Python实现共现矩阵可视化与代码详解

ls = ['我永远喜欢三上悠亚', '三上悠亚又出新作了']

['',    '我', '永远', '喜欢', '三上', '悠亚', '又', '出', '新作', '了']
['我',    0,      1,     1,     1,    1,    0,    0,      0,     0]
['永远',  1,      0,     1,      1,    1,    0,    0,     0,     0] 
['喜欢'   1,      1,     0,      1,    1,    0,    0,     0,     0]
['三上',  1,      1,     1,      0,    1,    1,    1,     1,     1]
['悠亚',  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
# 获取关键词
def Get_file_keywords(dir):
    data_array = []  # 每篇文章关键词的二维数组
    set_word = []  # 所有关键词的集合
    try:
        fo = open('dic_test.txt', 'w+', encoding='UTF-8')
        # keywords = fo.read()
        for home, dirs, files in os.walk(dir):  # 遍历文件夹下的每篇文章
            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分词
                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))  # 所有关键词的集合
        return data_array, set_word
    except Exception as reason:
        print('出现错误：', reason)
        return data_array, set_word
# 初始化矩阵
def build_matirx(set_word):
    edge = len(set_word) + 1  # 建立矩阵，矩阵的高度和宽度为关键词集合的长度+1
    '''matrix = np.zeros((edge, edge), dtype=str)'''  # 另一种初始化方法
    matrix = [['' for j in range(edge)] for i in range(edge)]  # 初始化矩阵
    matrix[0][1:] = np.array(set_word)
    matrix = list(map(list, zip(*matrix)))
    matrix[0][1:] = np.array(set_word)  # 赋值矩阵的第一行与第一列
    return matrix
# 计算各个关键词的共现次数
def count_matrix(matrix, formated_data):
    for row in range(1, len(matrix)):
        # 遍历矩阵第一行，跳过下标为0的元素
        for col in range(1, len(matrix)):
            # 遍历矩阵第一列，跳过下标为0的元素
            # 实际上就是为了跳过matrix中下标为[0][0]的元素，因为[0][0]为空，不为关键词
            if matrix[0][row] == matrix[col][0]:
                # 如果取出的行关键词和取出的列关键词相同，则其对应的共现次数为0，即矩阵对角线为0
                matrix[col][row] = str(0)
            else:
                counter = 0  # 初始化计数器
                for ech in formated_data:
                    # 遍历格式化后的原始数据，让取出的行关键词和取出的列关键词进行组合，
                    # 再放到每条原始数据中查询
                    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，输入是df列，输出直接是矩阵
    names = locals()
    all_col0 = []   # 用来后续求所有字段的集合
    for row in vol_li:
        all_col0 += row
	    for each in row:  # 对每行的元素进行处理，存在该字段字典的话，再进行后续判断，否则创造该字段字典
	        try:
	            for each1 in row:  # 对已存在字典，循环该行每个元素，存在则在已有次数上加一，第一次出现创建键值对“字段：1”
	                try:
	                    names['dic_' + each][each1] = names['dic_' + each][each1] + 1  # 尝试，一起出现过的话，直接加1
	                except:
	                    names['dic_' + each][each1] = 1  # 没有的话，第一次加1
	        except:
	            names['dic_' + each] = dict.fromkeys(row, 1)  # 字段首次出现，创造字典
    # 根据生成的计数字典生成矩阵
    all_col = list(set(all_col0))   # 所有的字段（所有动物的集合）
    all_col.sort(reverse=False)  # 给定词汇列表排序排序，为了和生成空矩阵的横向列名一致
    df_final0 = pd.DataFrame(columns=all_col)  # 生成空矩阵
    for each in all_col:  # 空矩阵中每列，存在给字段字典，转为一列存入矩阵，否则先创造全为零的字典，再填充进矩阵
        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', '狮子', '孔雀', '猪']
    temp2 = ['大象', '狮子', '老虎', '猪']
    temp3 = ['大象', '北极熊', '老虎', '猪']
    temp4 = ['大象', '狗', '老虎', '小鸡']
    temp5 = ['狐狸', '狮子', '老虎', '猪']
    temp_all = [temp2, temp1, temp3, temp4, temp5]
    vol_li = pd.Series(temp_all)
    df_matrix = gx_matrix(vol_li)
    print(df_matrix)

# 计算每个字段的出现次数，并列为最后一行
    df_final['all_times'] = ''
    for each in df_final0.columns:
        df_final['all_times'].loc[each] = df_final0.loc[each, each]