def main():
    model = KMeansThresholding()
    
    train_files_x = find_files("data/train")
    train_files_y = find_files("data/train_cleaned")

    y_pred = map(lambda x: extract_x([x],0), train_files_x)
    y_pred = list(map(predict, y_pred))
    y_pred = np.concatenate(y_pred)

    y_true = np.concatenate(list(map(lambda x: extract_y([x],0) ,train_files_y)))

    print("Calculating MSE")

    mse =  metrics.mean_squared_error(y_true, y_pred)
    print("MSE: %0.2f (+/- %0.2f)" % (mse.mean()*100, mse.std() * 200))
def main():
    r = int(getarg(1, 0))
    k = int(getarg(2, 0))

    print("Extracting with radius=%d" % (r))

    prefix = "data/train"
    if(k > 0):
        prefix += "_k"+str(k)

    train_files_x = find_files(prefix)
    X = extract_x(train_files_x,r)

    train_files_y = find_files("data/train_cleaned")
    y = extract_y(train_files_y,r)

    outname = prefix+"_r"+str(r)+".npz"
    np.savez(outname,X=X,y=y)
def main():
    r = int(getarg(1, 0))
    k = int(getarg(2, 3))

    print("Extracting with radius=%d" % (r))

    prefix = "data/train"
    outname = prefix+"_c_k"+str(k)+"_r"+str(r)+".npz"
    print("Saving to: "+ outname)

    train_files_x = find_files(prefix)
    X = extract_x(train_files_x,r)
    Xk = extract_x(find_files(prefix+"_k"+str(k)),r,True)
    X = np.concatenate([X,Xk], axis=1)

    train_files_y = find_files("data/train_cleaned")
    y = extract_y(train_files_y,r)

    np.savez(outname,X=X,y=y)