pcatry

---

This project is an interactive Streamlit dashboard for exploring Principal Component Analysis (PCA) on financial return series.
You can either generate synthetic returns or upload your own CSV of asset returns and inspect:

• Scree plot and variance explained
• PCA biplot (scores and loadings)
• Loading heatmap
• Top contributors to the first principal component
• Equal-weight portfolio factor exposure

Requirements

• Python 3.9+ (3.10 or 3.11 recommended)
• The following Python packages:
  • streamlit
  • pandas
  • numpy
  • scikit-learn
  • plotly

You can install them with:

pip install streamlit pandas numpy scikit-learn plotly

How to Run the Dashboard

1. Open a terminal (PowerShell, Command Prompt, or any shell).

2. Change directory into the folder that contains pca.py:

   cd "C:\Users\sharm\Downloads\New folder"
   

3. Run the Streamlit app:

   streamlit run pca.py
   

4. After a few seconds Streamlit will print a local URL, for example:

   Local URL: http://localhost:8501
   

5. Open that URL in your browser to use the dashboard.

Notes

• If the default port (8501) is already in use, you can choose another one, e.g.:

  streamlit run pca.py --server.port 8505
  

• For reproducible synthetic data, you can adjust the random seed in the sidebar.