This project is a machine learning web application that predicts the survival of passengers on the Titanic based on various features such as age, gender, passenger class, etc.
This project leverages machine learning techniques to predict whether a passenger survived the Titanic disaster. The model is trained on the famous Titanic dataset from Kaggle. A web application is developed to allow users to input passenger details and get survival predictions.
Data preprocessing and feature engineering
Machine learning model training and evaluation
Web application for user interaction and prediction
Visualizations for better understanding of data and model performance
The dataset used in this project is the Titanic dataset from Kaggle. It contains information about the passengers on the Titanic, including:
PassengerId Pclass Name Sex Age SibSp Parch Ticket Fare Cabin Embarked
Python: Programming language Streamlit: Framework for building the web app Scikit-learn: Machine learning library Pandas: Data manipulation library NumPy: Numerical computing library Matplotlib/Seaborn: Data visualization libraries
Open your web browser and navigate to https://ml-project-15-titanic-survival-prediction-webapp-2yjtmkqvtilk8.streamlit.app/
Input the details like Passenger class, Gender, Age of the person, No of Siblings, Parch, Fare and Embarked.
Click on the "Survived Result" button to get the predicted survived.
EDA is performed to understand the underlying patterns and relationships in the dataset. Key steps include:
Visualizing the distribution of numerical and categorical features
Analyzing the correlation between features and the target variable (survival)
Identifying and handling missing values
Feature engineering to create new relevant features
The machine learning model used in this project is a Logistic Regression. The model is trained and evaluated using the Titanic dataset. Key steps in model development include:
Data preprocessing (handling missing values, encoding categorical variables, feature scaling) Model training Model evaluation using metrics such as accuracy
The web application is built using Streamlit, which allows for easy deployment and user interaction. Users can input passenger details such as age, gender, passenger class, etc., and get predictions on their survival.
The final model provides predictions for survived or not with a certain accuracy. The results are visualized using plots and graphs to show the actual vs. predicted prices.
Contributions are welcome! If you have any improvements or suggestions, feel free to open a pull request or create an issue.
The application is deployed using Streamlit. You can access it here = https://ml-project-15-titanic-survival-prediction-webapp-2yjtmkqvtilk8.streamlit.app/