Pandas中分类变量的顺序

import pandas as pd

# 定义分类变量的顺序
categories = ['low', 'medium', 'high']

# 创建Categorical类型的Series
s = pd.Series(['low', 'high', 'medium', 'low'], dtype='category', categories=categories, ordered=True)

# 输出Categorical类型的Series
print(s)

0       low
1      high
2    medium
3       low
dtype: category
Categories (3, object): ['low' < 'medium' < 'high']

import pandas as pd

# 定义分类变量的顺序
categories = ['low', 'medium', 'high']

# 创建DataFrame
df = pd.DataFrame({'Category': ['low', 'high', 'medium', 'low'],
                   'Value': [1, 3, 2, 4]})

# 将Category列转换为Categorical类型
df['Category'] = pd.Categorical(df['Category'], categories=categories, ordered=True)

# 按照Category列进行排序
df_sorted = df.sort_values('Category')

# 输出排序后的DataFrame
print(df_sorted)

  Category  Value
0      low      1
2   medium      2
1     high      3
3      low      4