How elbeteltaye/financial-news-and-stock-price-analysis works
Project type and purpose
• This is a data-analysis pipeline project (not a traditional full-stack app). It focuses on exploring the correlation between financial news sentiment and stock price movements.
• Key indicators from README:
• Three tasks: news descriptive analysis, stock technical analysis, sentiment-price correlation
• Uses Python, Pandas, Matplotlib/Seaborn, TA-Lib, VADER, LDA, yfinance
• Structure centered on Jupyter notebooks, auxiliary scripts, minimal Python modules, and unit tests
File structure
• Top-level directories:
• notebooks/ – contains Task1, Task2, Task3 analysis notebooks
• scripts/ – utility or ETL scripts to support data ingestion or processing
• src/ – placeholder for reusable Python modules (currently empty)
• tests/ – unit test stubs (run via GitHub Actions)
• .github/workflows/unittests.yml – CI workflow for running tests
• requirements.txt – dependency spec
• Patterns:
• Pipeline style: data flows through discrete steps (notebooks or scripts)
• CI integration for code quality
• Virtual-env & VSCode settings for development consistency
README for additional insights
• Architecture is implicitly a linear data pipeline:
• Data sources: historical news CSV, stock CSV or yfinance API
• Processing stages: cleaning, sentiment scoring, topic modeling, technical indicator calculation
• Analysis stage: correlation between sentiment time series and stock returns
• Visualization: charts in notebooks