# 📊 Learning Path: B.Sc. Data Science & Analytics

> **Program:** B.Sc. Data Science & Analytics  
> **Affiliation:** Veer Narmad South Gujarat University (VNSGU)  
> **Institution:** Sutex Bank College of Computer Applications & Science (Amroli College)

---

## 1. Curriculum Overview
The B.Sc. Data Science & Analytics program prepares students to extract actionable insights from structured and unstructured data, architect distributed pipelines, train machine learning algorithms, and explore modern Artificial Intelligence.

---

## 2. Learning Journey & Available Repositories

### Step 1: Exploratory Data Analysis & Python Foundations
* **Python for Data Analytics:**
  * Repository: [`data-analytics-using-python`](https://github.com/sbccas/data-analytics-using-python)
  * Focus: Data wrangling with Pandas & NumPy, data cleaning, automated EDA, regression, and supervised learning fundamentals.
  * Hands-on Work: Visualizing distributions, feature correlation matrices, and model evaluation metrics.

---

### Step 2: Distributed Systems & Big Data Handling (Sem 5)
* **Big Data Handling & Machine Learning Applications (DS-505):**
  * Repository: [`Big-Data-Handling-and-Management-for-Machine-Learning-Applications`](https://github.com/sbccas/Big-Data-Handling-and-Management-for-Machine-Learning-Applications)
  * Focus: Subject **DS-505** at SBCCAS (VNSGU).
  * Key Technologies:
    * **PySpark:** Distributed DataFrame operations, cluster computing, Resilient Distributed Datasets (RDDs).
    * **Scikit-learn Pipelines:** Cross-validation, hyperparameter tuning, classification, and regression.
    * **Hugging Face Transformers & LLMs:** Pretrained transformer pipelines, tokenization, sentiment extraction, and text generation.
  * Environment: Jupyter Notebooks runnable directly via Google Colab.

---

### Step 3: AI Augmentation & Applied Experimentation
* **AI-Assisted Workflows:**
  * Repository: [`amroli-ai-assist`](https://github.com/sbccas/amroli-ai-assist)
  * Focus: Practical integration of AI tools into data preprocessing, automated testing, and hypothesis generation.

---

## 3. Practical Competencies Acquired
* Writing production-grade data pipelines using Python and PySpark.
* Formulating predictive statistical models and interpreting evaluation curves (ROC-AUC, RMSE, Confusion Matrix).
* Integrating transformer models from Hugging Face into data engineering workflows.