lossj / statistical-machine-learning

Loss J's statistical machine learning course. 🚀

Statistical-Machine-Learning

Before

This's Loss J.'s statistical machine learning action course project.
You can learn to use Numpy, sklearn, TensorFlow 2.x and Pytorch 1.x to build various common statistical machine learning models. Of course, the principles of the model will be supplemented appropriately.

This course is designed to familiarize you with the basic APIs of computing frameworks such as TensorFlow, strengthen coding skills, and help you develop statistical machine learning intuition.

Maybe you can’t wait to learn this course, just click here，then you can start learning this course. By the way, don’t forget to follow me, give the video a like, bookmark the video, and coin the video. Your support is the biggest motivation for me to make courses, thank you!

Setup

1. Clone or download this repositories.
2. Install the necessary packages.

cd Statistical-Machine-Learning && pip install -r requirements.txt

It is recommended that you create an independent virtual environment and run this installation command in the virtual environment to avoid conflicts with your own Python environment.

Directory

• 1 kNN k-nearest neighbors

• 1.1 Principle of kNN model
• 1.2 Use sklearn's kNN model for classification and regression tasks
• 1.3 Build kNN classification model and regression model with NumPy
• 1.4 Build kNN classification model and regression model with TensorFlow2.x
• 1.5 Build kNN classification model and regression model with PyTorch1.x

• 2 Linear Regression

• 2.1 Principle of Linear Regression model
• 2.2 Use sklearn's LinearRegressor, Lasso, Ridge, SGDRegressor models for regression tasks
• 2.3 Build LinearRegressor, Ridge, SGDRegressor, LWLR models with NumPy
• 2.4 Build LinearRegressor, Ridge, SGDRegressor, LWLR models with TensorFlow2.x
• 2.5 Build LinearRegressor, Ridge, SGDRegressor, LWLR models with PyTorch1.x

• 3 Logistc Regression

• 3.1 Principle of Logistic Regression model