RabbitMQ之快速入门、上手

import pandas as pd
data=pd.read_csv(open('D://实训课//实训课数据csdn.csv'),sep=',') //导入数据
data  //数据预览

session=data.loc[:,'class'].values
set(session)//对数据表的class类别列切分
def classma(i):
    class1=data.loc[data['class']==class_list[i],:]
    print(class1)
    return class1
//定义切分函数，按类别列作为索引返回每一类别对应的数据信息

class_list=['ai', 'algo', 'big-data', 'blockchain', 'hardware', 'math', 'miniprog']
# for i in range(len(class_list)):
#     classma(i)
ai=classma(0)

file_path='D:/..csv'
def getStopword(file_path):
    stop_list=[line[:-1] for line in open(file_path+'/哈工大停用词表 .txt','r',encoding='UTF-8')]
    return stop_list
getStopword(file_path)

import jieba 
def preProcess(all_data,stop_list):
    xdata=all_data['content']
    result_data=list(xdata)
    result=[]
    for doc in result_data:
        doc=doc.strip()
        cut_list=jieba.lcut(doc)
        doc_result=[word for word in cut_list if word not in stop_list]
        result.append(doc_result)
    return result

# getStopword(file_path)
result1=preProcess(ai,getStopword(file_path))
print(result1)

from gensim.models.tfidfmodel import TfidfModel
from gensim import corpora
def calculate(resultx):
    dictionary=corpora.Dictionary(resultx)
    corpus=[dictionary.doc2bow(text) for text in resultx]

    tf_idf_model = TfidfModel(corpus, normalize=False)
    word_tf_tdf = list(tf_idf_model[corpus])
    print('词典:', dictionary.token2id)
    print('词频:', corpus)
    print('词的tf-idf值:', word_tf_tdf)
    return dictionary.token2id,corpus,word_tf_tdf
idic,corpus,word_tf_tdf=calculate(result1)

max_pic=[]
max_fre=[]
def search(resultx,a):
    maxmum=[]
    idic,corpus,word_tf_tdf=calculate(resultx)
    for row in word_tf_tdf[a]:
        maxmum.append(row[1])
    for col in word_tf_tdf[a]:
        if col[1]==max(maxmum):
            print(max(maxmum))
            max_fre.append(max(maxmum))
            max_sig=col[0]
            max_pic.append(max_sig)
    return max_pic,max_fre
for i in range(len(word_tf_tdf)):
    search(result1,i)
print(max_pic)
print(max_fre)

dictionary_s=idic
key_words=[]
for key,value in dictionary_s.items():
    if value in max_pic:
        key_words.append(key)
key_words.pop(-1)
print(key_words)

# 构造词频字典
dict_zip=dict(zip(key_words,max_fre))
print(dict_zip)

# 绘制词云
from wordcloud import WordCloud
import matplotlib.pyplot as plt
def draw(y):
    my_cloud = WordCloud(
        background_color='white',  # 设置背景颜色  默认是black
        width=900, height=600,
        max_words=100,            # 词云显示的最大词语数量
        font_path='simhei.ttf',   # 设置字体  显示中文
        max_font_size=99,         # 设置字体最大值
        min_font_size=16,         # 设置子图最小值
        random_state=50           # 设置随机生成状态，即多少种配色方案
    ).generate_from_frequencies(y)

    # 显示生成的词云图片
    plt.imshow(my_cloud, interpolation='bilinear')
    # 显示设置词云图中无坐标轴
    plt.axis('off')
    plt.show()
draw(dict_zip)