A binary classifier to predict whether a person would have survived, or not, to the Titanic’s disaster.
Training set (710 samples), and testing set (177 samples).
Each dataset row represents a specific passenger’s information (predictors/features), such as:
ticket class; gender; age; number of siblings and spouses aboard; number of parents and children
aboard; passenger fare.
Finally, is also known whether the person survived or not (target variable).
Are you interested in knowing which would have had your probability of surviving?
Change the my_info
values into the analysis.py file, then run the script.
- Training: 80.14% accuracy
- Testing: 78.53% accuracy
Scatterplot showing the distribution of the two classes in the plane defined by the two most influential features
The feature which discriminates more the probability of surviving is the gender.