https://github.com/tolumie/ibm-applied-data-science-capstone-project
Predicting SpaceX Falcon 9 first-stage landings using data science, machine learning, and interactive visualizations.
https://github.com/tolumie/ibm-applied-data-science-capstone-project
classification data-science data-visualization-dashboard folium geospatial-analysis machine-learning plotly-dash predictive-modeling python spacex sql webscraping
Last synced: 2 months ago
JSON representation
Predicting SpaceX Falcon 9 first-stage landings using data science, machine learning, and interactive visualizations.
- Host: GitHub
- URL: https://github.com/tolumie/ibm-applied-data-science-capstone-project
- Owner: Tolumie
- Created: 2024-06-19T11:39:50.000Z (11 months ago)
- Default Branch: main
- Last Pushed: 2025-03-06T13:07:50.000Z (3 months ago)
- Last Synced: 2025-03-06T14:23:01.225Z (3 months ago)
- Topics: classification, data-science, data-visualization-dashboard, folium, geospatial-analysis, machine-learning, plotly-dash, predictive-modeling, python, spacex, sql, webscraping
- Language: Jupyter Notebook
- Homepage:
- Size: 4.03 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
### **π IBM Applied Data Science Capstone Project**
This repository contains the **IBM Applied Data Science Capstone Project**, which applies **data science methodologies** to analyze **SpaceX launch data** and predict the success of **Falcon 9 first-stage landings**.
---
## **π Project Overview**
### **πΉ Context**
SpaceX has revolutionized space travel with reusable rockets, significantly reducing launch costs compared to competitors. The **Falcon 9 rocket launch** costs **$62 million**, while traditional providers charge over **$165 million**. Much of this cost reduction comes from **reusing the first stage of the rocket**.The objective of this project is to analyze **historical SpaceX launch data** to answer the following questions:
- **What factors affect the success of the first-stage landing?**
- **Has the success rate of landings improved over time?**
- **Which machine learning algorithm best predicts a successful landing?**By predicting whether the **first stage of a Falcon 9 rocket will successfully land**, we can estimate launch costs and help **competing companies bid against SpaceX** more accurately.
---
## **π Methodology**
This project follows a structured data science pipeline, including:
1οΈβ£ **Data Collection:** Web scraping and API requests to obtain SpaceX launch data.
2οΈβ£ **Data Wrangling & Cleaning:** Handling missing values, formatting data, and preparing for analysis.
3οΈβ£ **Exploratory Data Analysis (EDA):**
- Data visualization using **Matplotlib, Seaborn, and Plotly**.
- SQL-based data exploration.
- Interactive map visualization with **Folium**.
4οΈβ£ **Feature Engineering:** Creating new features to enhance machine learning models.
5οΈβ£ **Predictive Analysis (Classification):**
- Comparing multiple ML models to predict landing success.
- Evaluating model performance using metrics like accuracy, precision, recall, and F1-score.
6οΈβ£ **Building an Interactive Dashboard:** Using **Plotly Dash** for dynamic data visualizations.---
## **π Results & Insights**
### **πΉ Key Findings**
- Several factors influence the likelihood of a **successful first-stage landing**, including **launch site, payload mass, and booster type**.
- The **success rate of landings has improved over the years**, indicating advancements in SpaceX's technology.
- Among tested models, the best-performing **machine learning algorithm** effectively predicts **first-stage landing success**.### **πΉ Interactive Analytics**
- **Charts & Graphs** π: Data-driven insights visualized using Python.
- **Interactive Maps** πΊοΈ: SpaceX launch locations displayed with **Folium**.
- **Dashboards** π: Real-time analytics built with **Plotly Dash**.---
## **π Technology Stack**
| Tool/Library | Purpose |
|----------------------|---------|
| **Python** | Core Programming Language |
| **Pandas** | Data Handling & Manipulation |
| **Matplotlib & Seaborn** | Data Visualization |
| **Plotly Dash** | Interactive Dashboard Development |
| **Folium** | Geospatial Mapping |
| **Scikit-learn** | Machine Learning |
| **SQL** | Data Querying & Analysis |
| **BeautifulSoup & Requests** | Web Scraping |
| **IBM Watson Studio** | Cloud-based Data Science Environment |---
## **π How to Use**
### **πΉ Clone the Repository:**
```bash
git clone https://github.com/Tolumie/IBM-Applied-Data-Science-Capstone.git
```### **πΉ Navigate into the Folder:**
```bash
cd IBM-Applied-Data-Science-Capstone
```### **πΉ Install Required Dependencies:**
```bash
pip install -r requirements.txt
```### **πΉ Run the Jupyter Notebook:**
```bash
jupyter notebook
```---
## **π Contributions & Issues**
- Feel free to **fork** the repository and submit **pull requests**.
- If you encounter any issues, report them via [GitHub Issues](https://github.com/Tolumie/IBM-Applied-Data-Science-Capstone/issues).---
## **π§ Contact**
For any inquiries, reach out via **GitHub**. π---
πΉ **Happy Coding! ππ**
---
This **README** is structured professionally, ensuring clarity and completeness. Let me know if you need any refinements! π