机器学习基础算法20- 鸢尾花数据集分类-随机森林

代码

# 鸢尾花数据分类-随机森林
# 结果为6个随机森林得到的结果

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib as mpl
from sklearn.ensemble import RandomForestClassifier


# def iris_type(s):
#     it = {'Iris-setosa': 0, 'Iris-versicolor': 1, 'Iris-virginica': 2}
#     return it[s]

# 'sepal length', 'sepal width', 'petal length', 'petal width'
iris_feature = u'花萼长度', u'花萼宽度', u'花瓣长度', u'花瓣宽度'

if __name__ == "__main__":

    mpl.rcParams['font.sans-serif'] = [u'SimHei']  # 黑体 FangSong/KaiTi
    mpl.rcParams['axes.unicode_minus'] = False

    path = 'iris.data'  # 数据文件路径
    data = pd.read_csv(path, header=None)
    x_prime = data[range(4)]
    y = pd.Categorical(data[4]).codes
    # 特征两两组合，共6个
    feature_pairs = [[0, 1], [0, 2], [0, 3], [1, 2], [1, 3], [