import numpy as np
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn import datasets

# 载入红酒数据
wine = datasets.load_wine()

# 只选取前两个特征
x = wine.data[:, :2]
y = wine.target

# 拆分训练集和数据集
x_train, x_test, y_train, y_test = train_test_split(x, y)

forest = RandomForestClassifier(n_estimators=6, random_state=3)

# 拟合数据
forest.fit(x_train, y_train)

# 绘制图形
cmap_light = ListedColormap(['#FFAAAA', '#AAFFAA', '#AAAAFF'])
cmap_bold = ListedColormap(['#FF0000', '#00FF00', '#0000FF'])

x_min, x_max = x[:, 0].min() - 1, x[:, 0].max() + 1
y_min, y_max = x[:, 1].min() - 1, x[:, 1].max() + 1

xx, yy = np.meshgrid(np.arange(x_min, x_max, .02), np.arange(y_min, y_max, .02))

# 生成随机森林
z = forest.predict(np.c_[xx.ravel(), yy.ravel()]).reshape(xx.shape)

plt.figure()
plt.pcolormesh(xx, yy, z, cmap=cmap_light)

# 绘制训练数据和测试数据的散点图
plt.scatter(x_train[:, 0], x_train[:, 1], c=y_train, cmap=cmap_bold, edgecolor='k', s=20)
plt.scatter(x_test[:, 0], x_test[:, 1], c=y_test, cmap=cmap_bold, edgecolor='k', s=50, marker='x')

plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
plt.title("Random Forest Classification")
plt.show()