How otniel113/ba-jobsim works
Project type and purpose
• This is a data‐science “job simulation” project (BA-JobSim) consisting of two main Python Jupyter notebooks: one for web scraping/insight generation, and one for ML feature importance and prediction.
• Purpose: scrape customer reviews of British Airways, analyze perceptions, select key booking variables, train/predict a customer booking outcome, and summarize findings in a PPTX.
File structure
Top-level files:
• BA_01_Data_Scrapping.ipynb – notebook that fetches and cleans review data from external websites.
• BA_02_ML_Prediction.ipynb – notebook that engineers features, trains a model, and outputs predictions/importance.
• British Airways – Task 01.pptx & Task 02.pptx – slide decks containing visual summaries of each task’s results.
• README.md – high-level overview and links.
No separate “src” or “lib” folders; code and analysis live in notebooks. No deployment descriptors or service definitions–this is a local analysis pipeline.
README for additional insights
• Confirms two tasks: scraping & insight, then feature-importance and prediction.
• Shows screenshots of intermediate outputs (e.g., charts).
• Lists external links (Forage profile, certificate): ancillary to the core pipeline.
Elements
· From Web Data Source → Scraper
· Scraper → Raw Data Store → Processor → Model Trainer → Visualization
· Model Trainer → Trained Model artifact
· Visualization → PPTX & Report