This repository contains course materials for my Machine Learning class on the topic of Anomaly Detection:
- anomaly_detection_class.pdf : course presentation with teaching content
- anomaly_detection_class.ipynb : Python notebook illustrating the course notions
- anomaly_detection_class-empty.ipynb : same Python notebook to follow with students during class
An application exercise is also available:
- anomaly_detection_exercise.pdf : instructions for the exercise
- data/dataset.csv : the dataset to be used to answer the questions
To follow the notebooks with Google Colab, simply go to https://colab.research.google.com/. Import a new notebook from GitHub, search for "jfabrice" and open one of the notebooks of this class (ml-class-anomaly-detection), for example anomaly_detection_class-empty.ipynb. Then click on "Copy to Drive" to be able to execute it. The first section of the notebook is there to initialize the environment from Google Colab.
To setup the Anaconda environment with required dependencies, execute the following instructions in Anaconda prompt or Linux shell.
# Clone this github repository on your machine
git clone https://github.com/jfabrice/ml-class-anomaly-detection.git
# Change working directory inside the repo
cd ml-class-anomaly-detection
# Create a new virtual environment
conda create -n anomalydetectionenv python==3.6
# Activate the environment
## For Linux / MAC
source activate anomalydetectionenv
## For Windows
activate anomalydetectionenv
# Install the requirements
pip install -r requirements.txt