📊 Data Science & Analysis Portfolio

A comprehensive collection of end-to-end data analysis projects, showcasing expertise in Data Gathering, Advanced Cleaning Pipelines, Exploratory Data Analysis (EDA), and Feature Engineering.

---

📂 Featured Projects

1️⃣ Smartphone Data Cleaning Pipeline

Tools Used: pandas, numpy, regex

• Engineered a robust data wrangling pipeline to transform raw, unstructured smartphone specifications into a clean, analytical dataset.
• Handled missing values, standardized formats, extracted complex nested string patterns, and managed outlier detection to prepare data for machine learning modeling.

2️⃣ Ames Housing: Advanced EDA & Feature Engineering

Tools Used: pandas, matplotlib, seaborn, scikit-learn

• Conducted an exhaustive Exploratory Data Analysis on the Ames Housing dataset to identify key predictors of house prices.
• Implemented rigorous feature engineering, correlation analysis, and data scaling (Standardization/Normalization) strategies.
• Analyzed skewness and performed log transformations on the target variable.

3️⃣ Titanic Survival Analysis

Tools Used: pandas, seaborn

• Extracted actionable insights from the iconic Titanic dataset through deep univariate and bivariate analysis.
• Evaluated survival rates across socioeconomic classes, genders, and age groups using statistical visualizations.

---

📚 Data Science Handbook

A curated collection of theoretical implementations and best practices, combined into unified modules. Located in /4_Data_Science_Handbook.

Module	Description	Key Concepts
01_Statistical_Data_Analysis	Univariate and Bivariate analysis	Categorical/Numerical distributions, Correlation matrices, Probability distributions
02_Data_Wrangling_Techniques	Data assessment and cleaning	Missing data imputation, Iterative assessment (Define-Code-Test)
03_Data_Visualization_Masterclass	Advanced visualization strategies	Matplotlib Object-Oriented API, Seaborn Relational/Matrix/Joint plots
04_Data_Acquisition_and_Scraping	Gathering raw data	Pandas I/O (CSV, JSON, SQL, Excel), REST APIs, BeautifulSoup web scraping

---

🚀 Setup & Execution

1. Clone the repository:

git clone https://github.com/Ashwin14101/Data-Analysis-Portfolio.git
cd Data-Analysis-Portfolio

2. Install dependencies:

pip install pandas numpy matplotlib seaborn scikit-learn jupyterlab

3. Launch the environment:

jupyter lab

---

🤝 Let's Connect

Looking for a passionate Data Analyst/Scientist? Feel free to reach out via GitHub or LinkedIn!

---

MIT License © Ashwin14101