同时计算2列的频率计数

import pandas as pd

# 创建示例数据
data = {
    'ColumnA': ['A', 'B', 'A', 'C', 'B', 'A'],
    'ColumnB': [1, 2, 1, 3, 2, 1]
}
df = pd.DataFrame(data)

# 计算两列的频率计数
frequency_count = df.groupby(['ColumnA', 'ColumnB']).size().reset_index(name='Frequency')

print(frequency_count)

  ColumnA  ColumnB  Frequency
0       A        1         3
1       B        1         1
2       B        2         1
3       C        3         1

import pandas as pd

# 创建示例数据
data = {
    'ColumnA': ['A', 'B', 'A', 'C', 'B', 'A'] * 100000,
    'ColumnB': [1, 2, 1, 3, 2, 1] * 100000
}
df = pd.DataFrame(data)

# 分块处理
chunk_size = 100000
chunks = [df[i:i + chunk_size] for i in range(0, df.shape[0], chunk_size)]

# 计算每个块的频率计数
frequency_counts = []
for chunk in chunks:
    freq_count = chunk.groupby(['ColumnA', 'ColumnB']).size().reset_index(name='Frequency')
    frequency_counts.append(freq_count)

# 合并结果
result = pd.concat(frequency_counts).groupby(['ColumnA', 'ColumnB']).sum().reset_index()

print(result)