https://github.com/ianjure/titanic-survivor-prediction

Predicting Titanic passengers' survival using machine learning.
https://github.com/ianjure/titanic-survivor-prediction

predictive-modeling streamlit titanic-survival-prediction

Last synced: 19 days ago
JSON representation

Predicting Titanic passengers' survival using machine learning.

• Host: GitHub
• URL: https://github.com/ianjure/titanic-survivor-prediction
• Owner: ianjure
• Created: 2024-08-12T11:41:09.000Z (6 months ago)
• Default Branch: master
• Last Pushed: 2024-09-22T23:07:38.000Z (5 months ago)
• Last Synced: 2024-11-28T07:11:37.804Z (3 months ago)
• Topics: predictive-modeling, streamlit, titanic-survival-prediction
• Language: Jupyter Notebook
• Homepage: https://canyousurvivethetitanic.streamlit.app/
• Size: 1.03 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Titanic Survivor Prediction   [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ianjure/titanic-survivor-prediction/blob/master/Titanic_Survivor_Prediction_Notebook.ipynb)   [![Static Badge](https://img.shields.io/badge/Visit%20Website-red?style=flat&logo=streamlit&logoSize=auto&labelColor=%23ffffff&color=%23ff4b4c)](https://canyousurvivethetitanic.streamlit.app/)

Let’s travel back to 1912 and dive into the data behind the Titanic tragedy. The goal of this project is to develop a machine learning model to predict whether a passenger survived the incident. We will employ classification algorithms and processed data to identify the most effective model. Subsequently, we will build a web application that allows users to test the model with new data inputs.

## Data Overview

We will use the **[Titanic](https://www.kaggle.com/competitions/titanic/data)** dataset from **Kaggle**, which is semi-clean and includes passenger information such as name, age, gender, and socio-economic class.

## Project Method

1. **Clean the Data:** Address missing values and process categorical variables.

2. **Explore the Data:** Uncover meaningful insights and relationships among the variables.

3. **Create New Features:** Develop additional relevant features from the existing data.

4. **Build the Model:** Train various algorithms and fine-tune the best-performing model.

5. **Deploy the Model:** Create a web application to test the model with new data.

## Next Steps

* **Enhance** data quality by generating more features.

* **Experiment** with more advanced classification models and tuning techniques.




**This project is inspired by:** [Titanic Dataset using Random Forest](https://www.kaggle.com/code/murtadhanajim/80-in-titanic-dataset-using-random-forests/notebook)