validation.py

import pandas as pd 
import numpy as np 
from sys import exit 
from sklearn import cross_validation
from sklearn import datasets
from sklearn import svm
from sklearn.naive_bayes import GaussianNB

data = pd.read_csv('../../data/improv/train1.csv')

# 
X = np.array(data[['Pclass', 'Sex', 'Embarked']])
Y = np.array(data[['Survived']])

X_train, X_test, y_train, y_test = cross_validation.train_test_split(
	X, Y, test_size=0.4, random_state=0)

# SVM
clf = svm.SVC(kernel='linear', C=1).fit(X_train, y_train)

print clf.score(X_test, y_test)