DataFrame 去重，指定列去重drop_duplicates

import pandas as pd

# 创建示例 DataFrame
data = {
    'Name': ['Alice', 'Bob', 'Alice', 'Charlie', 'Bob'],
    'Age': [25, 30, 25, 35, 30]
}
df = pd.DataFrame(data)

# 去重操作
deduplicated_df = df.drop_duplicates()

print("Original DataFrame:")
print(df)

print("\nDeduplicated DataFrame:")
print(deduplicated_df)

 

import pandas as pd

# 创建示例 DataFrame
data = {
    'Name': ['Alice', 'Bob', 'Alice', 'Charlie', 'Bob'],
    'Age': [25, 30, 25, 35, 30],
    'Location': ['NY', 'CA', 'NY', 'TX', 'CA']
}
df = pd.DataFrame(data)

# 在 'Name' 和 'Location' 列上进行去重
deduplicated_df = df.drop_duplicates(subset=['Name', 'Location'])

print("Original DataFrame:")
print(df)

print("\nDeduplicated DataFrame:")
print(deduplicated_df)