This git repository contains the tutorial files for the Introduction to Data Science course of 4GI INSA Lyon:

Notebooks	Links
1. Data exploration
2. Data analysis
3. Regression
4. Sales prediction

This document explains how to install and set up a python environment with conda and install all the required libraries.

Information For those who have troubles installing a python environment on your computer you can simply download notebooks files (.ipynb) from this repository and run them remotely with Google Colab (Google account needed).

Conda is an open-source package management system and environment management system. It quiclky installs, runs and updates packages and their dependencies. We will use it for managing the python environment and all the python libraries needed for the tutorials. There are several ways to install conda on your computer:

1. Anaconda distribution: provides GUI applications, a lot of data science and machine learning package already installed
2. Miniconda: a minimal installer for conda, no GUI application
3. Miniforge: another minimal installer for conda, no GUI application (recommended for the Macbook M chips (Apple Silicon))

• Clone this github repository

git clone https://github.com/ludovicmoncla/insa-4gi-isd.git

• Download and save the following files in one of your folder :
  • requirements.txt
  • notebook.01-data-exploration.ipynb
  • notebook.02-data-analysis.ipynb
  • notebook.03-regression.ipynb
  • notebook.04-sales-prediction.ipynb

• Create a new environment called isd-4gi-py311

conda create -n isd-4gi-py311 python=3.11

• Activate the environment

conda activate isd-4gi-py311

• Install fiona package with conda (this prevent an issue while installing geopandas with pip)

conda install fiona=1.10.1

• Install dependencies with pip

pip install -r requirements.txt

jupyter notebook