Python Bokeh可视化分析：贷款利率与违约职业的关系

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

# 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')

# 数据清洗，去除缺失值和异常值
df.dropna(inplace=True)
df = df[df['lending_rate3m'] < 30]
df = df[df['default: job'] != 'unknown']

# 创建散点图
p = figure(title='贷款利率 vs 违约职业', x_axis_label='3个月贷款利率', y_axis_label='违约职业')

# 添加散点
p.circle(df['lending_rate3m'], df['default: job'], size=5)

# 输出到HTML文件
output_file('lending_rate_vs_default_job.html')

# 显示图形
show(p)