import numpy as np def data(n=1000): """ Generate 2d gaussian data. Few points but every model should have slightly different data. Then use a big dataset as comparison algo. Basically subsampling instead of feature bagging. """ return np.random.normal(1.0,0.5,(n,2)) if __name__ == '__main__': x=data() from plt import plt plt.plot(x[:,0],x[:,1],'.') plt.how() #print(x,y,z)