KNN with Adaboose

gistfile1.py

def cvalidate():
    from sklearn import cross_validation

    trainset = np.genfromtxt(open('train.csv','r'), delimiter=',')[1:]
    X = np.array([x[1:8] for x in trainset])
    y = np.array([x[8] for x in trainset])
    #print X,y
    import math
    for i, x in enumerate(X):
        for j, xx in enumerate(x):
            if(math.isnan(xx)):
                X[i][j] = 25.6
   
    #print X[0:3]
    #print y[0:3]
    X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size = 0.3, random_state = 0)

    X_train, X_test = decomposition_pca(X_train, X_test)
    
    bdt = AdaBoostClassifier(base_estimator = KNeighborsClassifier(n_neighbors=20, algorithm = 'auto'), algorithm="SAMME", n_estimators = 200)
    bdt.fit(X_train, y_train)
    
    

    print bdt.score(X_test, y_test)