瑶子的博客

'''Chinese sentiment analysis'''from sklearn.cross_validation import train_test_splitfrom gensim.models.word2vec import Word2Vecimport numpy as npimport pandas as pdimport jiebafrom sklearn.e...

news_stock练习:from sklearn.feature_extraction.text import CountVectorizer,TfidfVectorizerimport pandas as pdimport numpy as npfrom sklearn.svm import SVCfrom sklearn.metrics import roc_auc_scoref...

练习总共包括三级，char/word/picture第一部分：import numpy as npfrom keras.models import Sequentialfrom keras.layers import Dense #dense指普通的神经网络from keras.layers import Dropoutfrom keras.l...

代码实例：1、导入库和文件import numpy as npimport pandas as pdimport refrom gensim import corpora,models,similaritiesfrom nltk.corpus import stopwordsdf = pd.read_csv('H:/HillaryEmails.csv')df = df...

1、朴素贝叶斯(Naive Bayes)，“Naive”在何处？加上条件独立假设的贝叶斯方法就是朴素贝叶斯方法（Naive Bayes）。 Naive的发音是“乃一污”，意思是“朴素的”、“幼稚的”、“蠢蠢的”。咳咳，也就是说，大神们取名说该方法是一种比较萌蠢的方法，为啥？将句子（“我”,“司”,“可”,“办理”,“正规发票”) 中的 （“我”,“司”）与（“正规发票”）调换一下顺序，就变成了...

基于 TF-IDF 算法的关键词抽取import jieba.analysejieba.analyse.extract_tags(sentence, topK=20, withWeight=False, allowPOS=())sentence 为待提取的文本topK 为返回几个 TF/IDF 权重最大的关键词，默认值为 20withWeight 为是否一并返回关键词权重值，默认值为 F...

数据集来自七月在线练习import jiebaimport pandas as pdimport randomfrom sklearn.model_selection import train_test_split #划分训练/测试集from sklearn.feature_extraction.text import CountVectorizer ...

'''制作词云图,背景可以替换成任意图片，本例中未展示图片'''import numpy as npimport pandas as pdfrom wordcloud import WordCloud #词云包import jieba #中文分词包import codecs #提供的open方...

本篇文章旨在记录练习NLP中基础的熟悉和练习，可关联博客内容进行理解：https://blog.youkuaiyun.com/weixin_40924580/article/details/82962200from nltk.corpus import brownimport nltk# print(brown.categories())# print(len(brown.words()))# pr...

import osimport reimport numpy as npimport pandas as pdfrom bs4 import BeautifulSoupfrom sklearn.feature_extraction.text import CountVectorizer #计数from sklearn.ensemble import RandomForestC...

博客文章基于Google Tensorflow实战深度学习框架第九章部分内容，手写一遍代码加强模型理解。1、获取词汇表# -*- coding:utf-8 -*-'''@Author:zhangy@Modify:2019.7.5'''import codecsimport collectionsfrom operator import itemgetter#设置中英文类型，得...