End-to-end EDA on 300,153 Indian airline flight bookings | Analyzing price patterns across airlines, routes, departure times, booking windows & travel classes using Python, Pandas & Seaborn
An end-to-end Data Analysis project on 300,153 flight booking records across 6 Indian cities, completed as part of the Python for Data Analysis course.
Analyze flight pricing patterns across airlines, departure/arrival times, routes, last-minute booking behavior, and Economy vs Business class comparisons.
- Source: AirlinesFlightsData.csv
- Records: 300,153 flight bookings
- Airlines: SpiceJet, AirAsia, Vistara, GO_FIRST, Indigo, Air_India
- Cities: Delhi, Mumbai, Bangalore, Kolkata, Hyderabad, Chennai
- Features: airline, flight, source_city, departure_time, stops, arrival_time, destination_city, class, duration, days_left, price
| Library | Purpose |
|---|---|
| Pandas | Data cleaning, filtering, groupby |
| Matplotlib | Bar charts, line charts |
| Seaborn | Boxplots, heatmaps, scatter plots |
- Imports & Setup
- Load Dataset
- First Look (head / tail)
- Data Structure & Info
- Data Quality Check
- Unique Values per Column
- Analytical Questions (Q1 → Q9)
- Additional Visualizations
- Price Distribution
- Price vs Stops
- Price vs Duration
- Correlation Heatmap
- Key Insights
- Business class costs 5–6x more than Economy on average
- Last-minute bookings (1–2 days before) are significantly more expensive
- Vistara is the most premium airline; SpiceJet & AirAsia are budget-friendly
- Evening and Late Night departures tend to be cheaper
- Non-stop flights can be priced higher than one-stop — convenience premium
- Delhi and Mumbai dominate as source cities
git clone https://github.com/ammarelsayed-2a/Project-13-Python-For-Data-Analysis-Airlines.git
cd Project-13-Python-For-Data-Analysis-Airlines
jupyter notebook "Project 13 Airlines.ipynb"Ammar Elsayed — Python for Data Analysis | 2026 LinkedIn