This project demonstrates a complete Data Cleaning and Data Preprocessing workflow that prepares raw data for Machine Learning models. It covers the essential steps of transforming messy data into a structured, analysis-ready dataset through Exploratory Data Analysis (EDA), feature engineering, feature scaling, and visualization.
The objective is to build a strong data foundation before model training, following best practices commonly used in real-world Machine Learning projects.
- 📊 Exploratory Data Analysis (EDA)
- 🧹 Data Cleaning
- 🔍 Handling Missing Values
- 🏷️ Encoding Categorical Features
- ⚙️ Feature Engineering & Feature Extraction
- 📈 Feature Scaling
- 📉 Data Visualization
- ✅ Final Cleaned Dataset Ready for Machine Learning
Data_Preprocessing_Project/
│── Data_Preprocessing.ipynb
│── dataset.csv
│── cleaned_dataset.csv
│── requirements.txt
│── README.md
└── heatmap.png
- Python
- NumPy
- Pandas
- Matplotlib
- Seaborn
- Scikit-learn
- Jupyter Notebook
- Explored dataset characteristics and distributions
- Identified and handled missing values
- Removed duplicate records
- Encoded categorical variables
- Created meaningful features
- Scaled numerical features
- Generated multiple visualizations to understand relationships and patterns
- Prepared the dataset for Machine Learning model development
Screenshots of the analysis and visualizations are available in the images/ folder.
Through this project, I strengthened my understanding of:
- Data preprocessing pipeline
- Feature engineering techniques
- Exploratory Data Analysis (EDA)
- Data visualization
- Preparing high-quality data for Machine Learning
- Train and evaluate Machine Learning models on the processed dataset
- Compare different preprocessing techniques
- Build an end-to-end ML pipeline
- Perform hyperparameter tuning and model evaluation
Farheen Laraib
Software Engineering Student | Aspiring Machine Learning Engineer