Commit 04ef7b71 authored by Leodegario Lorenzo II's avatar Leodegario Lorenzo II
Browse files

Add installation instructions

parent 2ab40dbb
......@@ -3,33 +3,14 @@ Are you tired of copy pasting ML codes scattered accross different notebooks? Wa
This library/code contains all the learnings taken from the ML1 class and some more. This includes all the machine learning models used, the cross validation strategy, interpretability strategies, and many more! The code was designed to be beginner friendly, easy to use, easy to integrate, and encourage collaboration across team members!
Please check the table of recipes for the exact task that you need!
Please check the `recipe-book.ipynb` for a sample usage of `mltools.py`!
## Table of Recipes
## Installation
For a quick and easy integration to your project, we recommend you create a linked copy of `mltools.py` on the directory of your project so that it can be easily imported. Here are the recommended steps:
### 1 Training and Testing Machine Learning Models
#### 1.1 Train using all models
#### 1.2 Train using selected models
#### 1.3 Specify scaling
#### 1.4 Specify scorer
### 2 Hypertuning Models
#### 2.1 Specifying models and parameters
#### 2.2 Accuracy versus parameter plots
### 3 Interpreting the Prediction Results
#### 3.1 Regularization Plots
#### 3.2 Tree Feature Importance Plots
#### 3.3 Permutation Importance Plots
#### 3.4 Partial Dependence Plots
1. Clone the `mltools` project on any local directory.
2. Create a hard link of `mltools.py` to the directory of your project. This can be done using the sample code below executed on the `mltools` directory.
```user@host:~/mltools/$ ln mltools.py <target_directory>```
3. Import `mltools.py` on your project using `from mltools import *`.
Great! All of `mltools.py` functionalities can now be used on your project. Remember to update the `mltools` repository once in a while for possible new features!
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment