This repository contains a collection of data analysis and machine learning projects developed as part of academic coursework and capstone experiences. The focus ranges from real-world industry problem-solving to predictive modeling using structured datasets.
An in-depth capstone project in collaboration with Bright Motor Company, addressing business challenges using data-driven strategies and performance metrics.
- Techniques: Exploratory Data Analysis (EDA), segmentation, business insights
- Tools: Pandas, Seaborn, Excel, Jupyter Notebook
Built and evaluated multiple regression models to predict the resale prices of used cars based on various features such as brand, mileage, and manufacturing year.
- Techniques: Linear Regression, KNN, Decision Trees, Model Tuning
- Tools: Scikit-learn, Pandas, Matplotlib, XGBoost
Predicted individual labor earnings for the year 1978 using demographic and socio-economic data from earlier years. Analyzed relationships between variables such as education, region, and work experience.
- Techniques: Linear Regression, Feature Selection, Model Evaluation
- Tools: Pandas, Seaborn, Statsmodels, Scikit-learn
Performed exploratory data analysis on restaurant data from Zomato to uncover insights on customer preferences, cost dynamics, and location-based trends.
- Techniques: Data Cleaning, Clustering, Visualization
- Tools: Pandas, Seaborn, Matplotlib, Plotly
A summary notebook covering core concepts in data science and machine learning, with hands-on examples of model development and hyperparameter tuning. Includes implementation of Decision Tree classifiers and cross-validation.
- Contents: EDA workflows, model evaluation metrics, tuning methods
- Tools: Jupyter Notebook, Scikit-learn, Markdown
├── notebooks/
│ ├── capstone\_bright\_motor\_company.ipynb
│ ├── used\_car\_price\_prediction.ipynb
│ ├── labour\_earning\_prediction.ipynb
│ ├── zomato\_analysis.ipynb
│ └── viva\_credits.ipynb
├── datasets/ # (ignored in .gitignore)
├── README.md
├── requirements.txt
├── .gitignore
├── LICENSE
⚠️ Note: Datasets are excluded from the repository due to size and privacy constraints. Instructions for accessing required datasets are provided within each notebook.
To install the required Python packages:
pip install -r requirements.txtThis project is licensed under a Custom "All Rights Reserved" License.
Use, reproduction, or distribution of any part of this work is strictly prohibited without the author's explicit written permission.
See the LICENSE file for full details.
For usage inquiries, contact: [mowlick2006@gmail.com]