Titanic survivor classification challenge

Titanic classification challenge on Kaggle. Given a dataset of a subset of the Titanic's passengers predict whether they will survive or not.

Credits

Below are provided the steps that were followed for this project. Each step and classifiers have their own document.

Data visualization: data analysis to understand missing values, data relations and usefulness of features
Preprocessing: with the knowledge acquired with the preceding step, apply preprocessing of data including dealing with missing values, drop unuseful features and build new features
Classifier: build classifiers based on the preprocessed data using a variety of techniques

Classification techniques together with the relative scores.

Classifier	Test set score	CV score	Kaggle score
KNN	-	-	-
Logistic Regression	-	0.82	0.78947
Neural Networks	-	-	-
Random Forest	0.82	0.84	0.79425
Support Vector Machines	0.85	0.84	0.80861
Perceptron	0.78	-	0.62679
Naive Bayes	0.78	0.80	0.76076

\ contains all of the jupyter's notebooks including classifiers, preprocessing and data visualization
\Data contains the project dataset given in the Kaggle challenge
\Data\outputs contains the outputs given by the classifiers that were submitted to Kaggle

to run the jupyter's notebooks just go with jupyter notebook

Name		Name	Last commit message	Last commit date
Latest commit History 61 Commits
Data		Data
src		src
.gitignore		.gitignore
Ensemble.ipynb		Ensemble.ipynb
README.md		README.md
_config.yml		_config.yml
data-visualisation.ipynb		data-visualisation.ipynb
knn.ipynb		knn.ipynb
logistic-regression.ipynb		logistic-regression.ipynb
naive-bayes.ipynb		naive-bayes.ipynb
neural-net.ipynb		neural-net.ipynb
perceptron.ipynb		perceptron.ipynb
preprocessing.ipynb		preprocessing.ipynb
random-forest.ipynb		random-forest.ipynb
requirements.txt		requirements.txt
support-vector-machine.ipynb		support-vector-machine.ipynb