1.导入数据
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
iris = datasets.load_iris()
X = iris.data[:,2:]
y = iris.target
2.表示数据
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.scatter(X[y==2,0], X[y==2,1])
plt.show()
3.分类问题
以信息熵为标准:
from sklearn.tree import DecisionTreeClassifier
dt_clf = DecisionTreeClassifier(max_depth=2, criterion="entropy", random_state=42)
dt_clf.fit(X, y)
绘图表示:
def plot_decision_boundary(model, axis):
x0, x1 = np.meshgrid(
np.linspace(axis[0], axis[1], int((axis[1]-axis[0])*100)).reshape(-1, 1),
np.linspace(axis[2], axis[3], int((axis[3]-axis[2])*100)).reshape(-1, 1),
)
X_new = np.c_[x0.ravel(), x1.ravel()]
y_predict = model.predict(X_new)
zz = y_predict.reshape(x0.shape)
from matplotlib.colors import ListedColormap
custom_cmap = ListedColormap(['#EF9A9A','#FFF59D','#90CAF9'])
plt.contourf(x0, x1, zz, cmap=custom_cmap)
plot_decision_boundary(dt_clf, axis=[0.5, 7.5, 0, 3])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.scatter(X[y==2,0], X[y==2,1])
plt.show()
以基尼系数为标准:
from sklearn.tree import DecisionTreeClassifier
dt_clf = DecisionTreeClassifier(max_depth=2, criterion="gini", random_state=42)
dt_clf.fit(X, y)
plot_decision_boundary(dt_clf, axis=[0.5, 7.5, 0, 3])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.scatter(X[y==2,0], X[y==2,1])
plt.show()
4.回归问题
4.1 重新导入数据
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
boston = datasets.load_boston()
X = boston.data
y = boston.target
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=666)
4.2决策树回归
from sklearn.tree import DecisionTreeRegressor
dt_reg = DecisionTreeRegressor()
dt_reg.fit(X_train, y_train)
dt_reg.score(X_test, y_test)