Machine learning project predicting Titanic passenger survival using Python, pandas, and scikit-learn. Includes full data preprocessing, model training, and evaluation pipeline.

The goal is to build a model that predicts the Survived outcome (1 = survived, 0 = did not survive) based on passenger characteristics such as age, class, and sex.

1. Data Loading — Imported train.csv, test.csv, and gender_submission.csv
2. Data Cleaning — Filled missing values with median and mode
3. Feature Encoding — Converted categorical features like Sex and Embarked into numerical values
4. Model Training — Used Logistic Regression to train and validate survival predictions
5. Evaluation — Measured accuracy and classification metrics on a validation set
6. Prediction — Generated survival predictions for the test set and saved them as submission.csv

Algorithm: Logistic Regression
Libraries: pandas, numpy, scikit-learn, seaborn, matplotlib

Typical accuracy achieved: around 80% on validation data.

• train.csv — Training data with labels (Survived)
• test.csv — Test data without labels
• gender_submission.csv — Sample submission file for Kaggle format

Key features include:

• NumPy / Pandas — Data wrangling
• Matplotlib / Seaborn — Visualization
• Scikit-Learn — Machine learning modeling