def main():
training = datas.training
training = training.drop(["SibSp"], axis=1)
testing = datas.testing
testing = testing.drop(["SibSp"], axis=1)
random_forest = RandomForestClassifier(n_estimators=100, min_samples_split=1, max_depth=None, min_samples_leaf=5)
random_forest = random_forest.fit(pca.reduced_data(training),training.ix[:,'Survived'])
result = random_forest.predict(pca.reduced_data(testing))
return result
def main():
training = datas.training
training = training.drop(["Embarked"], axis=1)
testing = datas.testing
testing = testing.drop(["Embarked"], axis=1)
knn = KNeighborsClassifier(15, weights="uniform")
knn.fit(pca.reduced_data(training, 4), training.ix[:, "Survived"])
result = knn.predict(pca.reduced_data(testing, 4))
datas.write_data(result)
def main():
training = datas.training
training = training.drop(['Embarked'], axis=1)
testing = datas.testing
testing = testing.drop(['Embarked'], axis=1)
knn = KNeighborsClassifier(15, weights="uniform")
knn.fit(pca.reduced_data(training, 4), training.ix[:, 'Survived'])
result = knn.predict(pca.reduced_data(testing, 4))
datas.write_data(result)
def test():
training = datas.training
knn = KNeighborsClassifier(25, weights="uniform")
kfold = cross_validation.KFold(len(training), 3)
result = cross_validation.cross_val_score(knn,
pca.reduced_data(training),
training['Survived'],
cv=kfold,
n_jobs=1)
print result
def test():
training = datas.training
knn = KNeighborsClassifier(25, weights="uniform")
kfold = cross_validation.KFold(len(training), 3)
result = cross_validation.cross_val_score(knn, pca.reduced_data(training), training["Survived"], cv=kfold, n_jobs=1)
print result