组合重叠的分类变量

import pandas as pd

# 示例数据
data = {
    'Category1': ['A', 'B', 'C', 'A'],
    'Category2': ['B', 'A', 'D', 'E']
}

df = pd.DataFrame(data)

# 将分类变量转换为Categorical类型
df['Category1'] = pd.Categorical(df['Category1'])
df['Category2'] = pd.Categorical(df['Category2'])

# 添加新的类别
new_categories = ['AB', 'AC', 'AD', 'AE', 'BC', 'BD', 'BE', 'CD', 'CE', 'DE']
df['Category1'].cat.add_categories(new_categories, inplace=True)
df['Category2'].cat.add_categories(new_categories, inplace=True)

# 组合分类变量
df['Combined_Category'] = df['Category1'].cat.add_categories(df['Category2']).cat.add_categories(new_categories)

# 显示结果
print(df)

import pandas as pd
import itertools

# 示例数据
data = {
    'Category1': ['A', 'B', 'C', 'A'],
    'Category2': ['B', 'A', 'D', 'E']
}

df = pd.DataFrame(data)

# 生成所有可能的组合
combinations = list(itertools.product(df['Category1'].unique(), df['Category2'].unique()))

# 将组合转换为字符串
combinations_str = [''.join(comb) for comb in combinations]

# 添加新的类别
df['Combined_Category'] = df['Category1'].cat.add_categories(combinations_str)

# 显示结果
print(df)

import pandas as pd

# 示例数据
data = {
    'Category1': ['A', 'B', 'C', 'A'],
    'Category2': ['B', 'A', 'D', 'E']
}

df = pd.DataFrame(data)

# 创建多级索引
multi_index = pd.MultiIndex.from_arrays([df['Category1'], df['Category2']], names=['Category1', 'Category2'])

# 将多级索引转换为DataFrame
df_multi_index = pd.DataFrame(index=multi_index)

# 显示结果
print(df_multi_index)