• Air Paradis : Detect bad buzz with deep learning
  • Installation
    • Prerequisites
    • Virtual environment
    • Dependencies
  • Usage
    • Run Notebook
    • Quality Assurance
  • Troubleshooting

---

Air Paradis : Detect bad buzz with deep learning

Repository of OpenClassrooms' AI Engineer path, project #7

Goal : use Azure ML and NLP techniques (Gensim, Bert, Keras, ...), to perform sentiment analysis and prediction on tweets.

You can see the results here :

• Presentation
• Blog Article : Comparing Azure Tools for Sentiment Analysis
• Notebook : HTML page with interactive plots

Installation

Prerequisites

• Python 3.9

Virtual environment

# python -m venv env
# > or just :
make venv
source env/bin/activate

Dependencies

# pip install kaggle jupyterlab ipykernel ipywidgets widgetsnbextension graphviz python-dotenv requests matplotlib seaborn plotly numpy
# > or :
# pip install -r requirements.txt
# > or just :
make install

Usage

Run Notebook

jupyter-lab notebooks/main.ipynb

Quality Assurance

# make isort
# make format
# make lint
# make bandit
# make mypy
# make test
# > or just :
make qa

Troubleshooting

• Fix Plotly issues with JupyterLab

cf. Plotly troubleshooting

jupyter labextension install jupyterlab-plotly

• If using Jupyter Notebook instead of JupyterLab, uncomment the following lines in the notebook

import plotly.io as pio
pio.renderers.default='notebook'