STAT 503 - Statistical Learning II: Modern Multivariate Analysis

This page contains my course work from STAT 503 (Winter 2023)

• Programming language: Python
• Frameworks / Library: Numpy, Pandas, Matplotlib, Seaborn, Plotly, Missingno, Scikit-learn, XGBoost, LightGBM, Optuna, Imbalanced-Learn
• Topics:
  • Regression: Regression spline, Smoothing spline
  • Classification: KNN, LDA, QDA, Naive Bayes, Logistic regression, Kernel logistic regression, Tree based methods(Single tree, Bagging, Random forests, Boosting), SVM(Support Vector Machine), Kernel SVM(Kernel Support Vector Machine), MLP(Multilayer Perceptron)
  • Dimensionality reduction: PCA(Principal Component Analysis), Kernel PCA(Kernel Principal Component Analysis), MDS(Multi-dimensional Scaling), Isomap, LLE(Locally Linear Embedding)
  • Clustering: K-means, Hierarchical clustering, GMM(Gaussian Mixture Models), DBSCAN, Spectral clustering

---

Homeworks

1. KNN

Topic: EDA(Exploratory Data Analysis), KNN

Read More

2. LDA, QDA, Naive Bayes

Topic: EDA(Exploratory Data Analysis), LDA(Linear Discriminant Analysis), QDA(Quadratic Discriminant Analysis), Naive Bayes

Read More

3. KNN, Logistic regression

Topic: EDA(Exploratory Data Analysis), KNN, Logistic regression, LOOCV(Leave One Out Cross Validation)

Read More