### 特征分析

import simplestart as ss
import pandas as pd

ss.md('''
## 特征分析
''')

ss.space()

ss.md("#### 1. 特征的散点矩阵")
ss.space()
ss.image("./images/feature01.png", width=600, height = 500)

ss.space()

ss.md('''
本图来自:
[VuNus 【机器学习基础】1.7 鸢尾花分类](https://blog.csdn.net/qq_47809408/article/details/124632290)
''')

ss.space()
ss.md("#### 2. 特征浏览")
import pandas as pd
from bokeh.plotting import figure, show
from bokeh.models import ColumnDataSource
from bokeh.transform import factor_cmap
from bokeh.embed import file_html
from bokeh.resources import CDN
from bokeh.palettes import Category10

# 加载数据集
data = pd.read_csv("./data/iris.csv")

# 创建 Bokeh 图表
p = figure(title="Iris 数据集散点图", x_axis_label='花瓣长度 (cm)', y_axis_label='花瓣宽度 (cm)',
           tools="pan,wheel_zoom,box_zoom,reset,hover,save", width=800, height=600)

# 创建数据源
source = ColumnDataSource(data)

# 为 species 列设置颜色映射
species_list = data['species'].unique().tolist()
p.circle(x='petal_length', y='petal_width', source=source, size=10,
         color=factor_cmap('species', palette=Category10[3], factors=species_list), legend_field='species')

# 配置图例
p.legend.title = "Species"
p.legend.location = "top_left"

# 将 Bokeh 图表转换为 HTML 并显示
html_output = file_html(p, CDN, "Iris 数据集散点图")
#show(p)


ss.htmlview(html_output)