Titanic Survival Predition

This Jupyter Notebook uses the Titanic dataset to predict passenger survival based on various features. It includes data preprocessing, feature engineering, model training, and evaluation.

Requirements

• Python 3.x
• Jupyter Notebook
• Required Libraries:
  • pandas
  • numpy
  • scikit-learn
  • matplotlib
  • seaborn

Dataset

The Titanic dataset is sourced from Kaggle. It includes features like passenger class, age, gender, family size, and fare, which are used to predict survival.

Model Used

• Decision Tree Classifier
  • The model is used to classify passenger survival and is evaluated on accuracy, with a confusion matrix to visualize performance.

Structure

1. Data Loading - Loads the dataset and briefly explores its structure.
2. Data Preprocessing - Handles missing values and performs feature engineering.
3. Model Training - Trains a Decision Tree classifier to predict survival.
4. Evaluation - Evaluates model performance with accuracy and confusion matrix.

Usage

1. Open the Jupyter Notebook and run each cell sequentially.
2. Adjust model parameters as needed to experiment with different configurations.

Results

The model performance is measured using accuracy scores and visualized with a confusion matrix heatmap.