Examples

General examples

General-purpose and introductory examples for the scikit.

• Classification of text documents using sparse features
• Pipeline Anova SVM
• Parameter estimation using grid search with a nested cross-validation
• Sample pipeline for text feature extraction and evaluation
• Logistic Regression
• Classification of text documents: using a MLComp dataset
• Gaussian Naive Bayes
• Plot classification probability
• Confusion matrix
• Recognizing hand-written digits
• Univariate Feature Selection
• Linear Discriminant Analysis & Quadratic Discriminant Analysis with confidence
• Linear and Quadratic Discriminant Analysis with confidence ellipsoid
• Nearest Neighbors
• k-Nearest Neighbors regression
• Test with permutations the significance of a classification score
• PLS Partial Least Squares
• Precision-Recall
• Recursive feature elimination
• Recursive feature elimination with cross-validation
• Receiver operating characteristic (ROC)
• Receiver operating characteristic (ROC) with cross validation
• Train error vs Test error

Examples based on real world datasets

Applications to real world problems with some medium sized datasets or interactive user interface.

• Faces recognition example using eigenfaces and SVMs
• Species distribution modeling
• Finding structure in the stock market
• Libsvm GUI
  • Requirements
• Wikipedia princial eigenvector

Clustering

Examples concerning the scikits.learn.cluster package.

• A demo of K-Means clustering on the handwritten digits data
• Demo of affinity propagation clustering algorithm
• Feature agglomeration vs. univariate selection
• Segmenting the picture of Lena in regions
• A demo of structured Ward hierarchical clustering on Lena image
• A demo of the mean-shift clustering algorithm
• Spectral clustering for image segmentation
• Hierarchical clustering: structured vs unstructured ward

Covariance estimation

Examples concerning the scikits.learn.covariance package.

• Ledoit-Wolf vs Covariance simple estimation
• Ledoit-Wolf vs OAS estimation

Decomposition

Examples concerning the scikits.learn.decomposition package.

• Blind source separation using FastICA
• FastICA on 2D point clouds
• Kernel PCA
• NMF for digits feature extraction
• PCA 2D projection of Iris dataset

Gaussian Process for Machine Learning

Examples concerning the scikits.learn.gaussian_process package.

• Gaussian Processes regression: goodness-of-fit on the ‘diabetes’ dataset
• Gaussian Processes classification example: exploiting the probabilistic output
• Gaussian Processes regression: basic introductory example

Generalized Linear Models

Examples concerning the scikits.learn.linear_model package.

• Lasso regression example
• Lasso on dense and sparse data
• Lasso parameter estimation with path and cross-validation
• Automatic Relevance Determination Regression (ARD)
• Bayesian Ridge Regression
• Lasso and Elastic Net
• Lasso path using LARS
• Cross validated Lasso path with coordinate descent
• Path with L1- Logistic Regression
• Ordinary Least Squares
• Polynomial interpolation
• Plot multi-class SGD on the iris dataset
• SGD: Convex Loss Functions
• Ordinary Least Squares with SGD
• SGD: Penalties
• SGD: Maximum margin separating hyperplane
• SGD: Separating hyperplane with weighted classes
• SGD: Weighted samples

Gaussian Mixture Models

Examples concerning the scikits.learn.mixture package.

• Gaussian Mixture Model Ellipsoids
• GMM classification
• Density Estimation for a mixture of Gaussians

Support Vector Machines

Examples concerning the scikits.learn.svm package.

• SVM with custom kernel
• Plot different SVM classifiers in the iris dataset
• One-class SVM with non-linear kernel (RBF)
• SVM: Maximum margin separating hyperplane
• SVM: Separating hyperplane for unbalanced classes
• SVM-Anova: SVM with univariate feature selection
• Non-linear SVM
• Support Vector Regression (SVR) using linear and non-linear kernels
• SVM: Weighted samples