The Undeniable Asset: A Data Science Mastery Journey

This repository documents my intensive, structured journey to become a Python and Data Science expert.
The curriculum is designed to be comprehensive and rigorous, transforming me from a proficient data professional into an undeniable asset capable of solving complex, real-world problems and leaving interviewers impressed.

This project is a living portfolio, showcasing my skills in Python, data manipulation, statistical analysis, machine learning, and advanced data topics.
Each module is a step-by-step progression, complete with theoretical notes, practical examples, and hands-on mini-projects.

---

🚀 Curriculum & Project Structure

This repository is organized into distinct phases, each building upon the last.

✅ Phase 0: Setting the Stage for Excellence

• Module 0.1: Established a professional development environment using Git, GitHub, Python Virtual Environments (venv), and Jupyter Notebooks.
  Focused on best practices for version control and project reproducibility from day one.

✅ Phase 1: Python Fundamentals – The Bedrock

• Module 1.1: Mastered core Python concepts – data types, data structures (lists, tuples, dicts, sets), control flow, and functions.
• Module 1.2: Deep dive into advanced Python concepts – OOP, robust Error & Exception Handling, File I/O (JSON, Pickle), and Decorators.

✅ Phase 2: Data Manipulation & Analysis – The Workhorse

• Module 2.1: NumPy – Built a strong foundation in numerical computing: ndarray creation, indexing, slicing, broadcasting, vectorized operations.
• Module 2.2: Pandas – Covered Series & DataFrame creation, advanced selection (.loc, .iloc), cleaning, transformation, grouping (.groupby), merging (.merge), and time series analysis.

✅ Phase 3: Data Visualization & EDA – Unveiling Insights

• Module 3.1: Matplotlib – Learned Object-Oriented API, created publication-quality plots, subplots, 3D plots, and saved figures.
• Module 3.2: Seaborn – Leveraged high-level visualizations for statistical insights.
• Mini-Project: Performed a comprehensive EDA on Titanic dataset, using visualization to uncover patterns and tell a story with data.

✅ Phase 4: Statistical Foundations & Hypothesis Testing – The Rigor

• Module 4.1: Covered descriptive statistics, probability, distributions, Central Limit Theorem, and hypothesis testing framework.
• Mini-Project: Conducted a full A/B Test Analysis to determine statistical significance of a new feature.

✅ Phase 5: Machine Learning – The Predictive Power

• Modules 5.1 – 5.4: Supervised Learning Workflow

  • Regression: Linear, Ridge, Lasso, Trees, Random Forest, XGBoost, CatBoost
  • Classification: Logistic Regression, KNN, SVM, Naive Bayes, Ensembles
  • Evaluation & Tuning: Confusion Matrix, Precision, Recall, F1, ROC/AUC, SMOTE, class_weight, RandomizedSearchCV

  Mini-Project: Developed a Telco Customer Churn model, applying feature engineering, imbalance handling, and hyperparameter tuning.

• Module 5.5: Unsupervised Learning

  • Clustering: K-Means, Hierarchical, DBSCAN
  • Dimensionality Reduction: PCA, t-SNE
  • Mini-Project: Customer Segmentation on retail dataset → actionable "personas" for business stakeholders.

⏳ Phase 6: Advanced Topics & Real-World Application (In Progress)

• Modules 6.1 – 6.3:

  • Feature Engineering & Selection
  • Model Explainability (XAI) – SHAP, LIME
  • Large Datasets – Pandas optimization, Dask, Parquet

• Modules 6.4 – 6.5 (Upcoming): Introduction to NLP, Deep Learning, APIs, Web Scraping

🎯 Phase 7: Capstone & Interview Annihilation (Upcoming)

• End-to-end capstone projects
• Intensive preparation for data science interviews

---

🛠️ Tech Stack & Libraries

• Core Language: Python 3
• Data Science Stack: NumPy, Pandas, Matplotlib, Seaborn
• Machine Learning: Scikit-learn, XGBoost, LightGBM, CatBoost, imbalanced-learn
• Advanced & Specialized: SciPy, SHAP, LIME, Dask, category_encoders
• Tools: Git, GitHub, Jupyter Notebook/Lab, Virtual Environments (venv)

---

🚀 Getting Started

To explore this repository and run the notebooks:

Clone the repository:

git clone https://github.com/Riju-po/python_ds_mastery_journey.git
cd python_ds_mastery_journey

Create and activate a virtual environment:

# On Windows
python -m venv venv_ds
venv_ds\Scripts\activate

# On macOS/Linux
python3 -m venv venv_ds
source venv_ds/bin/activate

Install dependencies

pip install -r requirements.txt

Launch Jupyter Lab

jupyter lab

✨ Project Highlights

• Titanic EDA (Module 3.2) → Data storytelling through visualization
• Telco Churn Model (Module 5.4) → End-to-end ML workflow with imbalance handling & tuning
• Customer Segmentation (Module 5.5) → From raw clusters to actionable personas