频率矩阵-如何在Python中构建

import pandas as pd
import numpy as np

# 示例数据
data = {
    'Item1': ['A', 'B', 'C', 'A', 'B'],
    'Item2': ['B', 'C', 'A', 'B', 'C'],
    'Item3': ['C', 'A', 'B', 'C', 'A']
}

# 创建DataFrame
df = pd.DataFrame(data)

# 构建频率矩阵
freq_matrix = pd.crosstab(index=df['Item1'], columns=df['Item2'])

print(freq_matrix)

# 处理缺失值
df.fillna('', inplace=True)

# 使用Dask构建频率矩阵
import dask.dataframe as dd

ddf = dd.from_pandas(df, npartitions=2)
freq_matrix_dask = ddf.crosstab(index='Item1', columns='Item2').compute()
print(freq_matrix_dask)