This project focuses on analyzing SpaceX launch data to identify key factors influencing rocket launch success and first-stage reusability. By leveraging data science techniques, the project delivers actionable insights and predictive models to support decision-making.
- Web Scraping: Extracted SpaceX launch data from online sources.
- Data Cleaning: Processed raw data to ensure accuracy and consistency.
- Exploratory Data Analysis (EDA): Uncovered patterns and trends in launch success and reusability.
- Machine Learning Models: Developed predictive models with 85% accuracy to forecast outcomes.
- Visualization: Used Plotly for interactive visualizations to present insights.
- Languages & Libraries: Python, NumPy, Pandas, Scikit-Learn, Plotly.
- Data Analysis & Visualization: Exploratory Data Analysis (EDA), interactive dashboards.
- Data Extraction: Web Scraping using Python.
- Database: SQL for structured data manipulation.
-
Data Collection
- Web-scraped SpaceX launch data from online resources.
- Collected relevant details like launch dates, success rates, and reusability metrics.
-
Data Cleaning & Preparation
- Removed inconsistencies, handled missing values, and formatted the data for analysis.
-
Exploratory Data Analysis (EDA)
- Investigated relationships between features and launch success/reusability.
-
Machine Learning
- Built predictive models (e.g., Logistic Regression, Random Forest) to analyze:
- Launch success probabilities.
- First-stage reusability likelihood.
- Achieved 85% model accuracy.
- Built predictive models (e.g., Logistic Regression, Random Forest) to analyze:
-
Visualization & Insights
- Created interactive visualizations with Plotly to present findings.
- Identified significant factors affecting launch success and first-stage reusability.
- Provided actionable insights to optimize rocket launch decisions.
- Achieved a predictive accuracy of 85% in forecasting launch outcomes.