This repository contains my solutions to several Big Data Techniques labs from Gheorghe Asachi Technical University of Iași, implemented mostly from scratch in Python.
-
Lab 8 – Principal Component Analysis (PCA)
Manual PCA on small datasets: covariance matrix, eigenvalues/eigenvectors, principal components and projection to lower dimensions. -
Lab 9 – K-means & PCA
K-means clustering for multidimensional data, silhouette score evaluation, and comparison of clustering before vs. after PCA. -
Lab 10 – Classification
Basic classification methods on provided datasets, with simple preprocessing and performance metrics. -
Lab 11 – Statistical Data Analysis
Empirical vs. parametric distributions (uniform, normal), Maximum Likelihood Estimation, (R^2) evaluation, and Monte Carlo estimation of ( \pi ). -
Lab 12 – Data Compression
Lossless compression algorithms: Run-Length Encoding (RLE), Huffman coding, and Lempel–Ziv (LZ) with compression ratio calculations. -
Lab 13 – Streaming Data Processing
Simple streaming examples using sliding/tumbling windows and sampling: running averages, bit‑to‑integer conversion, word counting, and basic convolution filters.
- Python 3.x
- Standard libraries (e.g.
math,random,collections) - Optionally
numpy/matplotlibfor numerical work and plots