机器学习实践-2021-05-26-----GBDT

# 导入模块
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.ensemble import GradientBoostingRegressor

from sklearn.datasets import load_iris
iris=load_iris()

gbc=GradientBoostingClassifier()
gbc.fit(iris.data,iris.target)

gbc.predict(iris.data)

输出每次迭代的预测概率值




特征重要性:可见后两个特征比较重要，可以进行取舍，达到降维的目的

EM算法

%matplotlib inline
import numpy as np
from scipy.stats import multivariate_normal
from sklearn.mixture import GaussianMixture
from mpl_toolkits.mplot3d import Axes3D
import matplotlib as mpl
import matplotlib.pyplot as plt

mpl.rcParams['font.sans-serif']=[u'SimHei']
mpl.rcParams['axes.unicode_minus']=False

# 随机生成数据
mul=(0,0,0)
cov=np.identity(3)
data1=np.random.multivariate_normal(mul,cov,400)
mul=(2,2,1)
cov=np.identity(3)
data2=np.random.multivariate_normal(mul,cov,100)
data=np.vstack((data1,data2))

#参数赋予初始值
mu1=data.min(axis=0)
mu2=data.max(axis=0)
sigmal=np.identity(3)
sigma2=np.identity(3)
pi=0.5

#em算法估计gmm参数
for i in range(num_iter):
    norm1=multivariate_normal(mu1,sigma1)
    norm2=multivariate_norma1(mu2,sigma2)
    tau1=pi*norm1.pdf(data)
    tau2=(1-pi)*norm2.pdf(data)
    gamma=tau/(tau1+tau2)