This project focuses on predicting the success of SpaceX Falcon 9 first stage landings using data analysis and machine learning techniques. By analyzing historical data related to Falcon 9 launches and their outcomes, the project aims to develop models that can accurately forecast whether the first stage of the rocket will successfully land.
- Python
- Jupyter Notebook
- GitHub
- Pandas
- NumPy
- Scikit-learn
- Matplotlib
- Seaborn
- Plotly
- Dash
- Folium
- Exploratory Data Analysis (EDA) to understand the dataset and identify patterns.
- Interactive visual analytics using Plotly Dash and Folium to explore launch sites and proximity features.
- Predictive modeling using machine learning algorithms such as Logistic Regression, Support Vector Machines, Decision Trees, and K Nearest Neighbors.
- Deployment of a predictive dashboard using Plotly Dash for real-time analysis.
- Data wrangling
- Exploratory data analysis
- Machine learning model development
- Interactive visualization
- Deployment of web applications
- Achieved an accuracy of over 83% in predicting first stage landing success using various machine learning algorithms.
- Developed an interactive dashboard using Plotly Dash to visualize launch data and prediction results.
- Explored spatial relationships using Folium to analyze launch site proximity features.
- This repository provides valuable insights into the success factors of SpaceX Falcon 9 first stage landings.
- It demonstrates the application of data analysis and machine learning in predicting complex real-world outcomes.
- Users can explore the code, datasets, and visualizations to gain a deeper understanding of rocket launch dynamics and predictive modeling techniques.
