ESILV S1 2021–2022
The goal of this project was to use the python skills acquired during this semester to study and analyse a real dataset.
Our dataset was based on a drug consumption study which contains records for 1885 respondents. For each respondent 12 attributes are known.
After cleaning the data and make some visualizations. We have decided to focus on illegal drugs and especially on how the various features had an impact on a specific classification problem which was Can we find a relation between the personality measurements and the use of illegal drug ?
We succeed to set up various machine learning problem which made it possible to predict with an average 80% accuracy if a respondents is probably drugged.
The Project_python_for_data_analysis.ipynb contains all the code in python of the following sections
- Data Cleaning
- Data Visualization
- Machine Learning Modeling
However, you need to install the following librairies :
- Required librairies
- numpy
- pandas
- matplotlib
- geopandas
- seaborn
- folium
- random
- tensorflow
- mapping_data import
- pywaffle
- IPython.display
- sklearn
- tensorflow
- warnings
use the following command in your Anaconda console to download the required librairies
pip install "library name"
- Installation
use the following code in your Anaconda console
pip install flask
- Execution
execute run.py file Go to http://localhost:5000 on your web browser
- Navarre Quentin - @QuentinNav
- Pincet Bruno - @GitBrunoCode