import numpy as np
from scipy.stats import multivariate_normal
import random
from operator import truediv
import itertools
from scipy import linalg
import matplotlib.pyplot as plt
import matplotlib as mpl
from sklearn import mixture
#import some data which can be used for gmm
mix = np.loadtxt("mixture.txt", usecols=(0,1), unpack=True)
#print(mix.shape)
color_iter = itertools.cycle(['navy', 'c', 'cornflowerblue', 'gold',
'darkorange'])
def plot_results(X, Y_, means, covariances, index, title):
#function for plotting the gaussians
splot = plt.subplot(2, 1, 1 + index)
for i, (mean, covar, color) in enumerate(zip(
means, covariances, color_iter)):
v, w = linalg.eigh(covar)
v = 2. * np.sqrt(2.) * np.sqrt(v)
u = w[0] / linalg.norm(w[0])
# as the DP will not use every component it has access to
# unless it needs it, we shouldn't plot the redundant
# components.
if not np.any(Y_ == i):
continue
plt.scatter(X[Y_ == i, 0], X[Y_ == i, 1], .8, color=color)
# Plot an ellipse to show the Gaussian component
angle = np.arctan(u[1] / u[0])
angle = 180. * angle / np.pi # convert to degrees
ell = mpl.patches.Ellipse(mean, v[0], v[1], 180. + angle, color=color)
ell.set_clip_box(splot.bbox)
ell.set_alpha(0.5)
splot.add_artist(ell)
plt.xlim(-4., 3.)
plt.ylim(-4., 2.)
gmm = mixture.GaussianMixture(n_components=3, covariance_type='full').fit(mix.T)
print(gmm.predict(mix.T))
plot_results(mix.T, gmm.predict(mix.T), gmm.means_, gmm.covariances_, 0,
'Gaussian Mixture')
所以对于我的问题,结果图是这样的:
编辑:这里是你评论的答案。我会用熊猫来做这个。假设X是你的特征矩阵,y是你的标签,那么
^{pr2}$
在生成的数据帧中,您可以检查所需的所有信息,甚至可以排除算法误分类的样本:
df_wrong = df_all_info[df_all_info['name of y-column'] != df_all_info['name of y_pred column']]
这不是那么容易,因为你需要计算所有协方差矩阵的特征向量。下面是我研究的一个问题的一些示例代码
所以对于我的问题,结果图是这样的:
编辑:这里是你评论的答案。我会用熊猫来做这个。假设
^{pr2}$X
是你的特征矩阵,y
是你的标签,那么在生成的数据帧中,您可以检查所需的所有信息,甚至可以排除算法误分类的样本:
相关问题 更多 >
编程相关推荐