Data science

Jupyter Notebooks which I have been using in ML study.

• Matplotlib
• Bokeh
• Seaborn
• Pandas

Data Science

• Finding relationships in data

Scikit-learn

Pre-processing data

• Scaling numeric data, representing categorical data in numeric form

Supervised learning

Regression

• Simple linear regression
• Multiple linear regression
• Classification and regression with k-nearest neighbors
• Lasso/Ridge regression
• Gradient boosting regression

Classification

• Classification and regression with k-nearest neighbors
• Logistic regression
• Naive Bayes
• Document classification with SVM
• Nonlinear classification and regression with decision trees

Unsupervised learning

Clustering models

• Simple KMeans clustering
• Mutliple clustering techniques
• Clustering with mean shift
• Hyperparameter tuning for clustering models

Reducing dimensions

• Feature selection
• Dictionary learning
• Dimensionality reduction with PCA

Ensemble methods

• Ensemble learning techniques
• Bagging and pasting
• Random forests and other ensemble methods
• Random forest regression and classification
• Gradient boosting
• XGBoost
• AdaBoost regression and classification
• Stacking classification

Feature extraction

• Feature extraction

Neural Networks

• The perceptron
• Neural networks
• Regression and classification using neural networks
• Text and image classification using neural networks

Performance

• Scaling scikit-learn solutions

PyTorch

• Working with tensors
• Working with gradients (linear model)

Spark

• Spark