ds-knowledge-notebooks

A collection of Jupyter Notebooks : my understanding of theoretical and practical topics of Data Science

Table of Contents

• Pre-Processing
• Performance Metrics
• Model Evaluation
• Regression
• Regularized Regression
• Decision Tree Learning
• Neural Networks
• Bayesian Learning
• Ensemble Methods
• Clustering

---

Pre-Processing

[back to top]

• Scaling and Normalization
• Feature Extraction
• [Feature Selection]
• [Dimensionality Reduction]

---

Performance Metrics

[back to top]

• Regression Metrics
• Classification Metrics

---

Model Evaluation

[back to top]

• Resubstitution
• Hold Out
• Repeated Hold Out
• Stratified Hold Out
• Repeated Stratified Hold Out
• Cross Validation
  • K-Fold Cross Validation
  • 2-Fold Cross Validation
  • M-Fold Cross Validation
  • The Choice of K
  • Repeated K-Fold Cross Validation
• Bootstrap

---

Regression

[back to top]

• Introduction

• CLRM Assumptions

• Violation of CLRM Assumptions

  • Residual Analysis
  • Violation of Linearity
  • Violation of Exogeneity
  • Violation of Homoscedasticity
  • Violation of Indipendence of the Error Terms
  • Violation of Multicollinearity

• Estimation

  • Statistical Properties
  • Estimation Methods

---

Regularized Regression

[back to top]

• Ridge Regression
• Least Absolute Shrinkage and Selection Operator (LASSO)
• Elastic Net
• [Least Angle Regression (LARS)]

---

Decision Tree Learning

[back to top]

• [Classification and Regression Tree (CART)]
• [Iterative Dichotomiser 3 (ID3)]
• [C4.5 and C5.0]
• [Chi-square Automatic Interaction Detection (CHAID)]
• [Decision Stump]
• [Conditional Decision Tree]
• [M5]

---

Neural Networks

[back to top]

• Introduction
• Activation Functions
• Learning Algorithms
  • The Perceptron Rule
  • The Delta Rule
  • Back Propagation
• Perceptron
• Multi Layer Perceptron
• [Deep Neural Network]
• [Convolutional Neural Network]
• [Recurrent Neural Network]

---

Bayesian Learning

[back to top]

---

Ensemble Methods

[back to top]

---

Clustering

[back to top]