SpaceX Falcon 9 Launch-and-Landing Project

A collection of exploratory-data-analysis, data-engineering and machine-learning notebooks that walk from raw SpaceX REST-API calls all the way to an interactive Plotly-Dash dashboard. The goal is to predict whether the Falcon 9 first stage lands successfully and to visualise key factors such as payload, orbit and launch-site location.

---

Repository structure

File	Purpose
edadataviz.ipynb	End-to-end EDA and feature-engineering: statistical plots (seaborn/matplotlib), one-hot encoding, scaling, and CSV export (dataset_part_3.csv).
jupyter-labs-eda-sql-coursera_sqllite.ipynb	Loads Spacex.csv into SQLite, then answers 10 analytical SQL questions (landing outcomes, payload sums, etc.) using ipython-sql.
jupyter-labs-spacex-data-collection-api.ipynb	Queries the SpaceX REST API, dereferences nested IDs (rockets, payloads, cores, launchpads), cleans nulls and writes dataset_part_1.csv.
jupyter-labs-webscraping.ipynb	Scrapes the Falcon 9/Heavy launch table from a pinned 9-Jun-2021 Wikipedia snapshot with BeautifulSoup; saves fallback spacex_web_scraped.csv.
lab_jupyter_launch_site_location.ipynb	Interactive Folium map: marks each launch site, clusters individual launches by success (green) / failure (red), and computes distances to coast, rail, highways, etc.
labs-jupyter-spacex-Data wrangling.ipynb	Adds a binary Class column (1 = successful landing) and exploratory counts by orbit, outcome, launch-site; outputs dataset_part_2.csv.
ML0101EN_SkillUp_FinalAssignment.ipynb	Weather-dataset classification (unrelated to SpaceX but required by course): compares Linear Regression, KNN, Decision Tree, Logistic Regression, SVM.
SpaceX_Machine Learning Prediction_Part_5.ipynb	Hyper-parameter tuning (GridSearchCV) for Logistic Regression, SVM, Decision Tree and KNN on the engineered SpaceX dataset; confusion matrices + accuracy table.
spacex_dash_app.py	Stand-alone Plotly-Dash web app: dropdown for launch-site, payload slider, success pie chart and scatter correlation; run with python spacex_dash_app.py.
README.md	You are reading it. A roadmap for reproducing every notebook and running the dashboard.

---

Quick-start

1. Clone & activate venv

   git clone https://github.com/your-user/ibm-data-science.git
   cd ibm-data-science
   python3 -m venv venv && source venv/bin/activate

2. Install

   pip install -r requirements.txt

3. Launch Jupyter

   jupyter lab

4. Run the Dash app

   python spacex_dash_app.py
   # open http://127.0.0.1:8050 in your browser

---

Data flow

1. API Acquisition → jupyter-labs-spacex-data-collection-api.ipynb → dataset_part_1.csv

2. Data Wrangling & Label Engineering → labs-jupyter-spacex-Data wrangling.ipynb → dataset_part_2.csv

3. Feature Engineering & EDA → edadataviz.ipynb → dataset_part_3.csv

4. ML Modelling → SpaceX_Machine Learning Prediction_Part_5.ipynb

5. Dashboard → spacex_dash_app.py

---

Dependencies (excerpt)

• pandas ≥1.3
• numpy ≥1.21
• matplotlib ≥3.5, seaborn
• scikit-learn ≥0.24
• requests, beautifulsoup4
• folium
• dash ≥2.0, plotly
• ipython-sql, sqlalchemy, sqlite3

Install them automatically through the provided requirements.txt.

---

License

MIT © 2023 arenkis