Machine Learning with R

Machine Learning with R focuses on building predictive and analytical models using R’s statistical and data analysis capabilities. R provides a rich ecosystem of libraries that make it easy to implement classification, regression, clustering and advanced machine learning techniques.

Basics

In this section, we’ll introduce machine learning.

• Introduction
• Setting up Environment for Machine Learning
• Supervised and Unsupervised Learning

Statistical Analysis

In this section we will explore statistical tools and techniques that can enhance machine learning models.

• Introduction to Statistics
• Descriptive Analysis
• Measure of central tendency
• Measure of variability
• Probability Distributions
• Hypothesis Testing
• ANOVA (Analysis of Variance) Test
• Non-Parametric Tests
• Correlation and Regression
• Spearman Correlation Testing
• Skewness
• Bootstrapping

Data Processing

Data processing is an important step to prepare our data for modeling.

• Data Preprocessing
• Data Cleaning
• Feature Engineering
• Feature Scaling
• Data Visualization in R

Model Evaluation

Evaluating models is important to ensure it performs well on unseen data.

• Cross-Validation
• K-fold Cross Validation
• Repeated K-fold Cross Validation
• LOOCV (Leave One Out Cross-Validation)
• The Validation Set Approach

Supervised Learning

In this section, we’ll explore supervised learning algorithms like regression and classification.

Regression Algorithms

• Regression Analysis
• Linear Regression
• Lasso Regression
• Ridge Regression
• Decision Tree for Regression
• Random Forest Approach for Regression
• Regression using k-Nearest Neighbors

Classification Algorithms

• Logistic Regression
• Naive Bayes Classifier
• Decision Tree Classifiers
• Random Forest Approach for Classification
• K-NN Classifier

Unsupervised Learning

In this section, we’ll see unsupervised techniques like clustering, association and dimensionality reduction.

• K-Means Clustering
• Hierarchical Clustering
• DBScan Clustering
• Linear Discriminant Analysis
• Association Rule Mining
• Apriori Algorithm
• Dimensionality Reduction

Time Series Analysis

Time series analysis deals with data that is ordered by time.

• Time Series Analysis
• Exponential Smoothing
• Time Series Analysis

Popular Packages

In this section, we will explore popular and useful packages for building models.

• caret
• randomForest
• e1071
• xgboost
• nnet
• mlr3

Projects

These projects apply R's machine learning and statistical techniques to real-world problems:

• Netflix Stock Price Prediction & Forecasting
• Heart Disease Prediction
• Financial Fraud Detection
• Diabetes Prediction
• Predictive Healthcare Analysis