Pandas/Dask检查列中的值是否添加其他值

import pandas as pd

# 创建一个示例DataFrame
data = {'Name': ['Alice', 'Bob', 'Charlie', 'David'],
        'Age': [25, 30, 35, 40],
        'City': ['New York', 'London', 'Paris', 'Tokyo']}
df = pd.DataFrame(data)

# 检查'Name'列中的值是否在指定的列表中
names_to_check = ['Alice', 'Bob']
df['Name_Check'] = df['Name'].isin(names_to_check)

print(df)

      Name  Age      City  Name_Check
0    Alice   25  New York        True
1      Bob   30    London        True
2  Charlie   35     Paris       False
3    David   40     Tokyo       False

import dask.dataframe as dd

# 创建一个示例Dask DataFrame
data = {'Name': ['Alice', 'Bob', 'Charlie', 'David'],
        'Age': [25, 30, 35, 40],
        'City': ['New York', 'London', 'Paris', 'Tokyo']}
df = dd.from_pandas(pd.DataFrame(data), npartitions=2)

# 检查'Name'列中的值是否在指定的列表中
names_to_check = ['Alice', 'Bob']
df['Name_Check'] = df['Name'].isin(names_to_check)

print(df.compute())

      Name  Age      City  Name_Check
0    Alice   25  New York        True
1      Bob   30    London        True
2  Charlie   35     Paris       False
3    David   40     Tokyo       False