ls = ['我永遠(yuǎn)喜歡三上悠亞', '三上悠亞又出新作了']

['',    '我', '永遠(yuǎn)', '喜歡', '三上', '悠亞', '又', '出', '新作', '了']
['我',    0,      1,     1,     1,    1,    0,    0,      0,     0]
['永遠(yuǎn)',  1,      0,     1,      1,    1,    0,    0,     0,     0] 
['喜歡'   1,      1,     0,      1,    1,    0,    0,     0,     0]
['三上',  1,      1,     1,      0,    1,    1,    1,     1,     1]
['悠亞',  1,      1,     1,      1,    0,    1,    1,     1,     1]
['又',    0,      0,     0,      1,    1,    0,    1,     1,     1]
['出',    0,      0,     0,      1,    1,    1,    0,     1,     1]
['新作',  0,      0,     0,      1,    1,    1,    1,     0,     1]
['了',    0,      0,     0,      1,    1,    1,    1,     1,     0]]

# coding:utf-8
import numpy as np
import pandas as pd
import jieba.analyse
import os
# 獲取關(guān)鍵詞
def Get_file_keywords(dir):
    data_array = []  # 每篇文章關(guān)鍵詞的二維數(shù)組
    set_word = []  # 所有關(guān)鍵詞的集合
    try:
        fo = open('dic_test.txt', 'w+', encoding='UTF-8')
        # keywords = fo.read()
        for home, dirs, files in os.walk(dir):  # 遍歷文件夾下的每篇文章
            for filename in files:
                fullname = os.path.join(home, filename)
                f = open(fullname, 'r', encoding='UTF-8')
                sentence = f.read()
                words = " ".join(jieba.analyse.extract_tags(sentence=sentence, topK=30, withWeight=False,
                                                            allowPOS=('n')))  # TF-IDF分詞
                words = words.split(' ')
                data_array.append(words)
                for word in words:
                    if word not in set_word:
                        set_word.append(word)
        set_word = list(set(set_word))  # 所有關(guān)鍵詞的集合
        return data_array, set_word
    except Exception as reason:
        print('出現(xiàn)錯(cuò)誤：', reason)
        return data_array, set_word
# 初始化矩陣
def build_matirx(set_word):
    edge = len(set_word) + 1  # 建立矩陣，矩陣的高度和寬度為關(guān)鍵詞集合的長度+1
    '''matrix = np.zeros((edge, edge), dtype=str)'''  # 另一種初始化方法
    matrix = [['' for j in range(edge)] for i in range(edge)]  # 初始化矩陣
    matrix[0][1:] = np.array(set_word)
    matrix = list(map(list, zip(*matrix)))
    matrix[0][1:] = np.array(set_word)  # 賦值矩陣的第一行與第一列
    return matrix
# 計(jì)算各個(gè)關(guān)鍵詞的共現(xiàn)次數(shù)
def count_matrix(matrix, formated_data):
    for row in range(1, len(matrix)):
        # 遍歷矩陣第一行，跳過下標(biāo)為0的元素
        for col in range(1, len(matrix)):
            # 遍歷矩陣第一列，跳過下標(biāo)為0的元素
            # 實(shí)際上就是為了跳過matrix中下標(biāo)為[0][0]的元素，因?yàn)閇0][0]為空，不為關(guān)鍵詞
            if matrix[0][row] == matrix[col][0]:
                # 如果取出的行關(guān)鍵詞和取出的列關(guān)鍵詞相同，則其對(duì)應(yīng)的共現(xiàn)次數(shù)為0，即矩陣對(duì)角線為0
                matrix[col][row] = str(0)
            else:
                counter = 0  # 初始化計(jì)數(shù)器
                for ech in formated_data:
                    # 遍歷格式化后的原始數(shù)據(jù)，讓取出的行關(guān)鍵詞和取出的列關(guān)鍵詞進(jìn)行組合，
                    # 再放到每條原始數(shù)據(jù)中查詢
                    if matrix[0][row] in ech and matrix[col][0] in ech:
                        counter += 1
                    else:
                        continue
                matrix[col][row] = str(counter)
    return matrix
def main():
    formated_data, set_word = Get_file_keywords(r'D:\untitled\test')
    print(set_word)
    print(formated_data)
    matrix = build_matirx(set_word)
    matrix = count_matrix(matrix, formated_data)
    data1 = pd.DataFrame(matrix)
    data1.to_csv('data.csv', index=0, columns=None, encoding='utf_8_sig')
main()

import pandas as pd
def gx_matrix(vol_li):
    # 整合一下，輸入是df列，輸出直接是矩陣
    names = locals()
    all_col0 = []   # 用來后續(xù)求所有字段的集合
    for row in vol_li:
        all_col0 += row
	    for each in row:  # 對(duì)每行的元素進(jìn)行處理，存在該字段字典的話，再進(jìn)行后續(xù)判斷，否則創(chuàng)造該字段字典
	        try:
	            for each1 in row:  # 對(duì)已存在字典，循環(huán)該行每個(gè)元素，存在則在已有次數(shù)上加一，第一次出現(xiàn)創(chuàng)建鍵值對(duì)“字段：1”
	                try:
	                    names['dic_' + each][each1] = names['dic_' + each][each1] + 1  # 嘗試，一起出現(xiàn)過的話，直接加1
	                except:
	                    names['dic_' + each][each1] = 1  # 沒有的話，第一次加1
	        except:
	            names['dic_' + each] = dict.fromkeys(row, 1)  # 字段首次出現(xiàn)，創(chuàng)造字典
    # 根據(jù)生成的計(jì)數(shù)字典生成矩陣
    all_col = list(set(all_col0))   # 所有的字段（所有動(dòng)物的集合）
    all_col.sort(reverse=False)  # 給定詞匯列表排序排序，為了和生成空矩陣的橫向列名一致
    df_final0 = pd.DataFrame(columns=all_col)  # 生成空矩陣
    for each in all_col:  # 空矩陣中每列，存在給字段字典，轉(zhuǎn)為一列存入矩陣，否則先創(chuàng)造全為零的字典，再填充進(jìn)矩陣
        try:
            temp = pd.DataFrame(names['dic_' + each], index=[each])
        except:
            names['dic_' + each] = dict.fromkeys(all_col, 0)
            temp = pd.DataFrame(names['dic_' + each], index=[each])
        df_final0 = pd.concat([df_final0, temp])  # 拼接
    df_final = df_final0.fillna(0)
    return df_final
if __name__ == '__main__':
    temp1 = ['狗', '獅子', '孔雀', '豬']
    temp2 = ['大象', '獅子', '老虎', '豬']
    temp3 = ['大象', '北極熊', '老虎', '豬']
    temp4 = ['大象', '狗', '老虎', '小雞']
    temp5 = ['狐貍', '獅子', '老虎', '豬']
    temp_all = [temp2, temp1, temp3, temp4, temp5]
    vol_li = pd.Series(temp_all)
    df_matrix = gx_matrix(vol_li)
    print(df_matrix)

# 計(jì)算每個(gè)字段的出現(xiàn)次數(shù)，并列為最后一行
    df_final['all_times'] = ''
    for each in df_final0.columns:
        df_final['all_times'].loc[each] = df_final0.loc[each, each]