클러스터링 (Clustering)
라벨 없이 데이터의 구조를 군집으로 발견하는 비지도학습 영역입니다.핵심 개념
- 거리/밀도/그래프 기반 군집화 전략
- 클러스터 수 선택과 민감도 분석
- 노이즈 및 이상치 처리
자주 보는 평가 지표
SilhouetteDavies-BouldinCalinski-Harabasz
Machine Learning
분류 (Classification)
- 분류 (Classification)
- bernoulli-nb
- categorical-nb
- complement-nb
- decision-tree
- extra-tree-classifier
- gaussian-nb
- gp-classifier
- knn
- lda
- linear-svc
- logistic-regression
- logistic-regression-cv
- mlp-classifier
- multinomial-nb
- nearest-centroid
- nu-svc
- passive-aggressive-classifier
- perceptron
- qda
- radius-neighbors-classifier
- ridge-classifier
- ridge-classifier-cv
- sgd-classifier
- svm
회귀 (Regression)
- 회귀 (Regression)
- ard-regression
- bayesian-ridge
- decision-tree-regressor
- elastic-net
- elastic-net-cv
- extra-tree-regressor
- gamma-regressor
- gp-regressor
- huber-regressor
- isotonic-regression
- kernel-ridge
- kneighbors-regressor
- lars
- lars-cv
- lasso-cv
- lasso-lars-cv
- linear-regression
- linear-svr
- mlp-regressor
- multitask-elastic-net
- multitask-lasso
- nu-svr
- omp-cv
- passive-aggressive-regressor
- poisson-regressor
- polynomial-regression
- quantile-regression
- radius-neighbors-regressor
- ransac
- ridge-cv
- ridge-lasso
- sgd-regressor
- svr
- theil-sen
- tweedie-regressor
클러스터링 (Clustering)
차원 축소 (Dimensionality Reduction)
앙상블 (Ensemble)
- 앙상블 (Ensemble)
- adaboost-classifier
- adaboost-regressor
- bagging-classifier
- bagging-regressor
- catboost-classifier
- catboost-regressor
- extra-trees-classifier
- extra-trees-regressor
- gradient-boosting-classifier
- gradient-boosting-regressor
- hist-gb-classifier
- hist-gb-regressor
- lightgbm-classifier
- lightgbm-regressor
- random-forest-classifier
- random-forest-regressor
- stacking-classifier
- stacking-regressor
- voting-classifier
- voting-regressor
- xgboost-classifier
- xgboost-regressor
- xgboost-rf-classifier
- xgboost-rf-regressor
랭킹 (Learning to Rank)
이상치 탐지 (Anomaly Detection)
매니폴드 학습 (Manifold)
전처리 (Preprocessing)
교차 분해 (Cross Decomposition)
반지도 학습 (Semi-supervised)
불균형 샘플링 (Imbalanced Learning)
- 불균형 샘플링 (Imbalanced Learning)
- adasyn
- balanced-bagging
- balanced-random-forest
- borderline-smote
- cluster-centroids
- condensed-nearest-neighbours
- easy-ensemble
- edited-nearest-neighbours
- kmeans-smote
- nearmiss
- one-sided-selection
- random-oversampler
- random-undersampler
- rus-boost
- smote
- smote-enn
- smote-tomek
- svm-smote
- tomek-links
클러스터링 (Clustering)
클러스터링 (Clustering)
라벨 없이 데이터의 구조를 군집으로 발견하는 비지도학습 영역입니다.