import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_blobs
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
准备工作
n_train = 20 # samples for training
n_test = 200 # samples for testing
n_averages = 50 # how often to repeat classification
n_features_max = 75 # maximum number of features
step = 4 # step size for the calculation
def generate_data(n_samples, n_features):
"""Generate random blob-ish data with noisy features.
This returns an array of input data with shape `(n_samples, n_features)`
and an array of `n_samples` target labels.
Only one feature contains discriminative information, the other features
contain only noise.
"""
X, y = make_blobs(n_samples=n_samples, n_features=1, centers=[[-2], [2]])
# add non-discriminative features
if n_features > 1:
X = np.hstack([X, np.random.randn(n_samples, n_features - 1)])
return X, y
