ' as the default data frame name for the whole data set. Read your data into R and create your individual data using the following code:
rm(list = ls())
Phish <- read.csv("PhishingData.csv")
set.seed(XXXXXXXX) # Your Student ID is the random seed
L <- as.data.frame(c(1:50))
L <- L[sample(nrow(L), 10, replace = FALSE),]
Phish <- Phish[(Phish$A01 %in% L),]
PD <- Phish[sample(nrow(Phish), 2000, replace = FALSE),] # sample of 2000 rows
Questions (10 Marks)

  1. Explore the data: What is the proportion of phishing sites to legitimate sites? Obtain descriptions of the predictor (independent) variables -- mean, standard deviations, etc. for real-valued attributes. Is there anything noteworthy in the data? Are there any attributes you need to consider omitting from your analysis? (1 Mark)
  2. Document any pre-processing required to make the data set suitable for the model fitting that follows. (1 Mark)
  3. Divide your data into a 70% training and 30% test set by adapting the following code (written for the iris data). Use your student ID as the random seed.
    set.seed(XXXXXXXX) #Student ID as random seed
    train.row = sample(1:nrow(iris), 0.7*nrow(iris))
    iris.train = iris[train.row,]
    iris.test = iris[-train.row,]
  4. Implement a classification model using each of the following techniques. For this question you may use each of the R functions at their default settings if suitable. (5 Marks)
    • Decision Tree
    • Naïve Bayes
    • Bagging
    • Boosting
    • Random Forest
  5. Using the test data, classify each of the test cases as 'phishing (1)' or 'legitimate (0)'.
    Create a confusion matrix and report the accuracy of each model. (1 Mark)
  6. Using the test data, calculate the confidence of predicting 'phishing' for each case and construct an ROC curve for each classifier. You should be able to plot all the curves on the same axis. Use a different colour for each classifier. Calculate the AUC for each classifier. (1 Mark)
  7. Create a table comparing the results in Questions 5 and 6 for all classifiers. Is there a single "best" classifier? (1 Mark)
    Investigative Tasks (18 Marks)
  8. Examining each of the models, determine the most important variables in predicting whether a web site will be phishing or legitimate. Which variables could be omitted from the data with very little effect on performance? Give reasons. (2 Marks)
  9. Starting with one of the classifiers you created in Question 4, create a classifier that is simple enough for a person to be able to classify whether a site is phishing or legitimate by hand. Describe your model with either a diagram or written explanation. What factors were important in your decision? State why you chose the attributes you used. Using the test data created in Question 3, evaluate model performance using the measures you calculated for Questions 5 and 6. How does it compare to those in Question 4? (4 Marks )
  10. Create the best tree-based classifier you can. You may do this by adjusting the parameters, and/or cross-validation of the basic models in Question 4. Show that your model is better than the others using the measures you calculated for Questions 5 and 6.
    Describe how you created your improved model, and why you chose that model. What factors were important in your decision? State why you chose the attributes you used. (4 Marks)
  11. Using the insights from your analysis so far, implement an Artificial Neural Network classifier and report its performance. Comment on attributes used and your data preprocessing required. How does this classifier compare with the others? Can you give any reasons? (4 Marks)
  12. Fit a new classifier to the data, test and report its performance in the same way as for previous models. You can choose a new type of classifier not covered in the course, or a new version of any of the classifiers we have studied. Either way, you will be implementing a new R package. As a starting point, you might refer to James et al. (2021),
    or look online. When writing up, state the new classifier and package used. Include a web link to the package details. Give a brief description of the model type and how it works.
    Comment on the performance of your new model. (4 Marks)
相关推荐
菜鸟的人工智能之路44 分钟前
桑基图在医学数据分析中的更复杂应用示例
python·数据分析·健康医疗
阡之尘埃7 小时前
Python数据分析案例61——信贷风控评分卡模型(A卡)(scorecardpy 全面解析)
人工智能·python·机器学习·数据分析·智能风控·信贷风控
布说在见10 小时前
层次与网络的视觉对话:树图与力引导布局的双剑合璧
信息可视化·数据挖掘·数据分析
全栈开发圈16 小时前
新书速览|Spark SQL大数据分析快速上手
sql·数据分析·spark
spssau16 小时前
多分类logistic回归分析案例教程
分类·数据挖掘·数据分析·回归·回归分析·logistic回归·spssau
我就说好玩18 小时前
2020年美国总统大选数据分析与模型预测
大数据·python·数据挖掘·数据分析·pandas·sklearn
Aloudata19 小时前
在全域数据整合过程中,如何确保数据的一致性和准确性
大数据·数据库·人工智能·数据挖掘·数据分析
安静的_显眼包O_o20 小时前
【机器学习】连续属性离散化与sklearn.preprocessing.KBinsDiscretizer
数据挖掘·数据分析
叫我:松哥20 小时前
基于python多准则决策分析的汽车推荐算法设计与实现
python·算法·数据挖掘·数据分析·汽车·推荐算法
出发行进20 小时前
PySpark本地开发环境搭建
大数据·python·数据分析·spark·anaconda