This repository documents my hands-on labs from the Coursera Data Science Capstone, focused on classifying SpaceX Falcon 9 launch outcomes. Each folder represents a modular lab session, covering the full data science pipeline — from data collection to dashboard deployment.
The goal of this project is to predict the success of SpaceX Falcon 9 launches using historical data. I explored multiple stages of the workflow including API calls, web scraping, SQL-based EDA, geospatial mapping, and supervised machine learning.
| Lab | Description |
|---|---|
| 1. Data Collection | Collected Falcon 9 launch data using REST API calls, extracting relevant features for analysis |
| 2. Web Scraping | Parsed HTML tables to extract structured launch data using BeautifulSoup |
| 3. Data Wrangling | Cleaned and transformed the dataset, handled missing values, engineered features, and labeled outcomes |
| 4. EDA (SQL) | Queried launch data using SQL syntax in Jupyter to validate insights |
| 5. EDA (Visualization) | Explored relationships using statistical plots and prepared features for modeling |
| 6. Location Analysis | Mapped launch sites using Folium and calculated distances to key geographic features |
| 7. Dashboarding | Built an interactive Dash app with dropdowns, sliders, and dynamic charts |
| 8. Model Evaluation | Trained and compared Logistic Regression, SVM, Decision Tree, and KNN classifiers on launch data |
- REST API integration
- Web scraping with BeautifulSoup
- Data wrangling and feature engineering
- SQL-based analysis in Jupyter
- Geospatial visualization with Folium
- Interactive dashboarding with Dash
- Supervised learning with scikit-learn
1_Data_Collection/2_Data_Webscraping/3_Data_Wrangling/4_EDA_SQL/5_EDA_Visualization/6_Location_Analysis_with_Folium/7_Python_Dashboard/8_Model_Prediction/images/LICENSEREADME.mdrequirements.txt
Each folder contains a dedicated README explaining the lab’s goals, methods, and outcomes.
This project is licensed under the MIT License.
I’m Mukesh, a BSc Data Science student passionate about blending machine learning with geospatial insights. This project reflects my journey through Coursera’s Data Science Capstone and my commitment to building reproducible, real-world solutions.