Python Bokeh可视化分析：房贷与信用卡违约关系

from bokeh.plotting import figure, show,output_file
import numpy as np
import pandas as pd
import pandas

# 读取数据
df = pd.read_csv(r'/Users/fuchuanruo/Desktop/可视化作业/实践/train.csv')
test = pd.read_csv(r'/Users/fuchuanruo/Desktop/可视化作业/实践/test.csv')

# 数据预处理：将housing和default的值转换为0和1
df['housing'] = df['housing'].apply(lambda x: 0 if x == 'no' else 1)
df['default'] = df['default'].apply(lambda x: 0 if x == 'no' else 1)

# 创建图表：展示housing分布情况
p1 = figure(title='房贷分布情况', plot_width=400, plot_height=400)
p1.vbar(x=[0,1], top=df['housing'].value_counts().tolist(), width=0.4, color='blue')
p1.xaxis.ticker = [0,1]
p1.xaxis.major_label_overrides = {0: '无房贷', 1: '有房贷'}

# 创建图表：展示default分布情况
p2 = figure(title='信用卡违约分布情况', plot_width=400, plot_height=400)
p2.vbar(x=[0,1], top=df['default'].value_counts().tolist(), width=0.4, color='red')
p2.xaxis.ticker = [0,1]
p2.xaxis.major_label_overrides = {0: '无违约', 1: '违约'}

# 合并图表：使用gridplot布局
from bokeh.layouts import gridplot
grid = gridplot([[p1, p2]])

# 输出图表到HTML文件
output_file('housing_default.html')
show(grid)