10 Practical Ways to Iterate and Transform a Pandas DataFrame in Python

1. Iterate over DataFrame rows

import pandas as pd
# 创建示例 DataFrame
data = {'A': [1, 2, 3], 'B': [4, 5, 6]}
df = pd.DataFrame(data)
# 遍历 DataFrame 的每一行
for index, row in df.iterrows():
    print(f"Index: {index}, Row: {row}")

2. Iterate over DataFrame columns

import pandas as pd
# 创建示例 DataFrame
data = {'A': [1, 2, 3], 'B': [4, 5, 6]}
df = pd.DataFrame(data)
# 遍历 DataFrame 的每一列
for col_name in df.columns:
    print(f"Column Name: {col_name}")

3. Iterate over all values in a DataFrame

import pandas as pd
# 创建示例 DataFrame
data = {'A': [1, 2, 3], 'B': [4, 5, 6]}
df = pd.DataFrame(data)
# 遍历 DataFrame 的所有值
for value in df.values.flatten():
    print(f"Value: {value}")

4. Use the apply() function

import pandas as pd
# 创建示例 DataFrame
data = {'A': [1, 2, 3], 'B': [4, 5, 6]}
df = pd.DataFrame(data)
# 定义一个函数用于乘以2
def multiply_by_two(row):
    return row * 2
# 应用函数到 DataFrame 上
result = df.apply(multiply_by_two)
print(result)

5. Perform vectorized operations

import pandas as pd
# 创建示例 DataFrame
data = {'A': [1, 2, 3], 'B': [4, 5, 6]}
df = pd.DataFrame(data)
# 直接对 DataFrame 的每一项乘以2
result = df * 2
print(result)

6. Update values with map()

import pandas as pd
# 创建示例 DataFrame
data = {'A': [1, 2, 3], 'B': [4, 5, 6]}
df = pd.DataFrame(data)
# 更新 DataFrame 中的值
df['A'] = df['A'].map(lambda x: x + 1)
print(df)

7. Conditionally update values with mask()

import pandas as pd
# 创建示例 DataFrame
data = {'A': [1, 2, 3], 'B': [4, 5, 6]}
df = pd.DataFrame(data)
# 条件性地更新 DataFrame 中的值
df['A'] = df['A'].mask(df['A'] > 2, 0)
print(df)

8. Group data using groupby()

import pandas as pd
# 创建示例 DataFrame
data = {'Key': ['A', 'A', 'B', 'B', 'C'], 'Value': [1, 2, 3, 4, 5]}
df = pd.DataFrame(data)
# 使用 groupby 对 DataFrame 分组并计算每组的总和
grouped = df.groupby('Key')['Value'].sum()
print(grouped)

9. Compute cumulative sum with cumsum()

import pandas as pd
# 创建示例 DataFrame
data = {'Key': ['A', 'A', 'B', 'B', 'C'], 'Value': [1, 2, 3, 4, 5]}
df = pd.DataFrame(data)
# 计算 Value 列的累计求和
df['CumulativeSum'] = df['Value'].cumsum()
print(df)

10. Calculate rolling statistics with rolling()

import pandas as pd
# 创建示例 DataFrame
data = {'Key': ['A', 'A', 'B', 'B', 'C'], 'Value': [1, 2, 3, 4, 5]}
df = pd.DataFrame(data)
# 计算 Value 列的滚动平均值（窗口大小为2）
df['RollingMean'] = df['Value'].rolling(window=2).mean()
print(df)