hd77alu/pca-ml

This project implements Principal Component Analysis (PCA) using NumPy to analyze African CO2 emissions data. The implementation includes standardization, eigendecomposition, and dimension reduction. ## Project Overview This project implements **Principal Component Analysis (PCA)** using NumPy to analyze African CO2 emissions data. The implementation includes standardization, eigendecomposition, and dimension reduction. - Open the Notebook in Google Colab ## Project Structure ``` pca-ml/ ├── README.md ├── africa-co2-emissions.csv ├── PCA_Formative_2[Peer_Pair_Number].ipynb ``` ## Dataset Information **Dataset:** `africa-co2-emissions.csv` ### Dataset Characteristics: - **Rows:** 1,134 - **Columns:** 20 total (3 non-numeric, 17 numeric) - **Missing Values:** 1,013 (handled via mean imputation) - **Source:** African countries CO2 emissions data ## Installation & Setup ### Step 1: Clone or Download the Repository ```bash git clone github.com cd pca-ml ``` ### Step 2: Install Required Libraries ```bash # Install Jupyter Notebook (if not already installed) pip install jupyter # Install required Python libraries pip install numpy pandas matplotlib ``` ## How to Use the Notebook ### Method 1: Using Jupyter Notebook (Local) ```bash # Navigate to project directory cd pca-ml # Launch Jupyter Notebook jupyter notebook # Open the file: PCA_Formative_2.ipynb ``` ### Method 2: Using Google Colab 1. Click the "Open in Colab" badge at the top of the notebook 2. Upload `africa-co2-emissions.csv` to your files 3. Run all cells ### Method 3: Using VS Code 1. Open VS Code 2. Install the Jupyter extension (if not already installed) 3. Open the folder `pca-ml` 4. Click on `PCA_Formative_2.ipynb` 5. Select Run all 6. Select Python kernel when prompted ## PCA Implementation Steps The notebook implements PCA in 7 steps: ### **Step 1: Load and Standardize Data** - Loads the African CO2 emissions dataset - Handles missing values via mean imputation - Manual standardization using Z-score formula: `Z = (X - μ) / σ` - **No sklearn used** - Pure NumPy implementation ### **Step 2: Calculate Covariance Matrix** - Computes 17×17 covariance matrix - …