def dating_class_test(file_name: str, k_number: int):
"""
注意测试分类算法是否正确, 样本集和测试集必须随机从总的样本集里面取, 由于本次测试的数据并没有按照特定目的排序,
因此我们只是顺序挑取测试集(前10%)
:param file_name: 文件名
:param k_number: 截取的k个邻居
:return:
"""
ho_ratio = 0.10
with FTool.LD(file_name) as ld:
dating_mat, dating_labels = ld.load_to_ndarray(3, True)
with FTool.Painting3D(name="Personal hobby with love") as plt:
plt.paint(dating_mat,
dating_labels,
x_name="Fly miles",
y_name="Play game",
z_name="Ice Cream")
norm_mat, ranges, min_val = FTool.HM.average(dating_mat)
m = norm_mat.shape[0]
# 校验数据的数量, 一般为10%, 90%样本数据用来训练分类器
num_test_vec = int(m * ho_ratio)
error_count = 0
for i in range(num_test_vec):
# norm_mat[num_test_vec: m, :] 中num_test_vec: m是截取ndarray中第num_test_vec个后的数据
classifier_result = KnnLearning.classify0(
norm_mat[i, :], norm_mat[num_test_vec:m, :],
dating_labels[num_test_vec:m], k_number)
print("The classifier came back with {0}, the real answer is: {1}".
format(classifier_result, dating_labels[i]))
if classifier_result != dating_labels[i]:
error_count += 1
error_rate = error_count / num_test_vec
print("The total error rate is {}".format(error_rate))
def test_create_tree(self):
"""
测试创建决策树
:return:
"""
file_path = os.path.join(os.getcwd(), "lenses.txt")
with FTool.LD(file_path) as ld:
lenses = ld.load_data_list()
# 年龄, 材质硬度 散光, 流泪频率共四个特征. 第五个为结论
lenses_labels = ['age', 'prescript', 'astigmatic', 'tearRate']
lenses_tree = create_tree(lenses, lenses_labels)
# 画出决策树
print(lenses_tree)
PaintingTree().create_plot(lenses_tree)
self.store_tree(lenses_tree, 'classifierStorage.txt')
def classify_person(file_name: str, k_number: int):
"""
约会网站预测函数, 根据用户输入的对方信息和以往该用户对对象看法进行分类
:return:
"""
result_list = ["not at all", "in small doses", "in large doses"]
percent_tats = float(
input("percentage of time spent playing video games?"))
fly_miles = float(input("frequent flier miles earned per year?"))
ice_cream = float(input("liters of ice cream consumed per year?"))
with FTool.LD(file_name) as ld:
dating_data_mat, dating_labels = ld.load_to_ndarray(3, True)
norm_mat, ranges, min_val = FTool.HM.average(dating_data_mat)
in_arr = array([fly_miles, percent_tats, ice_cream])
classifier_result = KnnLearning.classify0(
(in_arr - min_val) / ranges, norm_mat, dating_labels, k_number)
print("You will probably like this person: ",
result_list[classifier_result - 1])
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2018/9/13
# @Author : Wenhao Shan
# Dsc : Test of tree(include create, use) and painting tree
import os
from MachineLearingInAction import functionUtils as FTool
from MachineLearingInAction.Code.Chapter3_Random_Forest.trees import create_tree
from MachineLearingInAction.Code.Chapter3_Random_Forest.tree_plot import PaintingTree
if __name__ == '__main__':
file_path = os.getcwd() + "\lenses.txt"
with FTool.LD(file_path) as ld:
lenses = ld.load_data_list()
# 年龄, 材质硬度 散光, 流泪频率共四个特征
lenses_labels = ['age', 'prescript', 'astigmatic', 'tearRate']
lenses_tree = create_tree(lenses, lenses_labels)
print(lenses_tree)
PaintingTree().create_plot(lenses_tree)