The commercial space age has opened up exciting opportunities for new players in the industry. Space Y, a new rocket company founded by Billionaire industrialist Allon Musk, aims to compete with SpaceX in providing affordable and reliable space travel services. In this capstone project, as a data scientist for Space Y, your primary task is to determine the cost of each launch and predict whether SpaceX will successfully reuse the first stage of their Falcon 9 rockets.
Launch Cost Determination: Utilize gathered information about SpaceX and create dashboards to analyze and determine the cost of Falcon 9 rocket launches. This will involve considering various factors such as mission parameters, payload, orbit, and customer requirements.
First Stage Reusability Prediction: Train a machine learning model using public information to predict whether SpaceX will successfully reuse the first stage of their Falcon 9 rockets for a given launch. This prediction will contribute to estimating the overall cost of a launch.
Gather information from public sources, including SpaceX's official website, space agencies, and reputable news outlets. Relevant data includes launch details, mission parameters, payload specifications, and historical information on first stage reusability.
Collect data on SpaceX launches, including mission details, payload specifications, and launch costs. Identify and compile information on the success or failure of first stage recovery for each launch. Data Cleaning and Preprocessing:
Clean and preprocess the gathered data to ensure its quality and suitability for analysis. Handle missing or inconsistent data points.
Explore the data to identify patterns, trends, and correlations. Visualize key metrics to gain insights into the factors influencing launch costs and first stage reusability.
Develop dashboards using visualization tools (e.g., Tableau, Power BI) to present key findings and trends to the Space Y team. Include interactive elements for dynamic exploration of data.
Design and train a machine learning model using historical data to predict the likelihood of successful first stage reusability. Evaluate and fine-tune the model for accuracy.
Incorporate the machine learning model's predictions into the dashboards to provide real-time insights into launch cost and first stage reusability.
This repository contains a powerpoint presentation which give an overview about the project.
data/: contains raw and processed data files.
notebooks/: Jupyter notebooks for data analysis, machine learning model development, and exploratory data analysis.
dashboards/: Files for creating interactive dashboards using visualization tools.
scripts/: Python scripts for data preprocessing, model training, and other functionalities.
README.md: Project overview, instructions, and documentation.
Clone the repository to your local machine. Follow the steps in the Jupyter notebooks for data analysis, model training, and dashboard creation. Refer to the README file for detailed instructions and project documentation.
Teja Niduram
IBM Skill Network Team.
This project is licensed under the IBM License.
Feel free to reach out for collaboration or further information. ๐