梯度提升算法代码(鸢尾花分类)+交叉验证调参

导入模块

import numpy as np
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
from matplotlib.font_manager import FontProperties
from sklearn.datasets import load_iris
from sklearn.ensemble import GradientBoostingClassifier
from sklearn import metrics
from sklearn.model_selection import GridSearchCV
%matplotlib inline
font = FontProperties(fname='/Library/Fonts/Heiti.ttc')

导入数据

iris_data = load_iris()
X = iris_data.data[0:100, [2, 3]]
y = iris_data.target[0:100]
label_list = ['山鸢尾', '杂色鸢尾']

构造决策边界

def plot_decision_regions(X, y, classifier=None):
    marker_list = ['o', 'x', 's']
    color_list = ['r', 'b', 'g']
    cmap = ListedColormap(color_list[:len(np.unique(y))])

    x1_min, x1_max = X[:, 0].min()-1, X[:, 0].max()+1
    x2_min, x2_max = X[:, 1].min()-1, X[:, 1].max()+1
    t1 = np.linspace(x1_min, x1_max, 666)
    t2 = np.linspace(x2_min, x2_max, 666)

    x1, x2 = np.meshgrid(t1, t2)
    y_hat = classifier.predict(np.array([x1.ravel(), x2.ravel()]).T)
    y_hat = y_hat.reshape(x1.shape)
    plt.contourf(x1, x2, y_hat, alpha=0.2, cmap=cmap)
    plt.xlim(x1_min, x1_max)
    plt.ylim(x2_min, x2_max)

    for ind, clas in enumerate(np.unique(y)):
        plt.scatter(X[y == clas, 0], X[y == clas, 1], alpha=0.8, s=50,
                    c=color_list[ind], marker=marker_list[ind], label=label_list[clas])

训练模型

gbc = GradientBoostingClassifier(random_state=1)
gbc.fit(X, y)
y_pred = gbc.predict(X)
y_predprob = gbc.predict_proba(X)[:, 1]
print("精准度:{:.4f}".format(metrics.accuracy_score(y, y_pred)))
print("AUC分数(训练集):{:.4f}".format(metrics.roc_auc_score(y, y_predprob)))

精准度:1.0000
AUC分数(训练集):1.0000

可视化

plot_decision_regions(X, y, classifier=gbc)
plt.xlabel('花瓣长度（cm）', fontproperties=font)
plt.ylabel('花瓣宽度（cm）', fontproperties=font)
plt.title('梯度提升法算法代码(鸢尾花分类)',
          fontproperties=font, fontsize=20)
plt.legend(prop=font)
plt.show()

交叉验证训练模型

找到合适n_estimators