Titanic Survival Prediction 🚢

Project Overview

The Titanic Survival Prediction project uses Machine Learning techniques to predict whether a passenger survived the Titanic disaster based on demographic and travel-related information.

This project demonstrates the complete Machine Learning workflow, including data preprocessing, exploratory data analysis (EDA), feature engineering, model training, and performance evaluation.

---

Dataset

The dataset contains information about Titanic passengers, such as:

• Passenger Class (Pclass)
• Gender (Sex)
• Age
• Number of Siblings/Spouses (SibSp)
• Number of Parents/Children (Parch)
• Ticket Fare
• Embarked Port

Target Variable:

• Survived
  • 0 = Did Not Survive
  • 1 = Survived

---

Technologies Used

• Python
• Pandas
• NumPy
• Matplotlib
• Seaborn
• Scikit-Learn
• Google Colab

---

Project Workflow

1. Data Collection

• Loaded Titanic dataset from CSV files.

2. Data Preprocessing

• Handled missing values.
• Removed unnecessary columns.
• Encoded categorical features.

3. Exploratory Data Analysis (EDA)

• Survival distribution analysis.
• Gender-wise survival comparison.
• Passenger class analysis.
• Age and fare distribution visualization.

4. Feature Engineering

• Converted categorical data into numerical format.
• Prepared features for machine learning models.

5. Model Training

• Split dataset into training and testing sets.
• Trained machine learning models.

6. Model Evaluation

• Accuracy Score
• Confusion Matrix
• Classification Report

---

Project Structure

Titanic-Survival-Prediction/
│
├── Titanic_Survival_Prediction.ipynb
├── train.csv
├── test.csv
├── README.md
└── images/

---

Key Learnings

• Data Cleaning and Preprocessing
• Exploratory Data Analysis (EDA)
• Feature Engineering
• Classification Algorithms
• Model Evaluation Techniques
• Machine Learning Workflow

---

Future Improvements

• Hyperparameter Tuning
• Feature Selection
• Ensemble Learning Methods
• Model Deployment using Streamlit or Flask

---

Author

Vivek Kumar

B.Tech CSE Core
VIT Vellore

---

Connect With Me

• GitHub: Your GitHub Profile Link
• LinkedIn: Your LinkedIn Profile Link