🚀 SpaceX Falcon 9 Launch Analysis Project

---

📖 Project Overview

This project analyzes SpaceX Falcon 9 rocket launches to predict first-stage landing success. Since SpaceX reuses first stages to reduce cost (e.g., $62M vs. $165M by others), predicting successful landings helps estimate launch costs and improve operational efficiency.

---

📁 Repository Contents

📡 Data Collection

• jupyter-labs-webscraping.ipynb: Scrapes Wikipedia using BeautifulSoup.
• jupyter-labs-spacex-data-collection-api-v2.ipynb: Uses SpaceX REST API to collect launch data.

🧹 Data Processing

• labs-jupyter-spacex-Data wrangling-v2.ipynb: Cleans and merges datasets.

📊 Exploratory Data Analysis

• jupyter-labs-eda-sql-coursera_sqllite.ipynb: SQL-based queries and insights.
• jupyter-labs-eda-dataviz-v2.ipynb: Visualizations using Seaborn and Matplotlib.

🗺️ Geospatial Analysis

• lab-jupyter-launch-site-location-v2.ipynb: Visualizes launch sites using Folium.

  • Marker clustering
  • Distance calculations
  • Success/failure rates by site

🤖 Machine Learning

• SpaceX-Machine-Learning-Prediction-Part-5-v1.ipynb: Predictive modeling using:

  • Logistic Regression
  • SVM
  • KNN
  • Decision Trees
  • Hyperparameter tuning & evaluation

📈 Interactive Dashboard

• spacex_dash_app.py: Dash app to explore launch data interactively.

---

🔧 Tech Stack

---

🚀 How to Use This Project

1. Clone the repository

   git clone https://github.com/your-username/spacex-falcon9-analysis.git
   cd spacex-falcon9-analysis

2. Install dependencies

   pip install -r requirements.txt

3. Run the notebooks in the order provided to follow the full pipeline.

4. Start the Dash application

   python spacex_dash_app.py

---

📌 Key Findings

• Launch success is highly correlated with launch site, payload mass, and orbit type.
• Machine learning models achieved good accuracy predicting first-stage landing success.
• Geospatial analysis revealed visual clusters of success/failure zones.

---

📈 Future Improvements

• Add more recent launch data via the SpaceX API.
• Engineer more complex features (weather, booster version, etc.).
• Explore advanced ML models like Gradient Boosting or Neural Nets.
• Expand dashboard features with filters, timelines, and real-time updates.

---

🔗 Live Demo

🌐 View the deployed dashboard on Render

---

🙌 Credits

Developed as part of a Data Science course using IBM-provided datasets and labs.