如何根据虚拟变量拆分数据帧

import pandas as pd

# 创建示例数据帧
data = {
    'Category': ['A', 'B', 'A', 'C', 'B'],
    'Value': [10, 15, 7, 20, 12]
}
df = pd.DataFrame(data)

# 创建虚拟变量
df_dummies = pd.get_dummies(df, columns=['Category'], drop_first=True)

print(df_dummies)

   Value  Category_B  Category_C
0     10           0           0
1     15           1           0
2      7           0           0
3     20           0           1
4     12           1           0

chunk_size = 1000
chunks = [df[i:i + chunk_size] for i in range(0, df.shape[0], chunk_size)]
processed_chunks = [pd.get_dummies(chunk, columns=['Category'], drop_first=True) for chunk in chunks]
result_df = pd.concat(processed_chunks)

import dask.dataframe as dd

ddf = dd.from_pandas(df, npartitions=10)
result_ddf = ddf.categorize(columns=['Category']).get_dummies(columns=['Category'], drop_first=True).compute()