day 11

day 10
## 预处理流程回顾

1. 导入库
2. 读取数据查看数据信息--理解数据
3. 缺失值处理
4. 异常值处理
5. 离散值处理
6. 删除无用列
7. 划分数据集
8. 特征工程
9. 模型训练
10. 模型评估
11. 模型保存
12. 模型预测

# 导入所需要的包
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False

# 查看数据信息
data=pd.read_csv('/Users/gj/东财-学习/Python60DaysChallenge-main/day31 文件的拆分/data/raw/data.csv')
print("数据基本信息")
data.info()
print("\n数据前5行预览：")
print(data.head())
#首先处理object 对象
# 先筛选字符串变量‘
dist_features = data.select_dtypes(include=['object']).columns.tolist()
dist_features
# 依次查看内容
for feature in dist_features:
    print(f"\n{feature}的唯一值：")
    print(data[feature].value_counts())
# Home Ownership 标签编码



home_ownership_mapping = {'Own Home':1,
'Rent':2,
'Have Mortgage':3,
'Home Mortgage':4 
}
data['Home Ownership'] = data['Home Ownership'].map(home_ownership_mapping)
#years in current job 标签编码
years_in_current_job_mapping = {
    '< 1 year': 1,
    '1 year': 2,
    '2 years': 3,
    '3 years': 4,
    '4 years': 5,
    '5 years': 6,
    '6 years': 7,
    '7 years':8,
    '8 years': 9,
    '9 years': 10,
    '10+ years': 11
}
data['Years in current job'] = data['Years in current job'].map(years_in_current_job_mapping)
# purpose 独热编码，bool类型转换为数值
data=pd.get_dummies(data,columns=['Purpose'])
data2=pd.read_csv('/Users/gj/东财-学习/Python60DaysChallenge-main/day31 文件的拆分/data/raw/data.csv')
list_final=[]
for i in data.columns:
    if  i not  in  data2.columns:
        list_final.append(i)
    if  i in list_final:
        data[i]=data[i].astype(int)


term_mapping={
    'Short Term':0,
    'Long Term':1
}
data['Term']=data['Term'].map(term_mapping)
data.rename(columns={'Term':'Loan Term'},inplace=True)

continuous_features = data.select_dtypes(include=['int64', 'float64']).columns.tolist()  #把筛选出来的列名转换成列表
 
 # 连续特征用中位数补全
for feature in continuous_features:     
    mode_value = data[feature].mode()[0]            #获取该列的众数。
    data[feature].fillna(mode_value, inplace=True)          #用众数填充该列的缺失值，inplace=True表示直接在原数据上修改。
data.info()

@浙大疏锦行