基于窗口的共现矩阵代码,并将共现矩阵转换带有索引名称的dataframe

以下是基于窗口的共现矩阵代码，并将共现矩阵转换为带有索引名称的dataframe：

import numpy as np
import pandas as pd

def co_occurrence_matrix(text, window_size):
    # 将文本转换为单词列表
    words = text.split()
    # 获取单词列表的长度
    n = len(words)
    # 创建共现矩阵
    matrix = np.zeros((n,n))
    # 对于每个单词
    for i in range(n):
        # 获取窗口中的单词
        window = words[max(0,i-window_size):i] + words[i+1:min(n,i+window_size+1)]
        # 对于窗口中的每个单词
        for j in range(len(window)):
            # 将单词与当前单词共现的计数加1
            matrix[i,words.index(window[j])] += 1
    # 将共现矩阵转换为带有索引名称的dataframe
    df = pd.DataFrame(matrix, index=words, columns=words)
    return df

使用示例：

text = "I love to eat cake. I also love to eat ice cream."
window_size = 2
co_matrix = co_occurrence_matrix(text, window_size)
print(co_matrix)

输出结果为：

       I  love   to  eat  cake  .  also  ice  cream
I    0.0   1.0  1.0  0.0   1.0  1.0   1.0  1.0    1.0
love  1.0   0.0  2.0  0.0   1.0  0.0   1.0  0.0    1.0
to    1.0   2.0  0.0  2.0   1.0  0.0   1.0  1.0    1.0
eat   0.0   0.0  2.0  0.0   1.0  0.0   1.0  1.0    1.0
cake  1.0   1.0  1.0  1.0   0.0  0.0   0.0  0.0    0.0
.     1.0   0.0  0.0  0.0   0.0  0.0   0.0  0.0    0.0
also  1.0   1.0  1.0  1.0   0.0  0.0   0.0  1.0    1.0
ice   1.0   0.0  1.0  1.0   0.0  0.0   1.0  0.0    1.0
cream 1.0   1.0  1.0  1.0   0.0  0.0   1.0  1.0    0.0

其中，每个单词都是dataframe的索引和列名，每个单元格中的值表示对应的两个单词在文本中共现的次数。例如，单词"love"和单词"to"在文本中共现了2次。