🫁 Lung Cancer Prediction with Machine Learning

A machine learning project predicting lung cancer severity based on patient lifestyle and health factors. The project includes data cleaning, visualization, and classification using Decision Tree, Random Forest, and Logistic Regression.

---

📁 Files

• lung_cancer_dataset.csv: Source dataset from Kaggle
• lung_cancer_prediction.ipynb: Main Jupyter notebook with full analysis

---

Dataset Source

Kaggle: Cancer Patients and Air Pollution

---

🔍 Techniques Used

• Data cleaning and preprocessing with pandas
• Data visualization using matplotlib and seaborn
• Feature engineering and correlation analysis
• Classification models:
  • Decision Tree
  • Random Forest
  • Logistic Regression

---

📊 Project Highlights

• Explores the relationship between air pollution, smoking, and lung disease severity
• Visualizes gender distribution, disease severity levels, and risk factors
• Compares model performance through accuracy, confusion matrices, and classification reports

---

📈 Results

• Achieved accuracy up to 87% using the Decision Tree model
• Decision Tree outperformed Random Forest and Logistic Regression overall
• Identified strong correlations between chronic lung disease and factors like smoking, air pollution, and occupational hazards

🧰 Tech Stack

• Python
• Pandas, NumPy
• Matplotlib, Seaborn
• Scikit-learn
• Jupyter Notebook