ChingTien / Kaggle_Titanic

Titanic Survival Prediction

Libraries

• pandas
• numpy
• matplotlib
• seaborn
• sklearn
  • RandomForestClassifier

Process

1. Import libraries and data
2. Information and description
3. HeatMap for EDA
4. Plot possible variables
5. Create new columns(family_size, title)
6. Deal with missing values
7. Encode categorical data
8. Use random forest to predict age
9. Train model and predict result
10. Submit

Model Performance

oob_score_ : 0.8171