xavier-homework8
Question Description
Q1 – Classifier Performance Comparison
Q1a –Analyze the data set Social_Network_Ads.csv and create the plot with correct titles on axes:
Q1b Use the following classifiers
- Naïve Bayes
- Logistic Regression
- Decision Trees
- KNN
- Support Vector Machine
- Random Forest
For each classifier show
- The classifier boundary for training and test
- Printout your 1st name on all graphs
Q1c Compare the confusion matrix in the following table for the above data set
TP |
TN |
FP |
FN |
Accuracy |
|
Naïve Bayes |
|||||
Logistic Regression |
|||||
Decision Trees |
|||||
KNN |
|||||
Support Vector Machine |
|||||
Random Forest |
Q2 – Principal Component Analysis
Summarize how the PCA algorithm works using the following link and recreate the code for the IRIS data set.
https://plot.ly/ipython-notebooks/principal-component-analysis/
Q3 Review the material on PCA in the following and visually describe how PCA works (use snapshots)
http://setosa.io/ev/principal-component-analysis/
Q4 LDA Explain how LDA differs from PCA
https://sebastianraschka.com/Articles/2014_python_lda.html
Q5 Compare accuracy of LDA vs PCA techniques using the dimensionality reduction on Wine data. The dataset is attached.
Q5 Dimensionality Reduction – on Wine data.zip
Q1 Classifier Comparison on Social Ads Network.zip
HW Classifier Comparison.docx