https://github.com/machinecyc/machine-learning-notes

https://github.com/machinecyc/machine-learning-notes

machine-learning

Last synced: 5 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/machinecyc/machine-learning-notes
• Owner: machineCYC
• Created: 2019-01-01T11:23:29.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2020-06-06T12:44:42.000Z (almost 6 years ago)
• Last Synced: 2025-02-01T01:51:21.712Z (over 1 year ago)
• Topics: machine-learning
• Size: 52.7 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Machine Learning Note

## Machine Learning

* **Supervised Learning**

    * Regression

        * Loss regression

        * Ridge regression

        * ElasticNet regression

    * Classification

        * SVM

        * KNN

        * Logistic regression

* **Unsupervised Learning**

    * Clustering

        * K-means

        * Mixture Normal Model

    * Dimension Reduction

        * t-SNE

        * PCA

* **Deep Learning**

    * Perceptions

    * CNN

    * RNN

    * GAN

    * AutoEncoder

* **Ensemble Learning**

    * Stacking

    * Bagging

    * [Boosting](https://github.com/machineCYC/Machine-Learning-Notes/tree/master/File/Boosting)

        * [Adaptive Boosting (AdaBoost)](https://github.com/machineCYC/Machine-Learning-Notes/tree/master/File/Adaptive_Boosting)

        * [Gradient Boosting (GBM)](https://github.com/machineCYC/Machine-Learning-Notes/tree/master/File/Gradient_Boosting)

        * [eXtreme Gradient Boosting (XGBoost)](https://github.com/machineCYC/Machine-Learning-Notes/tree/master/File/eXtreme_Gradient_Boosting)

* **Reinforcement Learning**

    * Q-Learning

* **Model selection**

    * [ROC](https://github.com/machineCYC/Machine-Learning-Notes/tree/master/File/ROC)

## Data

* **Data types**

    * Categorical

    * Numerical

## Data Processing

* **Data Cleaning and Pre-processing**

    * Outliers

    * Missing value

    * sampling

        * class imbalance

        * sample weight

* **Feature Engineering**

    * Single Feature

        * Feature Transform

            1. Log transform

            2. [Box-cox transform](https://github.com/machineCYC/Machine-Learning-Notes/tree/master/File/Box-cox_transform)

        * Dummies

            1. Ordering

                > Sklearn LabelEncoder

            2. Non-ordering

                > [Dummy encoder、One-hot encoder](https://github.com/machineCYC/Machine-Learning-Notes/tree/master/File/OneHotEncoding)

                > Mean encoding

        * Standerlize (規一化)

        * Creating features

            1. interaction variables

    * Muti Features

        * Dimension Reduction

            1. PCA

            2. LDA

        * Feature Selection

            1. Filter methods

                > baseline coefficients

            2. Embedded methods

                > L2: Ridge Regression

                > L1: Lasso regression

- [x] aaa

## Reference

- [feature eigenner](https://blog.csdn.net/u013421629/article/details/75098156)